diff --git a/.gitattributes b/.gitattributes index a994a3004dd5a01ca82e56f14deb1f7a68fac955..1cddae3d901968f918c46b9d8d32279d686d6fc5 100644 --- a/.gitattributes +++ b/.gitattributes @@ -1,2 +1,27 @@ # No LFS — all files are under 10MB after compression data/proteins.json.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=FremyCompany__BioLORD-2023-C/min=10/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=FremyCompany__BioLORD-2023-C/min=10/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=FremyCompany__BioLORD-2023-C/min=10/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=FremyCompany__BioLORD-2023-C/min=10/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=FremyCompany__BioLORD-2023-C/min=10/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=FremyCompany__BioLORD-2023-C/min=2/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=FremyCompany__BioLORD-2023-C/min=2/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=FremyCompany__BioLORD-2023-C/min=2/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=FremyCompany__BioLORD-2023-C/min=2/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=FremyCompany__BioLORD-2023-C/min=2/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=FremyCompany__BioLORD-2023-C/min=20/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=FremyCompany__BioLORD-2023-C/min=20/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=FremyCompany__BioLORD-2023-C/min=20/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=FremyCompany__BioLORD-2023-C/min=20/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=FremyCompany__BioLORD-2023-C/min=20/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=FremyCompany__BioLORD-2023-C/min=30/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=FremyCompany__BioLORD-2023-C/min=30/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=FremyCompany__BioLORD-2023-C/min=30/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=FremyCompany__BioLORD-2023-C/min=30/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=FremyCompany__BioLORD-2023-C/min=30/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=FremyCompany__BioLORD-2023-C/min=5/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=FremyCompany__BioLORD-2023-C/min=5/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=FremyCompany__BioLORD-2023-C/min=5/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=FremyCompany__BioLORD-2023-C/min=5/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=FremyCompany__BioLORD-2023-C/min=5/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=10/t=0.5_ALL_FIELDS.csv.gz b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=10/t=0.5_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..15c7b4885b5be670b129866d8c3cb4117b1e0fc7 --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=10/t=0.5_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ee3b814d7c90889215dfbef5d52281889cbe3d998dc5c49741fc2568e76dab9 +size 2587827 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=10/t=0.5_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=10/t=0.5_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..03e732f25eae2b810d9fff6e100f1c592d668f75 --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=10/t=0.5_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +organism_source,9834,9642,48,0.7765140533447266,1.5747321686520739,10,0.5 +inducer,11954,11814,36,0.6581193208694458,2.530466168875929,10,0.5 +expression_strain,8268,8176,21,0.4582940340042114,2.1158893373846537,10,0.5 +induction_temperature,5383,5342,14,0.43967002630233765,2.3791541015039877,10,0.5 +molecular_weight,495,456,6,0.34547069668769836,2.521824016467861,10,0.5 +lysis_buffer,5625,5509,42,0.05651351436972618,2.8663515457470163,10,0.5 +strain,3834,3715,31,0.05506212264299393,2.3717661791335503,10,0.5 +plasmid,8217,7642,172,0.03281834349036217,3.2982860061040813,10,0.5 +desalting_process,5540,5417,49,0.007013031281530857,3.030018954520278,10,0.5 +elution_buffer,5198,5036,70,-0.0006159988115541637,2.9760541403331784,10,0.5 +enzyme_name,12099,10293,403,-0.02263818494975567,3.4304557119786807,10,0.5 +medium_name,7644,7372,97,-0.04714787006378174,2.921985096772683,10,0.5 +source_key,12179,12179,1,,,10,0.5 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=10/t=0.6_ALL_FIELDS.csv.gz b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=10/t=0.6_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..5e0aaab67cce08a49c96700b72ecbda9c3db6363 --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=10/t=0.6_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1adde518454c2fe2ef35bab4b6c48c0bfb85488ba6eb3b0cc8cabac98ae45822 +size 2608055 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=10/t=0.6_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=10/t=0.6_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..7f339ef4b61a60f114f32dd8d880151bf110f036 --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=10/t=0.6_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +organism_source,9834,9433,52,0.8979952335357666,1.0901213506578726,10,0.6 +inducer,11954,11654,41,0.6156179308891296,2.678820303929045,10,0.6 +strain,3834,3477,30,0.5607370734214783,1.727890472599539,10,0.6 +molecular_weight,495,422,8,0.3856523334980011,2.204297432722646,10,0.6 +expression_strain,8268,8071,19,0.37494349479675293,1.5459352700427262,10,0.6 +induction_temperature,5383,5290,22,0.35219806432724,2.271784356311968,10,0.6 +plasmid,8217,6434,189,0.10814328491687775,2.8739892151935074,10,0.6 +enzyme_name,12099,7190,336,0.08393432945013046,2.7798237100005334,10,0.6 +medium_name,7644,6910,137,0.028949037194252014,2.853677602510012,10,0.6 +elution_buffer,5198,4707,106,0.011004805564880371,3.1113337278389133,10,0.6 +desalting_process,5540,5117,99,-0.004972841590642929,3.0775416809185767,10,0.6 +lysis_buffer,5625,5302,82,-0.03125309571623802,3.120772380598368,10,0.6 +source_key,12179,12179,1,,,10,0.6 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=10/t=0.7_ALL_FIELDS.csv.gz b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=10/t=0.7_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..4e07f5e6cca75d1653eb3b1d6a1af2a90713ba29 --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=10/t=0.7_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da90b64e49efb0f028c57b56679c4aed2eed1e058110670b3650c65853cdc66f +size 2556220 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=10/t=0.7_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=10/t=0.7_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..96411a7f78081dbc9828bb52e51f8f067e2193b1 --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=10/t=0.7_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +organism_source,9834,9281,51,0.9683900475502014,0.6517750846434909,10,0.7 +inducer,11954,11372,79,0.6167182922363281,2.5555095509229697,10,0.7 +source_key,12179,12172,3,0.6135690212249756,2.046940167239852,10,0.7 +strain,3834,3245,30,0.5277649164199829,1.325506307658839,10,0.7 +molecular_weight,495,358,8,0.49426698684692383,1.525941860517166,10,0.7 +expression_strain,8268,7953,36,0.3656609058380127,1.6824194036186213,10,0.7 +enzyme_name,12099,3766,194,0.31079819798469543,1.9052178338661754,10,0.7 +plasmid,8217,4820,131,0.21695227921009064,2.281671692974959,10,0.7 +induction_temperature,5383,5206,28,0.09935244172811508,1.9744257503717546,10,0.7 +medium_name,7644,5859,155,0.08067498356103897,2.528201966329758,10,0.7 +elution_buffer,5198,3989,140,0.058527737855911255,2.7644169849406364,10,0.7 +desalting_process,5540,4216,129,0.047316767275333405,2.8377312908314116,10,0.7 +lysis_buffer,5625,4744,132,-0.009378312155604362,2.7858222459276933,10,0.7 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=10/t=0.8_ALL_FIELDS.csv.gz b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=10/t=0.8_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..e43d2036770433eab47c4a31e097ed67950c2985 --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=10/t=0.8_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3904fe318eb04dfb60cb1ca57a3c78df8943c42499d210625d86b86cf79b89f1 +size 2433132 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=10/t=0.8_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=10/t=0.8_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..dee3df3130bda9eac89811dd98e2b48f79be4b83 --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=10/t=0.8_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +organism_source,9834,9071,50,0.9914687871932983,0.41983126160938666,10,0.8 +enzyme_name,12099,1604,82,0.6754606366157532,0.9029404768573337,10,0.8 +inducer,11954,10898,105,0.6387306451797485,2.025749330702004,10,0.8 +strain,3834,2951,32,0.47749897837638855,1.5464271444610542,10,0.8 +induction_temperature,5383,5020,31,0.39835259318351746,0.9913395039870158,10,0.8 +plasmid,8217,3215,93,0.34678468108177185,1.3771712660901856,10,0.8 +expression_strain,8268,7646,67,0.3369881808757782,1.76733071151102,10,0.8 +medium_name,7644,4011,136,0.30073943734169006,1.9066833731755348,10,0.8 +desalting_process,5540,2332,101,0.23947493731975555,2.1453684836426703,10,0.8 +elution_buffer,5198,2380,93,0.20412717759609222,2.0653235686660047,10,0.8 +molecular_weight,495,290,10,0.19174939393997192,1.9530966080176069,10,0.8 +source_key,12179,12140,26,0.14823652803897858,1.892632846537525,10,0.8 +lysis_buffer,5625,3125,120,0.09951784461736679,2.354160458412296,10,0.8 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=10/t=0.9_ALL_FIELDS.csv.gz b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=10/t=0.9_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..2fec8478d57b5d7602745ee6cacea7678ffa7e42 --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=10/t=0.9_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8c9d851a8e6b5ba62b9441bbc7134aeed4d93848ab6e5a8aa4024e828e7e763 +size 2341362 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=10/t=0.9_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=10/t=0.9_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..3acd1418228746e696d419fb213f748919fdd926 --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=10/t=0.9_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +organism_source,9834,8949,45,0.9984818696975708,0.20685364644427437,10,0.9 +strain,3834,2526,31,0.8235690593719482,0.7268177590331438,10,0.9 +induction_temperature,5383,4850,40,0.8091336488723755,0.5691038536757478,10,0.9 +desalting_process,5540,725,44,0.7864996790885925,0.7578852453910375,10,0.9 +inducer,11954,9679,119,0.7654550075531006,1.3944678813630587,10,0.9 +enzyme_name,12099,954,51,0.7572941780090332,0.6774228761784749,10,0.9 +medium_name,7644,2228,79,0.6482684016227722,0.9213915563651608,10,0.9 +plasmid,8217,2356,70,0.5839025378227234,0.7339878888011947,10,0.9 +lysis_buffer,5625,1033,59,0.581455409526825,0.9976054257159656,10,0.9 +expression_strain,8268,6865,81,0.5287676453590393,1.1652149057959604,10,0.9 +elution_buffer,5198,979,48,0.49888429045677185,1.2056493164814155,10,0.9 +molecular_weight,495,142,7,0.49686673283576965,1.2270091453013734,10,0.9 +source_key,12179,11760,145,-0.08388904482126236,2.417190174879529,10,0.9 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=2/t=0.5_ALL_FIELDS.csv.gz b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=2/t=0.5_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..431836bc2a8681e5b94171b80aa7e64183e1bb60 --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=2/t=0.5_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94dba4d448a59c772ceae94961c6397bc5184e0ad8ada4afcc71be83a1378663 +size 2640652 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=2/t=0.5_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=2/t=0.5_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..5c0970b3d8f93d1bb4e2418043559489c39127d4 --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=2/t=0.5_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +organism_source,9834,9806,116,0.7547335028648376,1.2202321139472418,2,0.5 +inducer,11954,11932,131,0.6263397932052612,1.5439647047700402,2,0.5 +expression_strain,8268,8255,86,0.4362073540687561,1.4435742670199958,2,0.5 +induction_temperature,5383,5381,41,0.41616952419281006,1.5655287936749562,2,0.5 +molecular_weight,495,490,29,0.1871105581521988,1.743021696172884,2,0.5 +strain,3834,3818,98,0.032661549746990204,1.6066869986291785,2,0.5 +lysis_buffer,5625,5608,140,0.013566150330007076,1.712128982539119,2,0.5 +plasmid,8217,8111,614,0.0016350895166397095,2.1021310583097237,2,0.5 +desalting_process,5540,5513,154,-0.031675711274147034,1.9066130898927625,2,0.5 +elution_buffer,5198,5175,212,-0.034511733800172806,1.8734981599416645,2,0.5 +enzyme_name,12099,11794,1532,-0.09131741523742676,2.2261883859641456,2,0.5 +medium_name,7644,7616,303,-0.09556292742490768,1.8632154187931589,2,0.5 +source_key,12179,12179,1,,,2,0.5 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=2/t=0.6_ALL_FIELDS.csv.gz b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=2/t=0.6_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..7dfa911f3e4be2d52c6d121f51e5b0409d25c7ec --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=2/t=0.6_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17267e418ab42fe51f89329000100ccf8d455b0326212efa4344be029f99d98c +size 2709827 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=2/t=0.6_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=2/t=0.6_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..76d17b1f9eb1319669cfd7d919ce7ad58a3566ed --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=2/t=0.6_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +organism_source,9834,9776,153,0.8844254016876221,0.9074780810009092,2,0.6 +inducer,11954,11900,156,0.5753810405731201,1.6349126311501625,2,0.6 +strain,3834,3777,147,0.4990290105342865,1.2603709571449646,2,0.6 +expression_strain,8268,8228,75,0.3469177782535553,1.1532438866299595,2,0.6 +induction_temperature,5383,5369,74,0.29357147216796875,1.4919104065769888,2,0.6 +molecular_weight,495,471,41,0.27599257230758667,1.546617792246692,2,0.6 +plasmid,8217,7775,888,0.08532395213842392,1.824345281646912,2,0.6 +enzyme_name,12099,10946,2036,0.04147512465715408,1.8115956982872512,2,0.6 +medium_name,7644,7514,502,0.029682043939828873,1.69565830428857,2,0.6 +elution_buffer,5198,5098,389,-0.003340788884088397,1.8537553212644535,2,0.6 +desalting_process,5540,5431,343,-0.01883251965045929,1.8555373922428384,2,0.6 +lysis_buffer,5625,5558,276,-0.044410210102796555,1.788842418360815,2,0.6 +source_key,12179,12179,1,,,2,0.6 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=2/t=0.7_ALL_FIELDS.csv.gz b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=2/t=0.7_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..b9410816cb2e295ef0c8ce78fce8abc29caf3c1c --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=2/t=0.7_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5d8d27cae79b01363dc0f502a47cff13ef6455750a46c846755633b02c53121 +size 2713524 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=2/t=0.7_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=2/t=0.7_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..abdb7ac9bdec0134c0adc9877240e7327e896301 --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=2/t=0.7_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +organism_source,9834,9748,181,0.9552238583564758,0.6261834206017272,2,0.7 +inducer,11954,11836,303,0.5885407328605652,1.46058715448931,2,0.7 +source_key,12179,12179,11,0.5360902547836304,1.2509504078899925,2,0.7 +strain,3834,3707,177,0.5185054540634155,0.990463078977701,2,0.7 +enzyme_name,12099,9204,2082,0.3158281147480011,1.3087931744049992,2,0.7 +expression_strain,8268,8191,134,0.2941238582134247,1.1539385222849505,2,0.7 +molecular_weight,495,449,44,0.2928175926208496,1.3682279173249123,2,0.7 +plasmid,8217,7091,1021,0.24638956785202026,1.3875027840245882,2,0.7 +medium_name,7644,7223,754,0.12622447311878204,1.4769623256419733,2,0.7 +desalting_process,5540,5168,597,0.09388542920351028,1.6211736968913855,2,0.7 +induction_temperature,5383,5345,87,0.08383338898420334,1.3622751597519114,2,0.7 +elution_buffer,5198,4850,558,0.08209343999624252,1.6799924075285437,2,0.7 +lysis_buffer,5625,5432,529,0.020793037489056587,1.627433154049928,2,0.7 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=2/t=0.8_ALL_FIELDS.csv.gz b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=2/t=0.8_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..e92ea5e7213d7ed2940e44248f12fd2bc76e751f --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=2/t=0.8_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c59536c9d3f160e31e8d6c6fe10c62d27dd533a6391e7e1686600d1081f3e197 +size 2647875 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=2/t=0.8_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=2/t=0.8_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..2b03395a11459d9f85db8248bcfe0f914af667f1 --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=2/t=0.8_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +organism_source,9834,9703,233,0.9831283092498779,0.4376599191708481,2,0.8 +enzyme_name,12099,7091,1964,0.6284089684486389,0.7837812147541556,2,0.8 +inducer,11954,11677,453,0.618333637714386,1.1583612552187004,2,0.8 +strain,3834,3580,238,0.5102024674415588,0.7971185660548089,2,0.8 +plasmid,8217,6179,1132,0.44961780309677124,0.8963540408034021,2,0.8 +medium_name,7644,6507,1003,0.4282604157924652,1.0227711249238087,2,0.8 +induction_temperature,5383,5296,120,0.4028104245662689,0.8957585427113448,2,0.8 +desalting_process,5540,4479,887,0.40119460225105286,1.1491137259520512,2,0.8 +elution_buffer,5198,4208,757,0.36757224798202515,1.093071450002556,2,0.8 +expression_strain,8268,8101,244,0.32445281744003296,1.1357426539080262,2,0.8 +lysis_buffer,5625,4975,821,0.2619685232639313,1.2402730450654837,2,0.8 +molecular_weight,495,419,61,0.194259375333786,1.1695085729876322,2,0.8 +source_key,12179,12173,58,0.13860011100769043,1.2687162185701555,2,0.8 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=2/t=0.9_ALL_FIELDS.csv.gz b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=2/t=0.9_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..1499cc01179eea06dc30ecfd1f6fc4853b511d0b --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=2/t=0.9_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:067bb17ef75f504e157634b8ca965ea414cfee653a9dbc36b4c4f5976981d3e2 +size 2551818 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=2/t=0.9_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=2/t=0.9_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..c02a518217a485df2e9517a5462310d36f508741 --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=2/t=0.9_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +organism_source,9834,9646,252,0.9975390434265137,0.20390942617497387,2,0.9 +desalting_process,5540,3549,1018,0.858129620552063,0.4978171061343614,2,0.9 +enzyme_name,12099,5086,1586,0.8345175981521606,0.43901337813561947,2,0.9 +strain,3834,3406,316,0.7817206382751465,0.5231726062779101,2,0.9 +lysis_buffer,5625,4141,1088,0.7789440155029297,0.5690003368918467,2,0.9 +induction_temperature,5383,5218,157,0.7767700552940369,0.40951037259926876,2,0.9 +medium_name,7644,5750,1213,0.7662512063980103,0.5134320399863648,2,0.9 +elution_buffer,5198,3509,899,0.7538833022117615,0.5445688470906149,2,0.9 +inducer,11954,11350,670,0.7462525963783264,0.8048286385221498,2,0.9 +plasmid,8217,5244,1088,0.718254566192627,0.4606868047797628,2,0.9 +expression_strain,8268,7899,396,0.5167157649993896,0.7779045640393959,2,0.9 +molecular_weight,495,353,86,0.48546266555786133,0.8371110902239867,2,0.9 +source_key,12179,12159,374,-0.15545551478862762,1.581865148458629,2,0.9 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=20/t=0.5_ALL_FIELDS.csv.gz b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=20/t=0.5_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..7d1b3b991946659eadd9528da0a6cc65c7368ec6 --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=20/t=0.5_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:731f972f13654b0d912ba68dbab507aabbdca34fb624499ee473f0fe05e394c3 +size 2534352 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=20/t=0.5_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=20/t=0.5_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..2f82fb849e64b0c2b6b8b8677acfacfd180cb47f --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=20/t=0.5_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +organism_source,9834,9492,30,0.7889127731323242,1.5250458212779088,20,0.5 +inducer,11954,11662,18,0.6712803840637207,2.87305533057862,20,0.5 +expression_strain,8268,8126,13,0.49044695496559143,1.8278349462311616,20,0.5 +molecular_weight,495,425,3,0.4596268832683563,1.5937490471706692,20,0.5 +induction_temperature,5383,5318,10,0.4548056721687317,2.109383652205483,20,0.5 +lysis_buffer,5625,5443,24,0.06692598760128021,3.4820209609078603,20,0.5 +strain,3834,3594,16,0.054695259779691696,2.79364017208802,20,0.5 +plasmid,8217,7255,94,0.04708298668265343,3.715356245978913,20,0.5 +desalting_process,5540,5312,25,0.019115395843982697,3.568038841371032,20,0.5 +elution_buffer,5198,4931,40,0.009398192167282104,3.669247398660044,20,0.5 +enzyme_name,12099,9248,208,-0.004382822662591934,3.8676341938746535,20,0.5 +medium_name,7644,7164,55,-0.04003603011369705,3.4401193647769746,20,0.5 +source_key,12179,12179,1,,,20,0.5 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=20/t=0.6_ALL_FIELDS.csv.gz b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=20/t=0.6_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..fcb273414d47836b761ccaa361713ba3294f8282 --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=20/t=0.6_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b912545a87ad9871bc7a3eb41ee0d8637210a8d96e06f3c2004c0a28e3137e3 +size 2546357 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=20/t=0.6_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=20/t=0.6_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..4523f8703f40db1f5f2296f6344c53121e90f2c6 --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=20/t=0.6_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +organism_source,9834,9178,30,0.9069605469703674,1.041994417963008,20,0.6 +inducer,11954,11571,26,0.6265498995780945,3.0906077848503464,20,0.6 +strain,3834,3306,13,0.6033597588539124,1.6268576870973597,20,0.6 +molecular_weight,495,390,4,0.4269387722015381,2.011100252173644,20,0.6 +induction_temperature,5383,5271,14,0.42000871896743774,2.4162388154836614,20,0.6 +expression_strain,8268,7990,11,0.40175870060920715,1.5068608594541877,20,0.6 +plasmid,8217,5837,92,0.11727797985076904,3.313946305018964,20,0.6 +enzyme_name,12099,5418,136,0.11442404240369797,3.0222110517649554,20,0.6 +medium_name,7644,6603,81,0.04299279302358627,3.296515062983775,20,0.6 +elution_buffer,5198,4500,60,0.028239304199814796,3.6226016089792186,20,0.6 +desalting_process,5540,4904,59,0.0030894442461431026,3.6098523534351274,20,0.6 +lysis_buffer,5625,5161,48,-0.02521170862019062,3.680194614408807,20,0.6 +source_key,12179,12179,1,,,20,0.6 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=20/t=0.7_ALL_FIELDS.csv.gz b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=20/t=0.7_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..e90965a260d09e9806ea7d370f27c06531d6f3dc --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=20/t=0.7_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:668394ab63533edaf43e3fd3dc048eeb8ec6f107755ee891926d9368440cd44c +size 2485462 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=20/t=0.7_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=20/t=0.7_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..1518ef6f9e0911921593378bb3e23bee7c42b177 --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=20/t=0.7_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +organism_source,9834,8968,27,0.9744349122047424,0.615737133200891,20,0.7 +inducer,11954,11209,46,0.6334101557731628,2.9195874735800973,20,0.7 +source_key,12179,12168,2,0.6221014261245728,1.2512290670280308,20,0.7 +molecular_weight,495,309,3,0.5451867580413818,1.267473306057637,20,0.7 +strain,3834,3083,16,0.5295166373252869,1.3770483862437315,20,0.7 +expression_strain,8268,7874,24,0.3857584297657013,1.7218280559832368,20,0.7 +enzyme_name,12099,2207,59,0.37887266278266907,1.7689349024536167,20,0.7 +plasmid,8217,4032,54,0.23199774324893951,2.544045522194478,20,0.7 +induction_temperature,5383,5133,16,0.11580777168273926,1.9953870592380163,20,0.7 +medium_name,7644,5199,70,0.08649027347564697,3.044423678519878,20,0.7 +elution_buffer,5198,3532,72,0.07186680287122726,3.11460131546768,20,0.7 +desalting_process,5540,3818,66,0.04619968682527542,3.350811665282105,20,0.7 +lysis_buffer,5625,4407,71,-0.0004941329243592918,3.2282886987899846,20,0.7 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=20/t=0.8_ALL_FIELDS.csv.gz b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=20/t=0.8_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..e97183d45e54c0e5a3a512406bdf5e5d89688a02 --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=20/t=0.8_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d71080376532bd3483fd9ec537b00c3282fa71cc2fc632999b0a756774794335 +size 2378556 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=20/t=0.8_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=20/t=0.8_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..b3c01032ea5f5e61a79c4411cbe78fc93d434555 --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=20/t=0.8_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +organism_source,9834,8716,23,0.9953827261924744,0.3254856764345753,20,0.8 +enzyme_name,12099,845,20,0.6944360733032227,0.8236984576760211,20,0.8 +inducer,11954,10544,57,0.6602927446365356,2.169022898901197,20,0.8 +strain,3834,2779,18,0.47263363003730774,1.8382398334582932,20,0.8 +induction_temperature,5383,4934,22,0.3981456160545349,1.0467581422383911,20,0.8 +expression_strain,8268,7427,43,0.35260316729545593,1.9141816746896751,20,0.8 +plasmid,8217,2565,37,0.30124154686927795,1.5905557591383543,20,0.8 +medium_name,7644,3271,59,0.29355311393737793,2.1655869021337617,20,0.8 +source_key,12179,12116,15,0.22103463113307953,2.334396979801379,20,0.8 +desalting_process,5540,1720,40,0.19993183016777039,2.6032327128404837,20,0.8 +elution_buffer,5198,1928,42,0.19566820561885834,2.3594777668149467,20,0.8 +molecular_weight,495,221,4,0.12183423340320587,2.8158804631617844,20,0.8 +lysis_buffer,5625,2570,59,0.07874302566051483,2.774642799544585,20,0.8 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=20/t=0.9_ALL_FIELDS.csv.gz b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=20/t=0.9_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..694ae7a501cec18ad1ec0330febf49b8fafea5f8 --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=20/t=0.9_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a659f1fabde8d26aa677c7d6d7b7996a508e4103984ff387c0169af784bdeae +size 2307769 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=20/t=0.9_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=20/t=0.9_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..1eeaf15e716967af176c98c2e81e8936fa5f5267 --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=20/t=0.9_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +organism_source,9834,8655,22,0.9988635778427124,0.20515843388582355,20,0.9 +strain,3834,2300,15,0.8325965404510498,0.7609182251621202,20,0.9 +desalting_process,5540,252,6,0.8255943059921265,0.8132881050760536,20,0.9 +induction_temperature,5383,4627,23,0.8220037817955017,0.44058122144355083,20,0.9 +inducer,11954,8979,53,0.7920964360237122,1.6379036642587397,20,0.9 +enzyme_name,12099,476,14,0.7093339562416077,0.8356267224207422,20,0.9 +medium_name,7644,1607,28,0.6533850431442261,1.0188739857498965,20,0.9 +expression_strain,8268,6467,47,0.5458638668060303,1.1793508857309924,20,0.9 +plasmid,8217,1837,27,0.5381083488464355,0.958970686964255,20,0.9 +molecular_weight,495,88,3,0.5228518843650818,1.245897502138617,20,0.9 +elution_buffer,5198,541,13,0.4513922929763794,1.5020923405212265,20,0.9 +lysis_buffer,5625,541,17,0.44705310463905334,1.490784173443591,20,0.9 +source_key,12179,11477,85,-0.049831729382276535,2.895323598830845,20,0.9 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=30/t=0.5_ALL_FIELDS.csv.gz b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=30/t=0.5_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..fab897ecf6583a2e3b942280ca144860a11948c0 --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=30/t=0.5_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c85200cd07b2f171cb905334e0cc69eeada3b34f1c2483adac11e74c8a0d194 +size 2506420 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=30/t=0.5_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=30/t=0.5_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..1019c863343035895a9b9e9edc475603b25a1335 --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=30/t=0.5_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +organism_source,9834,9327,20,0.8120043277740479,1.4400911497665614,30,0.5 +inducer,11954,11611,13,0.6745449304580688,2.7905535944979407,30,0.5 +expression_strain,8268,8078,9,0.5252421498298645,1.990156674818517,30,0.5 +molecular_weight,495,408,2,0.4993584156036377,1.3397671544231975,30,0.5 +induction_temperature,5383,5289,8,0.45292961597442627,2.3142231263470374,30,0.5 +lysis_buffer,5625,5375,16,0.07503698766231537,3.4606016255480867,30,0.5 +strain,3834,3531,12,0.052027080208063126,3.224344293221287,30,0.5 +plasmid,8217,6980,63,0.0498511902987957,3.901574282282354,30,0.5 +elution_buffer,5198,4869,28,0.022536758333444595,3.881841420148971,30,0.5 +desalting_process,5540,5251,19,0.022163448855280876,3.776475796223045,30,0.5 +enzyme_name,12099,8599,137,0.01082632876932621,4.014623011587257,30,0.5 +medium_name,7644,7102,42,-0.031244339421391487,3.6978495077164864,30,0.5 +source_key,12179,12179,1,,,30,0.5 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=30/t=0.6_ALL_FIELDS.csv.gz b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=30/t=0.6_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..b409c65755b2fcf3f9245e6f79dc00f898217b7a --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=30/t=0.6_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abeb6c3afa4ba861c34521245cae86d6cd22f34ea3dbbbaf602e8197368c478d +size 2505594 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=30/t=0.6_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=30/t=0.6_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..0b7d804da44be99e318f9a60dc10452bc0e52187 --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=30/t=0.6_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +organism_source,9834,9041,24,0.9112853407859802,1.0248965542690125,30,0.6 +inducer,11954,11487,20,0.6335229277610779,3.243045897234824,30,0.6 +strain,3834,3234,9,0.6266874074935913,1.4091180072711011,30,0.6 +molecular_weight,495,368,3,0.4486555755138397,1.6919716208360691,30,0.6 +induction_temperature,5383,5262,12,0.4224992096424103,2.1752412092348403,30,0.6 +expression_strain,8268,7942,8,0.4210352301597595,1.6830771723883675,30,0.6 +enzyme_name,12099,4522,79,0.1413145512342453,2.897975344223477,30,0.6 +plasmid,8217,5460,59,0.1326572597026825,3.4620045788257685,30,0.6 +medium_name,7644,6318,53,0.041093286126852036,3.558048937918787,30,0.6 +elution_buffer,5198,4358,43,0.027591021731495857,3.918902817961171,30,0.6 +desalting_process,5540,4768,41,0.009471197612583637,3.844528745721234,30,0.6 +lysis_buffer,5625,5076,37,-0.024496423080563545,4.094141145269903,30,0.6 +source_key,12179,12179,1,,,30,0.6 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=30/t=0.7_ALL_FIELDS.csv.gz b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=30/t=0.7_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..1d307bc1d7e70de8ef75a18264059e6137445e49 --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=30/t=0.7_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b862296da3322626691e63667295678566227c230c1c1a7645d6e2c22a196d96 +size 2443564 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=30/t=0.7_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=30/t=0.7_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..b637b554d6d8fcece3665b3814a5488d9e33af0c --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=30/t=0.7_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +organism_source,9834,8822,21,0.9771578311920166,0.5989483895153623,30,0.7 +molecular_weight,495,288,2,0.6803316473960876,0.9909354850032519,30,0.7 +inducer,11954,11044,32,0.6466913819313049,3.1135151199136963,30,0.7 +strain,3834,2959,10,0.5411802530288696,1.458244752246428,30,0.7 +enzyme_name,12099,1501,27,0.42779210209846497,1.6648230929467034,30,0.7 +expression_strain,8268,7763,17,0.395648330450058,1.9227809282039119,30,0.7 +plasmid,8217,3717,38,0.2546250820159912,2.4237515788494295,30,0.7 +induction_temperature,5383,5059,11,0.11674018949270248,1.5630218783490135,30,0.7 +medium_name,7644,4969,51,0.10198616981506348,3.0757314251037697,30,0.7 +elution_buffer,5198,3241,47,0.06167495995759964,3.395165594034296,30,0.7 +desalting_process,5540,3597,46,0.05480233207345009,3.6043793488420333,30,0.7 +lysis_buffer,5625,4180,45,0.014044519513845444,3.382796541873396,30,0.7 +source_key,12179,12148,1,,,30,0.7 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=30/t=0.8_ALL_FIELDS.csv.gz b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=30/t=0.8_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..d35036604278bd83b2c13335885099b8a031d5fe --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=30/t=0.8_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f077b4887f8374149142ab5e0b89c0043d1c1c880321794bda78ba8bfc4fb755 +size 2348792 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=30/t=0.8_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=30/t=0.8_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..eb5c24090e116dbc686902144e4209e9535bbf03 --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=30/t=0.8_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +organism_source,9834,8564,17,0.9966156482696533,0.28050665539709096,30,0.8 +inducer,11954,10413,38,0.6744100451469421,2.23585783235728,30,0.8 +enzyme_name,12099,578,9,0.6728971004486084,0.9080229173661445,30,0.8 +strain,3834,2702,13,0.4716242849826813,2.1094041222952113,30,0.8 +induction_temperature,5383,4787,15,0.4267418086528778,1.0550949828695475,30,0.8 +expression_strain,8268,7292,29,0.3808435797691345,1.9981555419784598,30,0.8 +medium_name,7644,2822,35,0.30842557549476624,2.1571026577661323,30,0.8 +plasmid,8217,2183,19,0.29571855068206787,1.8276449154833019,30,0.8 +source_key,12179,12102,10,0.2496994584798813,2.667805823271374,30,0.8 +elution_buffer,5198,1679,25,0.2275628000497818,2.19327674073951,30,0.8 +desalting_process,5540,1489,25,0.19879592955112457,2.729787315145492,30,0.8 +molecular_weight,495,220,3,0.14756034314632416,2.4264924303377566,30,0.8 +lysis_buffer,5625,2199,36,0.09101138263940811,2.9658582620880574,30,0.8 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=30/t=0.9_ALL_FIELDS.csv.gz b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=30/t=0.9_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..da94eed52854ce3c112c28702faa67cf816c5ba5 --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=30/t=0.9_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f64ec726defd2607d70a00fe265db8429ec8702a4c7f3db68a0e0f827d4306d1 +size 2295682 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=30/t=0.9_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=30/t=0.9_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..95d7010f4b2c48cafb0c3bf25bd12a22a03f3201 --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=30/t=0.9_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +organism_source,9834,8523,17,0.9999327659606934,0.008191005395515497,30,0.9 +desalting_process,5540,188,3,0.9653656482696533,0.33384266683909064,30,0.9 +strain,3834,2185,10,0.8305476307868958,0.8689420042637156,30,0.9 +induction_temperature,5383,4528,19,0.8199568390846252,0.4480763649355022,30,0.9 +inducer,11954,8584,33,0.8103165030479431,1.7035409143934692,30,0.9 +medium_name,7644,1336,16,0.6678114533424377,1.1219532706464097,30,0.9 +enzyme_name,12099,273,5,0.6544041633605957,1.0307831311337918,30,0.9 +elution_buffer,5198,471,9,0.57146155834198,1.1247039568563575,30,0.9 +expression_strain,8268,6272,36,0.5364038348197937,1.1434838944292562,30,0.9 +plasmid,8217,1577,16,0.5069786906242371,1.0543037841129406,30,0.9 +lysis_buffer,5625,390,9,0.49238765239715576,1.3313618922766586,30,0.9 +source_key,12179,11288,62,-0.028486600145697594,3.0477768577776603,30,0.9 +molecular_weight,495,35,1,,,30,0.9 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=5/t=0.5_ALL_FIELDS.csv.gz b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=5/t=0.5_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..5a97bc4dc18554f4a474a6c0bde56a6aabaa4820 --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=5/t=0.5_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a7af9d2eae03f266b8459930c126a05dd6143000dd03c98c38817199d7b91f9 +size 2619274 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=5/t=0.5_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=5/t=0.5_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..a2350e71a29eae44f0f2f0c15354fcdd4bf3a286 --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=5/t=0.5_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +organism_source,9834,9714,64,0.7690231204032898,1.4713049601700523,5,0.5 +inducer,11954,11884,66,0.6468091607093811,2.1456803680284575,5,0.5 +expression_strain,8268,8216,42,0.44276949763298035,1.8873996728703988,5,0.5 +induction_temperature,5383,5371,23,0.4342193901538849,2.1233659297663987,5,0.5 +molecular_weight,495,475,12,0.24714034795761108,2.539616417646546,5,0.5 +lysis_buffer,5625,5548,68,0.04329437017440796,2.427256057395215,5,0.5 +strain,3834,3758,51,0.03997762128710747,2.1192580143440227,5,0.5 +plasmid,8217,7870,304,0.026504581794142723,2.806879185986867,5,0.5 +desalting_process,5540,5451,76,-0.006838426925241947,2.635662879539973,5,0.5 +elution_buffer,5198,5116,118,-0.023992525413632393,2.509014961811464,5,0.5 +enzyme_name,12099,11063,737,-0.04618585854768753,2.946291148521033,5,0.5 +medium_name,7644,7524,171,-0.07619944214820862,2.420477499626408,5,0.5 +source_key,12179,12179,1,,,5,0.5 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=5/t=0.6_ALL_FIELDS.csv.gz b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=5/t=0.6_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..076d9685fbbb136d00f92612107593f7b0dcc0e8 --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=5/t=0.6_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0efb8f0694cdd71d89700ddb911578c4b3d28b954755064a0669af6c5d83597 +size 2662509 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=5/t=0.6_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=5/t=0.6_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..771d522c21cbf7da1d6239ca9caceee29ca52741 --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=5/t=0.6_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +organism_source,9834,9613,86,0.8886528611183167,1.0397491865103299,5,0.6 +inducer,11954,11796,74,0.5954770445823669,2.265906849328155,5,0.6 +strain,3834,3609,59,0.5285530090332031,1.5639356416696464,5,0.6 +expression_strain,8268,8152,35,0.3571571409702301,1.5149125975315845,5,0.6 +induction_temperature,5383,5320,37,0.33208751678466797,2.077684778904627,5,0.6 +molecular_weight,495,447,16,0.3244754672050476,2.0907506598749164,5,0.6 +plasmid,8217,7010,368,0.0955176129937172,2.469993541057654,5,0.6 +enzyme_name,12099,8966,784,0.0629134252667427,2.3865343813229702,5,0.6 +medium_name,7644,7233,259,0.023673877120018005,2.290769402607449,5,0.6 +elution_buffer,5198,4897,190,0.004984298255294561,2.542118074361617,5,0.6 +desalting_process,5540,5277,172,-0.013476425781846046,2.5794663213012012,5,0.6 +lysis_buffer,5625,5444,142,-0.041982147842645645,2.4772372750975133,5,0.6 +source_key,12179,12179,1,,,5,0.6 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=5/t=0.7_ALL_FIELDS.csv.gz b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=5/t=0.7_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..183a5f447d52ad545c322198f8ac60de0e112bf7 --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=5/t=0.7_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ba3bea163da9e00352bcb275c18c070b9517a1fefd487e31a9d961640ba1a95 +size 2627953 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=5/t=0.7_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=5/t=0.7_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..59a94ce9d8d80cad957759217e1bbd3086996d37 --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=5/t=0.7_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +organism_source,9834,9514,90,0.9628497958183289,0.6517809451127703,5,0.7 +inducer,11954,11605,145,0.6002359986305237,2.036236632824037,5,0.7 +source_key,12179,12173,6,0.5722149014472961,1.6461216033230384,5,0.7 +strain,3834,3436,63,0.5186837911605835,1.2528487096635497,5,0.7 +molecular_weight,495,393,15,0.35776329040527344,1.6700243536927124,5,0.7 +expression_strain,8268,8031,55,0.35323214530944824,1.6675101410192572,5,0.7 +enzyme_name,12099,5786,560,0.2886166274547577,1.746138146342485,5,0.7 +plasmid,8217,5615,307,0.21233218908309937,1.9814379900976458,5,0.7 +medium_name,7644,6435,312,0.08775883913040161,2.051075307313465,5,0.7 +induction_temperature,5383,5272,45,0.07968305051326752,1.7968711007413134,5,0.7 +elution_buffer,5198,4353,245,0.0637722760438919,2.343889966165847,5,0.7 +desalting_process,5540,4667,265,0.05537885054945946,2.2981153507855523,5,0.7 +lysis_buffer,5625,5028,243,-0.012461263686418533,2.263659762679935,5,0.7 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=5/t=0.8_ALL_FIELDS.csv.gz b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=5/t=0.8_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..9b036bef2fd5cfaf1482b0d94c9f015233b1a488 --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=5/t=0.8_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d47ba9d1d95419edfc14b6f2870a90755620d62a88a767a4b3b0625ed82a8de6 +size 2510219 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=5/t=0.8_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=5/t=0.8_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..778dbb12e17bc247dd0c445dd1a6ce23dd52aab4 --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=5/t=0.8_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +organism_source,9834,9352,96,0.9877485036849976,0.43791086219194675,5,0.8 +inducer,11954,11224,194,0.6279517412185669,1.685125943685053,5,0.8 +enzyme_name,12099,3106,329,0.604074239730835,0.9563671827492497,5,0.8 +strain,3834,3150,64,0.4955669045448303,1.151319242339573,5,0.8 +induction_temperature,5383,5134,51,0.3956093490123749,1.0553531949984065,5,0.8 +plasmid,8217,4091,250,0.3492598533630371,1.2320378812370067,5,0.8 +medium_name,7644,4957,325,0.34014028310775757,1.5104023384616176,5,0.8 +expression_strain,8268,7842,114,0.3157655894756317,1.5665787507226419,5,0.8 +desalting_process,5540,3105,258,0.29069796204566956,1.6906040450901156,5,0.8 +elution_buffer,5198,3052,230,0.26347267627716064,1.613554739654935,5,0.8 +lysis_buffer,5625,3898,291,0.16001982986927032,1.8240026233482876,5,0.8 +molecular_weight,495,336,20,0.1515883207321167,1.8732835172978384,5,0.8 +source_key,12179,12152,36,0.14387103915214539,1.688911789532797,5,0.8 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=5/t=0.9_ALL_FIELDS.csv.gz b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=5/t=0.9_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..8f96d56661434ab8e4743e75a2ea75f59e7d7b6d --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=5/t=0.9_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45b7142b1435590c3b367cd2fc57039154d12a86bbe64976194cc17b7d0f62c0 +size 2396827 diff --git a/data/clustering/model=FremyCompany__BioLORD-2023-C/min=5/t=0.9_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=5/t=0.9_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..84e113b30d668f2e6dd4de29ec160f9ca3cfe984 --- /dev/null +++ b/data/clustering/model=FremyCompany__BioLORD-2023-C/min=5/t=0.9_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +organism_source,9834,9236,91,0.9983723163604736,0.195409094030837,5,0.9 +desalting_process,5540,1518,175,0.7987412214279175,0.6679834498969747,5,0.9 +enzyme_name,12099,1752,188,0.7952802777290344,0.557429044538093,5,0.9 +induction_temperature,5383,4981,60,0.7904442548751831,0.504617694402376,5,0.9 +strain,3834,2809,77,0.7727811336517334,0.698016043961369,5,0.9 +inducer,11954,10379,244,0.751237690448761,1.1752453008654211,5,0.9 +medium_name,7644,3386,274,0.6939384937286377,0.7154096359976282,5,0.9 +lysis_buffer,5625,1979,217,0.6614541411399841,0.8014986409065298,5,0.9 +plasmid,8217,3110,192,0.6221994757652283,0.5898011836798316,5,0.9 +elution_buffer,5198,1729,176,0.6210601329803467,0.8154378999020092,5,0.9 +expression_strain,8268,7326,159,0.517829179763794,1.0153725936086218,5,0.9 +molecular_weight,495,204,18,0.3784116804599762,1.535015859660827,5,0.9 +source_key,12179,12029,235,-0.11407990008592606,2.0183491136381746,5,0.9