Add files using upload-large-folder tool

Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/all_proteins_db.pjs

@@ -0,0 +1,24 @@
+{
+  "version": "1.2",
+  "dbname": "all_proteins_db",
+  "dbtype": "Protein",
+  "db-version": 5,
+  "description": "/225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/all_proteins.faa",
+  "number-of-letters": 3874170,
+  "number-of-sequences": 11758,
+  "last-updated": "2026-05-20T14:29:00",
+  "number-of-volumes": 1,
+  "bytes-total": 6006212,
+  "bytes-to-cache": 3980217,
+  "files": [
+    "all_proteins_db.pdb",
+    "all_proteins_db.phr",
+    "all_proteins_db.pin",
+    "all_proteins_db.pog",
+    "all_proteins_db.pos",
+    "all_proteins_db.pot",
+    "all_proteins_db.psq",
+    "all_proteins_db.ptf",
+    "all_proteins_db.pto"
+  ]
+}

Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/cluster_annotation_mapping.csv

@@ -0,0 +1,607 @@
+cluster_number,consensus_annotation
+1,"hemL, [EC:5.4.3.8], Glutamate-1-semialdehyde 2,1-aminomutase"
+2,"argC, [EC:1.2.1.38], N-acetyl-gamma-glutamyl-phosphate reductase"
+3,"amt, amtB, Ammonium transporter"
+4,"cysG, Siroheme synthase"
+5,"gltX, [EC:6.1.1.17], Glutamate--tRNA ligase"
+6,"ychF, Ribosome-binding ATPase YchF"
+7,"alaS, [EC:6.1.1.7], Alanine--tRNA ligase"
+8,"proA, [EC:1.2.1.41], Gamma-glutamyl phosphate reductase"
+9,"pheS, [EC:6.1.1.20], Phenylalanine--tRNA ligase alpha subunit"
+10,"argS, [EC:6.1.1.19], Arginine--tRNA ligase"
+11,"[EC:2.5.1.68], [EC:2.5.1.88], (2Z,6E)-farnesyl diphosphate synthase"
+12,"tkt, [EC:2.2.1.1], Transketolase"
+13,"bkdB_1, bkdB_2, [EC:1.2.4.4], 3-methyl-2-oxobutanoate dehydrogenase subunit beta"
+14,"map_1, map_2, [EC:3.4.11.18], Methionine aminopeptidase 2"
+15,"ilvB, ilvB1, poxB, [EC:1.2.5.1], [EC:2.2.1.6], Pyruvate dehydrogenase [ubiquinone]"
+16,"ksgA, [EC:2.1.1.182], Ribosomal RNA small subunit methyltransferase A"
+17,"pgm, [EC:5.4.2.2], Phosphoglucomutase"
+18,"purF, [EC:2.4.2.14], Amidophosphoribosyltransferase"
+19,"rpe, [EC:5.1.3.1], Ribulose-phosphate 3-epimerase"
+20,"mdh, [EC:1.1.1.37], Malate dehydrogenase"
+21,"hisG, [EC:2.4.2.17], ATP phosphoribosyltransferase"
+22,"sucC, [EC:6.2.1.5], Succinate--CoA ligase [ADP-forming] subunit beta"
+23,"purL, [EC:6.3.5.3], Phosphoribosylformylglycinamidine synthase subunit PurL"
+24,"purQ, [EC:6.3.5.3], Phosphoribosylformylglycinamidine synthase subunit PurQ"
+25,"rpsL, Small ribosomal subunit protein uS12"
+26,"rpsG, Small ribosomal subunit protein uS7"
+27,"tuf, [EC:3.6.5.3], Elongation factor Tu"
+28,"rpsJ, Small ribosomal subunit protein uS10"
+29,"rpsB, Small ribosomal subunit protein uS2"
+30,"ilvC, [EC:1.1.1.86], Ketol-acid reductoisomerase (NADP(+))"
+31,"ileS, [EC:6.1.1.5], Isoleucine--tRNA ligase"
+32,"ppnK, [EC:2.7.1.23], NAD kinase"
+33,"nnr, Bifunctional NAD(P)H-hydrate repair enzyme Nnr"
+34,"gatB, [EC:6.3.5.-], Aspartyl/glutamyl-tRNA(Asn/Gln) amidotransferase subunit B"
+35,"gltB, [EC:1.4.1.13], Glutamate synthase [NADPH] large chain"
+36,"pheT, [EC:6.1.1.20], Phenylalanine--tRNA ligase beta subunit"
+37,"sucD, [EC:6.2.1.5], Succinate--CoA ligase [ADP-forming] subunit alpha"
+38,"hisC, pat, [EC:2.6.1.57], [EC:2.6.1.9], Histidinol-phosphate aminotransferase"
+39,"rplK, Large ribosomal subunit protein uL11"
+40,"rplA, Large ribosomal subunit protein uL1"
+41,"aroC, [EC:4.2.3.5], Chorismate synthase"
+42,"tatD, [EC:3.1.-.-], putative metal-dependent hydrolase TatD"
+43,"rpoC, [EC:2.7.7.6], DNA-directed RNA polymerase subunit beta'"
+44,"rplC, Large ribosomal subunit protein uL3"
+45,"rplD, Large ribosomal subunit protein uL4"
+46,"rplW, Large ribosomal subunit protein uL23"
+47,"rplB, Large ribosomal subunit protein uL2"
+48,"rplV, Large ribosomal subunit protein uL22"
+49,"rpsC, Small ribosomal subunit protein uS3"
+50,"rplN, Large ribosomal subunit protein uL14"
+51,"rplE, Large ribosomal subunit protein uL5"
+52,"rpsH, Small ribosomal subunit protein uS8"
+53,"rplF, Large ribosomal subunit protein uL6"
+54,"mihF, rpsM, Small ribosomal subunit protein uS13"
+55,"rpsK, Small ribosomal subunit protein uS11"
+56,"truA, [EC:5.4.99.12], tRNA pseudouridine synthase A"
+57,"rplM, Large ribosomal subunit protein uL13"
+58,"rpsI, Small ribosomal subunit protein uS9"
+59,"purA, [EC:6.3.4.4], Adenylosuccinate synthetase"
+60,"ndkA, [EC:2.7.4.6], Nucleoside diphosphate kinase"
+61,"hisA, [EC:5.3.1.16], 1-(5-phosphoribosyl)-5-[(5-phosphoribosylamino)methylideneamino] imidazole-4-carboxamide isomerase"
+62,"hisF, [EC:4.3.2.10], Imidazole glycerol phosphate synthase subunit HisF"
+63,"ribBA, Riboflavin biosynthesis protein RibBA"
+64,"ctaB, [EC:2.5.1.141], Protoheme IX farnesyltransferase"
+65,"serA, [EC:1.1.1.95], D-3-phosphoglycerate dehydrogenase"
+66,"glyA1, [EC:2.1.2.1], Serine hydroxymethyltransferase 1"
+67,"hemB, [EC:4.2.1.24], Delta-aminolevulinic acid dehydratase"
+68,"fumC, [EC:4.2.1.2], Fumarate hydratase class II"
+69,"ilvE, [EC:2.6.1.21], [EC:2.6.1.42], Branched-chain-amino-acid aminotransferase"
+70,"leuA, [EC:2.3.3.13], 2-isopropylmalate synthase"
+71,"hisS, [EC:6.1.1.21], Histidine--tRNA ligase"
+72,"pgk, [EC:2.7.2.3], Phosphoglycerate kinase"
+73,"aroA, [EC:2.5.1.19], 3-phosphoshikimate 1-carboxyvinyltransferase"
+74,"ilvD, [EC:4.2.1.9], Dihydroxy-acid dehydratase"
+75,"truB, [EC:5.4.99.25], tRNA pseudouridine synthase B"
+76,"hisB, [EC:4.2.1.19], Imidazoleglycerol-phosphate dehydratase"
+77,"trpB, trpB_1, trpB_2, [EC:4.2.1.20], Tryptophan synthase beta chain"
+78,"trpC, [EC:4.1.1.48], Indole-3-glycerol phosphate synthase"
+79,"argG, [EC:6.3.4.5], Argininosuccinate synthase"
+80,"purH, Bifunctional purine biosynthesis protein PurH"
+81,"hisE, [EC:3.6.1.31], Phosphoribosyl-ATP pyrophosphatase"
+82,"hisD, [EC:1.1.1.23], Histidinol dehydrogenase"
+83,"grcC1, idsA2, idsA2_1, idsA2_2, [EC:2.5.1.10], [EC:2.5.1.85], (2E,6E)-farnesyl diphosphate synthase"
+84,"[EC:2.1.1.-], Putative methyltransferase"
+85,"cmlB, trpE, [EC:2.6.1.85], [EC:4.1.3.27], Aminodeoxychorismate synthase"
+86,"eno, eno_1, eno_2, [EC:4.2.1.11], Enolase"
+87,"tpiA, [EC:5.3.1.1], Triosephosphate isomerase"
+88,"purM, [EC:6.3.3.1], Phosphoribosylformylglycinamidine cyclo-ligase"
+89,"amiB2, gatA, [EC:3.5.1.4], [EC:6.3.5.7], Glutamyl-tRNA(Gln) amidotransferase subunit A"
+90,"sir, [EC:1.8.7.1], Sulfite reductase [ferredoxin]"
+91,"nadC, [EC:2.4.2.19], putative nicotinate-nucleotide pyrophosphorylase [carboxylating]"
+92,"trpA, [EC:4.2.1.20], Tryptophan synthase alpha chain"
+93,"gabT, gabT_1, gabT_2, [EC:2.6.1.19], 4-aminobutyrate aminotransferase"
+94,"tyrS, [EC:6.1.1.1], Tyrosine--tRNA ligase"
+95,"argH, [EC:4.3.2.1], Argininosuccinate lyase"
+96,"pyrD, [EC:1.3.5.2], Dihydroorotate dehydrogenase (quinone)"
+97,"ktrB, ktrB_1, ktrB_2, Ktr system potassium uptake protein B"
+98,"aroE, ydiB, [EC:1.1.1.25], [EC:1.1.1.282], Shikimate dehydrogenase (NADP(+))"
+99,"nadE, [EC:6.3.1.5], NH(3)-dependent NAD(+) synthetase"
+100,"serS, [EC:6.1.1.11], Serine--tRNA ligase"
+101,"aspS, [EC:6.1.1.23], Aspartate--tRNA(Asp/Asn) ligase"
+102,"glnA, glnA2, [EC:6.3.1.-], [EC:6.3.1.2], Gamma-glutamylpolyamine synthetase GlnA2"
+103,"cysD, cysH, [EC:1.8.4.10], [EC:2.7.7.4], Adenosine 5'-phosphosulfate reductase"
+104,"tal, [EC:2.2.1.2], Transaldolase"
+105,"pdg, Ultraviolet N-glycosylase/AP lyase"
+106,"uvrA, uvrA_1, uvrA_2, UvrABC system protein A"
+107,"yisK, [EC:5.3.2.2], Oxaloacetate tautomerase YisK"
+108,"trpS, [EC:6.1.1.2], Tryptophan--tRNA ligase"
+109,"hemC, [EC:2.5.1.61], Porphobilinogen deaminase"
+110,"fadA, fadA6, fadA6_1, fadA6_2, fadI, paaJ, paaJ_1, paaJ_2, yhfS, [EC:2.3.1.-], [EC:2.3.1.16], [EC:2.3.1.174], [EC:2.3.1.9], 3-oxoadipyl-CoA/3-oxo-5,6-dehydrosuberyl-CoA thiolase"
+111,"rpsO, Small ribosomal subunit protein uS15"
+112,"rpsS, Small ribosomal subunit protein uS19"
+113,"rpsQ, Small ribosomal subunit protein uS17"
+114,"gyrB_1, gyrB_2, [EC:5.6.2.2], DNA gyrase subunit B"
+115,"gyrA_1, gyrA_2, [EC:5.6.2.2], DNA gyrase subunit A"
+116,"folD, Bifunctional protein FolD protein"
+117,"metK, [EC:2.5.1.6], S-adenosylmethionine synthase"
+118,"pth, [EC:3.1.1.29], Peptidyl-tRNA hydrolase"
+119,"nusA, Transcription termination/antitermination protein NusA"
+120,"rplP, Large ribosomal subunit protein uL16"
+121,"rplX, Large ribosomal subunit protein uL24"
+122,"rpsN, Small ribosomal subunit protein uS14A"
+123,"rplO, Large ribosomal subunit protein uL15"
+124,"secY, Protein translocase subunit SecY"
+125,"thyA, [EC:2.1.1.45], Thymidylate synthase"
+126,"nrdF2, [EC:1.17.4.1], Ribonucleoside-diphosphate reductase subunit beta nrdF2"
+127,"nrdE1, [EC:1.17.4.1], Ribonucleoside-diphosphate reductase subunit alpha 1"
+128,"uvrD1, uvrD2, [EC:5.6.2.4], ATP-dependent DNA helicase UvrD1"
+129,"rpmA, Large ribosomal subunit protein bL27"
+130,"[EC:6.3.3.2], 5-formyltetrahydrofolate cyclo-ligase"
+131,"deoA, [EC:2.4.2.4], Thymidine phosphorylase"
+132,"pdxS, [EC:4.3.3.6], Pyridoxal 5'-phosphate synthase subunit PdxS"
+133,"cysS, mshC, [EC:6.1.1.16], [EC:6.3.1.13], Cysteine--tRNA ligase"
+134,"prfA, prfB, Peptide chain release factor 2"
+135,putative transcriptional regulatory protein
+136,"ppa, ppa_1, ppa_2, [EC:3.6.1.1], Inorganic pyrophosphatase"
+137,"fmt, [EC:2.1.2.9], Methionyl-tRNA formyltransferase"
+138,"rpmH, Large ribosomal subunit protein bL34"
+139,"efp, Elongation factor P"
+140,"dgt, Deoxyguanosinetriphosphate triphosphohydrolase-like protein"
+141,"frr, Ribosome-recycling factor"
+142,"groES, Co-chaperonin GroES"
+143,"coaE, [EC:2.7.1.24], Dephospho-CoA kinase"
+144,"rpsR, Small ribosomal subunit protein bS18"
+145,"gpsA2, [EC:1.1.1.94], Glycerol-3-phosphate dehydrogenase [NAD(P)+] 2"
+146,"def, def_1, def_2, [EC:3.5.1.88], Peptide deformylase"
+147,"rplJ, Large ribosomal subunit protein uL10"
+148,"lutA, Lactate utilization protein A"
+149,"dapF, [EC:5.1.1.7], Diaminopimelate epimerase"
+150,"rpmE2, Large ribosomal subunit protein bL31B"
+151,"rpmC, Large ribosomal subunit protein uL29"
+152,"rplR, Large ribosomal subunit protein uL18"
+153,"rpmJ, Large ribosomal subunit protein bL36"
+154,"polA, [EC:2.7.7.7], DNA polymerase I"
+155,"pepA, [EC:3.4.11.1], putative cytosol aminopeptidase"
+156,"rplU, Large ribosomal subunit protein bL21"
+157,"folA, [EC:1.5.1.3], Dihydrofolate reductase"
+158,"proB, [EC:2.7.2.11], Glutamate 5-kinase"
+159,"tsf, Elongation factor Ts"
+160,"fpg1, nei1, nei2, [EC:3.2.2.-], [EC:3.2.2.23], Formamidopyrimidine-DNA glycosylase 1"
+161,"rpmG2, Large ribosomal subunit protein bL33B"
+162,"rpsT, Small ribosomal subunit protein bS20"
+163,"deoC, [EC:4.1.2.4], Deoxyribose-phosphate aldolase"
+164,"rsmH, [EC:2.1.1.199], Ribosomal RNA small subunit methyltransferase H"
+165,"lctD, [EC:1.1.1.436], [EC:1.1.2.-], Lactate dehydrogenase (NAD(+),ferredoxin) subunit LctD"
+166,"pyrF, [EC:4.1.1.23], Orotidine 5'-phosphate decarboxylase"
+167,"cynT, [EC:4.2.1.1], Carbonic anhydrase"
+168,"dapB, [EC:1.17.1.8], 4-hydroxy-tetrahydrodipicolinate reductase"
+169,"rpmI, Large ribosomal subunit protein bL35"
+170,"folP, folP1, [EC:2.5.1.15], Dihydropteroate synthase"
+171,"cdd, [EC:3.5.4.5], Cytidine deaminase"
+172,"glgB, treZ, [EC:2.4.1.18], [EC:3.2.1.141], 1,4-alpha-glucan branching enzyme GlgB"
+173,"glgM, [EC:2.4.1.11], [EC:2.4.1.342], Alpha-maltose-1-phosphate synthase"
+174,"purN, [EC:2.1.2.2], Phosphoribosylglycinamide formyltransferase"
+175,"dnaB, [EC:5.6.2.3], Replicative DNA helicase DnaB"
+176,"pdxT, pdxT_1, pdxT_2, [EC:4.3.3.6], Pyridoxal 5'-phosphate synthase subunit PdxT"
+177,"rsmI, [EC:2.1.1.198], Ribosomal RNA small subunit methyltransferase I"
+178,COG0316 family protein
+179,"relA, Bifunctional (p)ppGpp synthase/hydrolase RelA"
+180,"fadD3, lcfB_1, lcfB_2, lcfB_3, lcfB_4, lcfB_5, lcfB_6, menE, [EC:6.2.1.26], [EC:6.2.1.3], [EC:6.2.1.41], Long-chain-fatty-acid--CoA ligase"
+181,"ybeY, [EC:3.1.-.-], Endoribonuclease YbeY"
+182,"lipA, [EC:2.8.1.8], Lipoyl synthase"
+183,"uvrC, UvrABC system protein C"
+184,"miaA, [EC:2.5.1.75], tRNA dimethylallyltransferase"
+185,Pyridoxal phosphate homeostasis protein
+186,"dapA, [EC:4.3.3.7], 4-hydroxy-tetrahydrodipicolinate synthase"
+187,"fabD, [EC:2.3.1.39], Malonyl CoA-acyl carrier protein transacylase"
+188,"fabH, oleA, [EC:2.3.1.180], [EC:2.3.3.20], Beta-ketoacyl-[acyl-carrier-protein] synthase III"
+189,"gdh, gdhA, [EC:1.4.1.3], [EC:1.4.1.4], Glutamate dehydrogenase"
+190,"rplS, Large ribosomal subunit protein bL19"
+191,"aroB, [EC:4.2.3.4], 3-dehydroquinate synthase"
+192,"birA, [EC:6.3.4.15], Biotin--[acetyl-CoA-carboxylase] ligase"
+193,"secF, Protein translocase subunit SecF"
+194,"pdxK, thiD, [EC:2.7.1.35], [EC:2.7.1.49], Pyridoxine kinase"
+195,"thiE, [EC:2.5.1.3], Thiamine-phosphate synthase"
+196,"recR, Recombination protein RecR"
+197,"atpC, ATP synthase epsilon chain"
+198,"rsmG, [EC:2.1.1.-], Ribosomal RNA small subunit methyltransferase G"
+199,"dnaG, [EC:2.7.7.101], DNA primase"
+200,"rplI, Large ribosomal subunit protein bL9"
+201,"rpsF, Small ribosomal subunit protein bS6"
+202,"infA, Translation initiation factor IF-1"
+203,"gndA, [EC:1.1.1.44], 6-phosphogluconate dehydrogenase, NADP(+)-dependent, decarboxylating"
+204,"zwf, zwf2, [EC:1.1.1.49], Glucose-6-phosphate 1-dehydrogenase 2"
+205,"acsA_1, acsA_2, acsA_3, acsA_4, acsA_5, [EC:6.2.1.1], Acetyl-coenzyme A synthetase"
+206,"glgE1, treA, [EC:2.4.99.16], [EC:3.2.1.93], Trehalose-6-phosphate hydrolase"
+207,"gltA2, [EC:2.3.3.16], Citrate synthase 1"
+208,"hemA, [EC:1.2.1.70], Glutamyl-tRNA reductase"
+209,"nadA, [EC:2.5.1.72], Quinolinate synthase"
+210,"wecB, [EC:5.1.3.14], UDP-N-acetylglucosamine 2-epimerase"
+211,"ybeM, [EC:3.5.1.128], Deaminated glutathione amidase"
+212,Putative gluconeogenesis factor
+213,"arsC1, arsC1_1, arsC1_2, arsC2, [EC:2.8.4.2], [EC:3.1.3.48], Putative low molecular weight protein-tyrosine-phosphatase"
+214,"araQ, sugB, Trehalose transport system permease protein SugB"
+215,"sufC, Vegetative protein 296"
+216,"gcvP, [EC:1.4.4.2], putative glycine dehydrogenase (decarboxylating)"
+217,"gcvT, [EC:2.1.2.10], Aminomethyltransferase"
+218,"gpgP, pspA, [EC:3.1.3.3], [EC:3.1.3.85], Phosphoserine phosphatase 1"
+219,"hemE, [EC:4.1.1.37], Uroporphyrinogen decarboxylase"
+220,"panB, [EC:2.1.2.11], 3-methyl-2-oxobutanoate hydroxymethyltransferase"
+221,"sbcD, Nuclease SbcCD subunit D"
+222,"thiC, [EC:4.1.99.17], Phosphomethylpyrimidine synthase"
+223,"[EC:3.6.1.9], Nucleoside triphosphate pyrophosphatase"
+224,"aspB, aspC, aspC1, [EC:2.6.1.-], [EC:2.6.1.1], [EC:2.6.1.2], [EC:2.6.1.66], putative aminotransferase"
+225,"mgtA, mgtA_1, mgtA_2, [EC:2.4.1.-], GDP-mannose-dependent alpha-mannosyltransferase"
+226,"ilvH, [EC:2.2.1.6], Acetolactate synthase small subunit"
+227,"glyQS, thrS, [EC:6.1.1.14], [EC:6.1.1.3], Glycine--tRNA ligase"
+228,"proS, [EC:6.1.1.15], Proline--tRNA ligase"
+229,"dnaK, Chaperone protein DnaK"
+230,"fadH, [EC:1.3.1.34], 2,4-dienoyl-CoA reductase [(2E)-enoyl-CoA-producing]"
+231,"menB, [EC:4.1.3.36], 1,4-dihydroxy-2-naphthoyl-CoA synthase"
+232,"glgC, glgC_1, glgC_2, [EC:2.7.7.27], Glucose-1-phosphate adenylyltransferase"
+233,"glmS, [EC:2.6.1.16], Glutamine--fructose-6-phosphate aminotransferase [isomerizing]"
+234,"oleD, [EC:1.1.1.412], 2-alkyl-3-oxoalkanoate reductase"
+235,"coaBC, Coenzyme A biosynthesis bifunctional protein CoaBC"
+236,"mshD, [EC:2.3.1.-], [EC:2.3.1.189], Mycothiol acetyltransferase"
+237,"carB, [EC:6.3.4.16], Carbamoyl phosphate synthase large chain"
+238,"groEL2, [EC:5.6.1.7], Chaperonin GroEL 2"
+239,"hom, [EC:1.1.1.3], Homoserine dehydrogenase"
+240,"pyrE, [EC:2.4.2.10], Orotate phosphoribosyltransferase"
+241,"prs, [EC:2.7.6.1], Ribose-phosphate pyrophosphokinase"
+242,"ftsH, [EC:3.4.24.-], ATP-dependent zinc metalloprotease FtsH"
+243,"recA, Protein RecA"
+244,"pyk, [EC:2.7.1.40], Pyruvate kinase"
+245,"mraY, wecA, [EC:2.7.8.13], [EC:2.7.8.35], Decaprenyl-phosphate N-acetylglucosaminephosphotransferase"
+246,"leuB, [EC:1.1.1.85], 3-isopropylmalate dehydrogenase"
+247,"ctpE, [EC:7.2.2.10], Calcium-transporting ATPase CtpE"
+248,"moeZ, putative adenylyltransferase/sulfurtransferase MoeZ"
+249,"entS, kgtP, lfrA, mdtP, proP, shiA, stp_1, stp_2, stp_3, xylE, yhjE, Multidrug resistance protein Stp"
+250,"infB, lepA, [EC:3.6.5.-], Elongation factor 4"
+251,"mnmA, [EC:2.8.1.13], tRNA-specific 2-thiouridylase MnmA"
+252,"hisN, suhB, suhB_1, [EC:3.1.3.11], [EC:3.1.3.15], Fructose-1,6-bisphosphatase/inositol-1-monophosphatase"
+253,"cbpA, dnaJ, dnaJ2, Chaperone protein DnaJ 2"
+254,"ettA_1, ettA_2, ettA_3, vmlR, yheS, yheS_1, yheS_2, [EC:3.6.1.-], Energy-dependent translational throttle protein EttA"
+255,"mrp, Iron-sulfur cluster carrier protein"
+256,"gloC, yflN, [EC:3.-.-.-], [EC:3.1.2.6], Hydroxyacylglutathione hydrolase GloC"
+257,"trxB, trxB_1, trxB_2, [EC:1.8.1.9], Thioredoxin reductase"
+258,"fprA_1, fprA_2, gltD, [EC:1.18.1.2], [EC:1.4.1.13], NADPH-ferredoxin reductase FprA"
+259,"recN, DNA repair protein RecN"
+260,"thrC, [EC:4.2.3.1], Threonine synthase"
+261,"carA, [EC:6.3.5.5], Carbamoyl phosphate synthase small chain"
+262,"kgd, pdhC_1, pdhC_2, [EC:2.2.1.5], [EC:2.3.1.12], Dihydrolipoyllysine-residue acetyltransferase component of pyruvate dehydrogenase complex"
+263,"gcvH, Glycine cleavage system H protein"
+264,"trpG, [EC:4.1.3.27], Anthranilate synthase component 2"
+265,"guaB, guaB1, [EC:1.-.-.-], [EC:1.1.1.205], [EC:1.7.1.7], GMP reductase"
+266,"guaA, [EC:6.3.5.2], GMP synthase [glutamine-hydrolyzing]"
+267,"valS, [EC:6.1.1.9], Valine--tRNA ligase"
+268,"ask, [EC:2.7.2.4], Aspartokinase"
+269,"pyrH, [EC:2.7.4.22], Uridylate kinase"
+270,"cysNC, Bifunctional enzyme CysN/CysC"
+271,"bcaP, kimA, puuP, putative transporter"
+272,"tsaD, [EC:2.3.1.234], tRNA N6-adenosine threonylcarbamoyltransferase"
+273,"[EC:2.7.7.53], putative HIT-like protein"
+274,"rpsA, Small ribosomal subunit protein bS1"
+275,"pyrB, [EC:2.1.3.2], Aspartate carbamoyltransferase catalytic subunit"
+276,"ffh, [EC:3.6.5.4], Signal recognition particle protein"
+277,"clpB, clpC1, ATP-dependent Clp protease ATP-binding subunit ClpC1"
+278,"tig, [EC:5.2.1.8], Trigger factor"
+279,"trpD, [EC:2.4.2.18], Anthranilate phosphoribosyltransferase"
+280,"argB, [EC:2.7.2.8], Acetylglutamate kinase"
+281,"topA, [EC:5.6.2.1], DNA topoisomerase 1"
+282,"glpK, [EC:2.7.1.30], Glycerol kinase"
+283,"uvrB, UvrABC system protein B"
+284,"rnr, [EC:3.1.13.1], Ribonuclease R"
+285,"pgsA2, pgsA2_1, pgsA2_2, [EC:2.7.8.-], [EC:2.7.8.41], Phosphatidylinositol phosphate synthase"
+286,"ycsE, yhaX, yidA, yitU, ywpJ, [EC:3.1.3.-], [EC:3.1.3.104], [EC:3.1.3.23], Stress response protein YhaX"
+287,"adk, [EC:2.7.4.3], Adenylate kinase"
+288,"[EC:5.4.99.-], putative RNA pseudouridine synthase"
+289,"rlmP, rlmP_1, rlmP_2, trmH, [EC:2.1.1.-], [EC:2.1.1.34], 23S rRNA (guanosine(2553)-2'-O)-methyltransferase RlmP"
+290,"ktrA, ktrC, trkA, trkA_1, trkA_2, Trk system potassium uptake protein TrkA"
+291,"rnc, [EC:3.1.26.3], Ribonuclease 3"
+292,"pstC2, Phosphate transport system permease protein PstC 2"
+293,"grpE, Protein GrpE"
+294,"glpD2, [EC:1.1.5.3], Glycerol-3-phosphate dehydrogenase 2"
+295,"mqo, [EC:1.1.5.4], putative malate:quinone oxidoreductase"
+296,"gltC, lysG, lysG_1, lysG_2, Lysine export transcriptional regulatory protein LysG"
+297,"glpQ, glpQ1, glpQ2, glpQ2_1, glpQ2_2, [EC:3.1.4.46], putative glycerophosphodiester phosphodiesterase 2"
+298,"dnaE, dnaE1, dnaE2, [EC:2.7.7.7], DNA polymerase III subunit alpha"
+299,"gpmA, gpmA_1, [EC:5.4.2.11], 2,3-bisphosphoglycerate-dependent phosphoglycerate mutase"
+300,"opuE, putP, High-affinity proline transporter PutP"
+301,"rnj, [EC:3.1.-.-], Ribonuclease J"
+302,"ybfF, [EC:3.1.-.-], [EC:3.8.1.3], Esterase YbfF"
+303,"lspA, lspA_1, lspA_2, [EC:3.4.23.36], Lipoprotein signal peptidase"
+304,"cmpB, ssuC, Putative aliphatic sulfonates transport permease protein SsuC"
+305,"sodA, [EC:1.15.1.1], Superoxide dismutase [Mn]"
+306,"comM, Competence protein ComM"
+307,"fepD, feuB, hmuU, yfhA, putative siderophore transport system permease protein YfhA"
+308,"thiL, [EC:2.7.4.16], Thiamine-monophosphate kinase"
+309,"[EC:3.4.24.-], putative zinc protease"
+310,"phnPP, [EC:3.1.3.97], [EC:3.1.4.57], 3',5'-nucleoside bisphosphate phosphatase"
+311,"bioN, Energy-coupling factor transporter transmembrane protein BioN"
+312,"xecA1, [EC:4.4.1.23], 2-hydroxypropyl-CoM lyase"
+313,"miaB, [EC:2.8.4.3], tRNA-2-methylthio-N(6)-dimethylallyladenosine synthase"
+314,"dapE, dapE_1, dapE_2, [EC:3.5.1.18], Putative succinyl-diaminopimelate desuccinylase DapE"
+315,"metB_1, metB_2, metC, [EC:2.5.1.48], [EC:4.4.1.13], Cystathionine gamma-synthase"
+316,Putative transport protein
+317,"prpC, stp_2, [EC:3.1.3.16], Serine/threonine phosphatase stp"
+318,"ruvA, Holliday junction branch migration complex subunit RuvA"
+319,"[EC:3.1.3.-], Phosphorylated carbohydrates phosphatase"
+320,"pafA, [EC:6.3.1.19], Pup--protein ligase"
+321,"menJ, [EC:1.3.99.38], Menaquinone reductase"
+322,D-glycerol 3-phosphate phosphatase
+323,"mrpD_1, mrpD_2, Na(+)/H(+) antiporter subunit D"
+324,"yeaE, [EC:1.1.1.-], Aldo-keto reductase/MSMEI_2347"
+325,"dauA, C4-dicarboxylic acid transporter DauA"
+326,"[EC:4.2.1.1], Carbonic anhydrase"
+327,"iolS, yajO, yajO_1, yajO_2, [EC:1.1.-.-], [EC:1.1.1.-], 1-deoxyxylulose-5-phosphate synthase YajO"
+328,"wecC, [EC:1.1.1.336], UDP-N-acetyl-D-mannosamine dehydrogenase"
+329,"lepB_1, lepB_2, sipT, [EC:3.4.21.89], Signal peptidase I"
+330,"ald, [EC:1.4.1.1], Alanine dehydrogenase"
+331,"smpB, SsrA-binding protein"
+332,"ung, [EC:3.2.2.27], Uracil-DNA glycosylase"
+333,"hchA, yhbO, yraA, [EC:3.1.2.-], [EC:3.2.-.-], Putative cysteine protease YraA"
+334,"nrdH, [EC:1.-.-.-], Glutaredoxin-like protein NrdH"
+335,"yhfK, [EC:4.-.-.-], putative sugar epimerase YhfK"
+336,"phoU2, Phosphate-specific transport system accessory protein PhoU"
+337,"murG, [EC:2.4.1.227], UDP-N-acetylglucosamine--N-acetylmuramyl-(pentapeptide) pyrophosphoryl-undecaprenol N-acetylglucosamine transferase"
+338,"exoA, xthA, [EC:3.1.11.2], Exodeoxyribonuclease III"
+339,"atpF, ATP synthase subunit b"
+340,"dcd, [EC:3.5.4.30], dCTP deaminase, dUMP-forming"
+341,Iron-sulfur cluster assembly SufBD family protein
+342,"gatC, [EC:6.3.5.-], Glutamyl-tRNA(Gln) amidotransferase subunit C"
+343,"qcrA, Cytochrome bc1 complex Rieske iron-sulfur subunit"
+344,"yfcA, putative membrane transporter protein YfcA"
+345,"furA, zur, Transcriptional regulator FurA"
+346,"acpS, [EC:2.7.8.7], Holo-[acyl-carrier-protein] synthase"
+347,"clpP1, clpP2, [EC:3.4.21.92], ATP-dependent Clp protease proteolytic subunit 2"
+348,"[EC:2.1.1.-], RNA/DNA methyltransferase"
+349,"dxr, [EC:1.1.1.267], 1-deoxy-D-xylulose 5-phosphate reductoisomerase"
+350,"pbpF, ponA, Penicillin-binding protein 1A/1B"
+351,"mtrA, phoP, tcrX_1, tcrX_2, trcR, walR, putative transcriptional regulatory protein TcrX"
+352,"dppA, gsiB, hbpA, hbpA_1, hbpA_2, nikA, Heme-binding protein A"
+353,"katE, [EC:1.11.1.6], Catalase C"
+354,"dut, [EC:3.6.1.23], Deoxyuridine 5'-triphosphate nucleotidohydrolase"
+355,"ispH2, [EC:1.17.7.4], 4-hydroxy-3-methylbut-2-enyl diphosphate reductase 2"
+356,"gltK, gluC, gluD, Glutamate transport system permease protein GluC"
+357,"pbpA, pbpB, [EC:3.4.16.4], Peptidoglycan D,D-transpeptidase PbpA"
+358,"murE, [EC:6.3.2.13], UDP-N-acetylmuramoyl-L-alanyl-D-glutamate--2,6-diaminopimelate ligase"
+359,"murD, [EC:6.3.2.9], UDP-N-acetylmuramoylalanine--D-glutamate ligase"
+360,"ftsW, rodA, [EC:2.4.99.28], Peptidoglycan glycosyltransferase RodA"
+361,"hup1, DNA-binding protein HU 1"
+362,"rutE, ydjA, [EC:1.-.-.-], [EC:1.1.1.298], putative malonic semialdehyde reductase RutE"
+363,"nusB, Transcription antitermination protein NusB"
+364,"greA, Transcription elongation factor GreA"
+365,"alr, [EC:5.1.1.1], Alanine racemase"
+366,"purU, [EC:3.5.1.10], Formyltetrahydrofolate deformylase"
+367,"yfmP, putative HTH-type transcriptional regulator"
+368,"murI, [EC:5.1.1.3], Glutamate racemase"
+369,"mntA, Manganese-binding lipoprotein MntA"
+370,"tatC, Sec-independent protein translocase protein TatC"
+371,"rimM, Ribosome maturation factor RimM"
+372,"murB, [EC:1.3.1.98], UDP-N-acetylenolpyruvoylglucosamine reductase"
+373,"[EC:3.1.-.-], Putative pre-16S rRNA nuclease"
+374,"ispG, [EC:1.17.7.3], 4-hydroxy-3-methylbut-2-en-1-yl diphosphate synthase (flavodoxin)"
+375,"glnH, gluB, Glutamate-binding protein GluB"
+376,"swrC, Swarming motility protein SwrC"
+377,"ctaD, [EC:7.1.1.9], putative cytochrome c oxidase subunit 1"
+378,"cobB, cobB_1, cobB_2, [EC:2.3.1.286], NAD-dependent protein deacetylase"
+379,"panD, [EC:4.1.1.11], Aspartate 1-decarboxylase"
+380,"rbfA, Ribosome-binding factor A"
+381,putative membrane protein
+382,"rkpK, tuaD, [EC:1.1.1.22], UDP-glucose 6-dehydrogenase TuaD"
+383,"aldH1, feaB, gabD1, gabD1_1, gabD1_2, gbsA, hpcC, paaZ, sad_1, sad_2, vdh, [EC:1.2.1.-], [EC:1.2.1.16], [EC:1.2.1.39], [EC:1.2.1.60], [EC:1.2.1.67], [EC:1.2.1.79], [EC:1.2.1.8], Succinate-semialdehyde dehydrogenase [NADP(+)] 1"
+384,"hmp, [EC:1.14.12.17], Flavohemoprotein"
+385,"paaE, [EC:1.-.-.-], 1,2-phenylacetyl-CoA epoxidase, subunit E"
+386,"[EC:6.2.1.3], Long-chain-fatty-acid--CoA ligase FadD15"
+387,"crt, crt_1, crt_2, echA8_1, echA8_2, echA8_3, fadB, fadB_1, fadB_2, fadJ_1, fadJ_2, paaF, paaG, [EC:4.2.1.150], [EC:4.2.1.17], [EC:5.3.3.18], putative enoyl-CoA hydratase EchA8"
+388,"fabG4, mabA, ucpA, yghA_1, yghA_2, yghA_3, [EC:1.-.-.-], [EC:1.1.1.100], [EC:1.1.1.212], putative oxidoreductase YghA"
+389,"pyc, [EC:6.4.1.1], Pyruvate carboxylase"
+390,"cysE, [EC:2.3.1.30], Serine acetyltransferase"
+391,"acnA, [EC:4.2.1.3], Aconitate hydratase A"
+392,"mutT2, [EC:3.6.1.55], ADPR responsive transcriptional repressor NtrR"
+393,"sdhA, [EC:1.3.5.1], Succinate dehydrogenase flavoprotein subunit"
+394,"trhO, [EC:1.14.-.-], tRNA uridine(34) hydroxylase"
+395,"nadD, [EC:2.7.7.18], putative nicotinate-nucleotide adenylyltransferase"
+396,"[EC:1.1.1.1], putative zinc-binding alcohol dehydrogenase"
+397,"radA, [EC:3.6.4.-], DNA repair protein RadA"
+398,"bkdA_1, bkdA_2, [EC:1.2.4.4], 3-methyl-2-oxobutanoate dehydrogenase subunit alpha"
+399,"coaA, [EC:2.7.1.33], Pantothenate kinase"
+400,putative protein
+401,"neuA, [EC:2.7.7.82], CMP-N,N'-diacetyllegionaminic acid synthase"
+402,"galE, galE_1, galE_2, galE_3, [EC:5.1.3.2], UDP-glucose 4-epimerase"
+403,"rmlB, [EC:4.2.1.46], dTDP-glucose 4,6-dehydratase"
+404,"iscS_1, iscS_2, [EC:2.8.1.7], IscS-like cysteine desulfurase"
+405,"mntB, Manganese transport system membrane protein MntB"
+406,"glmM, [EC:5.4.2.10], [EC:5.4.2.8], putative phosphomannomutase"
+407,"yprA, [EC:3.6.4.-], putative ATP-dependent helicase YprA"
+408,"hutT, hutT_1, hutT_2, hutT_3, L-histidine transporter HutT"
+409,"alsT, Amino-acid carrier protein AlsT"
+410,"cmpD, nrtD, nrtD_1, nrtD_2, [EC:7.3.2.4], [EC:7.6.2.-], Nitrate import ATP-binding protein NrtD"
+411,"pstB1, [EC:7.3.2.1], Phosphate import ATP-binding protein PstB 1"
+412,"ylmA, [EC:7.-.-.-], putative ABC transporter ATP-binding protein YlmA"
+413,"fepC, yusV, [EC:7.2.2.17], putative siderophore transport system ATP-binding protein YusV"
+414,"gluA, [EC:7.4.2.1], Glutamate transport ATP-binding protein GluA"
+415,"lnrL, [EC:7.6.2.-], Linearmycin resistance ATP-binding protein LnrL"
+416,"pglK, ywjA_1, ywjA_2, ywjA_3, ywjA_4, [EC:7.5.2.5], [EC:7.6.2.-], putative ABC transporter ATP-binding protein YwjA"
+417,"metN, metN_1, metN_2, [EC:7.4.2.11], Methionine import ATP-binding protein MetN"
+418,"bceA, lolD, lolD_1, lolD_2, yknY, yknY_1, yknY_2, [EC:7.6.2.-], putative ABC transporter ATP-binding protein YknY"
+419,"lutB, Lactate utilization protein B"
+420,"era, GTPase Era"
+421,"menD, [EC:2.2.1.9], 2-succinyl-5-enolpyruvyl-6-hydroxy-3-cyclohexene-1-carboxylate synthase"
+422,"lysA, [EC:4.1.1.20], Diaminopimelate decarboxylase"
+423,"lysN, [EC:2.6.1.39], 2-aminoadipate transaminase"
+424,"opuBB, opuBB_1, opuBB_2, opuCB, opuCD, Choline transport system permease protein OpuBB"
+425,"malF, sugA, Trehalose transport system permease protein SugA"
+426,"ddl, [EC:6.3.2.4], D-alanine--D-alanine ligase"
+427,"pnp, [EC:2.7.7.8], Polyribonucleotide nucleotidyltransferase"
+428,"arfB, [EC:3.1.1.29], Peptidyl-tRNA hydrolase ArfB"
+429,"hslR, Heat shock protein 15"
+430,"lysS1, [EC:6.1.1.6], Lysine--tRNA ligase 1"
+431,"soj, [EC:3.6.4.-], Sporulation initiation inhibitor protein Soj"
+432,"mutY, [EC:3.2.2.31], Adenine DNA glycosylase"
+433,"recF, DNA replication and repair protein RecF"
+434,"mfd, [EC:3.6.4.-], Transcription-repair-coupling factor"
+435,"priA, putative replication restart protein PriA"
+436,"dinG, [EC:5.6.2.3], ATP-dependent helicase DinG"
+437,"recG, [EC:5.6.2.3], ATP-dependent DNA helicase RecG"
+438,"lhr, [EC:3.2.2.27], Lhr helicase/ probable uracil glycosylase"
+439,"glmU, Bifunctional protein GlmU"
+440,"rmlA, [EC:2.7.7.24], Glucose-1-phosphate thymidylyltransferase"
+441,"gtaB, [EC:2.7.7.9], UTP--glucose-1-phosphate uridylyltransferase"
+442,putative protein
+443,"valG, [EC:2.4.1.338], [EC:2.4.1.54], Undecaprenyl-phosphate mannosyltransferase"
+444,"bipA, [EC:3.6.5.-], Large ribosomal subunit assembly factor BipA"
+445,"clpX, ATP-dependent Clp protease ATP-binding subunit ClpX"
+446,"ahpE, bcp, [EC:1.11.1.24], [EC:1.11.1.29], Putative peroxiredoxin"
+447,"hutI, hutI_1, hutI_2, [EC:3.5.2.7], Imidazolonepropionase"
+448,putative protein
+449,"argA, [EC:2.3.1.1], Amino-acid acetyltransferase"
+450,"lpdA, mtr, rclA, [EC:1.6.5.2], [EC:1.8.1.15], NAD(P)H dehydrogenase (quinone)"
+451,"fhmpcd1, hbd, hbd_1, hbd_2, [EC:1.1.1.157], [EC:1.1.1.35], [EC:1.2.1.100], 3-hydroxybutyryl-CoA dehydrogenase"
+452,"ndbB, [EC:1.6.5.12], [EC:1.6.5.9], Type II NADH:quinone oxidoreductase"
+453,putative protein
+454,putative protein
+455,"ino1, [EC:5.5.1.4], Inositol-3-phosphate synthase"
+456,"appC, [EC:7.1.1.3], Cytochrome bd-II ubiquinol oxidase subunit 1"
+457,"cspA, putative cold shock protein A"
+458,"lysE, lysE_1, lysE_2, Lysine exporter LysE"
+459,"qcrB, [EC:7.1.1.8], Cytochrome bc1 complex cytochrome b subunit"
+460,"cydB, [EC:7.1.1.7], Cytochrome bd-I ubiquinol oxidase subunit 2"
+461,"gltP, Proton/glutamate-aspartate symporter"
+462,"fasR, kstR2, HTH-type transcriptional activator FasR"
+463,"nrdR, Transcriptional repressor NrdR"
+464,"carD, RNA polymerase-binding transcription factor CarD"
+465,"pncA, [EC:3.5.1.19], Nicotinamidase/pyrazinamidase"
+466,"yohK, Inner membrane protein YohK"
+467,"argJ, Arginine biosynthesis bifunctional protein ArgJ"
+468,"rsmE, [EC:2.1.1.193], Ribosomal RNA small subunit methyltransferase E"
+469,"ydhK, ydhK_1, ydhK_2, putative protein YdhK"
+470,putative protein
+471,"kdgR_1, kipR, pcaR, pcaR_1, pcaR_2, rhmR, xynR, yiaJ, Pca regulon regulatory protein"
+472,"hrcA, Heat-inducible transcription repressor HrcA"
+473,"argR, Arginine repressor"
+474,"metQ, metQ_1, metQ_2, D-methionine-binding lipoprotein MetQ"
+475,"holA, [EC:2.7.7.7], putative DNA polymerase III subunit delta"
+476,"hipO, scmP, [EC:3.-.-.-], [EC:3.5.1.-], [EC:3.5.1.32], putative hydrolase"
+477,"whiA, putative cell division protein WhiA"
+478,"manA, [EC:5.3.1.8], Mannose-6-phosphate isomerase"
+479,"pncB1, [EC:6.3.4.21], Nicotinate phosphoribosyltransferase pncB1"
+480,"dtd, [EC:3.1.1.96], D-aminoacyl-tRNA deacylase"
+481,"glpX, [EC:3.1.3.11], Fructose-1,6-bisphosphatase class 2"
+482,"clsA, [EC:2.7.8.-], Major cardiolipin synthase ClsA"
+483,"aldR, aldR_1, aldR_2, lrpA, HTH-type transcriptional regulator AldR"
+484,"glgX, [EC:3.2.1.-], Glycogen operon protein GlgX"
+485,"folB, [EC:4.1.2.25], Dihydroneopterin aldolase"
+486,"hpf, Ribosome hibernation promotion factor"
+487,"lutC, Lactate utilization protein C"
+488,"xseA, [EC:3.1.11.6], Exodeoxyribonuclease 7 large subunit"
+489,"menA, [EC:2.5.1.74], 1,4-dihydroxy-2-naphthoate octaprenyltransferase"
+490,"rlmH, [EC:2.1.1.177], Ribosomal RNA large subunit methyltransferase H"
+491,"lutP, L-lactate permease"
+492,"ctaC, [EC:7.1.1.9], Cytochrome c oxidase subunit 2"
+493,"nucS, [EC:3.1.-.-], Endonuclease NucS"
+494,"hrpA, hrpB, [EC:3.6.4.13], ATP-dependent RNA helicase HrpB"
+495,"lpqY, Trehalose-binding lipoprotein LpqY"
+496,Nucleotide-binding protein
+497,Nucleotide-binding protein
+498,"rimJ, rimJ_1, rimJ_2, [EC:2.3.1.267], [EC:2.8.1.-], [Ribosomal protein uS5]-alanine N-acetyltransferase"
+499,PhoH-like protein
+500,"bmpA, nupN, ABC transporter guanosine-binding protein NupN"
+501,"sdaA, sdaB, tdcG, [EC:4.3.1.17], L-serine dehydratase 2"
+502,"ohrA, osmC, [EC:1.11.1.-], Organic hydroperoxide resistance protein OhrA"
+503,"nrdI, Protein NrdI"
+504,"scoA, [EC:2.8.3.5], putative succinyl-CoA:3-ketoacid coenzyme A transferase subunit A"
+505,"rspR_1, rspR_2, HTH-type transcriptional repressor RspR"
+506,"caiB, mcr, mcr_1, mcr_2, [EC:2.8.3.-], [EC:5.1.99.4], Alpha-methylacyl-CoA racemase"
+507,"add1, [EC:3.5.4.4], Adenosine deaminase 1"
+508,"rplY, Large ribosomal subunit protein bL25"
+509,"khpA, RNA-binding protein KhpA"
+510,"vipp1, Membrane-associated protein Vipp1"
+511,"ctaE, [EC:7.1.1.9], Cytochrome c oxidase subunit 3"
+512,"phoH2, [EC:3.1.-.-], Protein PhoH2"
+513,"nemA, [EC:1.3.1.-], [EC:1.6.99.1], NADPH dehydrogenase"
+514,"serC, [EC:2.6.1.52], Phosphoserine aminotransferase"
+515,"ricR, ricR_1, ricR_2, ricR_3, Copper-sensing transcriptional repressor RicR"
+516,"ppgK, [EC:2.7.1.63], Polyphosphate glucokinase"
+517,"ispE, [EC:2.7.1.148], 4-diphosphocytidyl-2-C-methyl-D-erythritol kinase"
+518,"rihA, [EC:3.2.-.-], Pyrimidine-specific ribonucleoside hydrolase RihA"
+519,"nsrR, HTH-type transcriptional repressor NsrR"
+520,"acdA, acdA_1, acdA_2, acdA_3, mmgC_1, mmgC_2, mmgC_3, mmgC_4, mmgC_5, mmgC_6, [EC:1.3.99.-], Acyl-CoA dehydrogenase"
+521,"cstA, Peptide transporter CstA"
+522,"uppP, [EC:3.6.1.27], Undecaprenyl-diphosphatase"
+523,"mscL, Large-conductance mechanosensitive channel"
+524,"lexA, [EC:3.4.21.88], LexA repressor"
+525,"sdhC, Succinate dehydrogenase 2 membrane subunit SdhC"
+526,"qcrC, [EC:7.1.1.8], Cytochrome bc1 complex cytochrome c subunit"
+527,"metI_1, metI_2, metP, Methionine import system permease protein MetP"
+528,"yihR, putative protein YihR"
+529,"catD, metXA, [EC:2.3.1.31], [EC:3.1.1.24], Homoserine O-acetyltransferase"
+530,"thiG, [EC:2.8.1.10], Thiazole synthase"
+531,"etfA, Electron transfer flavoprotein subunit alpha"
+532,"htdX, htdZ, [EC:4.2.1.-], 3-hydroxyacyl-thioester dehydratase X"
+533,"paaI, [EC:3.1.2.-], Acyl-coenzyme A thioesterase PaaI"
+534,"pcaJ, scoB, [EC:2.8.3.5], [EC:2.8.3.6], putative succinyl-CoA:3-ketoacid coenzyme A transferase subunit B"
+535,"[EC:3.1.3.-], putative protein"
+536,"glsA1, [EC:3.5.1.2], Glutaminase 1"
+537,"czcO, czcO_1, czcO_2, tmm, [EC:1.-.-.-], [EC:1.14.13.-], [EC:1.14.13.148], putative oxidoreductase CzcO"
+538,"prpD2, [EC:4.2.1.79], 2-methylcitrate dehydratase 2"
+539,"[EC:3.2.2.-], Putative 3-methyladenine DNA glycosylase"
+540,"curA, yfmJ, [EC:1.-.-.-], [EC:1.3.1.-], NADPH-dependent curcumin reductase"
+541,"yedK, [EC:4.-.-.-], Abasic site processing protein YedK"
+542,"cmoO, ladA_1, ladA_2, scmK, [EC:1.14.13.-], [EC:1.14.14.-], [EC:1.14.14.28], N-acetyl-S-alkylcysteine monooxygenase"
+543,"hcaC, 3-phenylpropionate/cinnamic acid dioxygenase ferredoxin subunit"
+544,"paaD, Putative 1,2-phenylacetyl-CoA epoxidase, subunit D"
+545,putative SufE-like protein
+546,"[EC:6.3.2.2], Putative glutamate--cysteine ligase 2"
+547,"dapD, [EC:2.3.1.117], 2,3,4,5-tetrahydropyridine-2,6-dicarboxylate N-succinyltransferase"
+548,"glcC, Glc operon transcriptional activator"
+549,"degU, degU_1, degU_2, desR, desR_1, desR_2, liaR_1, liaR_2, lnrK, lnrK_1, lnrK_2, Transcriptional regulatory protein LiaR"
+550,"cadA, cadA_1, copA, copA_1, copA_2, copB, copB_1, copB_2, ctpA, ctpG, ctpG_1, ctpG_2, ctpG_3, [EC:7.2.2.-], [EC:7.2.2.12], [EC:7.2.2.8], Copper-exporting P-type ATPase B"
+551,"[EC:2.1.1.-], putative methyltransferase"
+552,"rutG, Putative pyrimidine permease RutG"
+553,"pbuG, Guanine/hypoxanthine permease PbuG"
+554,"ruvB, [EC:3.6.4.-], Holliday junction branch migration complex subunit RuvB"
+555,putative AAA domain-containing protein
+556,"rlmC, rlmCD, [EC:2.1.1.189], 23S rRNA (uracil-C(5))-methyltransferase RlmCD"
+557,"citE_1, citE_2, mcl1, [EC:4.1.-.-], [EC:4.1.3.24], Citrate lyase subunit beta-like protein"
+558,"ppk2B, [EC:2.7.4.-], [EC:2.7.4.1], Polyphosphate kinase PPK2B"
+559,"mhuD, [EC:1.14.99.57], Heme oxygenase (mycobilin-producing)"
+560,"yedI, Inner membrane protein YedI"
+561,"mmgF, prpB, [EC:4.1.3.-], [EC:4.1.3.30], 2-methylisocitrate lyase"
+562,"ybaK, [EC:4.2.-.-], Cys-tRNA(Pro)/Cys-tRNA(Cys) deacylase YbaK"
+563,"aceE, [EC:1.2.4.1], Pyruvate dehydrogenase E1 component"
+564,Thioredoxin-like reductase
+565,"bmr3, emrB, nepI, niaP, pbuE, rfnT, ribZ, ydhP, ydhP_1, ydhP_2, ydhP_3, ynfM, Inner membrane transport protein YdhP"
+566,"icd, [EC:1.1.1.42], Isocitrate dehydrogenase [NADP]"
+567,"metY, [EC:2.5.1.-], [EC:2.5.1.49], O-acetyl-L-homoserine sulfhydrylase"
+568,"sseA, sseB, [EC:2.8.1.1], Putative thiosulfate sulfurtransferase SseA"
+569,"aguA, [EC:3.5.3.12], Putative agmatine deiminase"
+570,"rarD, Protein RarD"
+571,Insertion element IS6110 uncharacterized 12.0 kDa protein
+572,"hutU, [EC:4.2.1.49], Urocanate hydratase"
+573,IS5 family transposase ISBli8
+574,"trxA, Thioredoxin"
+575,"aroH, [EC:2.5.1.54], Phospho-2-dehydro-3-deoxyheptonate aldolase"
+576,"ribM, Riboflavin/roseoflavin transporter RibM"
+577,"chdC, [EC:1.3.98.5], Coproheme decarboxylase"
+578,"paaA, paaC, [EC:1.14.13.149], 1,2-phenylacetyl-CoA epoxidase, subunit A"
+579,"fchA, [EC:3.5.4.9], Methenyltetrahydrofolate cyclohydrolase"
+580,"paaB, 1,2-phenylacetyl-CoA epoxidase, subunit B"
+581,"ylbL, putative protein YlbL"
+582,Cell wall synthesis protein Wag31
+583,"pdtaR, Transcriptional regulatory protein PdtaR"
+584,"gmk, [EC:2.7.4.8], Guanylate kinase"
+585,putative protein
+586,"msiK, potG, sugC, [EC:7.5.2.-], [EC:7.6.2.16], Trehalose import ATP-binding protein SugC"
+587,"nupA, [EC:7.6.2.-], Nucleoside import ATP-binding protein NupA"
+588,"pdtaS, [EC:2.7.13.3], Sensor histidine kinase PdtaS"
+589,"mazG, [EC:3.6.1.1], [EC:3.6.1.8], Nucleoside triphosphate pyrophosphohydrolase/pyrophosphatase MazG"
+590,"hpcG, [EC:4.2.1.163], 2-oxo-hept-4-ene-1,7-dioate hydratase"
+591,"tam, [EC:2.1.1.144], putative trans-aconitate 2-methyltransferase"
+592,"dop, [EC:2.1.1.-], [EC:3.4.-.-], Depupylase"
+593,"mctC, Monocarboxylic acid transporter"
+594,"gsiA, gsiA_1, gsiA_2, gsiA_3, [EC:7.4.2.10], Glutathione import ATP-binding protein GsiA"
+595,"[EC:1.-.-.-], putative oxidoreductase"
+596,"pmt, [EC:2.4.1.-], Polyprenol-phosphate-mannose--protein mannosyltransferase"
+597,"helY, [EC:3.6.4.-], putative helicase HelY"
+598,"cdsA, [EC:2.7.7.41], Phosphatidate cytidylyltransferase"
+599,"accA1, accA3, accA3_1, accA3_2, accA3_3, Biotin-dependent acyl-coenzyme A carboxylase alpha3 subunit"
+600,"accD1, accD5, [EC:2.1.3.-], [EC:2.1.3.15], Biotin-dependent acetyl-/propionyl-coenzyme A carboxylase beta5 subunit"
+601,"menC, ykfB, [EC:4.2.1.113], [EC:5.1.1.20], o-succinylbenzoate synthase"
+602,"xerC, xerD, Tyrosine recombinase XerC"
+603,"smoB, squF, [EC:1.1.1.432], 6-dehydroglucose reductase"
+604,"argD, [EC:2.6.1.11], Acetylornithine aminotransferase"
+605,"rhtA, Threonine/homoserine exporter RhtA"
+606,COG5032 family protein

Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/final_answer.txt

@@ -0,0 +1,35 @@
+<solution>
+## Summary
+
+I have successfully completed the comparative genomics task. Here's a summary of the workflow:
+
+### Data Processing Pipeline
+
+1. **Input Data Exploration**: Examined 5 *Micrococcus* genome FASTA files and a GFF annotation file from `/225040511/project/bioagent-bench/dataset/comparative-genomics/data/`
+   - KBS0714 (*Micrococcus* sp.) - GCF_002008305.4
+   - SA211 (*M. luteus*) - GCF_003691675.1
+   - AS2 (*M. luteus*) - GCF_005280335.1
+   - KD337-16 (*Micrococcus* sp.) - GCF_020097155.1
+   - TT9 (*M. yunnanensis*) - GCF_023573625.1
+
+2. **Genome Annotation**: Ran Prokka (v1.15.6) on all 5 genomes, generating protein predictions with COG functional annotations.
+
+3. **Ortholog Clustering**: Used Prokka's COG (Clusters of Orthologous Groups) assignments as the basis for identifying orthologous clusters across genomes.
+
+4. **Core Cluster Selection**: Filtered for clusters present in **all 5 genomes** (core genome), **coding-only** (CDS features), yielding **606 core COGs**.
+
+5. **Consensus Annotation**: For each cluster, generated a consensus annotation by combining:
+   - Gene names (from all genomes)
+   - EC numbers (from all genomes)
+   - Most frequently occurring product description
+
+### Final Output
+
+**File**: `cluster_annotation_mapping.csv` at the specified output path:
+`/225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/cluster_annotation_mapping.csv`
+
+**Format**: CSV with columns `cluster_number` and `consensus_annotation` containing 606 clusters with annotations following the format:
+- `"hemL, [EC:5.4.3.8], Glutamate-1-semialdehyde 2,1-aminomutase"`
+- `"amt, amtB, Ammonium transporter"`
+- `"xerC, xerD, Tyrosine recombinase XerC"`
+</solution>

Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/output_validation.json

@@ -0,0 +1,8 @@
+{
+  "postprocess": [
+    {
+      "file": "/225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/cluster_annotation_mapping.csv",
+      "actions": []
+    }
+  ]
+}

Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_005280335.1_ASM528033v1_genomic/ASM528033v1_genomic.log

@@ -0,0 +1,427 @@
+[14:17:24] This is prokka 1.15.6
+[14:17:24] Written by Torsten Seemann <torsten.seemann@gmail.com>
+[14:17:24] Homepage is https://github.com/tseemann/prokka
+[14:17:24] Local time is Wed May 20 14:17:24 2026
+[14:17:24] You are root
+[14:17:24] Operating system is linux
+[14:17:24] You have BioPerl 1.7.8
+[14:17:24] System has 104 cores.
+[14:17:24] Will use maximum of 4 cores.
+[14:17:24] Annotating as >>> Bacteria <<<
+[14:17:24] Generating locus_tag from '/225040511/project/bioagent-bench/dataset/comparative-genomics/data/GCF_005280335.1_ASM528033v1_genomic.fna' contents.
+[14:17:24] Setting --locustag ACLBLIBL from MD5 ac5b52b5b9a0fbc88b919620e476a41b
+[14:17:24] Creating new output folder: /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_005280335.1_ASM528033v1_genomic
+[14:17:24] Running: mkdir -p \/225040511\/project\/Biomanus\/experiments\/ablation\/results\/biomanus\/bioagentbench\/comparative\-genomics_20260520_140937\/prokka_output\/GCF_005280335\.1_ASM528033v1_genomic
+[14:17:24] Using filename prefix: ASM528033v1_genomic.XXX
+[14:17:24] Setting HMMER_NCPU=1
+[14:17:24] Writing log to: /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_005280335.1_ASM528033v1_genomic/ASM528033v1_genomic.log
+[14:17:24] Command: /225040511/miniconda3/envs/biomni_e1/bin/prokka --outdir /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_005280335.1_ASM528033v1_genomic --prefix ASM528033v1_genomic --genus Micrococcus --force --quiet --cpus 4 /225040511/project/bioagent-bench/dataset/comparative-genomics/data/GCF_005280335.1_ASM528033v1_genomic.fna
+[14:17:24] Looking for 'aragorn' - found /225040511/miniconda3/envs/biomni_e1/bin/aragorn
+[14:17:24] Determined aragorn version is v1.2 from 'ARAGORN v1.2.41 Dean Laslett'
+[14:17:24] Looking for 'barrnap' - found /225040511/miniconda3/envs/biomni_e1/bin/barrnap
+[14:17:24] Determined barrnap version is v0.9 from 'barrnap 0.9'
+[14:17:24] Looking for 'blastp' - found /225040511/miniconda3/envs/biomni_e1/bin/blastp
+[14:17:25] Determined blastp version is v2.17 from 'blastp: 2.17.0+'
+[14:17:25] Looking for 'cmpress' - found /225040511/miniconda3/envs/biomni_e1/bin/cmpress
+[14:17:25] Determined cmpress version is v1.1 from '# INFERNAL 1.1.5 (Sep 2023)'
+[14:17:25] Looking for 'cmscan' - found /225040511/miniconda3/envs/biomni_e1/bin/cmscan
+[14:17:25] Determined cmscan version is v1.1 from '# INFERNAL 1.1.5 (Sep 2023)'
+[14:17:25] Looking for 'egrep' - found /usr/bin/egrep
+[14:17:25] Looking for 'find' - found /usr/bin/find
+[14:17:25] Looking for 'grep' - found /usr/bin/grep
+[14:17:25] Looking for 'hmmpress' - found /225040511/miniconda3/envs/biomni_e1/bin/hmmpress
+[14:17:25] Determined hmmpress version is v3.4 from '# HMMER 3.4 (Aug 2023); http://hmmer.org/'
+[14:17:25] Looking for 'hmmscan' - found /225040511/miniconda3/envs/biomni_e1/bin/hmmscan
+[14:17:26] Determined hmmscan version is v3.4 from '# HMMER 3.4 (Aug 2023); http://hmmer.org/'
+[14:17:26] Looking for 'java' - found /225040511/miniconda3/envs/biomni_e1/bin/java
+[14:17:26] Looking for 'makeblastdb' - found /225040511/miniconda3/envs/biomni_e1/bin/makeblastdb
+[14:17:26] Determined makeblastdb version is v2.17 from 'makeblastdb: 2.17.0+'
+[14:17:26] Looking for 'minced' - found /225040511/miniconda3/envs/biomni_e1/bin/minced
+[14:17:26] Determined minced version is v4.2 from 'minced 0.4.2'
+[14:17:26] Looking for 'parallel' - found /225040511/miniconda3/envs/biomni_e1/bin/parallel
+[14:17:26] Determined parallel version is 20260422 from 'GNU parallel 20260422'
+[14:17:26] Looking for 'prodigal' - found /225040511/miniconda3/envs/biomni_e1/bin/prodigal
+[14:17:26] Determined prodigal version is v2.6 from 'Prodigal V2.6.3: February, 2016'
+[14:17:26] Looking for 'prokka-genbank_to_fasta_db' - found /225040511/miniconda3/envs/biomni_e1/bin/prokka-genbank_to_fasta_db
+[14:17:26] Looking for 'sed' - found /225040511/miniconda3/envs/biomni_e1/bin/sed
+[14:17:26] Looking for 'tbl2asn' - found /225040511/miniconda3/envs/biomni_e1/bin/tbl2asn
+[14:17:26] Determined tbl2asn version is v25.7 from 'tbl2asn 25.7   arguments:'
+[14:17:26] Using genetic code table 11.
+[14:17:26] Loading and checking input file: /225040511/project/bioagent-bench/dataset/comparative-genomics/data/GCF_005280335.1_ASM528033v1_genomic.fna
+[14:17:26] Wrote 1 contigs totalling 2848891 bp.
+[14:17:26] Predicting tRNAs and tmRNAs
+[14:17:26] Running: aragorn -l -gc11  -w \/225040511\/project\/Biomanus\/experiments\/ablation\/results\/biomanus\/bioagentbench\/comparative\-genomics_20260520_140937\/prokka_output\/GCF_005280335\.1_ASM528033v1_genomic\/ASM528033v1_genomic\.fna
+[14:17:30] 1 tRNA-Thr [29638,29713] 35 (cgt)
+[14:17:30] 2 tRNA-Ser [31517,31606] 35 (tga)
+[14:17:30] 3 tRNA-Ser [40470,40559] 35 (gct)
+[14:17:30] 4 tRNA-Arg [63633,63707] 35 (acg)
+[14:17:30] 5 tRNA-Ser [67201,67291] 35 (cga)
+[14:17:30] 6 tRNA-Ser c[174166,174252] 35 (gga)
+[14:17:30] 7 tRNA-Phe c[292563,292638] 34 (gaa)
+[14:17:30] 8 tRNA-Asp c[292710,292784] 35 (gtc)
+[14:17:30] 9 tRNA-Glu c[292901,292974] 35 (ttc)
+[14:17:30] 10 tRNA-Gly [304655,304743] 30 (ccc)
+[14:17:30] 11 tRNA-Lys c[311920,311994] 34 (ttt)
+[14:17:30] 12 tRNA-Leu c[407356,407441] 36 (cag)
+[14:17:30] 13 tRNA-Ala c[446978,447052] 34 (tgc)
+[14:17:30] 14 tRNA-Ile c[447282,447356] 35 (gat)
+[14:17:30] 15 tRNA-Arg [862364,862434] 31 (cct)
+[14:17:30] 16 tRNA-Ala [924811,924884] 34 (cgc)
+[14:17:30] 17 tRNA-Gly c[1014978,1015051] 33 (ccc)
+[14:17:30] 18 tRNA-Tyr [1176493,1176575] 35 (gta)
+[14:17:30] 19 tRNA-Thr [1188289,1188361] 33 (ggt)
+[14:17:30] 20 tRNA-Met [1188421,1188496] 35 (cat)
+[14:17:30] 21 tRNA-Trp [1206702,1206775] 34 (cca)
+[14:17:30] 22 tRNA-Met [1477314,1477388] 35 (cat)
+[14:17:30] 23 tRNA-Pro [1574941,1575017] 35 (ggg)
+[14:17:30] 24 tRNA-Leu [1852668,1852753] 35 (gag)
+[14:17:30] 25 tRNA-Leu c[1949372,1949455] 35 (caa)
+[14:17:30] 26 tRNA-Gly [1977815,1977889] 35 (gcc)
+[14:17:30] 27 tRNA-Cys [1977907,1977978] 33 (gca)
+[14:17:30] 28 tRNA-Val [1978036,1978108] 33 (gac)
+[14:17:30] 29 tRNA-Gly [1978138,1978214] 35 (gcc)
+[14:17:30] 30 tRNA-Ala c[2022453,2022529] 35 (ggc)
+[14:17:30] 31 tRNA-Ala c[2023915,2023990] 34 (ggc)
+[14:17:30] 32 tRNA-Pro c[2062808,2062882] 35 (tgg)
+[14:17:30] 33 tRNA-Gly [2063969,2064042] 33 (tcc)
+[14:17:30] 34 tRNA-Arg [2074896,2074971] 35 (tct)
+[14:17:30] 35 tRNA-His [2082250,2082325] 34 (gtg)
+[14:17:30] 36 tRNA-Val c[2143539,2143614] 35 (tac)
+[14:17:30] 37 tRNA-Glu c[2213130,2213205] 35 (ctc)
+[14:17:30] 38 tRNA-Glu c[2213342,2213415] 35 (ctc)
+[14:17:30] 39 tRNA-Gln c[2213472,2213544] 34 (ctg)
+[14:17:30] 40 tRNA-Lys [2233518,2233593] 34 (ctt)
+[14:17:30] 41 tRNA-Leu [2234241,2234322] 35 (tag)
+[14:17:30] 42 tRNA-Arg [2297894,2297969] 34 (ccg)
+[14:17:30] 43 tmRNA c[2330355,2330724] 96,134 AESKRTDFALAA*
+[14:17:30] 44 tRNA-Met c[2461047,2461121] 35 (cat)
+[14:17:30] 45 tRNA-Asn c[2490907,2490980] 34 (gtt)
+[14:17:30] 46 tRNA-Ala c[2538106,2538203] 36 (ggc)
+[14:17:30] 47 tRNA-Gln c[2601867,2601941] 33 (ttg)
+[14:17:30] 48 tRNA-Phe [2639905,2640002] 35 (gaa)
+[14:17:30] 49 tRNA-Leu c[2659513,2659587] 35 (taa)
+[14:17:30] 50 tRNA-Arg [2757271,2757346] 35 (cct)
+[14:17:30] 51 tRNA-Val c[2773796,2773871] 35 (cac)
+[14:17:30] 52 tRNA-Thr c[2783032,2783107] 34 (tgt)
+[14:17:30] 53 tRNA-Pro c[2838596,2838672] 35 (cgg)
+[14:17:30] Found 53 tRNAs
+[14:17:30] Predicting Ribosomal RNAs
+[14:17:30] Running Barrnap with 4 threads
+[14:17:32] 1 NZ_CP040019.1 31 5S ribosomal RNA
+[14:17:32] 2 NZ_CP040019.1 337 23S ribosomal RNA
+[14:17:32] 3 NZ_CP040019.1 3871 16S ribosomal RNA
+[14:17:32] 4 NZ_CP040019.1 1546240 16S ribosomal RNA
+[14:17:32] 5 NZ_CP040019.1 1548213 23S ribosomal RNA
+[14:17:32] 6 NZ_CP040019.1 1551497 5S ribosomal RNA
+[14:17:32] 7 NZ_CP040019.1 2839386 5S ribosomal RNA
+[14:17:32] 8 NZ_CP040019.1 2839692 23S ribosomal RNA
+[14:17:32] 9 NZ_CP040019.1 2843229 16S ribosomal RNA
+[14:17:32] Found 9 rRNAs
+[14:17:32] Skipping ncRNA search, enable with --rfam if desired.
+[14:17:32] Total of 61 tRNA + rRNA features
+[14:17:32] Searching for CRISPR repeats
+[14:17:33] Found 0 CRISPRs
+[14:17:33] Predicting coding sequences
+[14:17:33] Contigs total 2848891 bp, so using single mode
+[14:17:33] Running: prodigal -i \/225040511\/project\/Biomanus\/experiments\/ablation\/results\/biomanus\/bioagentbench\/comparative\-genomics_20260520_140937\/prokka_output\/GCF_005280335\.1_ASM528033v1_genomic\/ASM528033v1_genomic\.fna -c -m -g 11 -p single -f sco -q
+[14:17:40] Excluding CDS which overlaps existing RNA (tRNA) at NZ_CP040019.1:304708..305631 on - strand
+[14:17:41] Excluding CDS which overlaps existing RNA (tRNA) at NZ_CP040019.1:861816..862478 on + strand
+[14:17:42] Excluding CDS which overlaps existing RNA (tRNA) at NZ_CP040019.1:1574980..1575393 on - strand
+[14:17:42] Excluding CDS which overlaps existing RNA (tRNA) at NZ_CP040019.1:2210621..2213170 on + strand
+[14:17:42] Excluding CDS which overlaps existing RNA (tRNA) at NZ_CP040019.1:2537639..2540023 on - strand
+[14:17:42] Excluding CDS which overlaps existing RNA (tRNA) at NZ_CP040019.1:2639543..2640532 on - strand
+[14:17:43] Found 2623 CDS
+[14:17:43] Connecting features back to sequences
+[14:17:43] Not using genus-specific database. Try --usegenus to enable it.
+[14:17:43] Annotating CDS, please be patient.
+[14:17:43] Will use 4 CPUs for similarity searching.
+[14:17:43] There are still 2623 unannotated CDS left (started with 2623)
+[14:17:43] Will use blast to search against /225040511/miniconda3/envs/biomni_e1/db/kingdom/Bacteria/IS with 4 CPUs
+[14:17:43] Running: cat \/225040511\/project\/Biomanus\/experiments\/ablation\/results\/biomanus\/bioagentbench\/comparative\-genomics_20260520_140937\/prokka_output\/GCF_005280335\.1_ASM528033v1_genomic\/ASM528033v1_genomic\.IS\.tmp\.352040\.faa | parallel --gnu --plain -j 4 --block 106516 --recstart '>' --pipe blastp -query - -db /225040511/miniconda3/envs/biomni_e1/db/kingdom/Bacteria/IS -evalue 1e-30 -qcov_hsp_perc 90 -num_threads 1 -num_descriptions 1 -num_alignments 1 -seg no > \/225040511\/project\/Biomanus\/experiments\/ablation\/results\/biomanus\/bioagentbench\/comparative\-genomics_20260520_140937\/prokka_output\/GCF_005280335\.1_ASM528033v1_genomic\/ASM528033v1_genomic\.IS\.tmp\.352040\.blast 2> /dev/null
+[14:18:03] Deleting unwanted file: /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_005280335.1_ASM528033v1_genomic/ASM528033v1_genomic.IS.tmp.352040.faa
+[14:18:03] Deleting unwanted file: /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_005280335.1_ASM528033v1_genomic/ASM528033v1_genomic.IS.tmp.352040.blast
+[14:18:04] There are still 2546 unannotated CDS left (started with 2623)
+[14:18:04] Will use blast to search against /225040511/miniconda3/envs/biomni_e1/db/kingdom/Bacteria/AMR with 4 CPUs
+[14:18:04] Running: cat \/225040511\/project\/Biomanus\/experiments\/ablation\/results\/biomanus\/bioagentbench\/comparative\-genomics_20260520_140937\/prokka_output\/GCF_005280335\.1_ASM528033v1_genomic\/ASM528033v1_genomic\.AMR\.tmp\.352040\.faa | parallel --gnu --plain -j 4 --block 104136 --recstart '>' --pipe blastp -query - -db /225040511/miniconda3/envs/biomni_e1/db/kingdom/Bacteria/AMR -evalue 1e-300 -qcov_hsp_perc 90 -num_threads 1 -num_descriptions 1 -num_alignments 1 -seg no > \/225040511\/project\/Biomanus\/experiments\/ablation\/results\/biomanus\/bioagentbench\/comparative\-genomics_20260520_140937\/prokka_output\/GCF_005280335\.1_ASM528033v1_genomic\/ASM528033v1_genomic\.AMR\.tmp\.352040\.blast 2> /dev/null
+[14:18:33] Deleting unwanted file: /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_005280335.1_ASM528033v1_genomic/ASM528033v1_genomic.AMR.tmp.352040.faa
+[14:18:33] Deleting unwanted file: /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_005280335.1_ASM528033v1_genomic/ASM528033v1_genomic.AMR.tmp.352040.blast
+[14:18:34] There are still 2545 unannotated CDS left (started with 2623)
+[14:18:34] Will use blast to search against /225040511/miniconda3/envs/biomni_e1/db/kingdom/Bacteria/sprot with 4 CPUs
+[14:18:34] Running: cat \/225040511\/project\/Biomanus\/experiments\/ablation\/results\/biomanus\/bioagentbench\/comparative\-genomics_20260520_140937\/prokka_output\/GCF_005280335\.1_ASM528033v1_genomic\/ASM528033v1_genomic\.sprot\.tmp\.352040\.faa | parallel --gnu --plain -j 4 --block 103989 --recstart '>' --pipe blastp -query - -db /225040511/miniconda3/envs/biomni_e1/db/kingdom/Bacteria/sprot -evalue 1e-09 -qcov_hsp_perc 80 -num_threads 1 -num_descriptions 1 -num_alignments 1 -seg no > \/225040511\/project\/Biomanus\/experiments\/ablation\/results\/biomanus\/bioagentbench\/comparative\-genomics_20260520_140937\/prokka_output\/GCF_005280335\.1_ASM528033v1_genomic\/ASM528033v1_genomic\.sprot\.tmp\.352040\.blast 2> /dev/null
+[14:19:56] Modify product: Nudix hydrolase DR_1184 => Nudix hydrolase
+[14:19:56] Modify product: Uncharacterized ATP-dependent helicase YprA => putative ATP-dependent helicase YprA
+[14:19:56] Modify product: Uncharacterized protein Rv0498 => putative protein
+[14:19:56] Modify product: Uncharacterized protein Rv0525 => putative protein
+[14:19:56] Modify product: Probable 2-succinylbenzoate--CoA ligase => putative 2-succinylbenzoate--CoA ligase
+[14:19:56] Modify product: Probable enoyl-CoA hydratase EchA8 => putative enoyl-CoA hydratase EchA8
+[14:19:56] Modify product: Uncharacterized oxidoreductase Rv1144 => putative oxidoreductase
+[14:19:56] Modify product: Nucleotide-binding protein SCO4614 => Nucleotide-binding protein
+[14:19:56] Modify product: UPF0336 protein Rv0637 => hypothetical protein
+[14:19:56] Modify product: Glycogen operon protein GlgX homolog => Glycogen operon protein GlgX 
+[14:19:56] Modify product: Uncharacterized protein Rv3421c => putative protein
+[14:19:56] Modify product: Probable zinc-binding alcohol dehydrogenase Rv1895 => putative zinc-binding alcohol dehydrogenase
+[14:19:56] Modify product: Uncharacterized oxidoreductase MSMEG_1603/MSMEI_1564 => putative oxidoreductase/MSMEI_1564
+[14:19:56] Modify product: Macro domain-containing protein PG1779 => Macro domain-containing protein
+[14:19:56] Modify product: Protein Rv2133c => Protein
+[14:19:56] Modify product: Protein Rv2133c => Protein
+[14:19:56] Modify product: Probable nicotinate-nucleotide pyrophosphorylase [carboxylating] => putative nicotinate-nucleotide pyrophosphorylase [carboxylating]
+[14:19:56] Modify product: Uncharacterized lipoprotein Rv2585c => putative lipoprotein
+[14:19:56] Modify product: Probable aminotransferase Rv1178 => putative aminotransferase
+[14:19:56] Modify product: Probable O-methyltransferase Rv1220c => putative O-methyltransferase
+[14:19:56] Modify product: Probable ATP-binding protein YheS => putative ATP-binding protein YheS
+[14:19:56] Modify product: Transcriptional repressor SmtB homolog => Transcriptional repressor SmtB 
+[14:19:56] Modify product: Probable cation-transporting ATPase G => putative cation-transporting ATPase G
+[14:19:56] Modify product: Probable cation-transporting ATPase G => putative cation-transporting ATPase G
+[14:19:56] Modify product: Uncharacterized oxidoreductase CzcO => putative oxidoreductase CzcO
+[14:19:56] Modify product: UPF0371 protein DIP2346 => hypothetical protein
+[14:19:56] Modify product: Uncharacterized protein Rv1290c => putative protein
+[14:19:56] Modify product: Uncharacterized GMC-type oxidoreductase Rv1279 => putative GMC-type oxidoreductase
+[14:19:56] Modify product: Uncharacterized ABC transporter ATP-binding protein YknY => putative ABC transporter ATP-binding protein YknY
+[14:19:57] Modify product: Probable cold shock protein A => putative cold shock protein A
+[14:19:57] Modify product: Probable lipoprotein aminopeptidase LpqL => putative lipoprotein aminopeptidase LpqL
+[14:19:57] Modify product: Putative multidrug export ATP-binding/permease protein SA1683 => Putative multidrug export ATP-binding/permease protein
+[14:19:57] Modify product: Uncharacterized ABC transporter ATP-binding protein YwjA => putative ABC transporter ATP-binding protein YwjA
+[14:19:57] Modify product: Uncharacterized tRNA/rRNA methyltransferase Rv3579c => putative tRNA/rRNA methyltransferase
+[14:19:57] Modify product: Phosphate-specific transport system accessory protein PhoU homolog 2 => Phosphate-specific transport system accessory protein PhoU 
+[14:19:57] Modify product: Uncharacterized protein Rv1276c => putative protein
+[14:19:57] Modify product: Probable glycine dehydrogenase (decarboxylating) => putative glycine dehydrogenase (decarboxylating)
+[14:19:57] Modify product: UPF0324 inner membrane protein YeiH => hypothetical protein
+[14:19:57] Modify product: Uncharacterized oxidoreductase Rv1144 => putative oxidoreductase
+[14:19:57] Modify product: Probable enoyl-CoA hydratase EchA8 => putative enoyl-CoA hydratase EchA8
+[14:19:57] Modify product: Probable bifunctional transcriptional activator/DNA repair enzyme AlkA => putative bifunctional transcriptional activator/DNA repair enzyme AlkA
+[14:19:57] Modify product: Probable FMNH2-dependent monooxygenase SfnC => putative FMNH2-dependent monooxygenase SfnC
+[14:19:57] Modify product: Uncharacterized ABC transporter ATP-binding protein YwjA => putative ABC transporter ATP-binding protein YwjA
+[14:19:57] Modify product: Uncharacterized protein Rv2895c => putative protein
+[14:19:57] Modify product: Probable FMNH2-dependent monooxygenase SfnC => putative FMNH2-dependent monooxygenase SfnC
+[14:19:57] Modify product: Type I restriction enzyme BthVORF4518P methylase subunit => Type I restriction enzymeP methylase subunit
+[14:19:57] Modify product: Probable inactive lipase Rv1592c => putative inactive lipase
+[14:19:57] Modify product: Universal stress protein MT2698 => Universal stress protein
+[14:19:57] Modify product: UPF0045 protein Rv1898 => hypothetical protein
+[14:19:57] Modify product: Putative 2-hydroxyacid dehydrogenase SA2098 => Putative 2-hydroxyacid dehydrogenase
+[14:19:57] Modify product: Uncharacterized protein Rv0088 => putative protein
+[14:19:57] Modify product: Putative low molecular weight protein-tyrosine-phosphatase slr0328 => Putative low molecular weight protein-tyrosine-phosphatase
+[14:19:57] Modify product: Probable ketoamine kinase HMPREF0351_12196 => putative ketoamine kinase
+[14:19:57] Modify product: Carboxypeptidase Rv3627c => Carboxypeptidase
+[14:19:57] Modify product: Sulfurtransferase Alvin_2599 => Sulfurtransferase
+[14:19:57] Modify product: Probable glycerophosphodiester phosphodiesterase 2 => putative glycerophosphodiester phosphodiesterase 2
+[14:19:57] Modify product: UPF0312 protein SA2479 => hypothetical protein
+[14:19:57] Modify product: Uncharacterized protein Rv0102 => putative protein
+[14:19:57] Modify product: Probable M18 family aminopeptidase 2 => putative M18 family aminopeptidase 2
+[14:19:57] Modify product: Uncharacterized protein MSMEG_1279/MSMEI_1241 => putative protein/MSMEI_1241
+[14:19:57] Modify product: Probable zinc-binding alcohol dehydrogenase Rv1895 => putative zinc-binding alcohol dehydrogenase
+[14:19:57] Modify product: Uncharacterized oxidoreductase YghA => putative oxidoreductase YghA
+[14:19:57] Modify product: Putative glutaredoxin Rv3198A => Putative glutaredoxinA
+[14:19:57] Modify product: Acetyltransferase PA3944 => Acetyltransferase
+[14:19:57] Modify product: Uncharacterized N-acetyltransferase Rv2669 => putative N-acetyltransferase
+[14:19:57] Modify product: Uncharacterized sugar epimerase YhfK => putative sugar epimerase YhfK
+[14:19:57] Modify product: Probable siderophore transport system ATP-binding protein YusV => putative siderophore transport system ATP-binding protein YusV
+[14:19:57] Modify product: Probable transcriptional regulatory protein TcrX => putative transcriptional regulatory protein TcrX
+[14:19:57] Modify product: Uncharacterized ABC transporter ATP-binding protein YwjA => putative ABC transporter ATP-binding protein YwjA
+[14:19:57] Modify product: Uncharacterized glycosyl hydrolase MT2062 => putative glycosyl hydrolase
+[14:19:57] Modify product: Uncharacterized protein YdhK => putative protein YdhK
+[14:19:57] Modify product: Uncharacterized ABC transporter ATP-binding protein Rv1273c => putative ABC transporter ATP-binding protein
+[14:19:57] Modify product: Uncharacterized ABC transporter ATP-binding protein YknY => putative ABC transporter ATP-binding protein YknY
+[14:19:57] Modify product: Acetyl- and succinyl-CoA transferase Rv0802c => Acetyl- and succinyl-CoA transferase
+[14:19:57] Modify product: Uncharacterized protein Rv2237 => putative protein
+[14:19:57] Modify product: Acetyltransferase PA3944 => Acetyltransferase
+[14:19:57] Modify product: DegV domain-containing protein SA1258 => DegV domain-containing protein
+[14:19:57] Modify product: Probable DNA polymerase III subunit delta => putative DNA polymerase III subunit delta
+[14:19:57] Modify product: UPF0053 protein Rv2366c => hypothetical protein
+[14:19:57] Modify product: Uncharacterized protein Rv2206 => putative protein
+[14:19:57] Modify product: Protein Rv2204c => Protein
+[14:19:57] Modify product: Probable cytochrome c oxidase subunit 1 => putative cytochrome c oxidase subunit 1
+[14:19:57] Modify product: Probable cytochrome c oxidase polypeptide 4 => putative cytochrome c oxidase polypeptide 4
+[14:19:57] Modify product: Probable helicase HelY => putative helicase HelY
+[14:19:57] Modify product: Phosphorylated carbohydrates phosphatase TM_1254 => Phosphorylated carbohydrates phosphatase
+[14:19:57] Modify product: Uncharacterized ABC transporter ATP-binding protein YlmA => putative ABC transporter ATP-binding protein YlmA
+[14:19:57] Modify product: Uncharacterized SURF1-like protein Rv2235 => putative SURF1-like protein
+[14:19:57] Modify product: Probable ATP-binding protein YheS => putative ATP-binding protein YheS
+[14:19:57] Modify product: Uncharacterized protein Rv2575 => putative protein
+[14:19:57] Modify product: Iron-sulfur cluster assembly SufBD family protein Rv1462 => Iron-sulfur cluster assembly SufBD family protein
+[14:19:57] Modify product: Iron-sulfur cluster assembly SufBD family protein SA0778 => Iron-sulfur cluster assembly SufBD family protein
+[14:19:57] Modify product: Probable cell division protein WhiA => putative cell division protein WhiA
+[14:19:57] Modify product: Nucleotide-binding protein Rv1421 => Nucleotide-binding protein
+[14:19:57] Modify product: Probable trans-aconitate 2-methyltransferase => putative trans-aconitate 2-methyltransferase
+[14:19:57] Modify product: Uncharacterized membrane protein Rv2723 => putative membrane protein
+[14:19:57] Modify product: Putative methyltransferase Rv1407 => Putative methyltransferase
+[14:19:57] Modify product: Uncharacterized SufE-like protein Rv3284 => putative SufE-like protein
+[14:19:57] Modify product: Uncharacterized oxidoreductase YdgJ => putative oxidoreductase YdgJ
+[14:19:57] Modify product: Probable nicotinate-nucleotide adenylyltransferase => putative nicotinate-nucleotide adenylyltransferase
+[14:19:57] Modify product: Uncharacterized oxidoreductase Rv0484c => putative oxidoreductase
+[14:19:57] Modify product: Thioredoxin-like reductase Rv2466c => Thioredoxin-like reductase
+[14:19:57] Modify product: Uncharacterized protein YlbL => putative protein YlbL
+[14:19:57] Modify product: UPF0182 protein MSMEG_1959/MSMEI_1915 => hypothetical protein
+[14:19:57] Modify product: Uncharacterized protein Rv1708 => putative protein
+[14:19:57] Modify product: Uncharacterized HTH-type transcriptional regulator Rv1828 => putative HTH-type transcriptional regulator
+[14:19:57] Modify product: Uncharacterized protein Rv1829 => putative protein
+[14:19:57] Modify product: Uncharacterized HTH-type transcriptional regulator Rv1830 => putative HTH-type transcriptional regulator
+[14:19:57] Modify product: DNA-binding protein Rv2175c => DNA-binding protein
+[14:19:57] Modify product: Probable peptidoglycan glycosyltransferase FtsW => putative peptidoglycan glycosyltransferase FtsW
+[14:19:57] Modify product: Uncharacterized RNA pseudouridine synthase Rv1540 => putative RNA pseudouridine synthase
+[14:19:57] Modify product: Probable cytosol aminopeptidase => putative cytosol aminopeptidase
+[14:19:57] Modify product: Probable transcriptional regulatory protein Rv2603c => putative transcriptional regulatory protein
+[14:19:57] Modify product: Uncharacterized protein MSMEG_2731/MSMEI_2664 => putative protein/MSMEI_2664
+[14:19:57] Modify product: Uncharacterized transporter Rv1999c => putative transporter
+[14:19:57] Modify product: Uncharacterized AAA domain-containing protein Rv2559c => putative AAA domain-containing protein
+[14:19:57] Modify product: Probable replication restart protein PriA => putative replication restart protein PriA
+[14:19:57] Modify product: GTP cyclohydrolase 1 type 2 homolog => GTP cyclohydrolase 1 type 2 
+[14:19:57] Modify product: Uncharacterized protein Rv2239c => putative protein
+[14:19:57] Modify product: Uncharacterized protein Rv2242 => putative protein
+[14:19:57] Modify product: Uncharacterized protein Rv2901c => putative protein
+[14:19:57] Modify product: Uncharacterized protein Rv2926c => putative protein
+[14:19:57] Modify product: Probable N-succinyldiaminopimelate aminotransferase DapC => putative N-succinyldiaminopimelate aminotransferase DapC
+[14:19:57] Modify product: RNA/DNA methyltransferase Rv2966c => RNA/DNA methyltransferase
+[14:19:57] Modify product: Uncharacterized protein SA1069 => putative protein
+[14:19:57] Modify product: Protein Rv2993c => Protein
+[14:19:57] Modify product: Putative peroxiredoxin Rv2521 => Putative peroxiredoxin
+[14:19:58] Modify product: Probable malate:quinone oxidoreductase => putative malate:quinone oxidoreductase
+[14:19:58] Modify product: Uncharacterized protein Rv1339 => putative protein
+[14:19:58] Modify product: Uncharacterized protein Rv1324 => putative protein
+[14:19:58] Modify product: Uncharacterized protein Rv1322 => putative protein
+[14:19:58] Modify product: Probable adenylyltransferase/sulfurtransferase MoeZ => putative adenylyltransferase/sulfurtransferase MoeZ
+[14:19:58] Modify product: Uncharacterized HIT-like protein Rv0759c => putative HIT-like protein
+[14:19:58] Modify product: Uncharacterized protein Rv1841c => putative protein
+[14:19:58] Modify product: UPF0053 protein Rv1842c => hypothetical protein
+[14:19:58] Modify product: Probable succinyl-CoA:3-ketoacid coenzyme A transferase subunit B => putative succinyl-CoA:3-ketoacid coenzyme A transferase subunit B
+[14:19:58] Modify product: Probable succinyl-CoA:3-ketoacid coenzyme A transferase subunit A => putative succinyl-CoA:3-ketoacid coenzyme A transferase subunit A
+[14:19:58] Modify product: Probable acetyl-CoA acetyltransferase => putative acetyl-CoA acetyltransferase
+[14:19:58] Modify product: Probable pyridine nucleotide-disulfide oxidoreductase RclA => putative pyridine nucleotide-disulfide oxidoreductase RclA
+[14:19:58] Modify product: Uncharacterized zinc protease Rv2782c => putative zinc protease
+[14:19:58] Modify product: Uncharacterized methyltransferase Rv3342 => putative methyltransferase
+[14:19:58] Modify product: Probable membrane transporter protein YfcA => putative membrane transporter protein YfcA
+[14:19:58] Modify product: Aldo-keto reductase MSMEG_2408/MSMEI_2347 => Aldo-keto reductase/MSMEI_2347
+[14:19:58] Modify product: Uncharacterized oxidoreductase YghA => putative oxidoreductase YghA
+[14:19:58] Modify product: Uncharacterized protein Rv1841c => putative protein
+[14:19:58] Modify product: UPF0053 protein Rv1842c => hypothetical protein
+[14:19:58] Modify product: Uncharacterized oxidoreductase CzcO => putative oxidoreductase CzcO
+[14:19:58] Modify product: Probable cation-transporting ATPase G => putative cation-transporting ATPase G
+[14:19:58] Modify product: Probable phosphomannomutase => putative phosphomannomutase
+[14:19:58] Modify product: Uncharacterized metal-dependent hydrolase TatD => putative metal-dependent hydrolase TatD
+[14:19:58] Modify product: Putative transport protein Rv0205 => Putative transport protein
+[14:19:58] Modify product: Uncharacterized protein YihR => putative protein YihR
+[14:19:58] Modify product: Uncharacterized HTH-type transcriptional regulator YybR => putative HTH-type transcriptional regulator YybR
+[14:19:58] Modify product: Probable hydrolase sll0100 => putative hydrolase
+[14:19:58] Modify product: Bifunctional protein FolD => Bifunctional protein FolD protein
+[14:19:58] Modify product: Uncharacterized ABC transporter ATP-binding protein YwjA => putative ABC transporter ATP-binding protein YwjA
+[14:19:58] Modify product: Probable transcriptional regulatory protein TcrX => putative transcriptional regulatory protein TcrX
+[14:19:58] Modify product: Probable threonine/serine exporter => putative threonine/serine exporter
+[14:19:58] Modify product: Uncharacterized protein Rv0525 => putative protein
+[14:19:58] Modify product: cAMP/cGMP dual specificity phosphodiesterase Rv0805 => cAMP/cGMP dual specificity phosphodiesterase
+[14:19:58] Cleaned 159 /product names
+[14:19:58] Deleting unwanted file: /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_005280335.1_ASM528033v1_genomic/ASM528033v1_genomic.sprot.tmp.352040.faa
+[14:19:58] Deleting unwanted file: /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_005280335.1_ASM528033v1_genomic/ASM528033v1_genomic.sprot.tmp.352040.blast
+[14:19:58] Labelling remaining 1391 proteins as 'hypothetical protein'
+[14:19:58] Possible /pseudo 'Long-chain alkane monooxygenase' at NZ_CP040019.1 position 106330
+[14:19:58] Possible /pseudo 'IS481 family transposase ISKrh2' at NZ_CP040019.1 position 167070
+[14:19:58] Possible /pseudo 'IS256 family transposase ISMlu11' at NZ_CP040019.1 position 265295
+[14:19:58] Possible /pseudo 'putative cation-transporting ATPase G' at NZ_CP040019.1 position 761785
+[14:19:58] Possible /pseudo 'Arsenate-mycothiol transferase ArsC1' at NZ_CP040019.1 position 770468
+[14:19:58] Possible /pseudo 'IS5 family transposase ISBli8' at NZ_CP040019.1 position 781800
+[14:19:58] Possible /pseudo 'IS5 family transposase ISBli8' at NZ_CP040019.1 position 1340350
+[14:19:58] Possible /pseudo 'IS5 family transposase ISBli8' at NZ_CP040019.1 position 1360511
+[14:19:58] Possible /pseudo 'IS5 family transposase ISBli8' at NZ_CP040019.1 position 1368352
+[14:19:58] Possible /pseudo 'IS5 family transposase ISBli8' at NZ_CP040019.1 position 1371169
+[14:19:58] Possible /pseudo 'FK506-binding protein' at NZ_CP040019.1 position 1836839
+[14:19:58] Possible /pseudo 'Iron-sulfur cluster assembly SufBD family protein' at NZ_CP040019.1 position 1886567
+[14:19:58] Possible /pseudo 'IS5 family transposase ISBli8' at NZ_CP040019.1 position 2474605
+[14:19:58] Possible /pseudo 'IS5 family transposase ISBli8' at NZ_CP040019.1 position 2490265
+[14:19:58] Possible /pseudo 'IS3 family transposase ISBli17' at NZ_CP040019.1 position 2778878
+[14:19:58] Possible /pseudo 'IS5 family transposase ISBli8' at NZ_CP040019.1 position 2794140
+[14:19:58] Found 915 unique /gene codes.
+[14:19:58] Fixed 2 duplicate /gene - ettA_1 ettA_2
+[14:19:58] Fixed 2 duplicate /gene - metB_1 metB_2
+[14:19:58] Fixed 2 duplicate /gene - pcaR_1 pcaR_2
+[14:19:58] Fixed 2 duplicate /gene - trxB_1 trxB_2
+[14:19:58] Fixed 2 duplicate /gene - echA8_1 echA8_2
+[14:19:58] Fixed 2 duplicate /gene - czcO_1 czcO_2
+[14:19:58] Fixed 2 duplicate /gene - yheS_1 yheS_2
+[14:19:58] Fixed 2 duplicate /gene - lspA_1 lspA_2
+[14:19:58] Fixed 3 duplicate /gene - ctpG_1 ctpG_2 ctpG_3
+[14:19:58] Fixed 2 duplicate /gene - iscS_1 iscS_2
+[14:19:58] Fixed 2 duplicate /gene - def_1 def_2
+[14:19:58] Fixed 2 duplicate /gene - ladA_1 ladA_2
+[14:19:58] Fixed 2 duplicate /gene - ilvG_1 ilvG_2
+[14:19:58] Fixed 2 duplicate /gene - acp_1 acp_2
+[14:19:58] Fixed 2 duplicate /gene - copZ_1 copZ_2
+[14:19:58] Fixed 2 duplicate /gene - bkdB_1 bkdB_2
+[14:19:58] Fixed 2 duplicate /gene - gsiD_1 gsiD_2
+[14:19:58] Fixed 2 duplicate /gene - hbpA_1 hbpA_2
+[14:19:58] Fixed 2 duplicate /gene - lcfB_1 lcfB_2
+[14:19:58] Fixed 4 duplicate /gene - hin_1 hin_2 hin_3 hin_4
+[14:19:58] Fixed 2 duplicate /gene - mrpD_1 mrpD_2
+[14:19:58] Fixed 2 duplicate /gene - yghA_1 yghA_2
+[14:19:58] Fixed 2 duplicate /gene - fcs_1 fcs_2
+[14:19:58] Fixed 2 duplicate /gene - lepB_1 lepB_2
+[14:19:58] Fixed 2 duplicate /gene - sfnC_1 sfnC_2
+[14:19:58] Fixed 2 duplicate /gene - gyrA_1 gyrA_2
+[14:19:58] Fixed 4 duplicate /gene - ywjA_1 ywjA_2 ywjA_3 ywjA_4
+[14:19:58] Fixed 2 duplicate /gene - sad_1 sad_2
+[14:19:58] Fixed 2 duplicate /gene - acdA_1 acdA_2
+[14:19:58] Fixed 2 duplicate /gene - rspR_1 rspR_2
+[14:19:58] Fixed 2 duplicate /gene - liaR_1 liaR_2
+[14:19:58] Fixed 2 duplicate /gene - arsC1_1 arsC1_2
+[14:19:58] Fixed 3 duplicate /gene - ydhP_1 ydhP_2 ydhP_3
+[14:19:58] Fixed 5 duplicate /gene - mmgC_1 mmgC_2 mmgC_3 mmgC_4 mmgC_5
+[14:19:58] Fixed 3 duplicate /gene - galE_1 galE_2 galE_3
+[14:19:58] Fixed 2 duplicate /gene - metI_1 metI_2
+[14:19:58] Fixed 2 duplicate /gene - map_1 map_2
+[14:19:58] Fixed 2 duplicate /gene - tcrX_1 tcrX_2
+[14:19:58] Fixed 2 duplicate /gene - bkdA_1 bkdA_2
+[14:19:58] Fixed 2 duplicate /gene - desR_1 desR_2
+[14:19:58] Fixed 3 duplicate /gene - pepN_1 pepN_2 pepN_3
+[14:19:58] Fixed 2 duplicate /gene - fkbP_1 fkbP_2
+[14:19:58] Fixed 3 duplicate /gene - gsiA_1 gsiA_2 gsiA_3
+[14:19:58] Fixed 2 duplicate /gene - paaJ_1 paaJ_2
+[14:19:58] Fixed 2 duplicate /gene - citE_1 citE_2
+[14:19:58] Fixed 2 duplicate /gene - metN_1 metN_2
+[14:19:58] Fixed 2 duplicate /gene - cadA_1 cadA_2
+[14:19:58] Fixed 2 duplicate /gene - adh_1 adh_2
+[14:19:58] Fixed 2 duplicate /gene - yknY_1 yknY_2
+[14:19:58] Fixed 2 duplicate /gene - dapE_1 dapE_2
+[14:19:58] Fixed 2 duplicate /gene - fadA6_1 fadA6_2
+[14:19:58] Fixed 2 duplicate /gene - dmoA_1 dmoA_2
+[14:19:58] Fixed 2 duplicate /gene - fprA_1 fprA_2
+[14:19:58] Fixed 2 duplicate /gene - rimJ_1 rimJ_2
+[14:19:58] Fixed 2 duplicate /gene - aldR_1 aldR_2
+[14:19:58] Fixed 2 duplicate /gene - stp_1 stp_2
+[14:19:58] Fixed 3 duplicate /gene - cmtR_1 cmtR_2 cmtR_3
+[14:19:58] Fixed 5 duplicate /gene - acsA_1 acsA_2 acsA_3 acsA_4 acsA_5
+[14:19:58] Fixed 2 duplicate /gene - pgsA2_1 pgsA2_2
+[14:19:58] Fixed 2 duplicate /gene - ltaE_1 ltaE_2
+[14:19:58] Fixed 2 duplicate /gene - metQ_1 metQ_2
+[14:19:58] Fixed 2 duplicate /gene - pdhC_1 pdhC_2
+[14:19:58] Fixed 2 duplicate /gene - gyrB_1 gyrB_2
+[14:19:58] Fixed 63 colliding /gene names.
+[14:19:58] Adding /locus_tag identifiers
+[14:19:58] Assigned 2685 locus_tags to CDS and RNA features.
+[14:19:58] Writing outputs to /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_005280335.1_ASM528033v1_genomic/
+[14:19:59] Generating annotation statistics file
+[14:19:59] Generating Genbank and Sequin files
+[14:19:59] Running: tbl2asn -V b -a r10k -l paired-ends -M n -N 1 -y 'Annotated using prokka 1.15.6 from https://github.com/tseemann/prokka' -Z \/225040511\/project\/Biomanus\/experiments\/ablation\/results\/biomanus\/bioagentbench\/comparative\-genomics_20260520_140937\/prokka_output\/GCF_005280335\.1_ASM528033v1_genomic\/ASM528033v1_genomic\.err -i \/225040511\/project\/Biomanus\/experiments\/ablation\/results\/biomanus\/bioagentbench\/comparative\-genomics_20260520_140937\/prokka_output\/GCF_005280335\.1_ASM528033v1_genomic\/ASM528033v1_genomic\.fsa 2> /dev/null
+[14:20:04] Deleting unwanted file: /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_005280335.1_ASM528033v1_genomic/errorsummary.val
+[14:20:04] Deleting unwanted file: /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_005280335.1_ASM528033v1_genomic/ASM528033v1_genomic.dr
+[14:20:04] Deleting unwanted file: /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_005280335.1_ASM528033v1_genomic/ASM528033v1_genomic.fixedproducts
+[14:20:04] Deleting unwanted file: /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_005280335.1_ASM528033v1_genomic/ASM528033v1_genomic.ecn
+[14:20:04] Deleting unwanted file: /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_005280335.1_ASM528033v1_genomic/ASM528033v1_genomic.val
+[14:20:04] Repairing broken .GBK output that tbl2asn produces...
+[14:20:04] Running: sed 's/COORDINATES: profile/COORDINATES:profile/' < \/225040511\/project\/Biomanus\/experiments\/ablation\/results\/biomanus\/bioagentbench\/comparative\-genomics_20260520_140937\/prokka_output\/GCF_005280335\.1_ASM528033v1_genomic\/ASM528033v1_genomic\.gbf > \/225040511\/project\/Biomanus\/experiments\/ablation\/results\/biomanus\/bioagentbench\/comparative\-genomics_20260520_140937\/prokka_output\/GCF_005280335\.1_ASM528033v1_genomic\/ASM528033v1_genomic\.gbk
+[14:20:04] Deleting unwanted file: /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_005280335.1_ASM528033v1_genomic/ASM528033v1_genomic.gbf
+[14:20:04] Output files:
+[14:20:04] /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_005280335.1_ASM528033v1_genomic/ASM528033v1_genomic.err
+[14:20:04] /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_005280335.1_ASM528033v1_genomic/ASM528033v1_genomic.txt
+[14:20:04] /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_005280335.1_ASM528033v1_genomic/ASM528033v1_genomic.tsv
+[14:20:04] /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_005280335.1_ASM528033v1_genomic/ASM528033v1_genomic.ffn
+[14:20:04] /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_005280335.1_ASM528033v1_genomic/ASM528033v1_genomic.fna
+[14:20:04] /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_005280335.1_ASM528033v1_genomic/ASM528033v1_genomic.gff
+[14:20:04] /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_005280335.1_ASM528033v1_genomic/ASM528033v1_genomic.faa
+[14:20:04] /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_005280335.1_ASM528033v1_genomic/ASM528033v1_genomic.gbk
+[14:20:04] /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_005280335.1_ASM528033v1_genomic/ASM528033v1_genomic.fsa
+[14:20:04] /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_005280335.1_ASM528033v1_genomic/ASM528033v1_genomic.tbl
+[14:20:04] /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_005280335.1_ASM528033v1_genomic/ASM528033v1_genomic.log
+[14:20:04] /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_005280335.1_ASM528033v1_genomic/ASM528033v1_genomic.sqn
+[14:20:04] Annotation finished successfully.
+[14:20:04] Walltime used: 2.67 minutes
+[14:20:04] If you use this result please cite the Prokka paper:
+[14:20:04] Seemann T (2014) Prokka: rapid prokaryotic genome annotation. Bioinformatics. 30(14):2068-9.
+[14:20:04] Type 'prokka --citation' for more details.
+[14:20:04] Thank you, come again.

Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_005280335.1_ASM528033v1_genomic/ASM528033v1_genomic.txt

@@ -0,0 +1,7 @@
+organism: Micrococcus species strain 
+contigs: 1
+bases: 2848891
+CDS: 2623
+rRNA: 9
+tRNA: 52
+tmRNA: 1

Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_023573625.1_ASM2357362v1_genomic/ASM2357362v1_genomic.log

@@ -0,0 +1,396 @@
+[14:22:21] This is prokka 1.15.6
+[14:22:21] Written by Torsten Seemann <torsten.seemann@gmail.com>
+[14:22:21] Homepage is https://github.com/tseemann/prokka
+[14:22:21] Local time is Wed May 20 14:22:21 2026
+[14:22:21] You are root
+[14:22:21] Operating system is linux
+[14:22:21] You have BioPerl 1.7.8
+[14:22:21] System has 104 cores.
+[14:22:21] Will use maximum of 4 cores.
+[14:22:21] Annotating as >>> Bacteria <<<
+[14:22:21] Generating locus_tag from '/225040511/project/bioagent-bench/dataset/comparative-genomics/data/GCF_023573625.1_ASM2357362v1_genomic.fna' contents.
+[14:22:21] Setting --locustag LFPAFLNI from MD5 5f9af5721ebd084e6cea927e4f226a12
+[14:22:21] Creating new output folder: /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_023573625.1_ASM2357362v1_genomic
+[14:22:21] Running: mkdir -p \/225040511\/project\/Biomanus\/experiments\/ablation\/results\/biomanus\/bioagentbench\/comparative\-genomics_20260520_140937\/prokka_output\/GCF_023573625\.1_ASM2357362v1_genomic
+[14:22:21] Using filename prefix: ASM2357362v1_genomic.XXX
+[14:22:21] Setting HMMER_NCPU=1
+[14:22:21] Writing log to: /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_023573625.1_ASM2357362v1_genomic/ASM2357362v1_genomic.log
+[14:22:21] Command: /225040511/miniconda3/envs/biomni_e1/bin/prokka --outdir /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_023573625.1_ASM2357362v1_genomic --prefix ASM2357362v1_genomic --genus Micrococcus --force --quiet --cpus 4 /225040511/project/bioagent-bench/dataset/comparative-genomics/data/GCF_023573625.1_ASM2357362v1_genomic.fna
+[14:22:21] Looking for 'aragorn' - found /225040511/miniconda3/envs/biomni_e1/bin/aragorn
+[14:22:21] Determined aragorn version is v1.2 from 'ARAGORN v1.2.41 Dean Laslett'
+[14:22:21] Looking for 'barrnap' - found /225040511/miniconda3/envs/biomni_e1/bin/barrnap
+[14:22:21] Determined barrnap version is v0.9 from 'barrnap 0.9'
+[14:22:21] Looking for 'blastp' - found /225040511/miniconda3/envs/biomni_e1/bin/blastp
+[14:22:21] Determined blastp version is v2.17 from 'blastp: 2.17.0+'
+[14:22:21] Looking for 'cmpress' - found /225040511/miniconda3/envs/biomni_e1/bin/cmpress
+[14:22:21] Determined cmpress version is v1.1 from '# INFERNAL 1.1.5 (Sep 2023)'
+[14:22:21] Looking for 'cmscan' - found /225040511/miniconda3/envs/biomni_e1/bin/cmscan
+[14:22:21] Determined cmscan version is v1.1 from '# INFERNAL 1.1.5 (Sep 2023)'
+[14:22:21] Looking for 'egrep' - found /usr/bin/egrep
+[14:22:21] Looking for 'find' - found /usr/bin/find
+[14:22:21] Looking for 'grep' - found /usr/bin/grep
+[14:22:21] Looking for 'hmmpress' - found /225040511/miniconda3/envs/biomni_e1/bin/hmmpress
+[14:22:21] Determined hmmpress version is v3.4 from '# HMMER 3.4 (Aug 2023); http://hmmer.org/'
+[14:22:21] Looking for 'hmmscan' - found /225040511/miniconda3/envs/biomni_e1/bin/hmmscan
+[14:22:21] Determined hmmscan version is v3.4 from '# HMMER 3.4 (Aug 2023); http://hmmer.org/'
+[14:22:21] Looking for 'java' - found /225040511/miniconda3/envs/biomni_e1/bin/java
+[14:22:21] Looking for 'makeblastdb' - found /225040511/miniconda3/envs/biomni_e1/bin/makeblastdb
+[14:22:21] Determined makeblastdb version is v2.17 from 'makeblastdb: 2.17.0+'
+[14:22:21] Looking for 'minced' - found /225040511/miniconda3/envs/biomni_e1/bin/minced
+[14:22:21] Determined minced version is v4.2 from 'minced 0.4.2'
+[14:22:21] Looking for 'parallel' - found /225040511/miniconda3/envs/biomni_e1/bin/parallel
+[14:22:21] Determined parallel version is 20260422 from 'GNU parallel 20260422'
+[14:22:21] Looking for 'prodigal' - found /225040511/miniconda3/envs/biomni_e1/bin/prodigal
+[14:22:21] Determined prodigal version is v2.6 from 'Prodigal V2.6.3: February, 2016'
+[14:22:21] Looking for 'prokka-genbank_to_fasta_db' - found /225040511/miniconda3/envs/biomni_e1/bin/prokka-genbank_to_fasta_db
+[14:22:21] Looking for 'sed' - found /225040511/miniconda3/envs/biomni_e1/bin/sed
+[14:22:21] Looking for 'tbl2asn' - found /225040511/miniconda3/envs/biomni_e1/bin/tbl2asn
+[14:22:21] Determined tbl2asn version is v25.7 from 'tbl2asn 25.7   arguments:'
+[14:22:21] Using genetic code table 11.
+[14:22:21] Loading and checking input file: /225040511/project/bioagent-bench/dataset/comparative-genomics/data/GCF_023573625.1_ASM2357362v1_genomic.fna
+[14:22:21] Wrote 1 contigs totalling 2470932 bp.
+[14:22:21] Predicting tRNAs and tmRNAs
+[14:22:21] Running: aragorn -l -gc11  -w \/225040511\/project\/Biomanus\/experiments\/ablation\/results\/biomanus\/bioagentbench\/comparative\-genomics_20260520_140937\/prokka_output\/GCF_023573625\.1_ASM2357362v1_genomic\/ASM2357362v1_genomic\.fna
+[14:22:25] 1 tRNA-Ile [11082,11156] 35 (gat)
+[14:22:25] 2 tRNA-Ala [11387,11461] 34 (tgc)
+[14:22:25] 3 tRNA-Leu [28603,28688] 35 (cag)
+[14:22:25] 4 tRNA-Lys [115275,115349] 34 (ttt)
+[14:22:25] 5 tRNA-Glu [143665,143738] 35 (ttc)
+[14:22:25] 6 tRNA-Asp [143854,143928] 35 (gtc)
+[14:22:25] 7 tRNA-Phe [144000,144075] 34 (gaa)
+[14:22:25] 8 tRNA-Ser [251802,251888] 35 (gga)
+[14:22:25] 9 tRNA-Ser c[329862,329952] 35 (cga)
+[14:22:25] 10 tRNA-Arg c[333189,333263] 35 (acg)
+[14:22:25] 11 tRNA-Ser c[344747,344836] 35 (gct)
+[14:22:25] 12 tRNA-Ser c[353421,353509] 35 (tga)
+[14:22:25] 13 tRNA-Thr c[355226,355301] 35 (cgt)
+[14:22:25] 14 tRNA-Pro [382816,382892] 35 (cgg)
+[14:22:25] 15 tRNA-Thr [395787,395863] 35 (tgt)
+[14:22:25] 16 tRNA-Val [397791,397866] 35 (cac)
+[14:22:25] 17 tRNA-Arg c[414017,414092] 35 (cct)
+[14:22:25] 18 tRNA-Leu [507789,507865] 35 (taa)
+[14:22:25] 19 tRNA-Gln [550215,550288] 33 (ttg)
+[14:22:25] 20 tRNA-Ala [618062,618159] 36 (ggc)
+[14:22:25] 21 tRNA-Asn [651642,651714] 33 (gtt)
+[14:22:25] 22 tRNA-Met [684066,684140] 35 (cat)
+[14:22:25] 23 tmRNA [781613,781982] 96,134 AESKRTDFALAA*
+[14:22:25] 24 tRNA-Arg c[817752,817825] 34 (ccg)
+[14:22:25] 25 tRNA-Leu c[875212,875293] 35 (tag)
+[14:22:25] 26 tRNA-Lys c[875923,876000] 35 (ctt)
+[14:22:25] 27 tRNA-Gln [898229,898301] 34 (ctg)
+[14:22:25] 28 tRNA-Glu [898356,898429] 35 (ctc)
+[14:22:25] 29 tRNA-Glu [898558,898632] 35 (ctc)
+[14:22:25] 30 tRNA-Val [963741,963816] 35 (tac)
+[14:22:25] 31 tRNA-His c[988705,988780] 34 (gtg)
+[14:22:25] 32 tRNA-Arg c[995958,996033] 35 (tct)
+[14:22:25] 33 tRNA-Ala c[1004871,1004960] 31 (cgc)
+[14:22:25] 34 tRNA-Gly c[1006119,1006191] 33 (tcc)
+[14:22:25] 35 tRNA-Pro [1007245,1007319] 35 (tgg)
+[14:22:25] 36 tRNA-Ala [1045775,1045850] 34 (ggc)
+[14:22:25] 37 tRNA-Ala [1047240,1047315] 34 (ggc)
+[14:22:25] 38 tRNA-Gly c[1097064,1097142] 36 (gcc)
+[14:22:25] 39 tRNA-Val c[1097169,1097241] 33 (gac)
+[14:22:25] 40 tRNA-Cys c[1097299,1097370] 33 (gca)
+[14:22:25] 41 tRNA-Gly c[1097388,1097462] 35 (gcc)
+[14:22:25] 42 tRNA-Leu [1137389,1137472] 35 (caa)
+[14:22:25] 43 tRNA-Leu c[1224904,1224989] 35 (gag)
+[14:22:25] 44 tRNA-Ile [1317727,1317821] 35 (gat)
+[14:22:25] 45 tRNA-Pro c[1326486,1326573] 35 (tgg)
+[14:22:25] 46 tRNA-Pro c[1492383,1492459] 35 (ggg)
+[14:22:25] 47 tRNA-Met c[1593949,1594023] 35 (cat)
+[14:22:25] 48 tRNA-Trp c[1833146,1833219] 34 (cca)
+[14:22:25] 49 tRNA-Met c[1850814,1850888] 35 (cat)
+[14:22:25] 50 tRNA-Thr c[1850948,1851020] 33 (ggt)
+[14:22:25] 51 tRNA-Tyr c[1862271,1862354] 35 (gta)
+[14:22:25] 52 tRNA-Gly [1995326,1995399] 33 (ccc)
+[14:22:25] 53 tRNA-Ala c[2091913,2091986] 34 (cgc)
+[14:22:25] Found 53 tRNAs
+[14:22:25] Predicting Ribosomal RNAs
+[14:22:25] Running Barrnap with 4 threads
+[14:22:26] 1 NZ_CP097650.1 376768 16S ribosomal RNA
+[14:22:26] 2 NZ_CP097650.1 378730 23S ribosomal RNA
+[14:22:26] 3 NZ_CP097650.1 382014 5S ribosomal RNA
+[14:22:26] 4 NZ_CP097650.1 1519301 5S ribosomal RNA
+[14:22:26] 5 NZ_CP097650.1 1519609 23S ribosomal RNA
+[14:22:26] 6 NZ_CP097650.1 1523135 16S ribosomal RNA
+[14:22:26] Found 6 rRNAs
+[14:22:26] Skipping ncRNA search, enable with --rfam if desired.
+[14:22:26] Total of 58 tRNA + rRNA features
+[14:22:26] Searching for CRISPR repeats
+[14:22:26] CRISPR1 NZ_CP097650.1 2364726 with 6 spacers
+[14:22:26] CRISPR2 NZ_CP097650.1 2367750 with 8 spacers
+[14:22:26] Found 2 CRISPRs
+[14:22:26] Predicting coding sequences
+[14:22:26] Contigs total 2470932 bp, so using single mode
+[14:22:26] Running: prodigal -i \/225040511\/project\/Biomanus\/experiments\/ablation\/results\/biomanus\/bioagentbench\/comparative\-genomics_20260520_140937\/prokka_output\/GCF_023573625\.1_ASM2357362v1_genomic\/ASM2357362v1_genomic\.fna -c -m -g 11 -p single -f sco -q
+[14:22:32] Excluding CDS which overlaps existing RNA (tRNA) at NZ_CP097650.1:616242..618635 on + strand
+[14:22:32] Excluding CDS which overlaps existing RNA (tRNA) at NZ_CP097650.1:1004613..1005086 on + strand
+[14:22:33] Excluding CDS which overlaps existing RNA (tRNA) at NZ_CP097650.1:1317305..1318684 on - strand
+[14:22:33] Excluding CDS which overlaps existing RNA (tRNA) at NZ_CP097650.1:1325680..1326948 on - strand
+[14:22:33] Excluding CDS which overlaps existing RNA (repeat_region) at NZ_CP097650.1:2367760..2368752 on + strand
+[14:22:33] Found 2194 CDS
+[14:22:33] Connecting features back to sequences
+[14:22:33] Not using genus-specific database. Try --usegenus to enable it.
+[14:22:33] Annotating CDS, please be patient.
+[14:22:33] Will use 4 CPUs for similarity searching.
+[14:22:34] There are still 2194 unannotated CDS left (started with 2194)
+[14:22:34] Will use blast to search against /225040511/miniconda3/envs/biomni_e1/db/kingdom/Bacteria/IS with 4 CPUs
+[14:22:34] Running: cat \/225040511\/project\/Biomanus\/experiments\/ablation\/results\/biomanus\/bioagentbench\/comparative\-genomics_20260520_140937\/prokka_output\/GCF_023573625\.1_ASM2357362v1_genomic\/ASM2357362v1_genomic\.IS\.tmp\.354320\.faa | parallel --gnu --plain -j 4 --block 94419 --recstart '>' --pipe blastp -query - -db /225040511/miniconda3/envs/biomni_e1/db/kingdom/Bacteria/IS -evalue 1e-30 -qcov_hsp_perc 90 -num_threads 1 -num_descriptions 1 -num_alignments 1 -seg no > \/225040511\/project\/Biomanus\/experiments\/ablation\/results\/biomanus\/bioagentbench\/comparative\-genomics_20260520_140937\/prokka_output\/GCF_023573625\.1_ASM2357362v1_genomic\/ASM2357362v1_genomic\.IS\.tmp\.354320\.blast 2> /dev/null
+[14:22:48] Deleting unwanted file: /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_023573625.1_ASM2357362v1_genomic/ASM2357362v1_genomic.IS.tmp.354320.faa
+[14:22:48] Deleting unwanted file: /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_023573625.1_ASM2357362v1_genomic/ASM2357362v1_genomic.IS.tmp.354320.blast
+[14:22:49] There are still 2148 unannotated CDS left (started with 2194)
+[14:22:49] Will use blast to search against /225040511/miniconda3/envs/biomni_e1/db/kingdom/Bacteria/AMR with 4 CPUs
+[14:22:49] Running: cat \/225040511\/project\/Biomanus\/experiments\/ablation\/results\/biomanus\/bioagentbench\/comparative\-genomics_20260520_140937\/prokka_output\/GCF_023573625\.1_ASM2357362v1_genomic\/ASM2357362v1_genomic\.AMR\.tmp\.354320\.faa | parallel --gnu --plain -j 4 --block 92767 --recstart '>' --pipe blastp -query - -db /225040511/miniconda3/envs/biomni_e1/db/kingdom/Bacteria/AMR -evalue 1e-300 -qcov_hsp_perc 90 -num_threads 1 -num_descriptions 1 -num_alignments 1 -seg no > \/225040511\/project\/Biomanus\/experiments\/ablation\/results\/biomanus\/bioagentbench\/comparative\-genomics_20260520_140937\/prokka_output\/GCF_023573625\.1_ASM2357362v1_genomic\/ASM2357362v1_genomic\.AMR\.tmp\.354320\.blast 2> /dev/null
+[14:23:11] Deleting unwanted file: /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_023573625.1_ASM2357362v1_genomic/ASM2357362v1_genomic.AMR.tmp.354320.faa
+[14:23:11] Deleting unwanted file: /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_023573625.1_ASM2357362v1_genomic/ASM2357362v1_genomic.AMR.tmp.354320.blast
+[14:23:12] There are still 2145 unannotated CDS left (started with 2194)
+[14:23:12] Will use blast to search against /225040511/miniconda3/envs/biomni_e1/db/kingdom/Bacteria/sprot with 4 CPUs
+[14:23:12] Running: cat \/225040511\/project\/Biomanus\/experiments\/ablation\/results\/biomanus\/bioagentbench\/comparative\-genomics_20260520_140937\/prokka_output\/GCF_023573625\.1_ASM2357362v1_genomic\/ASM2357362v1_genomic\.sprot\.tmp\.354320\.faa | parallel --gnu --plain -j 4 --block 92418 --recstart '>' --pipe blastp -query - -db /225040511/miniconda3/envs/biomni_e1/db/kingdom/Bacteria/sprot -evalue 1e-09 -qcov_hsp_perc 80 -num_threads 1 -num_descriptions 1 -num_alignments 1 -seg no > \/225040511\/project\/Biomanus\/experiments\/ablation\/results\/biomanus\/bioagentbench\/comparative\-genomics_20260520_140937\/prokka_output\/GCF_023573625\.1_ASM2357362v1_genomic\/ASM2357362v1_genomic\.sprot\.tmp\.354320\.blast 2> /dev/null
+[14:24:21] Modify product: Probable tRNA-dihydrouridine synthase => putative tRNA-dihydrouridine synthase
+[14:24:21] Modify product: Uncharacterized oxidoreductase YghA => putative oxidoreductase YghA
+[14:24:21] Modify product: Aldo-keto reductase MSMEG_2408/MSMEI_2347 => Aldo-keto reductase/MSMEI_2347
+[14:24:21] Modify product: Probable membrane transporter protein YfcA => putative membrane transporter protein YfcA
+[14:24:21] Modify product: Uncharacterized methyltransferase Rv3342 => putative methyltransferase
+[14:24:21] Modify product: Uncharacterized zinc protease Rv2782c => putative zinc protease
+[14:24:21] Modify product: Protein MG115 homolog => Protein MG115 
+[14:24:21] Modify product: Probable acetyl-CoA acetyltransferase => putative acetyl-CoA acetyltransferase
+[14:24:21] Modify product: Probable succinyl-CoA:3-ketoacid coenzyme A transferase subunit A => putative succinyl-CoA:3-ketoacid coenzyme A transferase subunit A
+[14:24:21] Modify product: Probable succinyl-CoA:3-ketoacid coenzyme A transferase subunit B => putative succinyl-CoA:3-ketoacid coenzyme A transferase subunit B
+[14:24:21] Modify product: UPF0053 protein Rv1842c => hypothetical protein
+[14:24:21] Modify product: Uncharacterized protein Rv1841c => putative protein
+[14:24:21] Modify product: Uncharacterized HIT-like protein Rv0759c => putative HIT-like protein
+[14:24:21] Modify product: Uncharacterized ABC transporter ATP-binding protein YknY => putative ABC transporter ATP-binding protein YknY
+[14:24:21] Modify product: Probable adenylyltransferase/sulfurtransferase MoeZ => putative adenylyltransferase/sulfurtransferase MoeZ
+[14:24:21] Modify product: Uncharacterized protein Rv1324 => putative protein
+[14:24:21] Modify product: Uncharacterized protein Rv1339 => putative protein
+[14:24:21] Modify product: Probable malate:quinone oxidoreductase => putative malate:quinone oxidoreductase
+[14:24:21] Modify product: Putative peroxiredoxin Rv2521 => Putative peroxiredoxin
+[14:24:21] Modify product: Protein Rv2993c => Protein
+[14:24:21] Modify product: RNA/DNA methyltransferase Rv2966c => RNA/DNA methyltransferase
+[14:24:21] Modify product: Probable N-succinyldiaminopimelate aminotransferase DapC => putative N-succinyldiaminopimelate aminotransferase DapC
+[14:24:21] Modify product: Uncharacterized protein Rv2926c => putative protein
+[14:24:21] Modify product: Uncharacterized protein Rv2901c => putative protein
+[14:24:21] Modify product: Uncharacterized protein Rv2242 => putative protein
+[14:24:21] Modify product: Uncharacterized protein Rv2239c => putative protein
+[14:24:21] Modify product: GTP cyclohydrolase 1 type 2 homolog => GTP cyclohydrolase 1 type 2 
+[14:24:21] Modify product: Alpha-(1->6)-mannopyranosyltransferase Rv1459c => Alpha-(1->6)-mannopyranosyltransferase
+[14:24:21] Modify product: Thioredoxin-like reductase Rv2466c => Thioredoxin-like reductase
+[14:24:21] Modify product: Uncharacterized oxidoreductase Rv0484c => putative oxidoreductase
+[14:24:21] Modify product: Probable nicotinate-nucleotide adenylyltransferase => putative nicotinate-nucleotide adenylyltransferase
+[14:24:21] Modify product: Uncharacterized oxidoreductase YdgJ => putative oxidoreductase YdgJ
+[14:24:21] Modify product: Uncharacterized SufE-like protein Rv3284 => putative SufE-like protein
+[14:24:21] Modify product: Uncharacterized protein Rv2895c => putative protein
+[14:24:21] Modify product: Putative methyltransferase Rv1407 => Putative methyltransferase
+[14:24:21] Modify product: Transcriptional repressor SmtB homolog => Transcriptional repressor SmtB 
+[14:24:21] Modify product: Uncharacterized protein Rv1841c => putative protein
+[14:24:21] Modify product: UPF0053 protein Rv1842c => hypothetical protein
+[14:24:21] Modify product: Uncharacterized membrane protein Rv2723 => putative membrane protein
+[14:24:21] Modify product: Uncharacterized membrane protein Rv2723 => putative membrane protein
+[14:24:21] Modify product: Probable trans-aconitate 2-methyltransferase => putative trans-aconitate 2-methyltransferase
+[14:24:21] Modify product: Nucleotide-binding protein Rv1421 => Nucleotide-binding protein
+[14:24:21] Modify product: Probable cell division protein WhiA => putative cell division protein WhiA
+[14:24:21] Modify product: Iron-sulfur cluster assembly SufBD family protein SA0778 => Iron-sulfur cluster assembly SufBD family protein
+[14:24:21] Modify product: Iron-sulfur cluster assembly SufBD family protein Rv1462 => Iron-sulfur cluster assembly SufBD family protein
+[14:24:21] Modify product: Probable ATP-binding protein YheS => putative ATP-binding protein YheS
+[14:24:21] Modify product: Uncharacterized SURF1-like protein Rv2235 => putative SURF1-like protein
+[14:24:21] Modify product: Uncharacterized ABC transporter ATP-binding protein YlmA => putative ABC transporter ATP-binding protein YlmA
+[14:24:21] Modify product: Protein Rv0786c => Protein
+[14:24:21] Modify product: UPF0312 protein SA2479 => hypothetical protein
+[14:24:21] Modify product: Probable glycerophosphodiester phosphodiesterase 2 => putative glycerophosphodiester phosphodiesterase 2
+[14:24:21] Modify product: Putative low molecular weight protein-tyrosine-phosphatase slr0328 => Putative low molecular weight protein-tyrosine-phosphatase
+[14:24:21] Modify product: Putative 2-hydroxyacid dehydrogenase SA2098 => Putative 2-hydroxyacid dehydrogenase
+[14:24:21] Modify product: Probable glycerophosphodiester phosphodiesterase 1 => putative glycerophosphodiester phosphodiesterase 1
+[14:24:21] Modify product: UPF0045 protein Rv1898 => hypothetical protein
+[14:24:21] Modify product: Universal stress protein MT2698 => Universal stress protein
+[14:24:21] Modify product: Probable inactive lipase Rv1592c => putative inactive lipase
+[14:24:21] Modify product: Type I restriction enzyme BthVORF4518P methylase subunit => Type I restriction enzymeP methylase subunit
+[14:24:21] Modify product: Probable FMNH2-dependent monooxygenase SfnC => putative FMNH2-dependent monooxygenase SfnC
+[14:24:21] Modify product: Uncharacterized protein Rv2895c => putative protein
+[14:24:21] Modify product: Probable FMNH2-dependent monooxygenase SfnC => putative FMNH2-dependent monooxygenase SfnC
+[14:24:21] Modify product: Probable malonic semialdehyde reductase RutE => putative malonic semialdehyde reductase RutE
+[14:24:21] Modify product: Probable enoyl-CoA hydratase EchA8 => putative enoyl-CoA hydratase EchA8
+[14:24:21] Modify product: Probable 3-hydroxyisobutyrate dehydrogenase => putative 3-hydroxyisobutyrate dehydrogenase
+[14:24:21] Modify product: Uncharacterized oxidoreductase Rv1144 => putative oxidoreductase
+[14:24:21] Modify product: Probable glycine dehydrogenase (decarboxylating) => putative glycine dehydrogenase (decarboxylating)
+[14:24:22] Modify product: Uncharacterized protein Rv1276c => putative protein
+[14:24:22] Modify product: Phosphate-specific transport system accessory protein PhoU homolog 2 => Phosphate-specific transport system accessory protein PhoU 
+[14:24:22] Modify product: Uncharacterized tRNA/rRNA methyltransferase Rv3579c => putative tRNA/rRNA methyltransferase
+[14:24:22] Modify product: Probable transcriptional regulatory protein TcrX => putative transcriptional regulatory protein TcrX
+[14:24:22] Modify product: Uncharacterized ABC transporter ATP-binding protein YwjA => putative ABC transporter ATP-binding protein YwjA
+[14:24:22] Modify product: Bifunctional protein FolD => Bifunctional protein FolD protein
+[14:24:22] Modify product: Probable hydrolase sll0100 => putative hydrolase
+[14:24:22] Modify product: Uncharacterized protein YihR => putative protein YihR
+[14:24:22] Modify product: Putative transport protein Rv0205 => Putative transport protein
+[14:24:22] Modify product: Uncharacterized metal-dependent hydrolase TatD => putative metal-dependent hydrolase TatD
+[14:24:22] Modify product: Probable phosphomannomutase => putative phosphomannomutase
+[14:24:22] Modify product: pH-sensitive adenylate cyclase Rv1264 => pH-sensitive adenylate cyclase
+[14:24:22] Modify product: Phosphorylated carbohydrates phosphatase TM_1254 => Phosphorylated carbohydrates phosphatase
+[14:24:22] Modify product: Probable helicase HelY => putative helicase HelY
+[14:24:22] Modify product: Uncharacterized protein Rv1488 => putative protein
+[14:24:22] Modify product: Probable cytochrome c oxidase polypeptide 4 => putative cytochrome c oxidase polypeptide 4
+[14:24:22] Modify product: Probable cytochrome c oxidase subunit 1 => putative cytochrome c oxidase subunit 1
+[14:24:22] Modify product: Protein Rv2204c => Protein
+[14:24:22] Modify product: Uncharacterized protein Rv2206 => putative protein
+[14:24:22] Modify product: UPF0053 protein Rv2366c => hypothetical protein
+[14:24:22] Modify product: Probable DNA polymerase III subunit delta => putative DNA polymerase III subunit delta
+[14:24:22] Modify product: DegV domain-containing protein SA1258 => DegV domain-containing protein
+[14:24:22] Modify product: Probable replication restart protein PriA => putative replication restart protein PriA
+[14:24:22] Modify product: Uncharacterized AAA domain-containing protein Rv2559c => putative AAA domain-containing protein
+[14:24:22] Modify product: Uncharacterized transporter Rv1999c => putative transporter
+[14:24:22] Modify product: Uncharacterized protein MSMEG_2731/MSMEI_2664 => putative protein/MSMEI_2664
+[14:24:22] Modify product: Probable transcriptional regulatory protein Rv2603c => putative transcriptional regulatory protein
+[14:24:22] Modify product: Uncharacterized protein YdhK => putative protein YdhK
+[14:24:22] Modify product: Probable cytosol aminopeptidase => putative cytosol aminopeptidase
+[14:24:22] Modify product: Uncharacterized RNA pseudouridine synthase Rv1540 => putative RNA pseudouridine synthase
+[14:24:22] Modify product: Probable peptidoglycan glycosyltransferase FtsW => putative peptidoglycan glycosyltransferase FtsW
+[14:24:22] Modify product: Uncharacterized HTH-type transcriptional regulator Rv1830 => putative HTH-type transcriptional regulator
+[14:24:22] Modify product: Uncharacterized protein Rv1829 => putative protein
+[14:24:22] Modify product: Uncharacterized HTH-type transcriptional regulator Rv1828 => putative HTH-type transcriptional regulator
+[14:24:22] Modify product: Uncharacterized protein Rv1708 => putative protein
+[14:24:22] Modify product: UPF0336 protein Rv0637 => hypothetical protein
+[14:24:22] Modify product: Probable cystathionine beta-synthase Rv1077 => putative cystathionine beta-synthase
+[14:24:22] Modify product: Nucleotide-binding protein SCO4614 => Nucleotide-binding protein
+[14:24:22] Modify product: Probable 2-succinylbenzoate--CoA ligase => putative 2-succinylbenzoate--CoA ligase
+[14:24:22] Modify product: Uncharacterized protein Rv0525 => putative protein
+[14:24:22] Modify product: Uncharacterized protein Rv0498 => putative protein
+[14:24:22] Modify product: Uncharacterized ATP-dependent helicase YprA => putative ATP-dependent helicase YprA
+[14:24:22] Modify product: Uncharacterized ABC transporter ATP-binding protein YwjA => putative ABC transporter ATP-binding protein YwjA
+[14:24:22] Modify product: Putative multidrug export ATP-binding/permease protein SA1683 => Putative multidrug export ATP-binding/permease protein
+[14:24:22] Modify product: Probable lipoprotein aminopeptidase LpqL => putative lipoprotein aminopeptidase LpqL
+[14:24:22] Modify product: Putative hydro-lyase PSPTO_5379 => Putative hydro-lyase
+[14:24:22] Modify product: Probable cold shock protein A => putative cold shock protein A
+[14:24:22] Modify product: UPF0182 protein MSMEG_1959/MSMEI_1915 => hypothetical protein
+[14:24:22] Modify product: Uncharacterized protein YlbL => putative protein YlbL
+[14:24:22] Modify product: Probable O-methyltransferase Rv1220c => putative O-methyltransferase
+[14:24:22] Modify product: Probable aminotransferase Rv1178 => putative aminotransferase
+[14:24:22] Modify product: Uncharacterized lipoprotein Rv2585c => putative lipoprotein
+[14:24:22] Modify product: Probable bacterial non-heme ferritin => putative bacterial non-heme ferritin
+[14:24:22] Modify product: Probable nicotinate-nucleotide pyrophosphorylase [carboxylating] => putative nicotinate-nucleotide pyrophosphorylase [carboxylating]
+[14:24:22] Modify product: Protein Rv2133c => Protein
+[14:24:22] Modify product: Uncharacterized protein YdhK => putative protein YdhK
+[14:24:22] Modify product: Uncharacterized oxidoreductase MSMEG_1603/MSMEI_1564 => putative oxidoreductase/MSMEI_1564
+[14:24:22] Modify product: Probable zinc-binding alcohol dehydrogenase Rv1895 => putative zinc-binding alcohol dehydrogenase
+[14:24:22] Modify product: Uncharacterized protein Rv3421c => putative protein
+[14:24:22] Modify product: Glycogen operon protein GlgX homolog => Glycogen operon protein GlgX 
+[14:24:22] Modify product: Probable enoyl-CoA hydratase EchA8 => putative enoyl-CoA hydratase EchA8
+[14:24:22] Modify product: UPF0371 protein DIP2346 => hypothetical protein
+[14:24:22] Modify product: Putative acyltransferase Rv0859 => Putative acyltransferase
+[14:24:22] Modify product: Uncharacterized ABC transporter ATP-binding protein YknY => putative ABC transporter ATP-binding protein YknY
+[14:24:22] Modify product: Uncharacterized ABC transporter ATP-binding protein Rv1273c => putative ABC transporter ATP-binding protein
+[14:24:22] Modify product: Uncharacterized glycosyl hydrolase MT2062 => putative glycosyl hydrolase
+[14:24:22] Modify product: Uncharacterized ABC transporter ATP-binding protein YwjA => putative ABC transporter ATP-binding protein YwjA
+[14:24:22] Modify product: Probable sensor histidine kinase TcrY => putative sensor histidine kinase TcrY
+[14:24:22] Modify product: Probable transcriptional regulatory protein TcrX => putative transcriptional regulatory protein TcrX
+[14:24:22] Modify product: Probable siderophore transport system permease protein YfhA => putative siderophore transport system permease protein YfhA
+[14:24:22] Modify product: Probable siderophore transport system ATP-binding protein YusV => putative siderophore transport system ATP-binding protein YusV
+[14:24:22] Modify product: Uncharacterized sugar epimerase YhfK => putative sugar epimerase YhfK
+[14:24:22] Modify product: Uncharacterized N-acetyltransferase Rv2669 => putative N-acetyltransferase
+[14:24:22] Modify product: Putative glutaredoxin Rv3198A => Putative glutaredoxinA
+[14:24:22] Modify product: Uncharacterized oxidoreductase YghA => putative oxidoreductase YghA
+[14:24:22] Modify product: Probable ATP-binding protein YheS => putative ATP-binding protein YheS
+[14:24:22] Modify product: Probable zinc-binding alcohol dehydrogenase Rv1895 => putative zinc-binding alcohol dehydrogenase
+[14:24:22] Modify product: Probable glycerol uptake facilitator protein => putative glycerol uptake facilitator protein
+[14:24:22] Modify product: Probable metallo-hydrolase YflN => putative metallo-hydrolase YflN
+[14:24:22] Modify product: Probable M18 family aminopeptidase 2 => putative M18 family aminopeptidase 2
+[14:24:23] Modify product: Probable chromosome-partitioning protein ParB => putative chromosome-partitioning protein ParB
+[14:24:23] Cleaned 147 /product names
+[14:24:23] Deleting unwanted file: /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_023573625.1_ASM2357362v1_genomic/ASM2357362v1_genomic.sprot.tmp.354320.faa
+[14:24:23] Deleting unwanted file: /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_023573625.1_ASM2357362v1_genomic/ASM2357362v1_genomic.sprot.tmp.354320.blast
+[14:24:23] Labelling remaining 1039 proteins as 'hypothetical protein'
+[14:24:23] Possible /pseudo 'IS5 family transposase ISBli8' at NZ_CP097650.1 position 118354
+[14:24:23] Possible /pseudo 'putative membrane protein' at NZ_CP097650.1 position 1160163
+[14:24:23] Possible /pseudo 'Iron-sulfur cluster assembly SufBD family protein' at NZ_CP097650.1 position 1194506
+[14:24:23] Possible /pseudo 'IS5 family transposase ISBli8' at NZ_CP097650.1 position 1710015
+[14:24:23] Possible /pseudo 'IS5 family transposase ISBli8' at NZ_CP097650.1 position 2076609
+[14:24:23] Found 909 unique /gene codes.
+[14:24:23] Fixed 2 duplicate /gene - lysG_1 lysG_2
+[14:24:23] Fixed 2 duplicate /gene - cmtR_1 cmtR_2
+[14:24:23] Fixed 2 duplicate /gene - gabT_1 gabT_2
+[14:24:23] Fixed 2 duplicate /gene - qorA_1 qorA_2
+[14:24:23] Fixed 2 duplicate /gene - lnrK_1 lnrK_2
+[14:24:23] Fixed 2 duplicate /gene - gabD1_1 gabD1_2
+[14:24:23] Fixed 5 duplicate /gene - acsA_1 acsA_2 acsA_3 acsA_4 acsA_5
+[14:24:23] Fixed 3 duplicate /gene - stp_1 stp_2 stp_3
+[14:24:23] Fixed 2 duplicate /gene - glgC_1 glgC_2
+[14:24:23] Fixed 2 duplicate /gene - pdhC_1 pdhC_2
+[14:24:23] Fixed 2 duplicate /gene - yheS_1 yheS_2
+[14:24:23] Fixed 2 duplicate /gene - rlmP_1 rlmP_2
+[14:24:23] Fixed 2 duplicate /gene - mobA_1 mobA_2
+[14:24:23] Fixed 2 duplicate /gene - echA8_1 echA8_2
+[14:24:23] Fixed 2 duplicate /gene - accA3_1 accA3_2
+[14:24:23] Fixed 2 duplicate /gene - rspR_1 rspR_2
+[14:24:23] Fixed 2 duplicate /gene - ideR_1 ideR_2
+[14:24:23] Fixed 2 duplicate /gene - bkdA_1 bkdA_2
+[14:24:23] Fixed 2 duplicate /gene - ydhK_1 ydhK_2
+[14:24:23] Fixed 2 duplicate /gene - bkdB_1 bkdB_2
+[14:24:23] Fixed 2 duplicate /gene - sfnC_1 sfnC_2
+[14:24:23] Fixed 2 duplicate /gene - fadB_1 fadB_2
+[14:24:23] Fixed 2 duplicate /gene - def_1 def_2
+[14:24:23] Fixed 2 duplicate /gene - iscS_1 iscS_2
+[14:24:23] Fixed 2 duplicate /gene - map_1 map_2
+[14:24:23] Fixed 2 duplicate /gene - liaR_1 liaR_2
+[14:24:23] Fixed 2 duplicate /gene - fprA_1 fprA_2
+[14:24:23] Fixed 2 duplicate /gene - yghA_1 yghA_2
+[14:24:23] Fixed 2 duplicate /gene - yknY_1 yknY_2
+[14:24:23] Fixed 2 duplicate /gene - lsr2_1 lsr2_2
+[14:24:23] Fixed 2 duplicate /gene - mrpD_1 mrpD_2
+[14:24:23] Fixed 2 duplicate /gene - copB_1 copB_2
+[14:24:23] Fixed 3 duplicate /gene - pepN_1 pepN_2 pepN_3
+[14:24:23] Fixed 3 duplicate /gene - ettA_1 ettA_2 ettA_3
+[14:24:23] Fixed 2 duplicate /gene - trpB_1 trpB_2
+[14:24:23] Fixed 2 duplicate /gene - idsA2_1 idsA2_2
+[14:24:23] Fixed 2 duplicate /gene - paaJ_1 paaJ_2
+[14:24:23] Fixed 2 duplicate /gene - lysE_1 lysE_2
+[14:24:23] Fixed 2 duplicate /gene - ktrB_1 ktrB_2
+[14:24:23] Fixed 2 duplicate /gene - citE_1 citE_2
+[14:24:23] Fixed 5 duplicate /gene - lcfB_1 lcfB_2 lcfB_3 lcfB_4 lcfB_5
+[14:24:23] Fixed 2 duplicate /gene - dmoA_1 dmoA_2
+[14:24:23] Fixed 2 duplicate /gene - acp_1 acp_2
+[14:24:23] Fixed 2 duplicate /gene - kdgR_1 kdgR_2
+[14:24:23] Fixed 2 duplicate /gene - gyrB_1 gyrB_2
+[14:24:23] Fixed 2 duplicate /gene - gyrA_1 gyrA_2
+[14:24:23] Fixed 2 duplicate /gene - gap2_1 gap2_2
+[14:24:23] Fixed 6 duplicate /gene - mmgC_1 mmgC_2 mmgC_3 mmgC_4 mmgC_5 mmgC_6
+[14:24:23] Fixed 2 duplicate /gene - czcD_1 czcD_2
+[14:24:23] Fixed 3 duplicate /gene - ywjA_1 ywjA_2 ywjA_3
+[14:24:23] Fixed 2 duplicate /gene - gsiA_1 gsiA_2
+[14:24:23] Fixed 2 duplicate /gene - acdA_1 acdA_2
+[14:24:23] Fixed 2 duplicate /gene - tcrX_1 tcrX_2
+[14:24:23] Fixed 2 duplicate /gene - metB_1 metB_2
+[14:24:23] Fixed 2 duplicate /gene - mgtA_1 mgtA_2
+[14:24:23] Fixed 2 duplicate /gene - lepB_1 lepB_2
+[14:24:23] Fixed 2 duplicate /gene - galE_1 galE_2
+[14:24:23] Fixed 57 colliding /gene names.
+[14:24:23] Adding /locus_tag identifiers
+[14:24:23] Assigned 2253 locus_tags to CDS and RNA features.
+[14:24:23] Writing outputs to /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_023573625.1_ASM2357362v1_genomic/
+[14:24:24] Generating annotation statistics file
+[14:24:24] Generating Genbank and Sequin files
+[14:24:24] Running: tbl2asn -V b -a r10k -l paired-ends -M n -N 1 -y 'Annotated using prokka 1.15.6 from https://github.com/tseemann/prokka' -Z \/225040511\/project\/Biomanus\/experiments\/ablation\/results\/biomanus\/bioagentbench\/comparative\-genomics_20260520_140937\/prokka_output\/GCF_023573625\.1_ASM2357362v1_genomic\/ASM2357362v1_genomic\.err -i \/225040511\/project\/Biomanus\/experiments\/ablation\/results\/biomanus\/bioagentbench\/comparative\-genomics_20260520_140937\/prokka_output\/GCF_023573625\.1_ASM2357362v1_genomic\/ASM2357362v1_genomic\.fsa 2> /dev/null
+[14:24:27] Deleting unwanted file: /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_023573625.1_ASM2357362v1_genomic/errorsummary.val
+[14:24:27] Deleting unwanted file: /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_023573625.1_ASM2357362v1_genomic/ASM2357362v1_genomic.dr
+[14:24:27] Deleting unwanted file: /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_023573625.1_ASM2357362v1_genomic/ASM2357362v1_genomic.fixedproducts
+[14:24:27] Deleting unwanted file: /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_023573625.1_ASM2357362v1_genomic/ASM2357362v1_genomic.ecn
+[14:24:27] Deleting unwanted file: /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_023573625.1_ASM2357362v1_genomic/ASM2357362v1_genomic.val
+[14:24:27] Repairing broken .GBK output that tbl2asn produces...
+[14:24:27] Running: sed 's/COORDINATES: profile/COORDINATES:profile/' < \/225040511\/project\/Biomanus\/experiments\/ablation\/results\/biomanus\/bioagentbench\/comparative\-genomics_20260520_140937\/prokka_output\/GCF_023573625\.1_ASM2357362v1_genomic\/ASM2357362v1_genomic\.gbf > \/225040511\/project\/Biomanus\/experiments\/ablation\/results\/biomanus\/bioagentbench\/comparative\-genomics_20260520_140937\/prokka_output\/GCF_023573625\.1_ASM2357362v1_genomic\/ASM2357362v1_genomic\.gbk
+[14:24:27] Deleting unwanted file: /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_023573625.1_ASM2357362v1_genomic/ASM2357362v1_genomic.gbf
+[14:24:27] Output files:
+[14:24:27] /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_023573625.1_ASM2357362v1_genomic/ASM2357362v1_genomic.tsv
+[14:24:27] /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_023573625.1_ASM2357362v1_genomic/ASM2357362v1_genomic.sqn
+[14:24:27] /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_023573625.1_ASM2357362v1_genomic/ASM2357362v1_genomic.gff
+[14:24:27] /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_023573625.1_ASM2357362v1_genomic/ASM2357362v1_genomic.txt
+[14:24:27] /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_023573625.1_ASM2357362v1_genomic/ASM2357362v1_genomic.gbk
+[14:24:27] /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_023573625.1_ASM2357362v1_genomic/ASM2357362v1_genomic.ffn
+[14:24:27] /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_023573625.1_ASM2357362v1_genomic/ASM2357362v1_genomic.err
+[14:24:27] /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_023573625.1_ASM2357362v1_genomic/ASM2357362v1_genomic.fna
+[14:24:27] /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_023573625.1_ASM2357362v1_genomic/ASM2357362v1_genomic.tbl
+[14:24:27] /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_023573625.1_ASM2357362v1_genomic/ASM2357362v1_genomic.fsa
+[14:24:27] /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_023573625.1_ASM2357362v1_genomic/ASM2357362v1_genomic.log
+[14:24:27] /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_023573625.1_ASM2357362v1_genomic/ASM2357362v1_genomic.faa
+[14:24:27] Annotation finished successfully.
+[14:24:27] Walltime used: 2.10 minutes
+[14:24:27] If you use this result please cite the Prokka paper:
+[14:24:27] Seemann T (2014) Prokka: rapid prokaryotic genome annotation. Bioinformatics. 30(14):2068-9.
+[14:24:27] Type 'prokka --citation' for more details.
+[14:24:27] Thank you, come again.

Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/prokka_output/GCF_023573625.1_ASM2357362v1_genomic/ASM2357362v1_genomic.txt

@@ -0,0 +1,8 @@
+organism: Micrococcus species strain 
+contigs: 1
+bases: 2470932
+CDS: 2194
+rRNA: 6
+repeat_region: 2
+tRNA: 52
+tmRNA: 1

Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/run_metadata.json

@@ -0,0 +1,126 @@
+{
+  "task_id": "comparative-genomics",
+  "task_name": "Comparative Genomics: Co-evolving Gene Clusters",
+  "run_dir": "/225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937",
+  "dataset_dir": "/225040511/project/bioagent-bench/dataset/comparative-genomics",
+  "data_dir": "/225040511/project/bioagent-bench/dataset/comparative-genomics/data",
+  "reference_dir": "/225040511/project/bioagent-bench/dataset/comparative-genomics/reference",
+  "agent_runtime_dir": "/225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/agent_runtime",
+  "output_paths": [
+    "/225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/cluster_annotation_mapping.csv"
+  ],
+  "agent_kwargs": {
+    "expected_data_lake_files": [],
+    "rewrite_user_query": true,
+    "dynamic_mcp_registration": true,
+    "use_graph_retriever": true,
+    "use_tool_retriever": true,
+    "timeout_seconds": 1200,
+    "mcp_server_top_k": 20,
+    "mcp_tool_top_k": 12,
+    "llm": "deepseek-v4-flash",
+    "source": "Custom",
+    "base_url": "https://api.deepseek.com/v1",
+    "api_key": "sk-06e6154722b84e89b081b1c9571838ef",
+    "path": "/225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/agent_runtime",
+    "execution_env_prefix": "/225040511/miniconda3/envs/biomni_e1",
+    "benchmark_guard": {
+      "enabled": true,
+      "allowed_roots": [
+        "/225040511/project/bioagent-bench/dataset/comparative-genomics/data",
+        "/225040511/project/bioagent-bench/dataset/comparative-genomics/reference",
+        "/225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937"
+      ],
+      "forbidden_patterns": [
+        "/225040511/project/bioagent\\-bench/dataset/(?!comparative\\-genomics(?:/|$|[\\s'\\\"<>]))[^\\s'\\\"<>]+",
+        "/225040511/project/bioagent\\-bench/dataset/comparative\\-genomics/results(?:/|$|[^\\s'\\\"<>]*)",
+        "/225040511/project/bioagent\\-bench/dataset/comparative\\-genomics/(?:data|reference)/biomni_data(?:/|$|[^\\s'\\\"<>]*)",
+        "/225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/(?!comparative\\-genomics_20260520_140937(?:/|$|[\\s'\\\"<>]))[^\\s'\\\"<>]+",
+        "os\\\\.walk\\\\(['\\\"]/225040511/project/bioagent\\-bench/dataset['\\\"]\\\\)",
+        "Path\\\\(['\\\"]/225040511/project/bioagent\\-bench/dataset['\\\"]\\\\)\\\\.rglob"
+      ],
+      "forbidden_substrings": [
+        "pip install",
+        "conda install",
+        "mamba install",
+        "install.packages(",
+        "BiocManager::install",
+        "http://",
+        "https://"
+      ],
+      "forbidden_commands": [
+        "wget ",
+        "curl ",
+        "aws s3 cp",
+        "gsutil cp"
+      ]
+    },
+    "benchmark_task_context": {
+      "task_id": "comparative-genomics",
+      "task_name": "Comparative Genomics: Co-evolving Gene Clusters",
+      "description": "The datasets consists FASTA sequences and GFF annotations of a microbial genome for Micrococcus. The goal of is to do phylogenetic reconstruction of clusters of orthologous co-evolving genes; identify functionally conserved gene clusters across the genomes and group them into co-evolving functional modules.",
+      "task_prompt": "Reconstruct phylogeny and identify COGs across four Micrococcus genomes; filter clusters present in all genomes, coding-only, with high-confidence annotations. The output should be a CSV file with the following columns: 'cluster_number, 'consensus_annotation'.<example>cluster_number,consensus_annotation\n1,K07222  K07222, putative flavoprotein involved in K+ transport\n2,K01069  gloB, gloC, HAGH, hydroxyacylglutathione hydrolase [EC:3.1.2.6]\n</example>",
+      "extra_instruction": "",
+      "required_outputs": [
+        "cluster_annotation_mapping.csv"
+      ]
+    }
+  },
+  "query": "You are running a bioagent-bench task with local files already prepared.\n\nTask ID: comparative-genomics\nTask name: Comparative Genomics: Co-evolving Gene Clusters\nBenchmark prompt:\nReconstruct phylogeny and identify COGs across four Micrococcus genomes; filter clusters present in all genomes, coding-only, with high-confidence annotations. The output should be a CSV file with the following columns: 'cluster_number, 'consensus_annotation'.<example>cluster_number,consensus_annotation\n1,K07222  K07222, putative flavoprotein involved in K+ transport\n2,K01069  gloB, gloC, HAGH, hydroxyacylglutathione hydrolase [EC:3.1.2.6]\n</example>\nData background:\nThe datasets consists FASTA sequences and GFF annotations of a microbial genome for Micrococcus. The goal of is to do phylogenetic reconstruction of clusters of orthologous co-evolving genes; identify functionally conserved gene clusters across the genomes and group them into co-evolving functional modules.\nConstraints:\n1. Use only the benchmark inputs and references explicitly listed below.\n2. Do not inspect or use any files under benchmark truth/results directories, sibling task directories, generated biomni_data caches, or previous run outputs.\n3. Save the required final deliverables exactly to the paths listed below.\n4. Save any intermediate scripts, logs, and scratch outputs inside this run directory: /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937\n5. Keep final deliverables in the same schema/format requested by the benchmark prompt.\n6. Return a concise final summary after writing the required files.\n7. The runner, Python REPL, MCP servers, Rscript, and CLI subprocesses are bound to this conda environment: /225040511/miniconda3/envs/biomni_e1. Do not switch to another conda environment.\n\nBenchmark data policy:\n- Allowed input data directory: /225040511/project/bioagent-bench/dataset/comparative-genomics/data\n- Allowed reference directory: /225040511/project/bioagent-bench/dataset/comparative-genomics/reference\n- Allowed scratch/output directory: /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937\n- Forbidden truth/results directory: /225040511/project/bioagent-bench/dataset/comparative-genomics/results\n- Forbidden sibling benchmark task directories: /225040511/project/bioagent-bench/dataset/<any task other than comparative-genomics>\n- Forbidden generated Biomni cache/runtime directories inside benchmark inputs: /225040511/project/bioagent-bench/dataset/comparative-genomics/data/biomni_data and /225040511/project/bioagent-bench/dataset/comparative-genomics/reference/biomni_data\n- Do not inspect previous bioagent-bench-runs as data sources.\n- Do not download external databases or install new packages during the benchmark run.\n- You may use installed command-line tools, Python/R packages, and MCP servers as executors, but their inputs must come from the allowed paths above.\n\nInput data directory:\n/225040511/project/bioagent-bench/dataset/comparative-genomics/data\nVisible input files:\n- GCF_002008305.4_ASM200830v4_genomic.fna\n- GCF_003691675.1_ASM369167v1_genomic.fna\n- GCF_005280335.1_ASM528033v1_genomic.fna\n- GCF_020097155.1_ASM2009715v1_genomic.fna\n- GCF_023573625.1_ASM2357362v1_genomic.fna\n- assembly_data_report.jsonl\n- genomic.gff\n\nReference data directory:\n/225040511/project/bioagent-bench/dataset/comparative-genomics/reference\nVisible reference files:\n- Actinobacteria.RData\n\nRequired final output paths:\n- cluster_annotation_mapping.csv: /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/cluster_annotation_mapping.csv",
+  "benchmark_policy": "Benchmark data policy:\n- Allowed input data directory: /225040511/project/bioagent-bench/dataset/comparative-genomics/data\n- Allowed reference directory: /225040511/project/bioagent-bench/dataset/comparative-genomics/reference\n- Allowed scratch/output directory: /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937\n- Forbidden truth/results directory: /225040511/project/bioagent-bench/dataset/comparative-genomics/results\n- Forbidden sibling benchmark task directories: /225040511/project/bioagent-bench/dataset/<any task other than comparative-genomics>\n- Forbidden generated Biomni cache/runtime directories inside benchmark inputs: /225040511/project/bioagent-bench/dataset/comparative-genomics/data/biomni_data and /225040511/project/bioagent-bench/dataset/comparative-genomics/reference/biomni_data\n- Do not inspect previous bioagent-bench-runs as data sources.\n- Do not download external databases or install new packages during the benchmark run.\n- You may use installed command-line tools, Python/R packages, and MCP servers as executors, but their inputs must come from the allowed paths above.",
+  "benchmark_execution_guard": {
+    "enabled": true,
+    "allowed_roots": [
+      "/225040511/project/bioagent-bench/dataset/comparative-genomics/data",
+      "/225040511/project/bioagent-bench/dataset/comparative-genomics/reference",
+      "/225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937"
+    ],
+    "forbidden_patterns": [
+      "/225040511/project/bioagent\\-bench/dataset/(?!comparative\\-genomics(?:/|$|[\\s'\\\"<>]))[^\\s'\\\"<>]+",
+      "/225040511/project/bioagent\\-bench/dataset/comparative\\-genomics/results(?:/|$|[^\\s'\\\"<>]*)",
+      "/225040511/project/bioagent\\-bench/dataset/comparative\\-genomics/(?:data|reference)/biomni_data(?:/|$|[^\\s'\\\"<>]*)",
+      "/225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/(?!comparative\\-genomics_20260520_140937(?:/|$|[\\s'\\\"<>]))[^\\s'\\\"<>]+",
+      "os\\\\.walk\\\\(['\\\"]/225040511/project/bioagent\\-bench/dataset['\\\"]\\\\)",
+      "Path\\\\(['\\\"]/225040511/project/bioagent\\-bench/dataset['\\\"]\\\\)\\\\.rglob"
+    ],
+    "forbidden_substrings": [
+      "pip install",
+      "conda install",
+      "mamba install",
+      "install.packages(",
+      "BiocManager::install",
+      "http://",
+      "https://"
+    ],
+    "forbidden_commands": [
+      "wget ",
+      "curl ",
+      "aws s3 cp",
+      "gsutil cp"
+    ]
+  },
+  "benchmark_task_context": {
+    "task_id": "comparative-genomics",
+    "task_name": "Comparative Genomics: Co-evolving Gene Clusters",
+    "description": "The datasets consists FASTA sequences and GFF annotations of a microbial genome for Micrococcus. The goal of is to do phylogenetic reconstruction of clusters of orthologous co-evolving genes; identify functionally conserved gene clusters across the genomes and group them into co-evolving functional modules.",
+    "task_prompt": "Reconstruct phylogeny and identify COGs across four Micrococcus genomes; filter clusters present in all genomes, coding-only, with high-confidence annotations. The output should be a CSV file with the following columns: 'cluster_number, 'consensus_annotation'.<example>cluster_number,consensus_annotation\n1,K07222  K07222, putative flavoprotein involved in K+ transport\n2,K01069  gloB, gloC, HAGH, hydroxyacylglutathione hydrolase [EC:3.1.2.6]\n</example>",
+    "extra_instruction": "",
+    "required_outputs": [
+      "cluster_annotation_mapping.csv"
+    ]
+  },
+  "timestamp_utc": "20260520_140937",
+  "runtime_environment": {
+    "execution_env_prefix": "/225040511/miniconda3/envs/biomni_e1",
+    "execution_python": "/225040511/miniconda3/envs/biomni_e1/bin/python",
+    "conda_default_env": "biomni_e1",
+    "conda_prefix": "/225040511/miniconda3/envs/biomni_e1",
+    "path_head": [
+      "/225040511/miniconda3/envs/biomni_e1/bin",
+      "/225040511/miniconda3/envs/biomni_e1/bin",
+      "/225040511/miniconda3/bin",
+      "/225040511/miniconda3/condabin",
+      "/usr/local/nvm/versions/node/v18.20.3/bin"
+    ]
+  }
+}

Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/run_summary.json

@@ -0,0 +1,18 @@
+{
+  "task_id": "comparative-genomics",
+  "run_dir": "/225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937",
+  "final_answer_path": "/225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/final_answer.txt",
+  "metadata_path": "/225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/run_metadata.json",
+  "query_path": "/225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/task_query.txt",
+  "retrieval_plan_path": "/225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/retrieval_plan.json",
+  "output_validation_path": "/225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/output_validation.json",
+  "outputs": [
+    {
+      "path": "/225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/cluster_annotation_mapping.csv",
+      "exists": true,
+      "size_bytes": 38334
+    }
+  ],
+  "planning_latency_seconds": 38.00501701235771,
+  "total_runtime_seconds": 4270.746450684965
+}

Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/task_query.txt

@@ -0,0 +1,49 @@
+You are running a bioagent-bench task with local files already prepared.
+
+Task ID: comparative-genomics
+Task name: Comparative Genomics: Co-evolving Gene Clusters
+Benchmark prompt:
+Reconstruct phylogeny and identify COGs across four Micrococcus genomes; filter clusters present in all genomes, coding-only, with high-confidence annotations. The output should be a CSV file with the following columns: 'cluster_number, 'consensus_annotation'.<example>cluster_number,consensus_annotation
+1,K07222  K07222, putative flavoprotein involved in K+ transport
+2,K01069  gloB, gloC, HAGH, hydroxyacylglutathione hydrolase [EC:3.1.2.6]
+</example>
+Data background:
+The datasets consists FASTA sequences and GFF annotations of a microbial genome for Micrococcus. The goal of is to do phylogenetic reconstruction of clusters of orthologous co-evolving genes; identify functionally conserved gene clusters across the genomes and group them into co-evolving functional modules.
+Constraints:
+1. Use only the benchmark inputs and references explicitly listed below.
+2. Do not inspect or use any files under benchmark truth/results directories, sibling task directories, generated biomni_data caches, or previous run outputs.
+3. Save the required final deliverables exactly to the paths listed below.
+4. Save any intermediate scripts, logs, and scratch outputs inside this run directory: /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937
+5. Keep final deliverables in the same schema/format requested by the benchmark prompt.
+6. Return a concise final summary after writing the required files.
+7. The runner, Python REPL, MCP servers, Rscript, and CLI subprocesses are bound to this conda environment: /225040511/miniconda3/envs/biomni_e1. Do not switch to another conda environment.
+
+Benchmark data policy:
+- Allowed input data directory: /225040511/project/bioagent-bench/dataset/comparative-genomics/data
+- Allowed reference directory: /225040511/project/bioagent-bench/dataset/comparative-genomics/reference
+- Allowed scratch/output directory: /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937
+- Forbidden truth/results directory: /225040511/project/bioagent-bench/dataset/comparative-genomics/results
+- Forbidden sibling benchmark task directories: /225040511/project/bioagent-bench/dataset/<any task other than comparative-genomics>
+- Forbidden generated Biomni cache/runtime directories inside benchmark inputs: /225040511/project/bioagent-bench/dataset/comparative-genomics/data/biomni_data and /225040511/project/bioagent-bench/dataset/comparative-genomics/reference/biomni_data
+- Do not inspect previous bioagent-bench-runs as data sources.
+- Do not download external databases or install new packages during the benchmark run.
+- You may use installed command-line tools, Python/R packages, and MCP servers as executors, but their inputs must come from the allowed paths above.
+
+Input data directory:
+/225040511/project/bioagent-bench/dataset/comparative-genomics/data
+Visible input files:
+- GCF_002008305.4_ASM200830v4_genomic.fna
+- GCF_003691675.1_ASM369167v1_genomic.fna
+- GCF_005280335.1_ASM528033v1_genomic.fna
+- GCF_020097155.1_ASM2009715v1_genomic.fna
+- GCF_023573625.1_ASM2357362v1_genomic.fna
+- assembly_data_report.jsonl
+- genomic.gff
+
+Reference data directory:
+/225040511/project/bioagent-bench/dataset/comparative-genomics/reference
+Visible reference files:
+- Actinobacteria.RData
+
+Required final output paths:
+- cluster_annotation_mapping.csv: /225040511/project/Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260520_140937/cluster_annotation_mapping.csv

Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260522_115630/orthofinder_output/results/Results_May22/Resolved_Gene_Trees/OG0000007_tree.txt

@@ -0,0 +1 @@
+(AS2_ACLBLIBL_01214:0.00128387,(SA211_MHAAABBN_01011:0.00464154,(SA211_MHAAABBN_01114:0.00747385,((KBS0714_MOLHKGIG_00157:0,KBS0714_MOLHKGIG_01034:0,KBS0714_MOLHKGIG_01292:0,KBS0714_MOLHKGIG_02077:0,SA211_MHAAABBN_01104:0,TT9_LFPAFLNI_01250:0)n4:5e-09,(TT9_LFPAFLNI_01339:5e-09,((TT9_LFPAFLNI_00588:0,TT9_LFPAFLNI_02205:0)n7:0.00371775,((KBS0714_MOLHKGIG_01384:5e-09,(SA211_MHAAABBN_02023:0.00278449,TT9_LFPAFLNI_01885:0.0166207)n10:0.000941071)n9:5e-09,(TT9_LFPAFLNI_00590:0.0335204,SA211_MHAAABBN_01112:4.5e-09)n11:5e-10)n8:0.00372693)n6:5e-09)n5:5e-09)n3:5e-09)n2:0.00114773)n1:0.00128387)n0;

Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260522_115630/orthofinder_output/results/Results_May22/Resolved_Gene_Trees/OG0000025_tree.txt

@@ -0,0 +1 @@
+((AS2_ACLBLIBL_00590:0.97066,KD337_NAFOICDF_00524:1.10839)n1:0.173587,(KD337_NAFOICDF_00077:0.326182,(AS2_ACLBLIBL_00109:0.165968,(SA211_MHAAABBN_02273:0.00617869,(KBS0714_MOLHKGIG_00260:5e-09,TT9_LFPAFLNI_00258:0.00452942)n5:0.00755213)n4:0.230664)n3:0.367909)n2:0.173587)n0;

Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260522_115630/orthofinder_output/results/Results_May22/Resolved_Gene_Trees/OG0000026_tree.txt

@@ -0,0 +1 @@
+(KD337_NAFOICDF_00093:0.106919,(KBS0714_MOLHKGIG_00245:5e-09,((AS2_ACLBLIBL_00124:0.0119858,TT9_LFPAFLNI_00245:0.0104521)n3:0.0146913,((SA211_MHAAABBN_00096:0.753052,SA211_MHAAABBN_00100:0.999711)n5:0.423025,SA211_MHAAABBN_02257:4.5e-09)n4:5e-10)n2:0.00366845)n1:0.172288)n0;

Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260522_115630/orthofinder_output/results/Results_May22/Resolved_Gene_Trees/OG0000041_tree.txt

@@ -0,0 +1 @@
+(KD337_NAFOICDF_02214:0,(TT9_LFPAFLNI_02003:0.198198,(AS2_ACLBLIBL_00718:0.00848374,(SA211_MHAAABBN_00340:0,((KBS0714_MOLHKGIG_00617:0,KBS0714_MOLHKGIG_02075:0)n5:0.00507506,SA211_MHAAABBN_01780:5e-09)n4:0.00635949)n3:0.000706611)n2:5e-09)n1:0.0154271)n0;

Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260522_115630/orthofinder_output/results/Results_May22/Resolved_Gene_Trees/OG0000067_tree.txt

@@ -0,0 +1 @@
+((KD337_NAFOICDF_00088:0.0781417,KD337_NAFOICDF_02472:0.394103)n1:0.0485506,(AS2_ACLBLIBL_00120:0.0301196,(KBS0714_MOLHKGIG_00250:0.00617101,(SA211_MHAAABBN_02262:0.00491775,TT9_LFPAFLNI_00250:0.00185262)n4:0.00782996)n3:0.0346302)n2:0.0485506)n0;

Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260522_115630/orthofinder_output/results/Results_May22/Resolved_Gene_Trees/OG0000080_tree.txt

@@ -0,0 +1 @@
+(KD337_NAFOICDF_00273:0.0641015,((TT9_LFPAFLNI_00058:0.0165505,(KBS0714_MOLHKGIG_00063:0.00342973,SA211_MHAAABBN_02076:0.0271495)n3:0.00805598)n2:0.138072,(AS2_ACLBLIBL_00332:0.101313,AS2_ACLBLIBL_00201:1.60376)n4:0.178196)n1:5e-09)n0;

Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260522_115630/orthofinder_output/results/Results_May22/Resolved_Gene_Trees/OG0000081_tree.txt

@@ -0,0 +1 @@
+(KD337_NAFOICDF_00258:0.0828191,((KBS0714_MOLHKGIG_00076:0,TT9_LFPAFLNI_00070:0)n2:5e-09,(SA211_MHAAABBN_02089:0.00645918,(AS2_ACLBLIBL_02338:1.30606,AS2_ACLBLIBL_00317:0.0203714)n4:0.00226349)n3:0.00318119)n1:0.209305)n0;

Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260522_115630/orthofinder_output/results/Results_May22/Resolved_Gene_Trees/OG0000091_tree.txt

@@ -0,0 +1 @@
+(KD337_NAFOICDF_00386:0.0377915,((SA211_MHAAABBN_01996:0.00307433,(TT9_LFPAFLNI_02244:0.00575636,KBS0714_MOLHKGIG_02303:0.00301314)n3:0.00285659)n2:0.0374611,(AS2_ACLBLIBL_00739:0.590509,AS2_ACLBLIBL_00434:0.0396774)n4:0.0044086)n1:0.0515312)n0;

Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260522_115630/orthofinder_output/results/Results_May22/Resolved_Gene_Trees/OG0000094_tree.txt

@@ -0,0 +1 @@
+(KD337_NAFOICDF_00435:0.00424512,((SA211_MHAAABBN_01951:0.00564189,TT9_LFPAFLNI_02183:6e-09)n2:0.00565926,(AS2_ACLBLIBL_00489:0.0495112,(KBS0714_MOLHKGIG_02252:0.00563832,KBS0714_MOLHKGIG_02276:0.0170355)n4:0.00286199)n3:0.00279431)n1:0.00424512)n0;

Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260522_115630/orthofinder_output/results/Results_May22/Resolved_Gene_Trees/OG0000110_tree.txt

@@ -0,0 +1 @@
+(KD337_NAFOICDF_00762:0.0167156,(AS2_ACLBLIBL_00803:0.0678871,((TT9_LFPAFLNI_01955:0.00957505,(SA211_MHAAABBN_01727:0.0238886,SA211_MHAAABBN_00095:1.13126)n4:0.125695)n3:0.000656985,KBS0714_MOLHKGIG_02018:0.0101488)n2:0.00959661)n1:0.0167156)n0;

Biomanus/experiments/ablation/results/biomanus/bioagentbench/comparative-genomics_20260522_115630/orthofinder_output/results/Results_May22/Resolved_Gene_Trees/OG0000118_tree.txt

@@ -0,0 +1 @@
+(KD337_NAFOICDF_01000:0.0619796,(((KBS0714_MOLHKGIG_01809:0,SA211_MHAAABBN_01506:0)n3:0.00737441,TT9_LFPAFLNI_01730:0.0156063)n2:0.0714646,(AS2_ACLBLIBL_02644:0.967376,AS2_ACLBLIBL_01065:0.0451231)n4:0.00501368)n1:0.0529771)n0;