diff --git a/.gitattributes b/.gitattributes index 2062394199d842ee66b47835ae8771915b8674e0..eb60aaca039f604b12d7b3428fa1dd750846d593 100644 --- a/.gitattributes +++ b/.gitattributes @@ -75,3 +75,28 @@ data/clustering/model=allenai__scibert_scivocab_uncased/min=5/t=0.6_ALL_FIELDS.c data/clustering/model=allenai__scibert_scivocab_uncased/min=5/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text data/clustering/model=allenai__scibert_scivocab_uncased/min=5/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text data/clustering/model=allenai__scibert_scivocab_uncased/min=5/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=bioformers__bioformer-8L/min=10/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=bioformers__bioformer-8L/min=10/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=bioformers__bioformer-8L/min=10/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=bioformers__bioformer-8L/min=10/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=bioformers__bioformer-8L/min=10/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=bioformers__bioformer-8L/min=2/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=bioformers__bioformer-8L/min=2/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=bioformers__bioformer-8L/min=2/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=bioformers__bioformer-8L/min=2/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=bioformers__bioformer-8L/min=2/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=bioformers__bioformer-8L/min=20/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=bioformers__bioformer-8L/min=20/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=bioformers__bioformer-8L/min=20/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=bioformers__bioformer-8L/min=20/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=bioformers__bioformer-8L/min=20/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=bioformers__bioformer-8L/min=30/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=bioformers__bioformer-8L/min=30/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=bioformers__bioformer-8L/min=30/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=bioformers__bioformer-8L/min=30/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=bioformers__bioformer-8L/min=30/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=bioformers__bioformer-8L/min=5/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=bioformers__bioformer-8L/min=5/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +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 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=10/t=0.5_ALL_FIELDS.csv.gz b/data/clustering/model=bioformers__bioformer-8L/min=10/t=0.5_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..cefb105385b4dfc9899c5ef43ed3c228e83be89c --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/min=10/t=0.5_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f26dc3820f4e96f239d1afee19242edf9973f9ee3d5dd864640dc11247250d1f +size 1560161 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=10/t=0.5_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=bioformers__bioformer-8L/min=10/t=0.5_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..7c5388d726481b7a6bc6043d7f1a08cd9b875fd6 --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/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,3720,3720,1,,,10,0.5 +elution_buffer,3530,3530,1,,,10,0.5 +enzyme_name,7975,7972,1,,,10,0.5 +expression_strain,5677,5677,1,,,10,0.5 +inducer,7889,7889,1,,,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,6292,6291,1,,,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=bioformers__bioformer-8L/min=10/t=0.6_ALL_FIELDS.csv.gz b/data/clustering/model=bioformers__bioformer-8L/min=10/t=0.6_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..bd73c5e14c7623815240b894095c92230465f962 --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/min=10/t=0.6_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc1de6af23225d8b2f3123d82e204d6361d0f5e77e49c1f5a22c467a9828c328 +size 1563112 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=10/t=0.6_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=bioformers__bioformer-8L/min=10/t=0.6_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..999b95a41794fc810a6f32e2eff114bce723d451 --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/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 +lysis_buffer,3714,3713,2,0.7149391174316406,0.38312277129626476,10,0.6 +elution_buffer,3530,3525,2,0.6416854858398438,0.5236173353159038,10,0.6 +desalting_process,3720,3719,3,0.6262091994285583,0.5297506235986552,10,0.6 +induction_temperature,3656,3656,2,0.5875009298324585,1.3215446098942993,10,0.6 +inducer,7889,7884,2,0.41284435987472534,1.5155270752690744,10,0.6 +medium_name,4806,4799,4,0.3943176865577698,1.4343709036874446,10,0.6 +organism_source,6292,6287,3,0.3635418117046356,1.945829319821246,10,0.6 +enzyme_name,7975,7970,8,0.22373785078525543,3.2525240256027077,10,0.6 +expression_strain,5677,5672,1,,,10,0.6 +molecular_weight,295,295,1,,,10,0.6 +plasmid,5480,5478,1,,,10,0.6 +source_key,8021,8021,1,,,10,0.6 +strain,2444,2434,1,,,10,0.6 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=10/t=0.7_ALL_FIELDS.csv.gz b/data/clustering/model=bioformers__bioformer-8L/min=10/t=0.7_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..a17568f4788bf1618e22ca9d71d75caa8b226aab --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/min=10/t=0.7_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ab7b5eccaa8bcb0f91157c27d2ff9f23d361ae9b6f0fa5e6688a1e95c7e5963 +size 1579099 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=10/t=0.7_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=bioformers__bioformer-8L/min=10/t=0.7_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..4d686b35f024778e355062bde748cff3048ef398 --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/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,3714,3708,3,0.6311509013175964,1.0142492631865714,10,0.7 +induction_temperature,3656,3650,3,0.5572892427444458,1.3853928523499535,10,0.7 +expression_strain,5677,5667,5,0.5372771620750427,2.1938571882793543,10,0.7 +strain,2444,2430,6,0.39097705483436584,2.1538333038111612,10,0.7 +desalting_process,3720,3716,8,0.3220551013946533,2.3617481821345905,10,0.7 +elution_buffer,3530,3514,5,0.26606887578964233,1.4048616859839291,10,0.7 +plasmid,5480,5469,9,0.21868889033794403,2.209572053491067,10,0.7 +organism_source,6292,6263,15,0.1729055494070053,2.138371738543674,10,0.7 +medium_name,4806,4778,17,0.1461424082517624,2.415804187672867,10,0.7 +inducer,7889,7870,8,0.12644076347351074,2.631917361365306,10,0.7 +enzyme_name,7975,7907,38,0.015337507240474224,3.7870953314569853,10,0.7 +molecular_weight,295,295,1,,,10,0.7 +source_key,8021,8021,1,,,10,0.7 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=10/t=0.8_ALL_FIELDS.csv.gz b/data/clustering/model=bioformers__bioformer-8L/min=10/t=0.8_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..4cc96dfaf5a4156b37ea3ecfbbbc8323fa3073af --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/min=10/t=0.8_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4728f2aeb8d06254e3a8a79e4c2bb43be717b7e1ec149cbce19d692cf7a04765 +size 1626309 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=10/t=0.8_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=bioformers__bioformer-8L/min=10/t=0.8_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..12935b464a76bea3528801a891c5401776b99049 --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/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 +inducer,7889,7821,18,0.6738172769546509,2.3022584754860076,10,0.8 +source_key,8021,8010,3,0.46841925382614136,1.2742968926574407,10,0.8 +organism_source,6292,6134,36,0.4610093832015991,1.7430625433142568,10,0.8 +induction_temperature,3656,3632,12,0.4150533676147461,1.9234551784234342,10,0.8 +molecular_weight,295,286,3,0.3415808379650116,1.9982724618614054,10,0.8 +strain,2444,2373,23,0.3382608890533447,2.3172894226113887,10,0.8 +lysis_buffer,3714,3659,16,0.31946879625320435,2.1681982275092864,10,0.8 +desalting_process,3720,3669,35,0.17197661101818085,2.5277178670047142,10,0.8 +elution_buffer,3530,3476,26,0.16649818420410156,2.15905747547545,10,0.8 +plasmid,5480,5398,50,0.026219286024570465,3.1059834697942508,10,0.8 +medium_name,4806,4660,47,-0.018203629180788994,2.4726461380532747,10,0.8 +enzyme_name,7975,7372,118,-0.07867546379566193,3.6446685311558578,10,0.8 +expression_strain,5677,5612,18,-0.10762932151556015,1.5080693369770428,10,0.8 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=10/t=0.9_ALL_FIELDS.csv.gz b/data/clustering/model=bioformers__bioformer-8L/min=10/t=0.9_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..a00b2c8d427acc70973b146ec51fdeba89d5fe1a --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/min=10/t=0.9_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd89f38c41ecc24dedd28aa4d37bd7971a946347e7df2077de99eaecd7107dec +size 1644685 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=10/t=0.9_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=bioformers__bioformer-8L/min=10/t=0.9_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..6c2d45c1332d2c9a92e749b8356833c04db97d8d --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/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,6292,5712,42,0.9730017781257629,0.5937010264366096,10,0.9 +strain,2444,1965,25,0.8137739896774292,1.2408271591230229,10,0.9 +inducer,7889,7546,53,0.6193517446517944,2.222284215351568,10,0.9 +molecular_weight,295,210,6,0.419859379529953,1.2243215410704973,10,0.9 +induction_temperature,3656,3452,16,0.3239579498767853,1.2556622405536362,10,0.9 +expression_strain,5677,5421,34,0.2611028850078583,1.670109702550024,10,0.9 +enzyme_name,7975,2906,124,0.23763494193553925,2.345245458566267,10,0.9 +medium_name,4806,3827,97,0.12278519570827484,2.2318773881759135,10,0.9 +plasmid,5480,4107,114,0.09253305941820145,2.61380579832329,10,0.9 +desalting_process,3720,3034,79,0.05423152819275856,2.653039001360095,10,0.9 +lysis_buffer,3714,3274,40,0.04899848252534866,2.4504729521630373,10,0.9 +source_key,8021,7899,93,0.0324920117855072,2.551210367729064,10,0.9 +elution_buffer,3530,2900,80,0.01885065995156765,2.695277826170774,10,0.9 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=2/t=0.5_ALL_FIELDS.csv.gz b/data/clustering/model=bioformers__bioformer-8L/min=2/t=0.5_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..d5b3c2970b860e53a1a4b9e8e5ff1c1eaab52bee --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/min=2/t=0.5_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59adaa68c1e5b9d3bd928ef835517a095cd06c74cf48e8fd5c2166f4582f6e26 +size 1560198 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=2/t=0.5_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=bioformers__bioformer-8L/min=2/t=0.5_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..4eb809c5e4da88612fbedaec6aae6389b7f605c3 --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/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 +enzyme_name,7975,7974,2,0.4289400279521942,1.2794644727863338,2,0.5 +desalting_process,3720,3720,1,,,2,0.5 +elution_buffer,3530,3530,1,,,2,0.5 +expression_strain,5677,5677,1,,,2,0.5 +inducer,7889,7889,1,,,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,6292,6291,1,,,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=bioformers__bioformer-8L/min=2/t=0.6_ALL_FIELDS.csv.gz b/data/clustering/model=bioformers__bioformer-8L/min=2/t=0.6_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..92edfb07c3424f89dd76e668b725f735af1b1fcb --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/min=2/t=0.6_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a83779e6f5147e06959fb456eee47f368c993871d3b7efa5c82d3fe09d654006 +size 1562930 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=2/t=0.6_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=bioformers__bioformer-8L/min=2/t=0.6_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..7668d39351a7148e3f88b465f22e5d4de9208c4e --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/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,3714,3713,2,0.7149391174316406,0.38312277129626476,2,0.6 +desalting_process,3720,3719,3,0.6262091994285583,0.5297506235986552,2,0.6 +induction_temperature,3656,3656,2,0.5875009298324585,1.3215446098942993,2,0.6 +expression_strain,5677,5676,3,0.5725498795509338,0.7076705185862888,2,0.6 +strain,2444,2442,3,0.5285511612892151,1.3682750768926735,2,0.6 +plasmid,5480,5480,2,0.5036197304725647,1.1947752458993386,2,0.6 +elution_buffer,3530,3530,4,0.47634539008140564,0.93194391941934,2,0.6 +medium_name,4806,4806,10,0.36276108026504517,1.0063757774071225,2,0.6 +organism_source,6292,6292,8,0.3054196834564209,1.3625220610891837,2,0.6 +enzyme_name,7975,7974,20,0.16269348561763763,2.0800754530172365,2,0.6 +inducer,7889,7889,5,-0.0033008635509759188,0.8952346594864501,2,0.6 +molecular_weight,295,295,1,,,2,0.6 +source_key,8021,8021,1,,,2,0.6 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=2/t=0.7_ALL_FIELDS.csv.gz b/data/clustering/model=bioformers__bioformer-8L/min=2/t=0.7_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..533e033d3715a455c875fe8a21860cac2e2d6c2e --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/min=2/t=0.7_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea629e4c50f8feddd2ea8e15370510e306033757fc6210d51e12c850aaa1571c +size 1582073 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=2/t=0.7_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=bioformers__bioformer-8L/min=2/t=0.7_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..a706a55632a9a28400f100824aa935cc930808b3 --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/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 +lysis_buffer,3714,3713,10,0.5278180241584778,1.1298630905778135,2,0.7 +induction_temperature,3656,3656,8,0.4214417040348053,1.2991481241936165,2,0.7 +expression_strain,5677,5675,13,0.3697492778301239,1.67633288892614,2,0.7 +strain,2444,2440,19,0.22587160766124725,1.6554725770137704,2,0.7 +plasmid,5480,5479,22,0.19191834330558777,1.9313990693462157,2,0.7 +elution_buffer,3530,3528,12,0.18217502534389496,1.492989013235311,2,0.7 +desalting_process,3720,3718,18,0.16743354499340057,1.5899326438041215,2,0.7 +medium_name,4806,4805,45,0.09770962595939636,1.6529318763606868,2,0.7 +organism_source,6292,6291,34,0.09500207751989365,1.5626747406698633,2,0.7 +enzyme_name,7975,7963,114,-0.06975390017032623,2.3478973056940524,2,0.7 +inducer,7889,7887,19,-0.14101950824260712,1.6836250434412567,2,0.7 +molecular_weight,295,295,1,,,2,0.7 +source_key,8021,8021,1,,,2,0.7 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=2/t=0.8_ALL_FIELDS.csv.gz b/data/clustering/model=bioformers__bioformer-8L/min=2/t=0.8_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..48f42b48860ebe468adb450e24e0a7fe1ed275a8 --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/min=2/t=0.8_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52f310ce1de3139f406aed9b8a3e56e00c8ae1212e1ac7d47e44d5c75d143767 +size 1641443 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=2/t=0.8_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=bioformers__bioformer-8L/min=2/t=0.8_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..3cac9651e7746c37f8b46bf10c81e31c640ddcff --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/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 +inducer,7889,7874,59,0.6508716940879822,1.4521043654321772,2,0.8 +organism_source,6292,6277,93,0.4631325602531433,1.2760038515286216,2,0.8 +source_key,8021,8021,9,0.40538156032562256,1.1515865211658034,2,0.8 +induction_temperature,3656,3654,29,0.40405768156051636,1.6324756091726542,2,0.8 +strain,2444,2434,60,0.30020228028297424,1.7121340631245408,2,0.8 +lysis_buffer,3714,3705,53,0.26605844497680664,1.482137417053924,2,0.8 +molecular_weight,295,294,10,0.18039771914482117,1.4202038973592805,2,0.8 +desalting_process,3720,3709,99,0.1117052361369133,1.60905411149561,2,0.8 +elution_buffer,3530,3526,70,0.060803115367889404,1.5091119065748273,2,0.8 +plasmid,5480,5465,130,-0.02668573148548603,2.150440509116739,2,0.8 +medium_name,4806,4787,146,-0.06182580813765526,1.5819938116264838,2,0.8 +expression_strain,5677,5669,48,-0.11014596372842789,1.3334980347743752,2,0.8 +enzyme_name,7975,7861,460,-0.13913843035697937,2.177428176325984,2,0.8 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=2/t=0.9_ALL_FIELDS.csv.gz b/data/clustering/model=bioformers__bioformer-8L/min=2/t=0.9_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..d0c3df3ade338b52cb478ff551f90e212306c1fc --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/min=2/t=0.9_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1164bb38dd43b2f3aa98404187d70778fbff204f59cf548c22c50c327fb8af5e +size 1726388 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=2/t=0.9_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=bioformers__bioformer-8L/min=2/t=0.9_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..b1be70e83f91a7050b747d9516e30d48d8621d99 --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/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,6292,6199,184,0.9616791605949402,0.5624584293204616,2,0.9 +strain,2444,2351,135,0.764517068862915,0.9884232111227906,2,0.9 +inducer,7889,7808,185,0.588335394859314,1.350126410609476,2,0.9 +induction_temperature,3656,3621,73,0.3014829158782959,0.9982184855962515,2,0.9 +enzyme_name,7975,6235,1334,0.26497021317481995,1.4007342221800998,2,0.9 +molecular_weight,295,266,33,0.2547828257083893,1.2819329919659535,2,0.9 +expression_strain,5677,5619,112,0.2129213660955429,1.2517790630958885,2,0.9 +medium_name,4806,4584,430,0.1799621284008026,1.3185331249917491,2,0.9 +plasmid,5480,5098,515,0.10540688037872314,1.6590700286882765,2,0.9 +desalting_process,3720,3524,351,0.09138867259025574,1.4695843239393565,2,0.9 +elution_buffer,3530,3406,316,0.06699922680854797,1.6100551962006788,2,0.9 +lysis_buffer,3714,3622,203,0.058849599212408066,1.276946475913048,2,0.9 +source_key,8021,8006,235,-0.02426104061305523,1.5396585261391593,2,0.9 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=20/t=0.5_ALL_FIELDS.csv.gz b/data/clustering/model=bioformers__bioformer-8L/min=20/t=0.5_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..2f4ef60ac0163712cf1d0112e5036d7a85b8a099 --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/min=20/t=0.5_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88efe8327f51ee5d6998ae8ccca6247f7f6d98e802b4a3c7d1f0acf85fe8ca48 +size 1560161 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=20/t=0.5_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=bioformers__bioformer-8L/min=20/t=0.5_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..f213f849de071f06975fa7b374e6c3c14a993d12 --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/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,3720,3720,1,,,20,0.5 +elution_buffer,3530,3530,1,,,20,0.5 +enzyme_name,7975,7972,1,,,20,0.5 +expression_strain,5677,5677,1,,,20,0.5 +inducer,7889,7889,1,,,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,6292,6291,1,,,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=bioformers__bioformer-8L/min=20/t=0.6_ALL_FIELDS.csv.gz b/data/clustering/model=bioformers__bioformer-8L/min=20/t=0.6_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..cfc399bc78518b5acc157ccde46a997d757db877 --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/min=20/t=0.6_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32091b753a897609005b45f154dd347ba05c11f0cdc3f19ad2df1014779c7043 +size 1561751 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=20/t=0.6_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=bioformers__bioformer-8L/min=20/t=0.6_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..e2f2f66d7ba37b3018e922098a3ce44b010005c7 --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/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 +lysis_buffer,3714,3713,2,0.7149391174316406,0.38312277129626476,20,0.6 +desalting_process,3720,3719,3,0.6262091994285583,0.5297506235986552,20,0.6 +induction_temperature,3656,3656,2,0.5875009298324585,1.3215446098942993,20,0.6 +medium_name,4806,4790,2,0.4549894332885742,1.826338730267641,20,0.6 +organism_source,6292,6280,2,0.37994393706321716,2.056197049107056,20,0.6 +enzyme_name,7975,7945,4,0.25419294834136963,3.101018624031254,20,0.6 +elution_buffer,3530,3508,1,,,20,0.6 +expression_strain,5677,5672,1,,,20,0.6 +inducer,7889,7873,1,,,20,0.6 +molecular_weight,295,295,1,,,20,0.6 +plasmid,5480,5478,1,,,20,0.6 +source_key,8021,8021,1,,,20,0.6 +strain,2444,2434,1,,,20,0.6 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=20/t=0.7_ALL_FIELDS.csv.gz b/data/clustering/model=bioformers__bioformer-8L/min=20/t=0.7_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..952d10344426272a99ef9b9b38178aac5288b49d --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/min=20/t=0.7_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce08e962bc7096563cca159cd51d80b664db25233b5d00ef9e96cc0d810ec5b6 +size 1577101 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=20/t=0.7_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=bioformers__bioformer-8L/min=20/t=0.7_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..a53fbf66dd1cdf222a514d5121683120bf7d37db --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/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 +induction_temperature,3656,3642,2,0.7311743497848511,0.488285757220045,20,0.7 +lysis_buffer,3714,3708,3,0.6311509013175964,1.0142492631865714,20,0.7 +expression_strain,5677,5662,3,0.5611873865127563,1.4280595557309985,20,0.7 +strain,2444,2398,3,0.42226219177246094,2.4805751512792487,20,0.7 +elution_buffer,3530,3479,2,0.41077694296836853,2.1725323108246646,20,0.7 +desalting_process,3720,3706,6,0.34200671315193176,2.261817326867608,20,0.7 +plasmid,5480,5446,5,0.26647379994392395,2.36492389933976,20,0.7 +organism_source,6292,6256,11,0.22617939114570618,1.8750805572672804,20,0.7 +medium_name,4806,4749,10,0.19702892005443573,2.816061703269037,20,0.7 +inducer,7889,7850,6,0.12918692827224731,2.7514601081243915,20,0.7 +enzyme_name,7975,7868,21,0.03644954040646553,4.313164812817665,20,0.7 +molecular_weight,295,295,1,,,20,0.7 +source_key,8021,8021,1,,,20,0.7 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=20/t=0.8_ALL_FIELDS.csv.gz b/data/clustering/model=bioformers__bioformer-8L/min=20/t=0.8_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..aef39a4a584cf7310bdbbb0452e799399d1642ab --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/min=20/t=0.8_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5edb6520470a98b094c46af2f0dc2f8073a34f05a2c1d57b537041444f5ba1ed +size 1614162 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=20/t=0.8_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=bioformers__bioformer-8L/min=20/t=0.8_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..bb012ea4f8aac2e9a027fdef604023e070cde17c --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/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 +inducer,7889,7785,10,0.6922992467880249,2.045186989584112,20,0.8 +organism_source,6292,6053,22,0.4601461589336395,1.898573898280356,20,0.8 +lysis_buffer,3714,3628,10,0.43219175934791565,2.4462070008080317,20,0.8 +induction_temperature,3656,3614,8,0.4294532835483551,1.7110208940449005,20,0.8 +strain,2444,2339,14,0.34536221623420715,2.4285518664430015,20,0.8 +elution_buffer,3530,3376,13,0.19678443670272827,2.756169283815144,20,0.8 +desalting_process,3720,3634,21,0.17814189195632935,2.6828090441327426,20,0.8 +plasmid,5480,5309,28,0.040721941739320755,3.520882518464505,20,0.8 +medium_name,4806,4574,29,-0.01126893050968647,2.8639912611183065,20,0.8 +enzyme_name,7975,7105,67,-0.05909404903650284,4.0350587525390536,20,0.8 +expression_strain,5677,5608,12,-0.08953195810317993,1.8692179378891407,20,0.8 +molecular_weight,295,264,1,,,20,0.8 +source_key,8021,7989,1,,,20,0.8 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=20/t=0.9_ALL_FIELDS.csv.gz b/data/clustering/model=bioformers__bioformer-8L/min=20/t=0.9_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..87fb61b0307bbcb65e9e71d7d86702ce4a8eb526 --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/min=20/t=0.9_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:294a900fd15bc1299ced879483f2ab53eb660751607a470182c7f2e3563548ae +size 1605852 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=20/t=0.9_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=bioformers__bioformer-8L/min=20/t=0.9_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..15d723ca2e533621955dc512b3bb800e0e0f1710 --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/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,6292,5443,22,0.9805147051811218,0.5368095959375102,20,0.9 +strain,2444,1781,10,0.8416748642921448,1.2902561799842986,20,0.9 +inducer,7889,7356,28,0.6398031115531921,2.6752075115560925,20,0.9 +induction_temperature,3656,3425,12,0.41227486729621887,1.1994923356645564,20,0.9 +molecular_weight,295,175,3,0.38067957758903503,1.3598908921278277,20,0.9 +expression_strain,5677,5302,20,0.276198148727417,1.7209754611914139,20,0.9 +enzyme_name,7975,2020,44,0.23787984251976013,2.660095628820925,20,0.9 +medium_name,4806,3424,45,0.11288148909807205,2.7485712547677315,20,0.9 +plasmid,5480,3668,57,0.10968799889087677,2.875404322778638,20,0.9 +desalting_process,3720,2835,43,0.061065953224897385,2.977530931141224,20,0.9 +source_key,8021,7752,53,0.05195175111293793,3.1082064256823845,20,0.9 +lysis_buffer,3714,3124,18,0.04413185641169548,2.786993710831318,20,0.9 +elution_buffer,3530,2655,39,-0.0021400386467576027,3.2238104226139144,20,0.9 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=30/t=0.5_ALL_FIELDS.csv.gz b/data/clustering/model=bioformers__bioformer-8L/min=30/t=0.5_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..d4840ea47040661e9957e9b8f7e451a2d6380fad --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/min=30/t=0.5_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8837f5fc2373dc7385951ce47469c91b1fff041ba3a0f0951f3dce4219973c0 +size 1560161 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=30/t=0.5_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=bioformers__bioformer-8L/min=30/t=0.5_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..53a6bd98ef2eb25c1d63d68d8f009759350e4f9e --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/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,3720,3720,1,,,30,0.5 +elution_buffer,3530,3530,1,,,30,0.5 +enzyme_name,7975,7972,1,,,30,0.5 +expression_strain,5677,5677,1,,,30,0.5 +inducer,7889,7889,1,,,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,6292,6291,1,,,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=bioformers__bioformer-8L/min=30/t=0.6_ALL_FIELDS.csv.gz b/data/clustering/model=bioformers__bioformer-8L/min=30/t=0.6_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..cfac8b58b664b8f7288207356799f7018a60905e --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/min=30/t=0.6_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9a54724abd6aee597fb3b4a2de3a38cc16159c1dd15c6b7704a4afbea024648 +size 1561024 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=30/t=0.6_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=bioformers__bioformer-8L/min=30/t=0.6_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..3f6b53959ead5f208e8f06c4ef3bb68ebedacb56 --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/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,3720,3719,2,0.6374301910400391,0.7738399290993462,30,0.6 +induction_temperature,3656,3656,2,0.5875009298324585,1.3215446098942993,30,0.6 +enzyme_name,7975,7930,3,0.2790108025074005,3.1896831682726994,30,0.6 +elution_buffer,3530,3508,1,,,30,0.6 +expression_strain,5677,5672,1,,,30,0.6 +inducer,7889,7873,1,,,30,0.6 +lysis_buffer,3714,3693,1,,,30,0.6 +medium_name,4806,4768,1,,,30,0.6 +molecular_weight,295,295,1,,,30,0.6 +organism_source,6292,6259,1,,,30,0.6 +plasmid,5480,5478,1,,,30,0.6 +source_key,8021,8021,1,,,30,0.6 +strain,2444,2434,1,,,30,0.6 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=30/t=0.7_ALL_FIELDS.csv.gz b/data/clustering/model=bioformers__bioformer-8L/min=30/t=0.7_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..c4824f7a086b5275922b1d20ad7ee426fa1e50f9 --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/min=30/t=0.7_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e467e96d8088c964bbdc32cf30a13a9ad636ba841d12469e6070f1bf5b803add +size 1571329 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=30/t=0.7_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=bioformers__bioformer-8L/min=30/t=0.7_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..cdb48c559511bd54ebce6f8d299b2f5d7683fd22 --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/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 +induction_temperature,3656,3642,2,0.7311743497848511,0.488285757220045,30,0.7 +expression_strain,5677,5639,2,0.6173756718635559,0.6322668706741471,30,0.7 +strain,2444,2378,2,0.4288952946662903,1.8870831533302015,30,0.7 +desalting_process,3720,3664,3,0.4050860106945038,2.1134841217204836,30,0.7 +plasmid,5480,5428,3,0.3539765477180481,2.2509697296973923,30,0.7 +organism_source,6292,6231,8,0.2797265648841858,1.84147644004859,30,0.7 +medium_name,4806,4730,7,0.22741734981536865,2.817676209549055,30,0.7 +inducer,7889,7850,5,0.12988336384296417,2.8272199532430853,30,0.7 +enzyme_name,7975,7825,15,0.03896830603480339,4.3828826907513045,30,0.7 +elution_buffer,3530,3458,1,,,30,0.7 +lysis_buffer,3714,3658,1,,,30,0.7 +molecular_weight,295,295,1,,,30,0.7 +source_key,8021,8021,1,,,30,0.7 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=30/t=0.8_ALL_FIELDS.csv.gz b/data/clustering/model=bioformers__bioformer-8L/min=30/t=0.8_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..279a177c837b0fe3da18c52c3794407fd1ff090c --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/min=30/t=0.8_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83d5fd7b551016f1cafc9ead2ff778c4de6a1e71dc3e71d1953d4427a4e2c0d5 +size 1605741 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=30/t=0.8_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=bioformers__bioformer-8L/min=30/t=0.8_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..93529b0a233c318d64cd5e7ffe688e3f21940892 --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/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 +inducer,7889,7735,7,0.7055988907814026,1.939096311918662,30,0.8 +lysis_buffer,3714,3579,5,0.4764579236507416,2.564461387084605,30,0.8 +organism_source,6292,5965,15,0.4634239375591278,1.8802267025404595,30,0.8 +induction_temperature,3656,3591,6,0.43210306763648987,1.5159507909233518,30,0.8 +strain,2444,2269,9,0.3546215891838074,2.4820132916281383,30,0.8 +elution_buffer,3530,3374,10,0.20632404088974,2.8691991595225783,30,0.8 +desalting_process,3720,3592,14,0.20399931073188782,2.928785499624179,30,0.8 +medium_name,4806,4511,21,0.047330863773822784,2.983131764459463,30,0.8 +plasmid,5480,5248,21,0.04311712086200714,3.880653072433622,30,0.8 +enzyme_name,7975,6936,50,-0.05541257560253143,4.305211529755006,30,0.8 +expression_strain,5677,5554,9,-0.09135869145393372,1.6754101335222045,30,0.8 +molecular_weight,295,264,1,,,30,0.8 +source_key,8021,7989,1,,,30,0.8 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=30/t=0.9_ALL_FIELDS.csv.gz b/data/clustering/model=bioformers__bioformer-8L/min=30/t=0.9_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..1227430d9a75eaed399db1b6fd84ab493e609487 --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/min=30/t=0.9_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed3bcece249fa27177a1651ad2d391ed588f432c3d2ee4c3c7a87befd0706b9f +size 1581989 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=30/t=0.9_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=bioformers__bioformer-8L/min=30/t=0.9_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..140a74e0f59ea72f52b0091cb0d52259f06f363e --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/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,6292,5266,15,0.9854954481124878,0.2851689912562612,30,0.9 +strain,2444,1733,8,0.8470679521560669,1.343804212033218,30,0.9 +inducer,7889,7293,20,0.6506964564323425,2.765338611630116,30,0.9 +molecular_weight,295,163,2,0.44750261306762695,1.6975642469527275,30,0.9 +induction_temperature,3656,3340,8,0.44697147607803345,0.987109276264409,30,0.9 +enzyme_name,7975,1626,24,0.2817782461643219,2.421233665073658,30,0.9 +expression_strain,5677,5257,16,0.2769206166267395,1.7309105675607224,30,0.9 +medium_name,4806,3203,29,0.12058119475841522,2.9665202956082144,30,0.9 +plasmid,5480,3403,39,0.114617258310318,3.002515715749988,30,0.9 +lysis_buffer,3714,3015,10,0.07980635017156601,3.392229023562755,30,0.9 +desalting_process,3720,2667,27,0.07133529335260391,3.254077555718731,30,0.9 +source_key,8021,7610,35,0.05901448801159859,3.643503475536609,30,0.9 +elution_buffer,3530,2487,26,-0.005669980775564909,3.459764998183402,30,0.9 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=5/t=0.5_ALL_FIELDS.csv.gz b/data/clustering/model=bioformers__bioformer-8L/min=5/t=0.5_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..f08a4df9968bb0013c7695481630fc45f65be54a --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/min=5/t=0.5_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:933234018e90239b9ee07af14b60f099699c13659a211587fa2dc799eb03fd87 +size 1560161 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=5/t=0.5_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=bioformers__bioformer-8L/min=5/t=0.5_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..a13da57202a8c20d7c3c51578804b13ef1ac96b7 --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/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,3720,3720,1,,,5,0.5 +elution_buffer,3530,3530,1,,,5,0.5 +enzyme_name,7975,7972,1,,,5,0.5 +expression_strain,5677,5677,1,,,5,0.5 +inducer,7889,7889,1,,,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,6292,6291,1,,,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=bioformers__bioformer-8L/min=5/t=0.6_ALL_FIELDS.csv.gz b/data/clustering/model=bioformers__bioformer-8L/min=5/t=0.6_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..d3804c13979068a7cb02aec8fcc0831d2f8f01e9 --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/min=5/t=0.6_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ad0c47fbc085b9ce27c9ba9d11f48758101d5fafe9ce0c1052de18003b4cac8 +size 1562773 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=5/t=0.6_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=bioformers__bioformer-8L/min=5/t=0.6_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..8863405f24102944cea10d20ece59701bfc36cbf --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/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,3714,3713,2,0.7149391174316406,0.38312277129626476,5,0.6 +desalting_process,3720,3719,3,0.6262091994285583,0.5297506235986552,5,0.6 +strain,2444,2440,2,0.5890939235687256,0.5220098785323762,5,0.6 +induction_temperature,3656,3656,2,0.5875009298324585,1.3215446098942993,5,0.6 +elution_buffer,3530,3530,3,0.5096814632415771,0.9128937844311059,5,0.6 +medium_name,4806,4804,6,0.38017725944519043,1.3072663364990722,5,0.6 +inducer,7889,7887,3,0.3557615876197815,1.2483121294170345,5,0.6 +organism_source,6292,6290,5,0.3246673345565796,2.016319682225972,5,0.6 +enzyme_name,7975,7965,10,0.21475757658481598,2.8319730515798085,5,0.6 +expression_strain,5677,5672,1,,,5,0.6 +molecular_weight,295,295,1,,,5,0.6 +plasmid,5480,5478,1,,,5,0.6 +source_key,8021,8021,1,,,5,0.6 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=5/t=0.7_ALL_FIELDS.csv.gz b/data/clustering/model=bioformers__bioformer-8L/min=5/t=0.7_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..f7f9f31455d50d5dd696e47731155e21cddb425d --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/min=5/t=0.7_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f373602a813ad8b984cc3b188ff18bc97bd40b7b1321ab576c03039e2c758459 +size 1581326 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=5/t=0.7_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=bioformers__bioformer-8L/min=5/t=0.7_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..9e2e38a3858f26aacd0f35f27d3ffefd66f5c50d --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/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 +lysis_buffer,3714,3711,5,0.5507918000221252,1.3636381398705133,5,0.7 +induction_temperature,3656,3654,5,0.4207448959350586,0.9558708093395929,5,0.7 +expression_strain,5677,5664,6,0.3934195935726166,1.8975776902587642,5,0.7 +strain,2444,2432,10,0.3200376331806183,2.1180449548377047,5,0.7 +desalting_process,3720,3716,11,0.21291004121303558,2.1114014155787633,5,0.7 +plasmid,5480,5475,13,0.21220676600933075,2.155646306532552,5,0.7 +elution_buffer,3530,3524,8,0.21009083092212677,1.6738716746273976,5,0.7 +medium_name,4806,4789,26,0.13568684458732605,2.1025627219083844,5,0.7 +inducer,7889,7874,10,0.1284339427947998,2.268823051431932,5,0.7 +organism_source,6292,6283,23,0.09911264479160309,1.8760716067481988,5,0.7 +enzyme_name,7975,7935,62,-0.0060180071741342545,3.1957609285745634,5,0.7 +molecular_weight,295,295,1,,,5,0.7 +source_key,8021,8021,1,,,5,0.7 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=5/t=0.8_ALL_FIELDS.csv.gz b/data/clustering/model=bioformers__bioformer-8L/min=5/t=0.8_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..2574da32579700af40a3fba75cf03627c15dfd9a --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/min=5/t=0.8_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c09a651fbe550c471ee27fe32cd970a9b4b852273e2a9f137a72394b8642e6b +size 1635401 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=5/t=0.8_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=bioformers__bioformer-8L/min=5/t=0.8_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..1ab768d5dee87668fa8a46a136b314d116405728 --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/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 +inducer,7889,7852,30,0.6627641916275024,2.044325263695298,5,0.8 +organism_source,6292,6208,53,0.46414998173713684,1.5680341956960846,5,0.8 +source_key,8021,8017,5,0.42416778206825256,1.0850744082237114,5,0.8 +induction_temperature,3656,3641,18,0.4063742756843567,1.9196639352981768,5,0.8 +lysis_buffer,3714,3692,27,0.33277463912963867,2.0151115617595123,5,0.8 +strain,2444,2398,30,0.3316309452056885,2.191884426411687,5,0.8 +molecular_weight,295,291,5,0.2541064918041229,1.8278209302431137,5,0.8 +desalting_process,3720,3689,53,0.13984432816505432,2.169222040534551,5,0.8 +elution_buffer,3530,3510,39,0.11581364274024963,1.8924393232317045,5,0.8 +plasmid,5480,5444,83,0.004260723944753408,2.6839459834769994,5,0.8 +medium_name,4806,4733,78,-0.028180163353681564,2.1051961499962877,5,0.8 +enzyme_name,7975,7603,217,-0.10721132159233093,2.992378178619993,5,0.8 +expression_strain,5677,5636,26,-0.11020860075950623,1.6662297078273232,5,0.8 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=5/t=0.9_ALL_FIELDS.csv.gz b/data/clustering/model=bioformers__bioformer-8L/min=5/t=0.9_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..1ee83969c3fc4a4abcc62a4949e3401293bb0a17 --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/min=5/t=0.9_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bce857b878808045810251310bfeb8321df128770fd0bd541c9267ca20bc595b +size 1681222 diff --git a/data/clustering/model=bioformers__bioformer-8L/min=5/t=0.9_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=bioformers__bioformer-8L/min=5/t=0.9_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..fdc3a0a04abe2e5b5d7c0b62a5045dc59e651ff2 --- /dev/null +++ b/data/clustering/model=bioformers__bioformer-8L/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,6292,5918,74,0.9678415656089783,0.5906738182808923,5,0.9 +strain,2444,2162,59,0.7834396958351135,1.1982309754505087,5,0.9 +inducer,7889,7641,85,0.6066275835037231,1.9298785492922537,5,0.9 +induction_temperature,3656,3532,31,0.31207239627838135,1.2281197812554134,5,0.9 +molecular_weight,295,236,15,0.24960702657699585,1.5712266059737572,5,0.9 +enzyme_name,7975,4196,372,0.2318660467863083,1.9569467233714515,5,0.9 +expression_strain,5677,5522,55,0.2304627150297165,1.6120171175825142,5,0.9 +medium_name,4806,4154,192,0.13732187449932098,1.8661509579432058,5,0.9 +plasmid,5480,4581,229,0.0994955450296402,2.228590229961676,5,0.9 +elution_buffer,3530,3166,157,0.05566920340061188,2.12541123187403,5,0.9 +desalting_process,3720,3224,150,0.05099604278802872,2.1366022991019027,5,0.9 +lysis_buffer,3714,3425,79,0.05039551854133606,1.912689258461885,5,0.9 +source_key,8021,7965,148,0.00864329468458891,2.088058295073857,5,0.9