diff --git a/.gitattributes b/.gitattributes index eb60aaca039f604b12d7b3428fa1dd750846d593..b1f054333dde4892680472b12649243f62750085 100644 --- a/.gitattributes +++ b/.gitattributes @@ -100,3 +100,28 @@ data/clustering/model=bioformers__bioformer-8L/min=5/t=0.6_ALL_FIELDS.csv.gz fil data/clustering/model=bioformers__bioformer-8L/min=5/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text data/clustering/model=bioformers__bioformer-8L/min=5/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text data/clustering/model=bioformers__bioformer-8L/min=5/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=10/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=10/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=10/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=10/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=10/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=2/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=2/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=2/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=2/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=2/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=20/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=20/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=20/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=20/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=20/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=30/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=30/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=30/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=30/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=30/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=5/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=5/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=5/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=5/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=5/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=10/t=0.5_ALL_FIELDS.csv.gz b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=10/t=0.5_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..a271bfa019393bc8a4eb5f3f02a576b180b6ee4b --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=10/t=0.5_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:513a9762f3817c33217b1a07484137c43a428cded889cba62c3fb23ad1f3982d +size 1563340 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=10/t=0.5_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=10/t=0.5_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..6fffcb2d15b1325e237208b25b634b23e34b7158 --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/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 +desalting_process,3720,3720,2,0.8788251876831055,0.32694485661171474,10,0.5 +elution_buffer,3530,3527,1,,,10,0.5 +enzyme_name,7975,7975,1,,,10,0.5 +expression_strain,5677,5677,1,,,10,0.5 +inducer,7889,7883,1,,,10,0.5 +induction_temperature,3656,3656,1,,,10,0.5 +lysis_buffer,3714,3714,1,,,10,0.5 +medium_name,4806,4806,1,,,10,0.5 +molecular_weight,295,295,1,,,10,0.5 +organism_source,6292,6292,1,,,10,0.5 +plasmid,5480,5480,1,,,10,0.5 +source_key,8021,8021,1,,,10,0.5 +strain,2444,2444,1,,,10,0.5 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=10/t=0.6_ALL_FIELDS.csv.gz b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=10/t=0.6_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..ae810c3e5ed6752845e72a3f8683a85c78fc32dd --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=10/t=0.6_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bbf81fd78d8f1cbf4b7ef211fab3cec2cc058e4846478861e1288cc178fd553 +size 1563662 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=10/t=0.6_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=10/t=0.6_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..560b782f692b978fa1410e05182edd7f775f3861 --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/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 +desalting_process,3720,3719,2,0.8745836019515991,0.4613648418938652,10,0.6 +elution_buffer,3530,3523,1,,,10,0.6 +enzyme_name,7975,7975,1,,,10,0.6 +expression_strain,5677,5677,1,,,10,0.6 +inducer,7889,7883,1,,,10,0.6 +induction_temperature,3656,3656,1,,,10,0.6 +lysis_buffer,3714,3705,1,,,10,0.6 +medium_name,4806,4803,1,,,10,0.6 +molecular_weight,295,295,1,,,10,0.6 +organism_source,6292,6292,1,,,10,0.6 +plasmid,5480,5480,1,,,10,0.6 +source_key,8021,8021,1,,,10,0.6 +strain,2444,2444,1,,,10,0.6 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=10/t=0.7_ALL_FIELDS.csv.gz b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=10/t=0.7_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..3c487872a1ba5c46e256335ec85a0f0c6cedc64c --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=10/t=0.7_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42f7884e5a3479c863dcac7a43ff0b678e110e987b904ea8051d51d4d0567eeb +size 1564555 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=10/t=0.7_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=10/t=0.7_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..0cb8786f421e298d47c8030959f045c026d363f5 --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/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 +lysis_buffer,3714,3709,2,0.8211964964866638,0.5488298847337124,10,0.7 +desalting_process,3720,3718,4,0.816301703453064,1.1229649544580025,10,0.7 +elution_buffer,3530,3525,2,0.7869019508361816,0.579096432376577,10,0.7 +medium_name,4806,4803,2,0.7526958584785461,0.4563609629370891,10,0.7 +enzyme_name,7975,7974,1,,,10,0.7 +expression_strain,5677,5677,1,,,10,0.7 +inducer,7889,7882,1,,,10,0.7 +induction_temperature,3656,3655,1,,,10,0.7 +molecular_weight,295,295,1,,,10,0.7 +organism_source,6292,6292,1,,,10,0.7 +plasmid,5480,5478,1,,,10,0.7 +source_key,8021,8021,1,,,10,0.7 +strain,2444,2444,1,,,10,0.7 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=10/t=0.8_ALL_FIELDS.csv.gz b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=10/t=0.8_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..0f486beafc6193d46be0c2b7b7690ccd07bd797b --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=10/t=0.8_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09c24a6ba84db21e857b1e153aba5bfbcbdbd9e27881cf51671c0a14d702d4ed +size 1565816 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=10/t=0.8_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=10/t=0.8_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..48eb6c1e1efcd72a432721749a08e48e65c4ef03 --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/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 +induction_temperature,3656,3655,2,0.8691748380661011,0.4757545827342129,10,0.8 +lysis_buffer,3714,3704,3,0.8055402636528015,0.44524319910912186,10,0.8 +desalting_process,3720,3717,6,0.7704578042030334,1.2159110251474845,10,0.8 +elution_buffer,3530,3522,4,0.6940657496452332,0.8532043705317911,10,0.8 +medium_name,4806,4802,4,0.6845597624778748,0.983759543218852,10,0.8 +enzyme_name,7975,7965,1,,,10,0.8 +expression_strain,5677,5676,1,,,10,0.8 +inducer,7889,7878,1,,,10,0.8 +molecular_weight,295,295,1,,,10,0.8 +organism_source,6292,6291,1,,,10,0.8 +plasmid,5480,5477,1,,,10,0.8 +source_key,8021,8021,1,,,10,0.8 +strain,2444,2443,1,,,10,0.8 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=10/t=0.9_ALL_FIELDS.csv.gz b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=10/t=0.9_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..6d5855e87f55918a57983b662bb9afcb77aa912f --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=10/t=0.9_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7724dc75ee91980bad47598dc16b204cfdf3f90b768d4831b2ad618911c883d1 +size 1581109 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=10/t=0.9_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=10/t=0.9_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..17325a7aab9e2e0e51c647ea7b42b8e0406ec4ce --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/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 +induction_temperature,3656,3652,5,0.8086934685707092,1.0280707039053247,10,0.9 +expression_strain,5677,5668,3,0.6822381615638733,0.699462771299864,10,0.9 +plasmid,5480,5467,3,0.6482812762260437,0.7840006829081471,10,0.9 +organism_source,6292,6291,4,0.5304650068283081,1.4035409376991355,10,0.9 +lysis_buffer,3714,3700,8,0.38641488552093506,1.4458285488360456,10,0.9 +desalting_process,3720,3710,13,0.36983489990234375,2.5601425756037557,10,0.9 +enzyme_name,7975,7968,7,0.36080387234687805,1.9962244744311233,10,0.9 +elution_buffer,3530,3520,14,0.22809025645256042,2.0222147589390413,10,0.9 +medium_name,4806,4798,17,0.21437640488147736,2.4395763183588346,10,0.9 +inducer,7889,7877,4,0.19038663804531097,1.0384674090815986,10,0.9 +molecular_weight,295,292,1,,,10,0.9 +source_key,8021,8021,1,,,10,0.9 +strain,2444,2434,1,,,10,0.9 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=2/t=0.5_ALL_FIELDS.csv.gz b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=2/t=0.5_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..37e553848fd539a8ca91748a4fa7ad65ac3ab631 --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=2/t=0.5_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99c8cecb4d8b1bd25d08048d18976b03f178846743d5064ffd004e220aa249b6 +size 1563520 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=2/t=0.5_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=2/t=0.5_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..31b04081bfb10b5fb5c28253220902f1bc65b9d9 --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/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 +elution_buffer,3530,3530,2,0.8792910575866699,0.44481611387376074,2,0.5 +desalting_process,3720,3720,2,0.8788251876831055,0.32694485661171474,2,0.5 +inducer,7889,7889,2,0.8503222465515137,0.2637742658188704,2,0.5 +enzyme_name,7975,7975,1,,,2,0.5 +expression_strain,5677,5677,1,,,2,0.5 +induction_temperature,3656,3656,1,,,2,0.5 +lysis_buffer,3714,3714,1,,,2,0.5 +medium_name,4806,4806,1,,,2,0.5 +molecular_weight,295,295,1,,,2,0.5 +organism_source,6292,6292,1,,,2,0.5 +plasmid,5480,5480,1,,,2,0.5 +source_key,8021,8021,1,,,2,0.5 +strain,2444,2444,1,,,2,0.5 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=2/t=0.6_ALL_FIELDS.csv.gz b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=2/t=0.6_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..cfc0d7bcbf5a2af78565b64e187931a40c9c5d18 --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=2/t=0.6_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5af626f88895afa6237dbe45dbdae7fa0cf3515d2aff42e21d4ee71ab6c45104 +size 1564207 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=2/t=0.6_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=2/t=0.6_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..8577b7c215584f06381e5ae617557fd495f50626 --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/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 +lysis_buffer,3714,3714,2,0.8806324601173401,0.3936388353819188,2,0.6 +desalting_process,3720,3719,2,0.8745836019515991,0.4613648418938652,2,0.6 +inducer,7889,7889,2,0.8503222465515137,0.2637742658188704,2,0.6 +medium_name,4806,4805,2,0.8354217410087585,1.4161783537710249,2,0.6 +elution_buffer,3530,3530,4,0.833047091960907,1.1868684020509916,2,0.6 +enzyme_name,7975,7975,1,,,2,0.6 +expression_strain,5677,5677,1,,,2,0.6 +induction_temperature,3656,3656,1,,,2,0.6 +molecular_weight,295,295,1,,,2,0.6 +organism_source,6292,6292,1,,,2,0.6 +plasmid,5480,5480,1,,,2,0.6 +source_key,8021,8021,1,,,2,0.6 +strain,2444,2444,1,,,2,0.6 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=2/t=0.7_ALL_FIELDS.csv.gz b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=2/t=0.7_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..9b33a7e3d6b565ebb280466460019787744e9c9a --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=2/t=0.7_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c264c5b36d5273f8850f01f056266227d5e08dec948ef6844149b530db76be3 +size 1564909 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=2/t=0.7_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=2/t=0.7_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..870d96e91eccd4b350f39afe90eb5f721f380040 --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/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 +plasmid,5480,5480,2,0.915432870388031,0.19415939524171427,2,0.7 +inducer,7889,7888,2,0.8503597378730774,0.263748629939348,2,0.7 +desalting_process,3720,3719,11,0.8130825757980347,1.5616976510345681,2,0.7 +lysis_buffer,3714,3714,4,0.7766733765602112,0.6353328162586326,2,0.7 +medium_name,4806,4804,3,0.713419497013092,1.4079525854875765,2,0.7 +elution_buffer,3530,3529,5,0.6628036499023438,0.9329214162393397,2,0.7 +enzyme_name,7975,7974,1,,,2,0.7 +expression_strain,5677,5677,1,,,2,0.7 +induction_temperature,3656,3655,1,,,2,0.7 +molecular_weight,295,295,1,,,2,0.7 +organism_source,6292,6292,1,,,2,0.7 +source_key,8021,8021,1,,,2,0.7 +strain,2444,2444,1,,,2,0.7 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=2/t=0.8_ALL_FIELDS.csv.gz b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=2/t=0.8_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..33fb0257021967de2e1233b29d0fef1ca13d69ed --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=2/t=0.8_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f42541a798f5cb931d8d42ac4f1890fad5ee668ee89325ac01fe8177539fb6bc +size 1566626 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=2/t=0.8_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=2/t=0.8_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..0e2af99d36ac0735f6cc8dd1152b5780da0b839c --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/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 +plasmid,5480,5479,2,0.9155323505401611,0.19408247138542226,2,0.8 +induction_temperature,3656,3655,2,0.8691748380661011,0.4757545827342129,2,0.8 +enzyme_name,7975,7973,5,0.7250778675079346,1.709757453674736,2,0.8 +lysis_buffer,3714,3713,8,0.7195822596549988,0.5859150125884109,2,0.8 +desalting_process,3720,3719,18,0.6896914839744568,1.5744086276947111,2,0.8 +elution_buffer,3530,3530,14,0.5306541919708252,1.0595589868233841,2,0.8 +medium_name,4806,4805,9,0.5210984945297241,1.4946206330399565,2,0.8 +inducer,7889,7888,4,0.45318031311035156,0.6350327403873097,2,0.8 +expression_strain,5677,5676,1,,,2,0.8 +molecular_weight,295,295,1,,,2,0.8 +organism_source,6292,6291,1,,,2,0.8 +source_key,8021,8021,1,,,2,0.8 +strain,2444,2443,1,,,2,0.8 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=2/t=0.9_ALL_FIELDS.csv.gz b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=2/t=0.9_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..4ed0337d703a29b9cfaf32b4ef03c83ab7fcf973 --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=2/t=0.9_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e91b0ee143d25d311323a90fb1aecfca92db42c2e1dff3a67012a18c5c1d4e75 +size 1580749 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=2/t=0.9_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=2/t=0.9_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..cabe0887b936854c1dd5e8910b880c4da7f6b7e5 --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/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 +molecular_weight,295,295,2,0.8208003044128418,0.5787193554050322,2,0.9 +induction_temperature,3656,3654,13,0.7317935228347778,1.0625015025866578,2,0.9 +strain,2444,2442,4,0.6633882522583008,1.0660405653605156,2,0.9 +expression_strain,5677,5675,7,0.6499571800231934,0.9568541574965043,2,0.9 +plasmid,5480,5480,15,0.523720383644104,1.573519396993879,2,0.9 +organism_source,6292,6291,9,0.45336082577705383,1.6938654267524695,2,0.9 +desalting_process,3720,3719,39,0.2843758463859558,1.6991489911678785,2,0.9 +lysis_buffer,3714,3713,25,0.2541319727897644,1.1128311955379044,2,0.9 +enzyme_name,7975,7973,22,0.2349632978439331,1.7377421196901195,2,0.9 +elution_buffer,3530,3528,39,0.20281639695167542,1.45562300219501,2,0.9 +medium_name,4806,4802,49,0.1351454108953476,1.571778268802611,2,0.9 +inducer,7889,7888,11,-0.6601330637931824,0.8794936955604605,2,0.9 +source_key,8021,8021,1,,,2,0.9 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=20/t=0.5_ALL_FIELDS.csv.gz b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=20/t=0.5_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..fa6a1eb6ad8cc9f03fb24f2e4e2c862070345ebf --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=20/t=0.5_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6646df24d9c2d3175b13ea3236eb7de6f52b7baeb2ef742b23aded24428deda3 +size 1563331 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=20/t=0.5_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=20/t=0.5_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..e49afbab6735a04107258ee4a91669bc8c1ec0b3 --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/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 +desalting_process,3720,3710,1,,,20,0.5 +elution_buffer,3530,3527,1,,,20,0.5 +enzyme_name,7975,7975,1,,,20,0.5 +expression_strain,5677,5677,1,,,20,0.5 +inducer,7889,7883,1,,,20,0.5 +induction_temperature,3656,3656,1,,,20,0.5 +lysis_buffer,3714,3714,1,,,20,0.5 +medium_name,4806,4806,1,,,20,0.5 +molecular_weight,295,295,1,,,20,0.5 +organism_source,6292,6292,1,,,20,0.5 +plasmid,5480,5480,1,,,20,0.5 +source_key,8021,8021,1,,,20,0.5 +strain,2444,2444,1,,,20,0.5 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=20/t=0.6_ALL_FIELDS.csv.gz b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=20/t=0.6_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..68c42d369b4532bcb4cb4928f5d0b248aa87dfa4 --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=20/t=0.6_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da821b09fee4ca12bdca002e6b03372e6a58962933e7e9104e1aa50ce4ec73dc +size 1563662 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=20/t=0.6_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=20/t=0.6_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..fb7373d803cfe3375fc503865e82c72e4c1e0bff --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/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 +desalting_process,3720,3719,2,0.8745836019515991,0.4613648418938652,20,0.6 +elution_buffer,3530,3523,1,,,20,0.6 +enzyme_name,7975,7975,1,,,20,0.6 +expression_strain,5677,5677,1,,,20,0.6 +inducer,7889,7883,1,,,20,0.6 +induction_temperature,3656,3656,1,,,20,0.6 +lysis_buffer,3714,3705,1,,,20,0.6 +medium_name,4806,4803,1,,,20,0.6 +molecular_weight,295,295,1,,,20,0.6 +organism_source,6292,6292,1,,,20,0.6 +plasmid,5480,5480,1,,,20,0.6 +source_key,8021,8021,1,,,20,0.6 +strain,2444,2444,1,,,20,0.6 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=20/t=0.7_ALL_FIELDS.csv.gz b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=20/t=0.7_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..7ea1f7d16893026d5069cdcf1d24062b6d3e7931 --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=20/t=0.7_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:635f2ac4618df19cfa67fdb96283df9b512631692a510e3631b066e6b75e650e +size 1564531 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=20/t=0.7_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=20/t=0.7_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..aa4eb33095c062a2f70ba191d3a9d217216c0085 --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/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 +desalting_process,3720,3719,3,0.8212870955467224,0.9383764949385668,20,0.7 +elution_buffer,3530,3525,2,0.7869019508361816,0.579096432376577,20,0.7 +enzyme_name,7975,7974,1,,,20,0.7 +expression_strain,5677,5677,1,,,20,0.7 +inducer,7889,7882,1,,,20,0.7 +induction_temperature,3656,3655,1,,,20,0.7 +lysis_buffer,3714,3697,1,,,20,0.7 +medium_name,4806,4790,1,,,20,0.7 +molecular_weight,295,295,1,,,20,0.7 +organism_source,6292,6292,1,,,20,0.7 +plasmid,5480,5478,1,,,20,0.7 +source_key,8021,8021,1,,,20,0.7 +strain,2444,2444,1,,,20,0.7 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=20/t=0.8_ALL_FIELDS.csv.gz b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=20/t=0.8_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..b895db873b020ee9e2e3a011d3a23f324403a356 --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=20/t=0.8_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3be1935362e36fa6f1aa5542360ddd1594cf032f0ff48371569baa864dbba83a +size 1566162 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=20/t=0.8_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=20/t=0.8_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..424bfbe604b0744686542df0880d88a80be3f534 --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/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 +induction_temperature,3656,3655,2,0.8691748380661011,0.4757545827342129,20,0.8 +lysis_buffer,3714,3693,2,0.8465916514396667,0.26676832280696755,20,0.8 +desalting_process,3720,3717,4,0.7915120720863342,0.7802010269392264,20,0.8 +elution_buffer,3530,3521,3,0.7238301038742065,0.5474480436027243,20,0.8 +medium_name,4806,4801,3,0.6965180039405823,0.8222198481818616,20,0.8 +enzyme_name,7975,7965,1,,,20,0.8 +expression_strain,5677,5676,1,,,20,0.8 +inducer,7889,7878,1,,,20,0.8 +molecular_weight,295,295,1,,,20,0.8 +organism_source,6292,6291,1,,,20,0.8 +plasmid,5480,5477,1,,,20,0.8 +source_key,8021,8021,1,,,20,0.8 +strain,2444,2443,1,,,20,0.8 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=20/t=0.9_ALL_FIELDS.csv.gz b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=20/t=0.9_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..83fa6d53d0f0c32cbdaedc7b2683a1f4856350cb --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=20/t=0.9_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5419a12417029461bbb3286236a03529e1958b8c73f1fb10d644b8cb2f4c534d +size 1578370 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=20/t=0.9_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=20/t=0.9_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..9f1006c1b85fbcaa525172471bb3f506f3ef239b --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/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 +induction_temperature,3656,3635,3,0.8374854326248169,0.5420911725578342,20,0.9 +organism_source,6292,6280,2,0.7457679510116577,0.5979571708958273,20,0.9 +lysis_buffer,3714,3690,5,0.4458244740962982,1.2043708857254256,20,0.9 +desalting_process,3720,3709,8,0.4315110743045807,1.9100082672239802,20,0.9 +enzyme_name,7975,7961,4,0.41551539301872253,1.9535357949136247,20,0.9 +elution_buffer,3530,3490,7,0.30675801634788513,1.9956534281630398,20,0.9 +inducer,7889,7857,2,0.26399827003479004,1.0579343831647887,20,0.9 +medium_name,4806,4786,10,0.2513596713542938,2.453192151054448,20,0.9 +expression_strain,5677,5647,1,,,20,0.9 +molecular_weight,295,292,1,,,20,0.9 +plasmid,5480,5445,1,,,20,0.9 +source_key,8021,8021,1,,,20,0.9 +strain,2444,2434,1,,,20,0.9 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=30/t=0.5_ALL_FIELDS.csv.gz b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=30/t=0.5_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..37e726d21356e098679be3eb0270a688f3f1a6fe --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=30/t=0.5_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51c57e710a5eabc1521bbfb86e41658dabd2d06877fecf265d4fec5aeac38fec +size 1563331 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=30/t=0.5_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=30/t=0.5_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..4309c23304119f7aafc737da8b4700dc0942a4d1 --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/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 +desalting_process,3720,3710,1,,,30,0.5 +elution_buffer,3530,3527,1,,,30,0.5 +enzyme_name,7975,7975,1,,,30,0.5 +expression_strain,5677,5677,1,,,30,0.5 +inducer,7889,7883,1,,,30,0.5 +induction_temperature,3656,3656,1,,,30,0.5 +lysis_buffer,3714,3714,1,,,30,0.5 +medium_name,4806,4806,1,,,30,0.5 +molecular_weight,295,295,1,,,30,0.5 +organism_source,6292,6292,1,,,30,0.5 +plasmid,5480,5480,1,,,30,0.5 +source_key,8021,8021,1,,,30,0.5 +strain,2444,2444,1,,,30,0.5 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=30/t=0.6_ALL_FIELDS.csv.gz b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=30/t=0.6_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..a23b66f0a42c71f1f588bb0e2f64b9682e96c88a --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=30/t=0.6_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:903f6eb425a18960941a7aa1ab0dd49669eeaf09a93ca12bb8cd9d0fa3a6287c +size 1563437 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=30/t=0.6_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=30/t=0.6_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..70ab65fe2e0bd325b6381068d3224a2952fe50ce --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/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 +desalting_process,3720,3694,1,,,30,0.6 +elution_buffer,3530,3523,1,,,30,0.6 +enzyme_name,7975,7975,1,,,30,0.6 +expression_strain,5677,5677,1,,,30,0.6 +inducer,7889,7883,1,,,30,0.6 +induction_temperature,3656,3656,1,,,30,0.6 +lysis_buffer,3714,3705,1,,,30,0.6 +medium_name,4806,4803,1,,,30,0.6 +molecular_weight,295,295,1,,,30,0.6 +organism_source,6292,6292,1,,,30,0.6 +plasmid,5480,5480,1,,,30,0.6 +source_key,8021,8021,1,,,30,0.6 +strain,2444,2444,1,,,30,0.6 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=30/t=0.7_ALL_FIELDS.csv.gz b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=30/t=0.7_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..b9e7dafc82b4967fbc62c034d8a42f06aa05b561 --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=30/t=0.7_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:074f9f1c39a1f31f59a36bc6c811434fd6f95d5c846662952b5b3b2e6b508d1c +size 1564444 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=30/t=0.7_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=30/t=0.7_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..f739311aed57ff6ecd06622b1dde3de792c82aa8 --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/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 +desalting_process,3720,3709,2,0.8478197455406189,0.5635797647378765,30,0.7 +elution_buffer,3530,3504,1,,,30,0.7 +enzyme_name,7975,7974,1,,,30,0.7 +expression_strain,5677,5677,1,,,30,0.7 +inducer,7889,7882,1,,,30,0.7 +induction_temperature,3656,3655,1,,,30,0.7 +lysis_buffer,3714,3697,1,,,30,0.7 +medium_name,4806,4790,1,,,30,0.7 +molecular_weight,295,295,1,,,30,0.7 +organism_source,6292,6292,1,,,30,0.7 +plasmid,5480,5478,1,,,30,0.7 +source_key,8021,8021,1,,,30,0.7 +strain,2444,2444,1,,,30,0.7 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=30/t=0.8_ALL_FIELDS.csv.gz b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=30/t=0.8_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..99fb18105b079a2fba7feb2ead38be9b1f47a967 --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=30/t=0.8_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:048c377780adaa360c8622546970d349eca8c0a01e211f4dad1f59adbc46742b +size 1564598 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=30/t=0.8_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=30/t=0.8_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..6bdbe983306acd7d75bfaf360f5bd1faa37ae667 --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/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 +desalting_process,3720,3707,3,0.8040115833282471,0.47464063306159215,30,0.8 +elution_buffer,3530,3480,1,,,30,0.8 +enzyme_name,7975,7965,1,,,30,0.8 +expression_strain,5677,5676,1,,,30,0.8 +inducer,7889,7878,1,,,30,0.8 +induction_temperature,3656,3632,1,,,30,0.8 +lysis_buffer,3714,3671,1,,,30,0.8 +medium_name,4806,4754,1,,,30,0.8 +molecular_weight,295,295,1,,,30,0.8 +organism_source,6292,6291,1,,,30,0.8 +plasmid,5480,5477,1,,,30,0.8 +source_key,8021,8021,1,,,30,0.8 +strain,2444,2443,1,,,30,0.8 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=30/t=0.9_ALL_FIELDS.csv.gz b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=30/t=0.9_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..e4710623033e96c6e0ba0f860c7c40f84be01ed8 --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=30/t=0.9_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:903aa73be0e08d5913aaa74f4c56fb2e0c8bdc279d20dcb5a312f9870a774b17 +size 1576390 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=30/t=0.9_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=30/t=0.9_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..e790d88248ccc1653540ea754a373ef382cc1ab4 --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/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 +induction_temperature,3656,3642,3,0.8519780039787292,0.5133759606798728,30,0.9 +lysis_buffer,3714,3638,2,0.5913897752761841,1.081265668451442,30,0.9 +desalting_process,3720,3676,5,0.5525792837142944,1.5523264596629696,30,0.9 +enzyme_name,7975,7927,2,0.5090072751045227,0.7869680823396571,30,0.9 +elution_buffer,3530,3496,6,0.3129810094833374,1.7492070292575785,30,0.9 +medium_name,4806,4769,7,0.2724228799343109,1.9800312288739674,30,0.9 +inducer,7889,7857,2,0.26399827003479004,1.0579343831647887,30,0.9 +expression_strain,5677,5647,1,,,30,0.9 +molecular_weight,295,292,1,,,30,0.9 +organism_source,6292,6258,1,,,30,0.9 +plasmid,5480,5445,1,,,30,0.9 +source_key,8021,8021,1,,,30,0.9 +strain,2444,2434,1,,,30,0.9 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=5/t=0.5_ALL_FIELDS.csv.gz b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=5/t=0.5_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..3df1609fc42b5b355707d035610f3e980cbe2db1 --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=5/t=0.5_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e129b782e751175f5145f5c0396235a238f3518519ae20d661fb4d1ef123e7f +size 1563375 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=5/t=0.5_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=5/t=0.5_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..ea54c889313838b13a2947ec70c864e26d6b5866 --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/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 +desalting_process,3720,3720,2,0.8788251876831055,0.32694485661171474,5,0.5 +inducer,7889,7889,2,0.8503222465515137,0.2637742658188704,5,0.5 +elution_buffer,3530,3527,1,,,5,0.5 +enzyme_name,7975,7975,1,,,5,0.5 +expression_strain,5677,5677,1,,,5,0.5 +induction_temperature,3656,3656,1,,,5,0.5 +lysis_buffer,3714,3714,1,,,5,0.5 +medium_name,4806,4806,1,,,5,0.5 +molecular_weight,295,295,1,,,5,0.5 +organism_source,6292,6292,1,,,5,0.5 +plasmid,5480,5480,1,,,5,0.5 +source_key,8021,8021,1,,,5,0.5 +strain,2444,2444,1,,,5,0.5 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=5/t=0.6_ALL_FIELDS.csv.gz b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=5/t=0.6_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..bfff7789234bdde6f7e25d08fdd9d0fcdd90aac5 --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=5/t=0.6_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2a76bc0de690955637ff4dbaf0b99fdda0728e529871ae65eeb518779159c79 +size 1564154 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=5/t=0.6_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=5/t=0.6_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..573ee21168743695b8b44fc6875dc08b7970dc2a --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/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 +lysis_buffer,3714,3714,2,0.8806324601173401,0.3936388353819188,5,0.6 +desalting_process,3720,3719,2,0.8745836019515991,0.4613648418938652,5,0.6 +elution_buffer,3530,3528,2,0.8544107675552368,0.8248842193717606,5,0.6 +inducer,7889,7889,2,0.8503222465515137,0.2637742658188704,5,0.6 +enzyme_name,7975,7975,1,,,5,0.6 +expression_strain,5677,5677,1,,,5,0.6 +induction_temperature,3656,3656,1,,,5,0.6 +medium_name,4806,4803,1,,,5,0.6 +molecular_weight,295,295,1,,,5,0.6 +organism_source,6292,6292,1,,,5,0.6 +plasmid,5480,5480,1,,,5,0.6 +source_key,8021,8021,1,,,5,0.6 +strain,2444,2444,1,,,5,0.6 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=5/t=0.7_ALL_FIELDS.csv.gz b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=5/t=0.7_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..9a2e66c85ab6a252cdc3d108838fcab713bb03fc --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=5/t=0.7_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9ab80857c0454cdce518210372f0381d298f1ec1b193d05746fec5e9f3649ea +size 1564925 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=5/t=0.7_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=5/t=0.7_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..cafe50616dced85bfc8fe20a2f012dfceaa4b44c --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/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 +inducer,7889,7888,2,0.8503597378730774,0.263748629939348,5,0.7 +desalting_process,3720,3719,6,0.813032329082489,2.3827400948441695,5,0.7 +lysis_buffer,3714,3714,3,0.7767648696899414,0.5740359018015954,5,0.7 +elution_buffer,3530,3530,3,0.7710232734680176,0.5370489860484522,5,0.7 +medium_name,4806,4803,2,0.7526958584785461,0.4563609629370891,5,0.7 +enzyme_name,7975,7974,1,,,5,0.7 +expression_strain,5677,5677,1,,,5,0.7 +induction_temperature,3656,3655,1,,,5,0.7 +molecular_weight,295,295,1,,,5,0.7 +organism_source,6292,6292,1,,,5,0.7 +plasmid,5480,5478,1,,,5,0.7 +source_key,8021,8021,1,,,5,0.7 +strain,2444,2444,1,,,5,0.7 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=5/t=0.8_ALL_FIELDS.csv.gz b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=5/t=0.8_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..de341664b67d5b4b86c41675bcc59b5b678effd2 --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=5/t=0.8_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfbf5e1ac8be6c2dc0eb52a2aa7d91c5d2026618b21e451db130ab3181e5e457 +size 1566556 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=5/t=0.8_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=5/t=0.8_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..828a67d6445cd333304de6c27ef81f4a9e36e756 --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/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 +induction_temperature,3656,3655,2,0.8691748380661011,0.4757545827342129,5,0.8 +inducer,7889,7884,2,0.8510527610778809,0.2634310239361656,5,0.8 +enzyme_name,7975,7970,2,0.756263017654419,0.6801263646371739,5,0.8 +desalting_process,3720,3717,10,0.754392683506012,2.0968164704385255,5,0.8 +lysis_buffer,3714,3714,6,0.725355863571167,0.6460456091979208,5,0.8 +elution_buffer,3530,3525,6,0.6276204586029053,1.0165608568476268,5,0.8 +medium_name,4806,4803,6,0.5776232481002808,1.2922019600394454,5,0.8 +expression_strain,5677,5676,1,,,5,0.8 +molecular_weight,295,295,1,,,5,0.8 +organism_source,6292,6291,1,,,5,0.8 +plasmid,5480,5477,1,,,5,0.8 +source_key,8021,8021,1,,,5,0.8 +strain,2444,2443,1,,,5,0.8 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=5/t=0.9_ALL_FIELDS.csv.gz b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=5/t=0.9_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..0a2eace00ab2efae189215b5de5cb8a3f29ddee6 --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=5/t=0.9_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ec9438eda2efecbd240582bb7af19e1892b8ca33f1680b521bd4138ee3d8026 +size 1581999 diff --git a/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=5/t=0.9_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/min=5/t=0.9_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..09512d374046facdd385e90390fc046ca536a31a --- /dev/null +++ b/data/clustering/model=dmis-lab__biobert-large-cased-v1.1-mnli/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 +induction_temperature,3656,3654,7,0.7670583128929138,1.0466952177139546,5,0.9 +strain,2444,2440,2,0.7114551067352295,0.6282433978775203,5,0.9 +expression_strain,5677,5671,4,0.6758527159690857,0.6540016353153453,5,0.9 +plasmid,5480,5473,6,0.5978834629058838,1.5732382194107164,5,0.9 +organism_source,6292,6290,6,0.5193297266960144,1.4703393288315292,5,0.9 +lysis_buffer,3714,3711,15,0.3525126278400421,1.3712845147047545,5,0.9 +desalting_process,3720,3717,22,0.3231964707374573,2.1883937961032824,5,0.9 +enzyme_name,7975,7971,11,0.30487626791000366,1.7280390175055909,5,0.9 +elution_buffer,3530,3524,21,0.22199414670467377,1.6945910123705485,5,0.9 +medium_name,4806,4801,28,0.19696331024169922,2.083703898808138,5,0.9 +inducer,7889,7881,6,0.15044039487838745,1.0950381312295843,5,0.9 +molecular_weight,295,292,1,,,5,0.9 +source_key,8021,8021,1,,,5,0.9