diff --git a/.gitattributes b/.gitattributes index 865df7fcbf72a924174b1ab1e5f4bd2bee627ef8..35795ca9e312353c4fcb97f4d835e9b66114c0ec 100644 --- a/.gitattributes +++ b/.gitattributes @@ -200,3 +200,28 @@ data/clustering/model=pritamdeka__BioBERT-mnli-snli-scinli-scitail-mednli-stsb/m data/clustering/model=pritamdeka__BioBERT-mnli-snli-scinli-scitail-mednli-stsb/min=5/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text data/clustering/model=pritamdeka__BioBERT-mnli-snli-scinli-scitail-mednli-stsb/min=5/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text data/clustering/model=pritamdeka__BioBERT-mnli-snli-scinli-scitail-mednli-stsb/min=5/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=10/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=10/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=10/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=10/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=10/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=2/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=2/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=2/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=2/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=2/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=20/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=20/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=20/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=20/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=20/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=30/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=30/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=30/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=30/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=30/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=5/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=5/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=5/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=5/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=5/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=10/t=0.5_ALL_FIELDS.csv.gz b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=10/t=0.5_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..b2a65cb9302de3c8a83a8be46672e98ecb6dec27 --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=10/t=0.5_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09ca2e876d8e5036ce95498bda782d2720428b0c6a53153b2f85c5b3b4976570 +size 2582070 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=10/t=0.5_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=10/t=0.5_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..47aeaa2212f42e5cda925584c8e9c039532ae805 --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/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,9834,9572,45,0.6859212517738342,1.5964706842175915,10,0.5 +strain,3834,3645,39,0.3887566030025482,2.361134385487578,10,0.5 +expression_strain,8268,8205,25,0.37382158637046814,2.3352285841677407,10,0.5 +induction_temperature,5383,5351,25,0.3094424605369568,1.8049660747944836,10,0.5 +inducer,11954,11845,54,0.25794321298599243,2.5383613290650766,10,0.5 +lysis_buffer,5625,5545,32,0.10325564444065094,2.5934740108069634,10,0.5 +desalting_process,5540,5475,33,0.058322880417108536,2.8762737178153728,10,0.5 +elution_buffer,5198,5128,56,0.018321527168154716,2.763262512662069,10,0.5 +molecular_weight,495,422,14,-0.01032125111669302,2.936083647693433,10,0.5 +enzyme_name,12099,10986,387,-0.05262689292430878,3.571045375233803,10,0.5 +source_key,12179,12176,54,-0.08566398173570633,3.143388663946649,10,0.5 +plasmid,8217,8051,87,-0.0943443551659584,3.383369746412934,10,0.5 +medium_name,7644,7478,80,-0.10115828365087509,2.7714374777803523,10,0.5 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=10/t=0.6_ALL_FIELDS.csv.gz b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=10/t=0.6_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..1010d90e03350e104924a4798d5299cb424a4887 --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=10/t=0.6_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a6ab88233a385f9dd12da153b47eb4b5fad8afee62a4e5986f0fa241313e3b3 +size 2608731 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=10/t=0.6_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=10/t=0.6_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..9ebd5634c18d044498bf299a256d757c814e6324 --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/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,9834,9382,46,0.8315644860267639,1.0968846816298672,10,0.6 +inducer,11954,11677,51,0.5356959104537964,2.4847950624152397,10,0.6 +strain,3834,3452,36,0.44477683305740356,1.9357904675013506,10,0.6 +induction_temperature,5383,5292,34,0.4217080771923065,1.6115081264969064,10,0.6 +expression_strain,8268,8114,24,0.38894540071487427,2.301271811376401,10,0.6 +molecular_weight,495,371,19,0.22974713146686554,1.9370846921305702,10,0.6 +enzyme_name,12099,8123,380,0.03485294431447983,2.9190030778222034,10,0.6 +lysis_buffer,5625,5425,53,0.031918663531541824,2.9006761283811002,10,0.6 +plasmid,8217,7484,209,-0.015525907278060913,3.141398393765599,10,0.6 +desalting_process,5540,5226,70,-0.028160059824585915,3.0262587619360506,10,0.6 +elution_buffer,5198,4956,90,-0.04158775135874748,2.7172129885791736,10,0.6 +medium_name,7644,7163,112,-0.05647153779864311,2.8643035781998636,10,0.6 +source_key,12179,12080,183,-0.08706450462341309,2.6747524390750845,10,0.6 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=10/t=0.7_ALL_FIELDS.csv.gz b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=10/t=0.7_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..82849b39ba6e0a6c9b1361aaa6cbfcd9bef16ce3 --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=10/t=0.7_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e3a2f8e5a63ad97c9fe75d263eeccd1f7cc4b92faa26422c9cb1addadce1ca3 +size 2612824 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=10/t=0.7_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=10/t=0.7_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..4c84ddf63484f775a30537773f00f7d7868d1ee1 --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/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,9834,9242,46,0.9466846585273743,0.7236169666087298,10,0.7 +strain,3834,3145,44,0.565053403377533,1.5559208847808315,10,0.7 +inducer,11954,11362,72,0.5429345369338989,2.462818988340495,10,0.7 +induction_temperature,5383,5202,36,0.44828498363494873,1.469030615290585,10,0.7 +molecular_weight,495,257,18,0.4434238374233246,1.3396230642575762,10,0.7 +expression_strain,8268,7925,71,0.43037569522857666,2.079271419014267,10,0.7 +enzyme_name,12099,4024,220,0.25147920846939087,2.0199749693744598,10,0.7 +plasmid,8217,5750,181,0.16367320716381073,2.439680155334173,10,0.7 +medium_name,7644,6486,149,0.07253237813711166,2.6755053479004096,10,0.7 +source_key,12179,11503,293,0.03306351229548454,2.3661764115758612,10,0.7 +elution_buffer,5198,4467,128,0.0204304251819849,2.6929717612881907,10,0.7 +desalting_process,5540,4649,125,0.006688971072435379,2.7841206830139145,10,0.7 +lysis_buffer,5625,5026,97,-0.029900426045060158,2.9055338820082888,10,0.7 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=10/t=0.8_ALL_FIELDS.csv.gz b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=10/t=0.8_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..700930207cf24d7045d142294351e3e24586b79e --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=10/t=0.8_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:630a2cde0560cf7351885aa4af8750f253bc196f3124ca50b34accfd8cd59baf +size 2517675 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=10/t=0.8_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=10/t=0.8_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..7d3adc54dcd75c62166b3e72d64a6441f16574a9 --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/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,9834,9091,50,0.9609859585762024,0.4713954876555749,10,0.8 +induction_temperature,5383,4991,30,0.8820443153381348,0.6289888971674816,10,0.8 +molecular_weight,495,77,6,0.7381584048271179,0.7244761472742365,10,0.8 +strain,3834,2747,42,0.6737307906150818,1.0531086614146252,10,0.8 +enzyme_name,12099,1334,80,0.6321789026260376,0.9772103202663651,10,0.8 +inducer,11954,10865,120,0.6086933612823486,2.1251237992170195,10,0.8 +expression_strain,8268,7449,88,0.5437607765197754,1.3351239344014818,10,0.8 +plasmid,8217,3513,91,0.4276926815509796,1.3758739090250744,10,0.8 +source_key,12179,10098,334,0.3921198844909668,1.4626443745434132,10,0.8 +desalting_process,5540,2684,118,0.18591715395450592,2.200920606692973,10,0.8 +medium_name,7644,4850,146,0.15399283170700073,2.2313824719991473,10,0.8 +elution_buffer,5198,2907,128,0.14113454520702362,2.1420915226059707,10,0.8 +lysis_buffer,5625,4001,133,0.04472555220127106,2.5670119255046373,10,0.8 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=10/t=0.9_ALL_FIELDS.csv.gz b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=10/t=0.9_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..1f9a2838de7b244308f1c6690ffdcc96fc41e0ce --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=10/t=0.9_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14a7a76c52a34f8dc8ab6209af32068b5f657cb702b2f7955546b5a2fb09058d +size 2339931 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=10/t=0.9_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=10/t=0.9_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..d4eb4d128ac5b00108e33a2fdfc1a41370d1e1ab --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/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,9834,8933,44,0.998249888420105,0.21925802264707894,10,0.9 +strain,3834,2419,32,0.9517265558242798,0.3185429431863286,10,0.9 +molecular_weight,495,31,3,0.9425767064094543,0.2947725111699637,10,0.9 +enzyme_name,12099,520,36,0.9085906744003296,0.4282297181958293,10,0.9 +induction_temperature,5383,4778,29,0.8972811698913574,0.3256626785625169,10,0.9 +inducer,11954,9605,104,0.8028183579444885,1.27422787820579,10,0.9 +source_key,12179,3203,220,0.7930075526237488,0.6524226643927599,10,0.9 +desalting_process,5540,688,39,0.781925618648529,0.6811760817772753,10,0.9 +plasmid,8217,2292,69,0.7293703556060791,0.558886158369757,10,0.9 +expression_strain,8268,6562,78,0.5886973738670349,0.7104876592242283,10,0.9 +medium_name,7644,2709,95,0.5442994832992554,1.1065494393653463,10,0.9 +elution_buffer,5198,884,48,0.5436325073242188,1.058603635278028,10,0.9 +lysis_buffer,5625,1527,80,0.37812721729278564,1.5836955889800834,10,0.9 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=2/t=0.5_ALL_FIELDS.csv.gz b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=2/t=0.5_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..b2824ecf8aaebf86b1e388dbef74abac3b7fbce4 --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=2/t=0.5_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fbf32a7c54ff45123e06b1838bf628c37d53ac2cd9f16fc8e5e5d62ebc62115 +size 2613323 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=2/t=0.5_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=2/t=0.5_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..d5b9819d9b07513d8e05fd3529555ac2af46b12f --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/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,9834,9802,129,0.6780164241790771,1.2256505275429672,2,0.5 +strain,3834,3811,144,0.3498580753803253,1.4830415200580023,2,0.5 +inducer,11954,11938,169,0.23287788033485413,1.5794902504588904,2,0.5 +induction_temperature,5383,5377,44,0.22990873456001282,1.614566928236816,2,0.5 +expression_strain,8268,8257,81,0.06429289281368256,1.4745329737519066,2,0.5 +lysis_buffer,5625,5618,104,0.053896062076091766,1.5931871509772824,2,0.5 +desalting_process,5540,5529,92,-0.002713533118367195,1.8943817863861656,2,0.5 +elution_buffer,5198,5191,141,-0.02154548279941082,1.9446803651177995,2,0.5 +molecular_weight,495,487,52,-0.09526506811380386,2.053325855390442,2,0.5 +medium_name,7644,7626,220,-0.11653927713632584,1.8051701494536572,2,0.5 +enzyme_name,12099,11963,1222,-0.1176801398396492,2.3801955556958614,2,0.5 +source_key,12179,12179,99,-0.1424853354692459,2.1102816474054222,2,0.5 +plasmid,8217,8193,257,-0.1608523577451706,2.221833572162764,2,0.5 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=2/t=0.6_ALL_FIELDS.csv.gz b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=2/t=0.6_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..392456d287f832060c287f8f1de218d2bc7f8e2d --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=2/t=0.6_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34a1af99e26a5e9c03e9b7951b95a5e872a372bc096e1221a763de8fe0c658ae +size 2689536 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=2/t=0.6_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=2/t=0.6_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..b97633535db95e65c45e11d745da2f683be09a40 --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/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,9834,9768,162,0.8123151659965515,0.891435926976726,2,0.6 +inducer,11954,11909,202,0.5009335279464722,1.50141676911047,2,0.6 +strain,3834,3761,147,0.42982858419418335,1.2881429499434045,2,0.6 +induction_temperature,5383,5368,72,0.3770945072174072,1.317439124766019,2,0.6 +expression_strain,8268,8249,77,0.1425793468952179,1.549450749215708,2,0.6 +molecular_weight,495,460,61,0.0876990258693695,1.7681907295010657,2,0.6 +enzyme_name,12099,11315,1930,-0.024796035140752792,1.9659796426602536,2,0.6 +lysis_buffer,5625,5588,190,-0.03475573658943176,1.6129701504459102,2,0.6 +plasmid,8217,8101,694,-0.05500331521034241,2.141229959510721,2,0.6 +desalting_process,5540,5479,228,-0.05962241813540459,1.8530857573361357,2,0.6 +elution_buffer,5198,5163,269,-0.07627935707569122,1.7771701976403598,2,0.6 +medium_name,7644,7574,385,-0.08117346465587616,1.7438626888356037,2,0.6 +source_key,12179,12174,385,-0.1337893307209015,1.8072901909647214,2,0.6 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=2/t=0.7_ALL_FIELDS.csv.gz b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=2/t=0.7_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..243f1804556dc0cebd18702dad2dde59d6125eff --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=2/t=0.7_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c718a4a81574fc52be09a0dc76170a006889e21419e183a86364bc64da6874dc +size 2747230 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=2/t=0.7_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=2/t=0.7_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..17bac86efbbd0cd1fa5447b0bba77fede662efcb --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/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,9834,9731,186,0.9222168326377869,0.6467992269664734,2,0.7 +strain,3834,3694,236,0.5251205563545227,1.1337143290579315,2,0.7 +inducer,11954,11846,285,0.5146743655204773,1.3982947714967557,2,0.7 +induction_temperature,5383,5348,96,0.4400424361228943,1.1811155367202322,2,0.7 +expression_strain,8268,8205,200,0.3929457664489746,1.5418938693676596,2,0.7 +molecular_weight,495,411,61,0.3904179036617279,1.2119965848954137,2,0.7 +enzyme_name,12099,9547,2155,0.22678028047084808,1.4309653217944136,2,0.7 +plasmid,8217,7538,946,0.1469815969467163,1.6453547615106232,2,0.7 +medium_name,7644,7413,591,0.08565498888492584,1.5711137686869867,2,0.7 +desalting_process,5540,5310,482,0.021070199087262154,1.6916229457457381,2,0.7 +elution_buffer,5198,5030,472,0.018657978624105453,1.629454248466902,2,0.7 +source_key,12179,12147,660,-0.01781006157398224,1.6452897404221645,2,0.7 +lysis_buffer,5625,5517,374,-0.033773306757211685,1.6224257955625265,2,0.7 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=2/t=0.8_ALL_FIELDS.csv.gz b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=2/t=0.8_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..6c7696c291413ece23e6da6c556635d561f425a1 --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=2/t=0.8_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e4aeddc05b56f025641c23dd48fc0b92ce4841347ffbb243c4a5acc2ca072ad +size 2728306 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=2/t=0.8_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=2/t=0.8_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..aca11ab0216aabfe65dbe76a227eff205b88b5a9 --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/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,9834,9686,229,0.9572328925132751,0.4397506586716961,2,0.8 +induction_temperature,5383,5291,119,0.8446872234344482,0.6908602367054061,2,0.8 +molecular_weight,495,352,77,0.7225258350372314,0.6932834079991462,2,0.8 +strain,3834,3521,292,0.67866051197052,0.7960020228518555,2,0.8 +inducer,11954,11695,456,0.5833052396774292,1.2802340184661325,2,0.8 +enzyme_name,12099,7003,1991,0.5644457340240479,0.8803254272272604,2,0.8 +expression_strain,8268,8058,306,0.5061991810798645,1.0468455966897592,2,0.8 +plasmid,8217,6442,1050,0.43919673562049866,1.0245161032081613,2,0.8 +source_key,12179,12034,923,0.3269834518432617,1.157384162792504,2,0.8 +desalting_process,5540,4638,853,0.3239937722682953,1.2411543534586615,2,0.8 +elution_buffer,5198,4524,726,0.25231027603149414,1.315855089960473,2,0.8 +medium_name,7644,6859,892,0.24795590341091156,1.2155266794354358,2,0.8 +lysis_buffer,5625,5219,656,0.12612177431583405,1.4044102329590016,2,0.8 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=2/t=0.9_ALL_FIELDS.csv.gz b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=2/t=0.9_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..8e5ea1446eb47627bcc9921489c650fba4015bcc --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=2/t=0.9_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c008ad7fd98b0a89a56d7f6bf5ceb1f1c18104c7ed46768e2f484b843ddadbf7 +size 2579397 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=2/t=0.9_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=2/t=0.9_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..6797e9c3e64a185b7206adc7535a9f0f3194257a --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/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,9834,9659,257,0.9969485998153687,0.2409388842400483,2,0.9 +strain,3834,3319,322,0.9193541407585144,0.3769339979219886,2,0.9 +molecular_weight,495,301,80,0.8911254405975342,0.34445644211859444,2,0.9 +enzyme_name,12099,4477,1506,0.872164785861969,0.4292431303469919,2,0.9 +desalting_process,5540,3572,1033,0.8632161617279053,0.5101931312338516,2,0.9 +source_key,12179,11313,2314,0.8365621566772461,0.5090362268047465,2,0.9 +induction_temperature,5383,5233,161,0.8335573077201843,0.3669360873487719,2,0.9 +elution_buffer,5198,3520,938,0.7743985056877136,0.5441500484416552,2,0.9 +inducer,11954,11393,657,0.7729544639587402,0.755367392067666,2,0.9 +plasmid,8217,5119,1053,0.7352403402328491,0.5035259942437131,2,0.9 +medium_name,7644,5926,1149,0.6840539574623108,0.6075129852732638,2,0.9 +lysis_buffer,5625,4380,1030,0.6375762224197388,0.7453407952573826,2,0.9 +expression_strain,8268,7790,449,0.5808180570602417,0.5575074832450428,2,0.9 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=20/t=0.5_ALL_FIELDS.csv.gz b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=20/t=0.5_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..f6af24331ffaff437f28051680bf8002dcf6a58e --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=20/t=0.5_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46b36c327c5318963e9d13c14ffbb095b8c0bf764c89c36562e453824bee2389 +size 2546640 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=20/t=0.5_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=20/t=0.5_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..7c5163b7e1c72c57bec03b843b5e3dc529790f14 --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/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,9834,9468,29,0.6944819688796997,1.6074184789475812,20,0.5 +strain,3834,3485,18,0.4123495817184448,2.693304281356441,20,0.5 +expression_strain,8268,8148,13,0.3941309452056885,2.0747963739594546,20,0.5 +induction_temperature,5383,5314,20,0.3268693685531616,1.88116220409179,20,0.5 +inducer,11954,11782,30,0.26220160722732544,2.863868139408105,20,0.5 +lysis_buffer,5625,5507,17,0.11639048159122467,3.2683792992935388,20,0.5 +desalting_process,5540,5412,19,0.0832335576415062,3.371589836814463,20,0.5 +elution_buffer,5198,5056,31,0.052440572530031204,3.2525341808014954,20,0.5 +molecular_weight,495,341,6,0.03604482114315033,3.161419250354124,20,0.5 +enzyme_name,12099,10146,217,-0.029270080849528313,3.9243390320073543,20,0.5 +source_key,12179,12143,38,-0.061951033771038055,3.493840411186325,20,0.5 +plasmid,8217,7847,52,-0.06832297146320343,3.8571945518617032,20,0.5 +medium_name,7644,7359,46,-0.07698120176792145,3.2656879402630836,20,0.5 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=20/t=0.6_ALL_FIELDS.csv.gz b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=20/t=0.6_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..f232403161c35051e74c0861c8903999b30c31e9 --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=20/t=0.6_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cd22036060c41a2c160832f3533797ef0ea19afbaa1eb0a6c47efca1e158e42 +size 2555515 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=20/t=0.6_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=20/t=0.6_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..46bcdb86abc6854cfe5813e22352b54717c96498 --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/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,9834,9192,29,0.8371265530586243,1.113791572804182,20,0.6 +inducer,11954,11499,24,0.5488783717155457,2.8457092225554894,20,0.6 +induction_temperature,5383,5231,24,0.4833644926548004,1.2922924675634662,20,0.6 +strain,3834,3246,17,0.45645755529403687,2.20222601110685,20,0.6 +expression_strain,8268,8075,18,0.39860498905181885,2.4187900892097085,20,0.6 +molecular_weight,495,269,8,0.21589632332324982,2.285370988360359,20,0.6 +enzyme_name,12099,6201,158,0.05227068066596985,3.2130315309952913,20,0.6 +lysis_buffer,5625,5247,27,0.04636301100254059,3.5143891719051776,20,0.6 +plasmid,8217,7033,119,-0.0037182015366852283,3.4049318630368637,20,0.6 +desalting_process,5540,5113,42,-0.007803318090736866,3.654051484714285,20,0.6 +elution_buffer,5198,4839,55,-0.027301451191306114,3.0441020005124444,20,0.6 +medium_name,7644,6909,63,-0.053983449935913086,3.286720821544009,20,0.6 +source_key,12179,11937,117,-0.06625042855739594,3.1557173267165304,20,0.6 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=20/t=0.7_ALL_FIELDS.csv.gz b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=20/t=0.7_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..462ff9332477421165d206397aea08b003be4d4a --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=20/t=0.7_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c9a929b6c73c93f3afec36d0cf1cd1e9b991f018d11a46ee3105fc8dabbf802 +size 2545790 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=20/t=0.7_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=20/t=0.7_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..d69081546285ca771f4c8509c293f20c805aa9e0 --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/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,9834,8940,23,0.9552887082099915,0.71474054013163,20,0.7 +strain,3834,2913,24,0.5852909088134766,1.5327221283535497,20,0.7 +inducer,11954,11217,43,0.5607924461364746,2.85145084254143,20,0.7 +molecular_weight,495,82,3,0.5316680669784546,1.2616011625085053,20,0.7 +expression_strain,8268,7751,45,0.46647462248802185,2.2011301501122453,20,0.7 +induction_temperature,5383,5093,25,0.4519576132297516,1.414033402891248,20,0.7 +enzyme_name,12099,2177,62,0.319841593503952,1.9187984508645477,20,0.7 +plasmid,8217,4920,83,0.215868279337883,2.3673804755780714,20,0.7 +medium_name,7644,6110,84,0.07681573927402496,3.0403719497441637,20,0.7 +source_key,12179,10791,183,0.05039200559258461,2.6874047882569503,20,0.7 +elution_buffer,5198,4101,68,0.023327862843871117,3.062668513609801,20,0.7 +desalting_process,5540,4250,62,0.0066610039211809635,3.2683115263367015,20,0.7 +lysis_buffer,5625,4841,56,-0.0176224485039711,3.400573394955429,20,0.7 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=20/t=0.8_ALL_FIELDS.csv.gz b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=20/t=0.8_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..2d35cacd97152ca1e5a8568c9423763192dcc9ee --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=20/t=0.8_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2975c7d9dce210f7030d82cb4f486028766d0af99aaa851c147935b457834e0 +size 2441310 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=20/t=0.8_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=20/t=0.8_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..fcf554d42856404b60ead52e25bb83e92181327e --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/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,9834,8726,22,0.9701414108276367,0.4172653883348097,20,0.8 +induction_temperature,5383,4814,17,0.9191182255744934,0.42765792725923474,20,0.8 +strain,3834,2519,22,0.6952298283576965,1.1238044041243918,20,0.8 +enzyme_name,12099,581,19,0.6596435904502869,0.9523464217005506,20,0.8 +inducer,11954,10517,64,0.6369159817695618,2.385409718338227,20,0.8 +expression_strain,8268,7008,48,0.5863747596740723,1.0861642801073916,20,0.8 +plasmid,8217,2923,43,0.4602383077144623,1.454462407435808,20,0.8 +source_key,12179,8363,183,0.44081631302833557,1.4524895154725401,20,0.8 +medium_name,7644,4118,67,0.16666226089000702,2.633862212871955,20,0.8 +elution_buffer,5198,2208,52,0.16207127273082733,2.463059071897654,20,0.8 +desalting_process,5540,1930,44,0.15330913662910461,2.6193305286766257,20,0.8 +lysis_buffer,5625,3488,62,0.03983919322490692,3.020738931983308,20,0.8 +molecular_weight,495,0,0,,,20,0.8 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=20/t=0.9_ALL_FIELDS.csv.gz b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=20/t=0.9_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..5463e2797b85b20bc91c6c2bc6707644a58f9acc --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=20/t=0.9_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fae90b021eb81e0660c8d1d24e2f0ddf6dbdfe3afe884f09f4a4998c76affa50 +size 2300061 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=20/t=0.9_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=20/t=0.9_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..5ce28be3f7fcc793564c77c8572dd8e749435461 --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/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,9834,8630,21,0.9990015029907227,0.2150955708977953,20,0.9 +enzyme_name,12099,121,5,0.966403603553772,0.2868022440473822,20,0.9 +strain,3834,2165,13,0.958252489566803,0.31678251382889083,20,0.9 +induction_temperature,5383,4630,18,0.9336817860603333,0.3021315905619815,20,0.9 +inducer,11954,9054,51,0.8288679122924805,1.433517666902332,20,0.9 +plasmid,8217,1801,31,0.7937244772911072,0.5773760717690696,20,0.9 +source_key,12179,875,35,0.78330397605896,0.724020014802023,20,0.9 +desalting_process,5540,318,9,0.7765031456947327,0.7688950493842941,20,0.9 +expression_strain,8268,6149,44,0.6016548275947571,0.7019531924269297,20,0.9 +medium_name,7644,1889,27,0.5807583332061768,1.1635028986563614,20,0.9 +elution_buffer,5198,486,14,0.4640120565891266,1.4789575135220632,20,0.9 +lysis_buffer,5625,924,27,0.32853734493255615,1.8713127216931515,20,0.9 +molecular_weight,495,0,0,,,20,0.9 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=30/t=0.5_ALL_FIELDS.csv.gz b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=30/t=0.5_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..ab74de631421976bda4975061e9acf57f40db08f --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=30/t=0.5_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cea5ced03cb0ef36398d368a285fa155cb88810488e472815fd4620f8d6df0a +size 2523847 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=30/t=0.5_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=30/t=0.5_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..9cea47566ed857d2ac0eac17a5336d3eb2353524 --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/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,9834,9385,24,0.6959324479103088,1.621247602168325,30,0.5 +strain,3834,3488,15,0.4216921329498291,2.6939536711419665,30,0.5 +expression_strain,8268,8119,11,0.4206995368003845,2.4026072349383885,30,0.5 +induction_temperature,5383,5307,17,0.33675140142440796,1.890297613158668,30,0.5 +inducer,11954,11724,20,0.2997589111328125,3.0234326027367704,30,0.5 +lysis_buffer,5625,5423,10,0.12266062945127487,3.601230178107623,30,0.5 +desalting_process,5540,5348,14,0.09128496050834656,3.301160463109049,30,0.5 +elution_buffer,5198,5025,23,0.07475155591964722,3.423147234994284,30,0.5 +molecular_weight,495,322,5,0.03778699412941933,3.2782248535751926,30,0.5 +enzyme_name,12099,9516,149,-0.01875469647347927,4.196246835919551,30,0.5 +plasmid,8217,7773,39,-0.049662262201309204,3.999363757055578,30,0.5 +source_key,12179,12113,31,-0.04991086572408676,3.706510974366113,30,0.5 +medium_name,7644,7234,31,-0.07323428988456726,3.5615675602657406,30,0.5 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=30/t=0.6_ALL_FIELDS.csv.gz b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=30/t=0.6_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..95b45c2652ec44377221f3bdc893c3d3eef51590 --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=30/t=0.6_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed1000272cec59522f0e98707abf361076c2c23b9d3d04df0ef89a9be2d00803 +size 2521418 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=30/t=0.6_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=30/t=0.6_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..ea205504061e0c88ed3ae62f4d8e0b0ac4965813 --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/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,9834,9041,21,0.8477003574371338,0.9576767848886412,30,0.6 +inducer,11954,11454,19,0.5608282089233398,2.837677795797898,30,0.6 +induction_temperature,5383,5218,21,0.49113729596138,1.2565712144944807,30,0.6 +strain,3834,3138,12,0.4833256006240845,2.4345902669227555,30,0.6 +expression_strain,8268,7956,12,0.40748274326324463,2.6805999838483423,30,0.6 +molecular_weight,495,210,5,0.29524660110473633,1.9311519698173396,30,0.6 +enzyme_name,12099,5118,91,0.0784328281879425,3.3164355566467556,30,0.6 +lysis_buffer,5625,5165,20,0.05151115357875824,3.7754753319621286,30,0.6 +plasmid,8217,6770,86,0.009089118801057339,3.4160153568998126,30,0.6 +desalting_process,5540,4941,28,0.002085871994495392,3.8658244278755505,30,0.6 +elution_buffer,5198,4680,36,-0.012900298461318016,3.277995665299363,30,0.6 +medium_name,7644,6773,46,-0.017958257347345352,3.604529827772788,30,0.6 +source_key,12179,11794,94,-0.04887797310948372,3.3525671773890227,30,0.6 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=30/t=0.7_ALL_FIELDS.csv.gz b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=30/t=0.7_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..ce2e430f8775e4392842fda3a9a70f79da6a420e --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=30/t=0.7_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2314d6905de041a1b63c73c6e3b5b173188cd2293d4ecc4dbce3ec4685dd4465 +size 2501921 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=30/t=0.7_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=30/t=0.7_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..070cca2810a5916a8092fe346b5bc6ec8c5a3e91 --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/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,9834,8770,16,0.9623826146125793,0.5022314382245494,30,0.7 +molecular_weight,495,62,2,0.6074885129928589,1.0809282002121368,30,0.7 +strain,3834,2739,15,0.6062254905700684,1.704124886607578,30,0.7 +inducer,11954,11002,27,0.5736951231956482,2.8314486071601475,30,0.7 +expression_strain,8268,7627,32,0.4747351109981537,2.12933377649831,30,0.7 +induction_temperature,5383,5001,20,0.467640221118927,1.3881609007394224,30,0.7 +enzyme_name,12099,1468,29,0.3663622736930847,1.748840455871888,30,0.7 +plasmid,8217,4449,55,0.23499901592731476,2.327100138675344,30,0.7 +medium_name,7644,5813,58,0.09461566060781479,3.2834232582556773,30,0.7 +source_key,12179,10108,134,0.053450193256139755,2.8713516726889274,30,0.7 +elution_buffer,5198,3848,46,0.027025075629353523,3.2904923160691424,30,0.7 +desalting_process,5540,4032,42,0.013479492627084255,3.542268923612469,30,0.7 +lysis_buffer,5625,4656,37,-0.00979724619537592,3.7364143837910633,30,0.7 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=30/t=0.8_ALL_FIELDS.csv.gz b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=30/t=0.8_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..409b70380730ba4a0593cd5b9995455a779660ca --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=30/t=0.8_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:341ae48aebba9009b409e6bd0caf2789f0ff76739b43bf0b1fffce2e10a2cf18 +size 2399466 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=30/t=0.8_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=30/t=0.8_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..1e47be34ade9c928bcebc2f21f37eeedcbb0718b --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/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,9834,8624,18,0.9701882600784302,0.41768382216016303,30,0.8 +induction_temperature,5383,4759,15,0.9207344651222229,0.4215759552094291,30,0.8 +enzyme_name,12099,310,8,0.7706252336502075,0.7700080211831376,30,0.8 +strain,3834,2301,12,0.7581266164779663,0.8721027937895066,30,0.8 +inducer,11954,10359,46,0.6462844014167786,2.528751652569929,30,0.8 +expression_strain,8268,6713,32,0.5898532867431641,1.0549178639694958,30,0.8 +plasmid,8217,2636,29,0.4770966172218323,1.4940179854139517,30,0.8 +source_key,12179,7275,134,0.4486226439476013,1.4423312346494352,30,0.8 +medium_name,7644,3660,40,0.1882116049528122,2.6832492592889485,30,0.8 +desalting_process,5540,1620,25,0.17580264806747437,2.6089319248334197,30,0.8 +elution_buffer,5198,1851,30,0.1693132370710373,2.619925399329474,30,0.8 +lysis_buffer,5625,3112,36,0.041954997926950455,3.4334871723440674,30,0.8 +molecular_weight,495,0,0,,,30,0.8 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=30/t=0.9_ALL_FIELDS.csv.gz b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=30/t=0.9_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..b5fb3e77dad95d7d0bb6db2578985f561c4569bc --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=30/t=0.9_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70b14be00f033615be9c87fa966bbe2a0c364e202db2671e80904356c7406e7f +size 2284001 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=30/t=0.9_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=30/t=0.9_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..52a8f6c092ce7506a24402d3033a9220c903f7b0 --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/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,9834,8522,17,0.9999468326568604,0.006735492516078417,30,0.9 +strain,3834,2119,11,0.9583682417869568,0.3283560715256501,30,0.9 +desalting_process,5540,198,4,0.9562246203422546,0.31097318164815096,30,0.9 +induction_temperature,5383,4554,15,0.9485726356506348,0.30684316759986385,30,0.9 +inducer,11954,8608,29,0.8705289959907532,1.2852807357906992,30,0.9 +source_key,12179,212,6,0.8472281694412231,0.575699362697555,30,0.9 +plasmid,8217,1481,17,0.7943127751350403,0.5692455965505211,30,0.9 +expression_strain,8268,5782,28,0.5875058174133301,0.7625587621482514,30,0.9 +medium_name,7644,1651,16,0.5862548351287842,1.3139927515989354,30,0.9 +elution_buffer,5198,318,6,0.5727202296257019,1.1723338688281881,30,0.9 +lysis_buffer,5625,707,16,0.3427216112613678,1.9371730213586087,30,0.9 +enzyme_name,12099,0,0,,,30,0.9 +molecular_weight,495,0,0,,,30,0.9 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=5/t=0.5_ALL_FIELDS.csv.gz b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=5/t=0.5_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..32987b152923b75758e56a6beac275d0afcf4fa9 --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=5/t=0.5_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1de134121eb70bc32fc68bb5413075eece8ed9ddcd0ac276d5080226f5c37880 +size 2600526 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=5/t=0.5_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=5/t=0.5_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..e25630dc3005fb5e6840a3fd70c0e6f89c3852f7 --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/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,9834,9697,75,0.6798974275588989,1.462344101616873,5,0.5 +strain,3834,3718,69,0.3654930591583252,2.009931714966699,5,0.5 +expression_strain,8268,8231,44,0.3535119593143463,1.9469829059633332,5,0.5 +induction_temperature,5383,5366,33,0.24867087602615356,1.672334180118883,5,0.5 +inducer,11954,11902,95,0.24384336173534393,2.0791809913146992,5,0.5 +lysis_buffer,5625,5584,58,0.08228866755962372,2.0897364657473356,5,0.5 +desalting_process,5540,5500,51,0.024186450988054276,2.5407814701623463,5,0.5 +elution_buffer,5198,5170,88,0.003209158778190613,2.338975496256013,5,0.5 +molecular_weight,495,459,26,-0.05946159362792969,2.6126911522695035,5,0.5 +enzyme_name,12099,11524,645,-0.07704289257526398,3.094499604414356,5,0.5 +medium_name,7644,7565,126,-0.10564478486776352,2.3346150033973334,5,0.5 +source_key,12179,12173,70,-0.11068613827228546,2.7075648798180247,5,0.5 +plasmid,8217,8135,139,-0.12109757214784622,2.940559705705408,5,0.5 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=5/t=0.6_ALL_FIELDS.csv.gz b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=5/t=0.6_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..d68d41158544d242eaffda415bb78980a426cdb2 --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=5/t=0.6_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:747edddadcb6a95539842723acb76747b6b370cc7ca6c7e1632fad0522d1ca6d +size 2655150 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=5/t=0.6_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=5/t=0.6_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..b9e9f9ce1c7feee82848c3f37f2bb55ab887b934 --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/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,9834,9584,80,0.8171652555465698,1.042899521846173,5,0.6 +inducer,11954,11823,100,0.5203410983085632,2.1199408926680015,5,0.6 +strain,3834,3577,62,0.4280261695384979,1.8007474501950411,5,0.6 +induction_temperature,5383,5339,47,0.40034425258636475,1.525826440885524,5,0.6 +expression_strain,8268,8177,40,0.3532277047634125,2.0461662661704154,5,0.6 +molecular_weight,495,407,31,0.1522579938173294,2.1576019094309045,5,0.6 +enzyme_name,12099,9771,821,0.014644897542893887,2.53484599658367,5,0.6 +lysis_buffer,5625,5502,91,0.013205650262534618,2.396112840751667,5,0.6 +plasmid,8217,7791,361,-0.03546280786395073,2.75390115692079,5,0.6 +desalting_process,5540,5388,116,-0.036144498735666275,2.5924109791989536,5,0.6 +elution_buffer,5198,5084,155,-0.06091875210404396,2.2556553008106137,5,0.6 +medium_name,7644,7383,202,-0.0666692778468132,2.3682763259659367,5,0.6 +source_key,12179,12140,268,-0.11497709900140762,2.2577824000675313,5,0.6 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=5/t=0.7_ALL_FIELDS.csv.gz b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=5/t=0.7_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..b13fa64016dd16b8ba23d10041b4c86142442854 --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=5/t=0.7_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10abb6586bfa92caab13c72343e81a512b0eaf3da2f17002cb8b6bc02538baa6 +size 2674776 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=5/t=0.7_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=5/t=0.7_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..12309518ea6e912ff3ad8316fd0c54215eaad317 --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/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,9834,9469,82,0.9360809922218323,0.7322145972427341,5,0.7 +inducer,11954,11623,141,0.5289301872253418,1.976804308894141,5,0.7 +strain,3834,3359,88,0.5169442892074585,1.5685720755394212,5,0.7 +induction_temperature,5383,5262,53,0.4427502155303955,1.443549098109181,5,0.7 +expression_strain,8268,8061,110,0.4207003712654114,1.8925534447400834,5,0.7 +molecular_weight,495,342,32,0.39928334951400757,1.4558611367072798,5,0.7 +enzyme_name,12099,6281,639,0.2309132218360901,1.8309441936727633,5,0.7 +plasmid,8217,6537,369,0.15478336811065674,2.177446926398514,5,0.7 +medium_name,7644,6853,268,0.07835797965526581,2.2152908584643196,5,0.7 +elution_buffer,5198,4705,223,0.01908757910132408,2.229570540825758,5,0.7 +source_key,12179,11943,442,0.016012921929359436,2.045271311289823,5,0.7 +desalting_process,5540,4948,224,0.00829404965043068,2.3109306783892447,5,0.7 +lysis_buffer,5625,5259,177,-0.039761606603860855,2.3334950252763904,5,0.7 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=5/t=0.8_ALL_FIELDS.csv.gz b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=5/t=0.8_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..f5551f639da9c59233d9b661610097c53de4a2fb --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=5/t=0.8_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0b2a38581b4d109c69a7d064f5f3e3fd8feac0843a5f351dbd7c413ea4f3f8a +size 2600464 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=5/t=0.8_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=5/t=0.8_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..aa05eaa24a6af27fb68624020c1bfcc82b47f838 --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/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,9834,9322,87,0.9601907730102539,0.45568603714371425,5,0.8 +induction_temperature,5383,5130,53,0.8690458536148071,0.7452405780520684,5,0.8 +molecular_weight,495,234,29,0.7556167244911194,0.6949397394298964,5,0.8 +strain,3834,2992,85,0.6668508052825928,1.0639544553035312,5,0.8 +inducer,11954,11203,207,0.5876430869102478,1.8078744445423622,5,0.8 +enzyme_name,12099,3017,352,0.565686047077179,1.0718656501818216,5,0.8 +expression_strain,8268,7707,142,0.5244877934455872,1.2539616928131845,5,0.8 +plasmid,8217,4689,290,0.4115038812160492,1.3039498712581388,5,0.8 +source_key,12179,11239,547,0.3626689314842224,1.3754450171087476,5,0.8 +desalting_process,5540,3412,270,0.23506753146648407,1.8209711657790666,5,0.8 +elution_buffer,5198,3567,265,0.1803000271320343,1.8331654618889868,5,0.8 +medium_name,7644,5634,318,0.17832325398921967,1.7811232412603306,5,0.8 +lysis_buffer,5625,4547,267,0.0718018040060997,2.050217670431301,5,0.8 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=5/t=0.9_ALL_FIELDS.csv.gz b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=5/t=0.9_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..de7c9a2e827eea1de1380c82835583f3a4711a49 --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=5/t=0.9_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d3bde7a61e7c99a7d8454af950a5764de70883ffa3e1455c92f15acd48a3b84 +size 2408388 diff --git a/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=5/t=0.9_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=5/t=0.9_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..9834d0774feed5b8b35dbf28bf8803e25e391f1a --- /dev/null +++ b/data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/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,9834,9240,92,0.9978997707366943,0.21953320491599146,5,0.9 +strain,3834,2679,73,0.9459735751152039,0.39179950772739236,5,0.9 +molecular_weight,495,158,22,0.9038535952568054,0.3972342218189741,5,0.9 +enzyme_name,12099,1235,156,0.881007730960846,0.46045357973716006,5,0.9 +induction_temperature,5383,4966,56,0.8538946509361267,0.3592699244893785,5,0.9 +desalting_process,5540,1491,176,0.8129881024360657,0.618707830724108,5,0.9 +source_key,12179,7368,865,0.8077046275138855,0.5997526894248214,5,0.9 +inducer,11954,10410,240,0.7828522324562073,1.0273891400402186,5,0.9 +plasmid,8217,3071,193,0.719433069229126,0.5946458125473094,5,0.9 +elution_buffer,5198,1674,180,0.6666745543479919,0.7578198532425844,5,0.9 +medium_name,7644,3711,264,0.5987329483032227,0.8383796973652534,5,0.9 +expression_strain,8268,7068,161,0.5721978545188904,0.6736243114029122,5,0.9 +lysis_buffer,5625,2520,256,0.48891958594322205,1.1455285845796572,5,0.9