pino-source-code / artifacts /data_split_diagnostics_v9.json
Matthew Ford
Add Fraterworks ingestion and upload data split support
2671b56
Raw
History Blame Contribute Delete
36.2 kB
{
"canonicalization": {
"ethanol_control": "CONTROL_64-17-5 excluded as a control",
"identifier": "InChIKey from RDKit structure when available; fallback to CAS/name for unresolved rows"
},
"chosen_strategy": {
"diagnostics": {
"component_count": 210,
"hub_threshold": 0.02,
"target_validation_records": 1122,
"top_component_record_counts": [
5393,
3,
2,
2,
2,
2,
2,
1,
1,
1
]
},
"excluded_records": 1,
"hub_count": 2,
"hub_threshold": 0.02,
"justification": "Canonicalization fixes identifier fragmentation and includes nearly all records. The requested 20/10/5% hub thresholds do not identify any hubs in v9; lower thresholds are reported as sensitivity analysis because aggressive hub removal can ignore too many aroma materials.",
"leakage_spectrum": {
"n_validation_with_fingerprint": 216,
"nearest_train_jaccard": {
"max": 0.0,
"mean": 0.0,
"p50": 0.0,
"p90": 0.0,
"p95": 0.0
}
},
"meaningful_train_validation_overlap": 0,
"name": "canonicalized component split with optional hub exclusion",
"selection_bias": {
"excluded": {
"formula_size": {
"mean": 0.0,
"p50": 0.0,
"p90": 0.0
},
"mean_molecule_formula_frequency": {
"mean": null,
"p50": null,
"p90": null
},
"n": 1,
"objective_target_length": {
"mean": 49.0,
"p50": 49.0,
"p90": 49.0
},
"psychometric_target_mean": {
"mean": 0.20714285544285715,
"p50": 0.20714285544285715,
"p90": 0.20714285544285715
}
},
"included": {
"formula_size": {
"mean": 5.8862542342663575,
"p50": 6.0,
"p90": 10.0
},
"mean_molecule_formula_frequency": {
"mean": 61.626451677717675,
"p50": 63.5,
"p90": 74.5
},
"n": 5609,
"objective_target_length": {
"mean": 49.0,
"p50": 49.0,
"p90": 49.0
},
"psychometric_target_mean": {
"mean": 0.24383717903518365,
"p50": 0.2120879036857143,
"p90": 0.3306122555142857
}
}
},
"train_records": 5393,
"validation_records": 216
},
"graph": {
"duplicate_identities_after_canonicalization": [
{
"aliases": [
"68606-83-7",
"Rosa centifolia absolute [68606-83-7]"
],
"key": "68606-83-7"
},
{
"aliases": [
"8000-25-7",
"Bay oil [8000-25-7]"
],
"key": "8000-25-7"
},
{
"aliases": [
"8000-27-9",
"Lemon oil [8000-27-9]"
],
"key": "8000-27-9"
},
{
"aliases": [
"8000-28-0",
"Lime oil [8000-28-0]"
],
"key": "8000-28-0"
},
{
"aliases": [
"8000-29-1",
"Neroli oil [8000-29-1]"
],
"key": "8000-29-1"
},
{
"aliases": [
"8000-34-8",
"Clove oil [8000-34-8]"
],
"key": "8000-34-8"
},
{
"aliases": [
"8000-41-7",
"Rose oil [8000-41-7]"
],
"key": "8000-41-7"
},
{
"aliases": [
"8000-46-2",
"Rosemary oil [8000-46-2]"
],
"key": "8000-46-2"
},
{
"aliases": [
"8007-00-9",
"Amber oil [8007-00-9]"
],
"key": "8007-00-9"
},
{
"aliases": [
"8007-01-0",
"Rose otto [8007-01-0]"
],
"key": "8007-01-0"
},
{
"aliases": [
"8007-06-5",
"Cascarilla oil [8007-06-5]"
],
"key": "8007-06-5"
},
{
"aliases": [
"8007-46-3",
"Cinnamon oil [8007-46-3]"
],
"key": "8007-46-3"
},
{
"aliases": [
"8007-75-8",
"Bergamot oil [8007-75-8]"
],
"key": "8007-75-8"
},
{
"aliases": [
"8007-80-5",
"Musk seed oil [8007-80-5]"
],
"key": "8007-80-5"
},
{
"aliases": [
"8014-09-3",
"Patchouli oil [8014-09-3]"
],
"key": "8014-09-3"
},
{
"aliases": [
"8014-17-3",
"Petitgrain oil [8014-17-3]"
],
"key": "8014-17-3"
},
{
"aliases": [
"8016-26-0",
"Labdanum clair [8016-26-0]"
],
"key": "8016-26-0"
},
{
"aliases": [
"8016-38-4",
"Basil oil [8016-38-4]"
],
"key": "8016-38-4"
},
{
"aliases": [
"8016-63-5",
"Lavender oil [8016-63-5]"
],
"key": "8016-63-5"
},
{
"aliases": [
"8016-78-2",
"Pine needle oil [8016-78-2]"
],
"key": "8016-78-2"
},
{
"aliases": [
"8016-96-4",
"Geranium oil [8016-96-4]"
],
"key": "8016-96-4"
},
{
"aliases": [
"8022-96-6",
"Jasmin absolute [8022-96-6]"
],
"key": "8022-96-6"
},
{
"aliases": [
"8023-75-2",
"Ylang ylang oil [8023-75-2]"
],
"key": "8023-75-2"
},
{
"aliases": [
"8023-79-2",
"Musk tonkin [8023-79-2]"
],
"key": "8023-79-2"
},
{
"aliases": [
"8023-91-4",
"Jasmin sambac [8023-91-4]"
],
"key": "8023-91-4"
},
{
"aliases": [
"8024-13-1",
"Styrax resinoid [8024-13-1]"
],
"key": "8024-13-1"
},
{
"aliases": [
"8031-03-6",
"Cardamom oil [8031-03-6]"
],
"key": "8031-03-6"
},
{
"aliases": [
"8046-19-3",
"Labdanum resinoid [8046-19-3]"
],
"key": "8046-19-3"
},
{
"aliases": [
"9000-50-4",
"Frankincense oil [9000-50-4]"
],
"key": "9000-50-4"
},
{
"aliases": [
"9000-64-0",
"Mimosa absolute [9000-64-0]"
],
"key": "9000-64-0"
},
{
"aliases": [
"9000-64-2",
"Orange flower absolute [9000-64-2]"
],
"key": "9000-64-2"
},
{
"aliases": [
"9000-65-5",
"Tuberose absolute [9000-65-5]"
],
"key": "9000-65-5"
},
{
"aliases": [
"1,2-dimethoxybenzene [SMILES:COc1ccccc1OC]",
"SMILES:COc1ccccc1OC"
],
"key": "InChIKey:ABDKAPXRBAPSQN-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:O=C(O)CO",
"glycolic acid [SMILES:O=C(O)CO]"
],
"key": "InChIKey:AEMRFAOFKBGASW-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:CCC(C)C(N)C(=O)O",
"dl-isoleucine [SMILES:CCC(C)C(N)C(=O)O]"
],
"key": "InChIKey:AGPKZVBTJJNPAG-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:CC[C@H](C)[C@H](N)C(=O)O",
"l-isoleucine [SMILES:CC[C@H](C)[C@H](N)C(=O)O]"
],
"key": "InChIKey:AGPKZVBTJJNPAG-WHFBIAKZSA-N"
},
{
"aliases": [
"SMILES:CC(=O)C=O",
"methylglyoxal [SMILES:CC(=O)C=O]"
],
"key": "InChIKey:AIJULSRZWUXGPQ-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:CC(C)C=O",
"isobutyraldehyde [SMILES:CC(C)C=O]"
],
"key": "InChIKey:AMIMRNSIRUDHCM-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:CCCCCCCCOC=O",
"octyl formate [SMILES:CCCCCCCCOC=O]"
],
"key": "InChIKey:AVBRYQRTMPHARE-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:CCCCCCCCCCCCCC(=O)OC(C)C",
"isopropyl myristate [SMILES:CCCCCCCCCCCCCC(=O)OC(C)C]"
],
"key": "InChIKey:AXISYYRBXTVTFY-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:C[C@@H](O)[C@H](N)C(=O)O",
"l-threonine [SMILES:C[C@@H](O)[C@H](N)C(=O)O]"
],
"key": "InChIKey:AYFVYJQAPQTCCC-GBXIJSLDSA-N"
},
{
"aliases": [
"SMILES:CCCCOC(=O)CC(C)C",
"butyl isovalerate [SMILES:CCCCOC(=O)CC(C)C]"
],
"key": "InChIKey:AYWJSCLAAPJZEF-UHFFFAOYSA-N"
},
{
"aliases": [
"110-98-5 [SMILES:CC(O)COCC(C)O]",
"SMILES:CC(O)COCC(C)O"
],
"key": "InChIKey:AZUXKVXMJOIAOF-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:CCCCCCCCCCCC(=O)N(C)CC(=O)O",
"n-lauroylsarcosine [SMILES:CCCCCCCCCCCC(=O)N(C)CC(=O)O]"
],
"key": "InChIKey:BACYUWVYYTXETD-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:C=C(C)C1CC=C(C)C(O)C1",
"carveol [SMILES:C=C(C)C1CC=C(C)C(O)C1]"
],
"key": "InChIKey:BAVONGHXFVOKBV-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:COC(=O)CC(=O)OC",
"dimethyl malonate [SMILES:COC(=O)CC(=O)OC]"
],
"key": "InChIKey:BEPAFCGSDWSTEL-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:O=C(O)CC(O)C(=O)O",
"malic acid [SMILES:O=C(O)CC(O)C(=O)O]"
],
"key": "InChIKey:BJEPYKJPYRNKOW-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:O=C(CO)[C@@H](O)[C@H](O)[C@H](O)CO",
"d-(-)-fructose [SMILES:O=C(CO)[C@@H](O)[C@H](O)[C@H](O)CO]"
],
"key": "InChIKey:BJHIKXHVCXFQLS-UYFOZJQFSA-N"
},
{
"aliases": [
"SMILES:CCCCCCCCC",
"nonane [SMILES:CCCCCCCCC]"
],
"key": "InChIKey:BKIMMITUMNQMOS-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:CC(C)CCN",
"isoamylamine [SMILES:CC(C)CCN]"
],
"key": "InChIKey:BMFVGAAISNGQNM-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:CCCCCCN",
"hexylamine [SMILES:CCCCCCN]"
],
"key": "InChIKey:BMVXCPBXGZKUPN-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:OCC1CCCO1",
"tetrahydrofurfuryl alcohol [SMILES:OCC1CCCO1]"
],
"key": "InChIKey:BSYVTEYKTMYBMK-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:O=C(O)C(=O)Cc1ccccc1",
"phenylpyruvic acid [SMILES:O=C(O)C(=O)Cc1ccccc1]"
],
"key": "InChIKey:BTNMPGBKDVTSJY-UHFFFAOYSA-N"
},
{
"aliases": [
"4'-chloroacetophenone [SMILES:CC(=O)c1ccc(Cl)cc1]",
"SMILES:CC(=O)c1ccc(Cl)cc1"
],
"key": "InChIKey:BUZYGTVTZYSBCU-UHFFFAOYSA-N"
},
{
"aliases": [
"C1=CC(=CC=C1CO)O [SMILES:C1=CC(=CC=C1CO)O]",
"SMILES:C1=CC(=CC=C1CO)O"
],
"key": "InChIKey:BVJSUAQZOZWCKN-UHFFFAOYSA-N"
},
{
"aliases": [
"2-methylbutyraldehyde [SMILES:CCC(C)C=O]",
"SMILES:CCC(C)C=O"
],
"key": "InChIKey:BYGQBDHUGHBGMD-UHFFFAOYSA-N"
},
{
"aliases": [
"(3S,5R,10S,13R,14R,17R)-4,4,10,13,14-pentamethyl-17-(6-methylhept-5-en-2-yl)-2,3,5,6,7,11,12,15,16,17-decahydro-1H-cyclopenta[a]phenanthren-3-ol [SMILES:CC(C)=CCCC(C)[C@H]1CC[C@@]2(C)C3=C(CC[C@]12C)[C@@]1(C)CC[C@H](O)C(C)(C)[C@@H]1CC3]",
"SMILES:CC(C)=CCCC(C)[C@H]1CC[C@@]2(C)C3=C(CC[C@]12C)[C@@]1(C)CC[C@H](O)C(C)(C)[C@@H]1CC3"
],
"key": "InChIKey:CAHGCLMLTWQZNJ-UDJFBIGMSA-N"
},
{
"aliases": [
"3-(methylthio)propionic acid [SMILES:CSCCC(=O)O]",
"SMILES:CSCCC(=O)O"
],
"key": "InChIKey:CAOMCZAIALVUPA-UHFFFAOYSA-N"
},
{
"aliases": [
"2-heptanone [SMILES:CCCCCC(C)=O]",
"SMILES:CCCCCC(C)=O"
],
"key": "InChIKey:CATSNJVOTSVZJV-UHFFFAOYSA-N"
},
{
"aliases": [
"2-methylpyrazine [SMILES:Cc1cnccn1]",
"SMILES:Cc1cnccn1"
],
"key": "InChIKey:CAWHJQAVHZEVTJ-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:COC(=O)C=Cc1ccccc1",
"methyl 3-phenylprop-2-enoate [SMILES:COC(=O)C=Cc1ccccc1]"
],
"key": "InChIKey:CCRCUPLGCSFEDV-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:CCSSCC",
"diethyl disulfide [SMILES:CCSSCC]"
],
"key": "InChIKey:CETBSQOFQKLHHZ-UHFFFAOYSA-N"
},
{
"aliases": [
"80-71-7 [SMILES:CC1=C(O)C(=O)CC1]",
"SMILES:CC1=C(O)C(=O)CC1"
],
"key": "InChIKey:CFAKWWQIUFSQFU-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:CC1CCC(C(C)C)CC1",
"p-menthane [SMILES:CC1CCC(C(C)C)CC1]"
],
"key": "InChIKey:CFJYNSNXFXLKNS-UHFFFAOYSA-N"
},
{
"aliases": [
"4-methylanisole [SMILES:COc1ccc(C)cc1]",
"SMILES:COc1ccc(C)cc1"
],
"key": "InChIKey:CHLICZRVGGXEOD-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:N[C@@H](CC(=O)O)C(=O)O",
"l-aspartic acid [SMILES:N[C@@H](CC(=O)O)C(=O)O]"
],
"key": "InChIKey:CKLJMWTZIZZHCS-REOHCLBHSA-N"
},
{
"aliases": [
"SMILES:NC(CC(=O)O)C(=O)O",
"dl-aspartic acid [SMILES:NC(CC(=O)O)C(=O)O]"
],
"key": "InChIKey:CKLJMWTZIZZHCS-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:O=Cc1cccs1",
"thiophene-2-carbaldehyde [SMILES:O=Cc1cccs1]"
],
"key": "InChIKey:CNUDBTRUORMMPA-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:N[C@@H](Cc1ccccc1)C(=O)O",
"l-phenylalanine [SMILES:N[C@@H](Cc1ccccc1)C(=O)O]"
],
"key": "InChIKey:COLNVLDHVKWLRT-QMMMGPOBSA-N"
},
{
"aliases": [
"SMILES:NC(Cc1ccccc1)C(=O)O",
"dl-phenylalanine [SMILES:NC(Cc1ccccc1)C(=O)O]"
],
"key": "InChIKey:COLNVLDHVKWLRT-UHFFFAOYSA-N"
},
{
"aliases": [
"1,3-dimethylbutyl acetate [SMILES:CC(=O)OC(C)CC(C)C]",
"SMILES:CC(=O)OC(C)CC(C)C"
],
"key": "InChIKey:CPIVYSAVIPTCCX-UHFFFAOYSA-N"
},
{
"aliases": [
"2-isopropylphenol [SMILES:CC(C)c1ccccc1O]",
"SMILES:CC(C)c1ccccc1O"
],
"key": "InChIKey:CRBJBYGJVIBWIY-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:C=C1C2CCC(C2)C1(C)C",
"camphene [SMILES:C=C1C2CCC(C2)C1(C)C]"
],
"key": "InChIKey:CRPUJAZIXJMDBK-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:COC(=O)Cc1ccccc1",
"methyl phenylacetate [SMILES:COC(=O)Cc1ccccc1]"
],
"key": "InChIKey:CRZQGDNQQAALAY-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:Cc1ccccc1C",
"o-xylene [SMILES:Cc1ccccc1C]"
],
"key": "InChIKey:CTQNGGLPUBDAKN-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:CC(=O)CC(=O)c1ccccc1",
"benzoylacetone [SMILES:CC(=O)CC(=O)c1ccccc1]"
],
"key": "InChIKey:CVBUKMMMRLOKQR-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:c1ccc(Cc2ccccc2)cc1",
"diphenylmethane [SMILES:c1ccc(Cc2ccccc2)cc1]"
],
"key": "InChIKey:CZZYITDELCSZES-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:CCC(C)OC(C)=O",
"sec-butyl acetate [SMILES:CCC(C)OC(C)=O]"
],
"key": "InChIKey:DCKVNWZUADLDEH-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:NC(=O)C[C@H](N)C(=O)O",
"l-asparagine [SMILES:NC(=O)C[C@H](N)C(=O)O]"
],
"key": "InChIKey:DCXYFEDJOCDNAF-REOHCLBHSA-N"
},
{
"aliases": [
"SMILES:COc1cc(C(C)=O)ccc1O",
"acetovanillone [SMILES:COc1cc(C(C)=O)ccc1O]"
],
"key": "InChIKey:DFYRUELUNQRZTB-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:CCCCCCCCCCCCCC(=O)OCCCC",
"butyl myristate [SMILES:CCCCCCCCCCCCCC(=O)OCCCC]"
],
"key": "InChIKey:DHAZIUXMHRHVMP-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:CCOC(C)OCC",
"acetal [SMILES:CCOC(C)OCC]"
],
"key": "InChIKey:DHKHKXVYLBGOIT-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:NCC(=O)O",
"glycine [SMILES:NCC(=O)O]"
],
"key": "InChIKey:DHMQDGOQFOQNFH-UHFFFAOYSA-N"
},
{
"aliases": [
"3,7-dimethyloctan-3-ol [SMILES:CCC(C)(O)CCCC(C)C]",
"SMILES:CCC(C)(O)CCCC(C)C"
],
"key": "InChIKey:DLHQZZUEERVIGQ-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:CC(O)CO",
"propylene glycol [SMILES:CC(O)CO]"
],
"key": "InChIKey:DNIAPMSPPWPWGF-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:CCS",
"ethanethiol [SMILES:CCS]"
],
"key": "InChIKey:DNJIEGIFACGWOD-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:CCCCOC(=O)c1ccccc1C(=O)OCCCC",
"dibutyl phthalate [SMILES:CCCCOC(=O)c1ccccc1C(=O)OCCCC]"
],
"key": "InChIKey:DOIRQSBPFJWKBE-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:CCOC(=O)CC(O)(CC(=O)OCC)C(=O)OCC",
"triethyl citrate [SMILES:CCOC(=O)CC(O)(CC(=O)OCC)C(=O)OCC]"
],
"key": "InChIKey:DOOTYTYQINUNNV-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:CCCCCN",
"amylamine [SMILES:CCCCCN]"
],
"key": "InChIKey:DPBLXKKOBLCELK-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:O=CCc1ccccc1",
"phenylacetaldehyde [SMILES:O=CCc1ccccc1]"
],
"key": "InChIKey:DTUQWGWMVIHBKE-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:CCOC(=O)Cc1ccccc1",
"ethyl phenylacetate [SMILES:CCOC(=O)Cc1ccccc1]"
],
"key": "InChIKey:DULCUDSUACXJJC-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:NCCc1ccc(O)cc1",
"tyramine [SMILES:NCCc1ccc(O)cc1]"
],
"key": "InChIKey:DZGWFCGJZKJUFP-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:CC(C)=CCCC(C)CCOC=O",
"citronellyl formate [SMILES:CC(C)=CCCC(C)CCOC=O]"
],
"key": "InChIKey:DZNVIZQPWLDQHI-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:OC[C@@H](O)[C@@H](O)[C@H](O)[C@@H](O)CO",
"d-sorbitol [SMILES:OC[C@@H](O)[C@@H](O)[C@H](O)[C@@H](O)CO]"
],
"key": "InChIKey:FBPFZTCFMRRESA-JGWLITMVSA-N"
},
{
"aliases": [
"SMILES:OC[C@@H](O)[C@@H](O)[C@H](O)[C@H](O)CO",
"d-mannitol [SMILES:OC[C@@H](O)[C@@H](O)[C@H](O)[C@H](O)CO]"
],
"key": "InChIKey:FBPFZTCFMRRESA-KVTDHHQDSA-N"
},
{
"aliases": [
"SMILES:CCCCCCCCC(=O)O",
"nonanoic acid [SMILES:CCCCCCCCC(=O)O]"
],
"key": "InChIKey:FBUKVWPVBMHYJY-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:O=C(Oc1ccccc1)c1ccccc1",
"phenyl benzoate [SMILES:O=C(Oc1ccccc1)c1ccccc1]"
],
"key": "InChIKey:FCJSHPDYVMKCHI-UHFFFAOYSA-N"
},
{
"aliases": [
"3-pentanone [SMILES:CCC(=O)CC]",
"SMILES:CCC(=O)CC"
],
"key": "InChIKey:FDPIMTJIUBPUKL-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:CCCC(=O)O",
"butyric acid [SMILES:CCCC(=O)O]"
],
"key": "InChIKey:FERIUCNNQQJTOY-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:O=C(O)C(O)C(O)C(=O)O",
"dl-tartaric acid [SMILES:O=C(O)C(O)C(O)C(=O)O]"
],
"key": "InChIKey:FEWJPZIEWOKRBE-UHFFFAOYSA-N"
}
],
"n_data_records": 5609,
"n_molecules": 757,
"n_nonempty_records": 5609,
"n_records": 5610,
"thresholds": [
{
"covered_records": 5609,
"hub_count": 0,
"hub_only_records": 0,
"hubs": [],
"largest_component_molecules": 548,
"largest_component_records": 5393,
"max_validation_records_if_largest_component_trains": 216,
"n_components": 210,
"threshold": 0.2,
"top_component_record_counts": [
5393,
3,
2,
2,
2,
2,
2,
1,
1,
1
]
},
{
"covered_records": 5609,
"hub_count": 0,
"hub_only_records": 0,
"hubs": [],
"largest_component_molecules": 548,
"largest_component_records": 5393,
"max_validation_records_if_largest_component_trains": 216,
"n_components": 210,
"threshold": 0.1,
"top_component_record_counts": [
5393,
3,
2,
2,
2,
2,
2,
1,
1,
1
]
},
{
"covered_records": 5609,
"hub_count": 0,
"hub_only_records": 0,
"hubs": [],
"largest_component_molecules": 548,
"largest_component_records": 5393,
"max_validation_records_if_largest_component_trains": 216,
"n_components": 210,
"threshold": 0.05,
"top_component_record_counts": [
5393,
3,
2,
2,
2,
2,
2,
1,
1,
1
]
},
{
"covered_records": 5609,
"hub_count": 2,
"hub_only_records": 0,
"hubs": [
{
"aliases": [
"NATURAL:8006-87-9"
],
"formula_count": 116,
"formula_fraction": 0.0206810483152077,
"key": "NATURAL:8006-87-9"
},
{
"aliases": [
"NATURAL:8007-35-0"
],
"formula_count": 113,
"formula_fraction": 0.020146193617400606,
"key": "NATURAL:8007-35-0"
}
],
"largest_component_molecules": 546,
"largest_component_records": 5393,
"max_validation_records_if_largest_component_trains": 216,
"n_components": 210,
"threshold": 0.02,
"top_component_record_counts": [
5393,
3,
2,
2,
2,
2,
2,
1,
1,
1
]
},
{
"covered_records": 4789,
"hub_count": 303,
"hub_only_records": 820,
"hubs": [
{
"aliases": [
"NATURAL:8006-87-9"
],
"formula_count": 116,
"formula_fraction": 0.0206810483152077,
"key": "NATURAL:8006-87-9"
},
{
"aliases": [
"NATURAL:8007-35-0"
],
"formula_count": 113,
"formula_fraction": 0.020146193617400606,
"key": "NATURAL:8007-35-0"
},
{
"aliases": [
"NATURAL:8000-46-2"
],
"formula_count": 108,
"formula_fraction": 0.019254769121055445,
"key": "NATURAL:8000-46-2"
},
{
"aliases": [
"NATURAL:8000-66-6"
],
"formula_count": 107,
"formula_fraction": 0.019076484221786413,
"key": "NATURAL:8000-66-6"
},
{
"aliases": [
"NATURAL:8023-83-4"
],
"formula_count": 105,
"formula_fraction": 0.01871991442324835,
"key": "NATURAL:8023-83-4"
},
{
"aliases": [
"SMILES:CCc1cc2c(cc1C(C)=O)C(C)(C)CCC2(C)C",
"versalide [SMILES:CCc1cc2c(cc1C(C)=O)C(C)(C)CCC2(C)C]"
],
"formula_count": 104,
"formula_fraction": 0.01854162952397932,
"key": "InChIKey:KSEZPRJUTHMFGZ-UHFFFAOYSA-N"
},
{
"aliases": [
"NATURAL:9000-05-9"
],
"formula_count": 103,
"formula_fraction": 0.018363344624710287,
"key": "NATURAL:9000-05-9"
},
{
"aliases": [
"NATURAL:8008-52-4"
],
"formula_count": 101,
"formula_fraction": 0.018006774826172224,
"key": "NATURAL:8008-52-4"
},
{
"aliases": [
"NATURAL:8016-23-7"
],
"formula_count": 101,
"formula_fraction": 0.018006774826172224,
"key": "NATURAL:8016-23-7"
},
{
"aliases": [
"NATURAL:8008-56-8"
],
"formula_count": 99,
"formula_fraction": 0.01765020502763416,
"key": "NATURAL:8008-56-8"
},
{
"aliases": [
"NATURAL:8008-57-9"
],
"formula_count": 97,
"formula_fraction": 0.017293635229096094,
"key": "NATURAL:8008-57-9"
},
{
"aliases": [
"NATURAL:8014-17-3"
],
"formula_count": 96,
"formula_fraction": 0.017115350329827063,
"key": "NATURAL:8014-17-3"
},
{
"aliases": [
"NATURAL:9000-78-6"
],
"formula_count": 96,
"formula_fraction": 0.017115350329827063,
"key": "NATURAL:9000-78-6"
},
{
"aliases": [
"SMILES:CCCCCC(=O)OC",
"methyl hexanoate [SMILES:CCCCCC(=O)OC]"
],
"formula_count": 94,
"formula_fraction": 0.016758780531289,
"key": "InChIKey:NUKZAGXMHTUAFE-UHFFFAOYSA-N"
},
{
"aliases": [
"NATURAL:8007-01-0"
],
"formula_count": 94,
"formula_fraction": 0.016758780531289,
"key": "NATURAL:8007-01-0"
},
{
"aliases": [
"NATURAL:8016-37-3"
],
"formula_count": 94,
"formula_fraction": 0.016758780531289,
"key": "NATURAL:8016-37-3"
},
{
"aliases": [
"NATURAL:8016-96-4"
],
"formula_count": 94,
"formula_fraction": 0.016758780531289,
"key": "NATURAL:8016-96-4"
},
{
"aliases": [
"NATURAL:68916-26-7"
],
"formula_count": 93,
"formula_fraction": 0.016580495632019968,
"key": "NATURAL:68916-26-7"
},
{
"aliases": [
"NATURAL:8029-66-5"
],
"formula_count": 93,
"formula_fraction": 0.016580495632019968,
"key": "NATURAL:8029-66-5"
},
{
"aliases": [
"10458-14-7 [SMILES:CC1CCC(C(C)C)C(=O)C1]",
"SMILES:CC1CCC(C(C)C)C(=O)C1"
],
"formula_count": 92,
"formula_fraction": 0.016402210732750937,
"key": "InChIKey:NFLGAXVYCFJBMK-UHFFFAOYSA-N"
},
{
"aliases": [
"NATURAL:8000-25-7"
],
"formula_count": 92,
"formula_fraction": 0.016402210732750937,
"key": "NATURAL:8000-25-7"
},
{
"aliases": [
"104-54-1"
],
"formula_count": 90,
"formula_fraction": 0.016045640934212874,
"key": "104-54-1"
},
{
"aliases": [
"541-91-3"
],
"formula_count": 90,
"formula_fraction": 0.016045640934212874,
"key": "541-91-3"
},
{
"aliases": [
"SMILES:CCCCCCCCCCCCCC(=O)OC(C)C",
"isopropyl myristate [SMILES:CCCCCCCCCCCCCC(=O)OC(C)C]"
],
"formula_count": 90,
"formula_fraction": 0.016045640934212874,
"key": "InChIKey:AXISYYRBXTVTFY-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:CCOCC",
"diethyl ether [SMILES:CCOCC]"
],
"formula_count": 90,
"formula_fraction": 0.016045640934212874,
"key": "InChIKey:RTZKZFJDLAIYFH-UHFFFAOYSA-N"
}
],
"largest_component_molecules": 245,
"largest_component_records": 4573,
"max_validation_records_if_largest_component_trains": 1036,
"n_components": 210,
"threshold": 0.01,
"top_component_record_counts": [
4573,
3,
2,
2,
2,
2,
2,
1,
1,
1
]
}
],
"top_molecules": [
{
"aliases": [
"NATURAL:8006-87-9"
],
"formula_count": 116,
"formula_fraction": 0.0206810483152077,
"key": "NATURAL:8006-87-9"
},
{
"aliases": [
"NATURAL:8007-35-0"
],
"formula_count": 113,
"formula_fraction": 0.020146193617400606,
"key": "NATURAL:8007-35-0"
},
{
"aliases": [
"NATURAL:8000-46-2"
],
"formula_count": 108,
"formula_fraction": 0.019254769121055445,
"key": "NATURAL:8000-46-2"
},
{
"aliases": [
"NATURAL:8000-66-6"
],
"formula_count": 107,
"formula_fraction": 0.019076484221786413,
"key": "NATURAL:8000-66-6"
},
{
"aliases": [
"NATURAL:8023-83-4"
],
"formula_count": 105,
"formula_fraction": 0.01871991442324835,
"key": "NATURAL:8023-83-4"
},
{
"aliases": [
"SMILES:CCc1cc2c(cc1C(C)=O)C(C)(C)CCC2(C)C",
"versalide [SMILES:CCc1cc2c(cc1C(C)=O)C(C)(C)CCC2(C)C]"
],
"formula_count": 104,
"formula_fraction": 0.01854162952397932,
"key": "InChIKey:KSEZPRJUTHMFGZ-UHFFFAOYSA-N"
},
{
"aliases": [
"NATURAL:9000-05-9"
],
"formula_count": 103,
"formula_fraction": 0.018363344624710287,
"key": "NATURAL:9000-05-9"
},
{
"aliases": [
"NATURAL:8016-23-7"
],
"formula_count": 101,
"formula_fraction": 0.018006774826172224,
"key": "NATURAL:8016-23-7"
},
{
"aliases": [
"NATURAL:8008-52-4"
],
"formula_count": 101,
"formula_fraction": 0.018006774826172224,
"key": "NATURAL:8008-52-4"
},
{
"aliases": [
"NATURAL:8008-56-8"
],
"formula_count": 99,
"formula_fraction": 0.01765020502763416,
"key": "NATURAL:8008-56-8"
},
{
"aliases": [
"NATURAL:8008-57-9"
],
"formula_count": 97,
"formula_fraction": 0.017293635229096094,
"key": "NATURAL:8008-57-9"
},
{
"aliases": [
"NATURAL:8014-17-3"
],
"formula_count": 96,
"formula_fraction": 0.017115350329827063,
"key": "NATURAL:8014-17-3"
},
{
"aliases": [
"NATURAL:9000-78-6"
],
"formula_count": 96,
"formula_fraction": 0.017115350329827063,
"key": "NATURAL:9000-78-6"
},
{
"aliases": [
"SMILES:CCCCCC(=O)OC",
"methyl hexanoate [SMILES:CCCCCC(=O)OC]"
],
"formula_count": 94,
"formula_fraction": 0.016758780531289,
"key": "InChIKey:NUKZAGXMHTUAFE-UHFFFAOYSA-N"
},
{
"aliases": [
"NATURAL:8007-01-0"
],
"formula_count": 94,
"formula_fraction": 0.016758780531289,
"key": "NATURAL:8007-01-0"
},
{
"aliases": [
"NATURAL:8016-96-4"
],
"formula_count": 94,
"formula_fraction": 0.016758780531289,
"key": "NATURAL:8016-96-4"
},
{
"aliases": [
"NATURAL:8016-37-3"
],
"formula_count": 94,
"formula_fraction": 0.016758780531289,
"key": "NATURAL:8016-37-3"
},
{
"aliases": [
"NATURAL:8029-66-5"
],
"formula_count": 93,
"formula_fraction": 0.016580495632019968,
"key": "NATURAL:8029-66-5"
},
{
"aliases": [
"NATURAL:68916-26-7"
],
"formula_count": 93,
"formula_fraction": 0.016580495632019968,
"key": "NATURAL:68916-26-7"
},
{
"aliases": [
"10458-14-7 [SMILES:CC1CCC(C(C)C)C(=O)C1]",
"SMILES:CC1CCC(C(C)C)C(=O)C1"
],
"formula_count": 92,
"formula_fraction": 0.016402210732750937,
"key": "InChIKey:NFLGAXVYCFJBMK-UHFFFAOYSA-N"
},
{
"aliases": [
"NATURAL:8000-25-7"
],
"formula_count": 92,
"formula_fraction": 0.016402210732750937,
"key": "NATURAL:8000-25-7"
},
{
"aliases": [
"SMILES:CCOCC",
"diethyl ether [SMILES:CCOCC]"
],
"formula_count": 90,
"formula_fraction": 0.016045640934212874,
"key": "InChIKey:RTZKZFJDLAIYFH-UHFFFAOYSA-N"
},
{
"aliases": [
"SMILES:CCCCCCCCCCCCCC(=O)OC(C)C",
"isopropyl myristate [SMILES:CCCCCCCCCCCCCC(=O)OC(C)C]"
],
"formula_count": 90,
"formula_fraction": 0.016045640934212874,
"key": "InChIKey:AXISYYRBXTVTFY-UHFFFAOYSA-N"
},
{
"aliases": [
"541-91-3"
],
"formula_count": 90,
"formula_fraction": 0.016045640934212874,
"key": "541-91-3"
},
{
"aliases": [
"104-54-1"
],
"formula_count": 90,
"formula_fraction": 0.016045640934212874,
"key": "104-54-1"
}
]
},
"strict_random_molecule_split": {
"excluded_records": 3815,
"selection_bias": {
"excluded": {
"formula_size": {
"mean": 6.82961992136304,
"p50": 7.0,
"p90": 10.0
},
"mean_molecule_formula_frequency": {
"mean": 64.84327009513812,
"p50": 64.33333333333333,
"p90": 74.83333333333333
},
"n": 3815,
"objective_target_length": {
"mean": 49.0,
"p50": 49.0,
"p90": 49.0
},
"psychometric_target_mean": {
"mean": 0.23699836942156172,
"p50": 0.2071428597,
"p90": 0.3196428545857143
}
},
"included": {
"formula_size": {
"mean": 3.8779944289693593,
"p50": 3.0,
"p90": 8.0
},
"mean_molecule_formula_frequency": {
"mean": 54.79138457797232,
"p50": 60.833333333333336,
"p90": 73.0
},
"n": 1795,
"objective_target_length": {
"mean": 49.0,
"p50": 49.0,
"p90": 49.0
},
"psychometric_target_mean": {
"mean": 0.2583515881451413,
"p50": 0.24285714327142857,
"p90": 0.35714285714285715
}
}
},
"train_records": 1663,
"validation_records": 132
}
}