richiam commited on
Commit
62bc5d4
·
verified ·
1 Parent(s): f40e003

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +25 -0
  2. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=10/t=0.5_ALL_FIELDS.csv.gz +2 -2
  3. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=10/t=0.5_FIELD_CLUSTER_METRICS.csv +13 -13
  4. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=10/t=0.6_ALL_FIELDS.csv.gz +2 -2
  5. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=10/t=0.6_FIELD_CLUSTER_METRICS.csv +13 -13
  6. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=10/t=0.7_ALL_FIELDS.csv.gz +2 -2
  7. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=10/t=0.7_FIELD_CLUSTER_METRICS.csv +13 -13
  8. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=10/t=0.8_ALL_FIELDS.csv.gz +2 -2
  9. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=10/t=0.8_FIELD_CLUSTER_METRICS.csv +13 -13
  10. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=10/t=0.9_ALL_FIELDS.csv.gz +2 -2
  11. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=10/t=0.9_FIELD_CLUSTER_METRICS.csv +13 -13
  12. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=2/t=0.5_ALL_FIELDS.csv.gz +2 -2
  13. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=2/t=0.5_FIELD_CLUSTER_METRICS.csv +13 -13
  14. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=2/t=0.6_ALL_FIELDS.csv.gz +2 -2
  15. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=2/t=0.6_FIELD_CLUSTER_METRICS.csv +13 -13
  16. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=2/t=0.7_ALL_FIELDS.csv.gz +2 -2
  17. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=2/t=0.7_FIELD_CLUSTER_METRICS.csv +13 -13
  18. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=2/t=0.8_ALL_FIELDS.csv.gz +2 -2
  19. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=2/t=0.8_FIELD_CLUSTER_METRICS.csv +13 -13
  20. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=2/t=0.9_ALL_FIELDS.csv.gz +2 -2
  21. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=2/t=0.9_FIELD_CLUSTER_METRICS.csv +13 -13
  22. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=20/t=0.5_ALL_FIELDS.csv.gz +2 -2
  23. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=20/t=0.5_FIELD_CLUSTER_METRICS.csv +13 -13
  24. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=20/t=0.6_ALL_FIELDS.csv.gz +2 -2
  25. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=20/t=0.6_FIELD_CLUSTER_METRICS.csv +13 -13
  26. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=20/t=0.7_ALL_FIELDS.csv.gz +2 -2
  27. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=20/t=0.7_FIELD_CLUSTER_METRICS.csv +13 -13
  28. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=20/t=0.8_ALL_FIELDS.csv.gz +2 -2
  29. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=20/t=0.8_FIELD_CLUSTER_METRICS.csv +13 -13
  30. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=20/t=0.9_ALL_FIELDS.csv.gz +2 -2
  31. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=20/t=0.9_FIELD_CLUSTER_METRICS.csv +13 -13
  32. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=30/t=0.5_ALL_FIELDS.csv.gz +2 -2
  33. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=30/t=0.5_FIELD_CLUSTER_METRICS.csv +13 -13
  34. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=30/t=0.6_ALL_FIELDS.csv.gz +2 -2
  35. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=30/t=0.6_FIELD_CLUSTER_METRICS.csv +13 -13
  36. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=30/t=0.7_ALL_FIELDS.csv.gz +2 -2
  37. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=30/t=0.7_FIELD_CLUSTER_METRICS.csv +13 -13
  38. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=30/t=0.8_ALL_FIELDS.csv.gz +2 -2
  39. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=30/t=0.8_FIELD_CLUSTER_METRICS.csv +13 -13
  40. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=30/t=0.9_ALL_FIELDS.csv.gz +2 -2
  41. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=30/t=0.9_FIELD_CLUSTER_METRICS.csv +13 -13
  42. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=5/t=0.5_ALL_FIELDS.csv.gz +2 -2
  43. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=5/t=0.5_FIELD_CLUSTER_METRICS.csv +13 -13
  44. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=5/t=0.6_ALL_FIELDS.csv.gz +2 -2
  45. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=5/t=0.6_FIELD_CLUSTER_METRICS.csv +13 -13
  46. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=5/t=0.7_ALL_FIELDS.csv.gz +2 -2
  47. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=5/t=0.7_FIELD_CLUSTER_METRICS.csv +13 -13
  48. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=5/t=0.8_ALL_FIELDS.csv.gz +2 -2
  49. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=5/t=0.8_FIELD_CLUSTER_METRICS.csv +13 -13
  50. data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=5/t=0.9_ALL_FIELDS.csv.gz +2 -2
.gitattributes CHANGED
@@ -325,3 +325,28 @@ data/clustering/model=cambridgeltl__SapBERT-from-PubMedBERT-fulltext/min=5/t=0.6
325
  data/clustering/model=cambridgeltl__SapBERT-from-PubMedBERT-fulltext/min=5/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
326
  data/clustering/model=cambridgeltl__SapBERT-from-PubMedBERT-fulltext/min=5/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
327
  data/clustering/model=cambridgeltl__SapBERT-from-PubMedBERT-fulltext/min=5/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
325
  data/clustering/model=cambridgeltl__SapBERT-from-PubMedBERT-fulltext/min=5/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
326
  data/clustering/model=cambridgeltl__SapBERT-from-PubMedBERT-fulltext/min=5/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
327
  data/clustering/model=cambridgeltl__SapBERT-from-PubMedBERT-fulltext/min=5/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
328
+ data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=10/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
329
+ data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=10/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
330
+ data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=10/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
331
+ data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=10/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
332
+ data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=10/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
333
+ data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=2/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
334
+ data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=2/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
335
+ data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=2/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
336
+ data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=2/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
337
+ data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=2/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
338
+ data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=20/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
339
+ data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=20/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
340
+ data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=20/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
341
+ data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=20/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
342
+ data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=20/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
343
+ data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=30/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
344
+ data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=30/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
345
+ data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=30/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
346
+ data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=30/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
347
+ data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=30/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
348
+ data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=5/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
349
+ data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=5/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
350
+ data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=5/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
351
+ data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=5/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
352
+ data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=5/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=10/t=0.5_ALL_FIELDS.csv.gz CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d9b600cf5fece56ab8eee48ff032cc4d46c75191b28b0d2be8d6b6ae6084e85e
3
- size 1658126
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aaf5b729433b8c0781c23f5629e18793ca602b4cd0902e2e74b6743183d32c10
3
+ size 2633180
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=10/t=0.5_FIELD_CLUSTER_METRICS.csv CHANGED
@@ -1,14 +1,14 @@
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
- organism_source,6292,6049,44,0.7428889870643616,1.5642801113253901,10,0.5
3
- strain,2444,2107,29,0.6680693030357361,1.896349708375672,10,0.5
4
- inducer,7889,7739,41,0.32499629259109497,2.788636899622803,10,0.5
5
- expression_strain,5677,5554,35,0.2630155086517334,2.035410018635815,10,0.5
6
- induction_temperature,3656,3605,25,0.10567609965801239,2.0479237776878874,10,0.5
7
- lysis_buffer,3714,3531,32,0.10488671064376831,2.6585990067806735,10,0.5
8
- molecular_weight,295,211,11,0.1023046150803566,2.7204379371697227,10,0.5
9
- plasmid,5480,4906,143,0.04579225555062294,3.00997037242903,10,0.5
10
- desalting_process,3720,3432,74,0.03073844686150551,2.866870660949277,10,0.5
11
- elution_buffer,3530,3306,61,0.029316093772649765,2.746199312592459,10,0.5
12
- enzyme_name,7975,6476,262,-0.00482341879978776,3.4917127917021125,10,0.5
13
- source_key,8021,8011,20,-0.005727624986320734,3.8939346299830673,10,0.5
14
- medium_name,4806,4470,74,-0.08255395293235779,2.729018282440274,10,0.5
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,9834,9567,52,0.7728445529937744,1.7278577641991768,10,0.5
3
+ expression_strain,8268,8113,51,0.261109322309494,2.5493846596854195,10,0.5
4
+ inducer,11954,11793,65,0.2262050211429596,2.75131081856206,10,0.5
5
+ strain,3834,3424,47,0.14346283674240112,2.3521358717187706,10,0.5
6
+ lysis_buffer,5625,5345,39,0.0847732275724411,2.862800994966256,10,0.5
7
+ molecular_weight,495,382,16,0.0608510822057724,3.0355136677962156,10,0.5
8
+ induction_temperature,5383,5322,34,0.038768570870161057,2.071407974826724,10,0.5
9
+ desalting_process,5540,5110,100,0.0254802368581295,3.0120623079949085,10,0.5
10
+ elution_buffer,5198,4900,79,0.012768981046974659,2.8639148357145006,10,0.5
11
+ plasmid,8217,7429,225,0.0037938584573566914,3.235717893057847,10,0.5
12
+ enzyme_name,12099,10081,395,-0.01509098894894123,3.5583141974715677,10,0.5
13
+ source_key,12179,12166,26,-0.03412937372922897,3.748048814150507,10,0.5
14
+ medium_name,7644,7180,99,-0.0427350178360939,2.9180884494034265,10,0.5
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=10/t=0.6_ALL_FIELDS.csv.gz CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06aa24ca383295f96aeaf9d50929565e97eecdb57273978e87223825eacc5ab2
3
- size 1655364
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:709319ff58c279ea5be4b3d6da34e23175bac69506ce2a8c6435d783ff8aca35
3
+ size 2595655
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=10/t=0.6_FIELD_CLUSTER_METRICS.csv CHANGED
@@ -1,14 +1,14 @@
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
- strain,2444,1874,26,0.84322190284729,1.1459159874123552,10,0.6
3
- organism_source,6292,5835,39,0.8355168104171753,0.8497138271554118,10,0.6
4
- inducer,7889,7583,59,0.5557193756103516,2.4736205203238435,10,0.6
5
- expression_strain,5677,5354,41,0.4763530194759369,1.7562876061348012,10,0.6
6
- molecular_weight,295,154,10,0.23354272544384003,2.0288739670469287,10,0.6
7
- induction_temperature,3656,3502,27,0.1882535070180893,1.626142201677759,10,0.6
8
- plasmid,5480,3925,127,0.13001714646816254,2.3252846507438383,10,0.6
9
- enzyme_name,7975,4099,200,0.11223941296339035,2.6924055646299188,10,0.6
10
- medium_name,4806,4079,103,0.10212472826242447,2.6213524816258618,10,0.6
11
- desalting_process,3720,2972,90,0.053893957287073135,2.842094247938232,10,0.6
12
- elution_buffer,3530,2979,80,0.045601051300764084,2.6777816514921624,10,0.6
13
- lysis_buffer,3714,3314,48,0.030361270532011986,2.7499578015212394,10,0.6
14
- source_key,8021,7954,95,-0.050610851496458054,3.017466279586629,10,0.6
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,9834,9297,48,0.8658580780029297,1.0759750619459103,10,0.6
3
+ strain,3834,3031,42,0.5288842916488647,1.669394451158521,10,0.6
4
+ inducer,11954,11579,94,0.520630955696106,2.4965901300310955,10,0.6
5
+ expression_strain,8268,7835,82,0.38554930686950684,2.10976832916197,10,0.6
6
+ induction_temperature,5383,5188,33,0.25265684723854065,1.7898789028145303,10,0.6
7
+ molecular_weight,495,249,13,0.15108126401901245,2.33066045854505,10,0.6
8
+ enzyme_name,12099,6615,305,0.1017250046133995,2.7516531148159444,10,0.6
9
+ medium_name,7644,6648,140,0.09073975682258606,2.777307748460663,10,0.6
10
+ plasmid,8217,5822,196,0.07760035991668701,2.58634543848069,10,0.6
11
+ desalting_process,5540,4370,116,0.03545484319329262,3.0419897548722843,10,0.6
12
+ lysis_buffer,5625,5063,68,0.010331906378269196,2.9954174282882904,10,0.6
13
+ elution_buffer,5198,4439,106,0.0030753230676054955,2.764920429309308,10,0.6
14
+ source_key,12179,12095,133,-0.08010421693325043,2.91806404423541,10,0.6
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=10/t=0.7_ALL_FIELDS.csv.gz CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cbfe0e1d916eeb014bd0e70b05fc65c67a17006f82ab44dcc5a49b4d3973fda7
3
- size 1616527
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d8c0cadce45f2424b14041f006d52bf81fdff57163aad93fec7aebcae5c04ad
3
+ size 2539436
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=10/t=0.7_FIELD_CLUSTER_METRICS.csv CHANGED
@@ -1,14 +1,14 @@
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
- organism_source,6292,5698,39,0.9486824870109558,0.5575971815595288,10,0.7
3
- strain,2444,1748,23,0.9339799284934998,0.7713665928566809,10,0.7
4
- molecular_weight,295,50,4,0.6097593903541565,1.1077781060023761,10,0.7
5
- inducer,7889,7310,72,0.6080440282821655,2.3252534079803002,10,0.7
6
- expression_strain,5677,5138,56,0.42238134145736694,1.273274018094027,10,0.7
7
- induction_temperature,3656,3341,30,0.4200872778892517,1.1275285565216626,10,0.7
8
- plasmid,5480,2808,93,0.3360345661640167,1.575408648819748,10,0.7
9
- enzyme_name,7975,1900,102,0.3207155168056488,1.9011136338258734,10,0.7
10
- desalting_process,3720,1952,68,0.1837780773639679,2.1976018398226933,10,0.7
11
- medium_name,4806,3179,91,0.1626473069190979,2.2859338526529287,10,0.7
12
- elution_buffer,3530,2145,89,0.11014509946107864,2.5392472776953907,10,0.7
13
- source_key,8021,6995,270,0.08171913772821426,2.299826538101346,10,0.7
14
- lysis_buffer,3714,2770,75,0.021063663065433502,2.7133604919570993,10,0.7
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,9834,9153,46,0.9610770344734192,0.7145873735046969,10,0.7
3
+ strain,3834,2763,46,0.6699687838554382,1.044114162452001,10,0.7
4
+ inducer,11954,11085,108,0.5856119990348816,2.4129878534787386,10,0.7
5
+ induction_temperature,5383,4997,36,0.45266231894493103,1.2363091655396055,10,0.7
6
+ molecular_weight,495,123,9,0.4492281377315521,1.319903159448924,10,0.7
7
+ expression_strain,8268,7298,83,0.4038277268409729,1.4183691748643454,10,0.7
8
+ enzyme_name,12099,3345,166,0.2855040431022644,1.96780597535178,10,0.7
9
+ plasmid,8217,3779,126,0.2812192440032959,1.796538736983627,10,0.7
10
+ desalting_process,5540,2883,99,0.14409910142421722,2.4422434449768,10,0.7
11
+ medium_name,7644,5304,147,0.11483242362737656,2.5154844075138216,10,0.7
12
+ elution_buffer,5198,3252,129,0.09060917794704437,2.6949359835509625,10,0.7
13
+ source_key,12179,11071,410,0.04482627660036087,2.3878633208018023,10,0.7
14
+ lysis_buffer,5625,4267,117,0.0022203540429472923,2.8922662281763984,10,0.7
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=10/t=0.8_ALL_FIELDS.csv.gz CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:88beeba89b1388d309726ff4d403d64f7480f5070df30a4255106ecf1486547a
3
- size 1535403
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acf2018495b499a5f7ea251999275d2ec7cf1c9eef423d3b22c211ef2f2f2d02
3
+ size 2384982
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=10/t=0.8_FIELD_CLUSTER_METRICS.csv CHANGED
@@ -1,14 +1,14 @@
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
- organism_source,6292,5632,40,0.9908291101455688,0.3898187315273147,10,0.8
3
- strain,2444,1617,17,0.9731556177139282,0.45329211555730364,10,0.8
4
- induction_temperature,3656,3231,29,0.833589494228363,0.7467113853921747,10,0.8
5
- source_key,8021,2090,155,0.7653384804725647,0.8455786238685956,10,0.8
6
- inducer,7889,6822,86,0.7018435597419739,1.8214089944414222,10,0.8
7
- enzyme_name,7975,473,28,0.6845092177391052,0.9401438082579848,10,0.8
8
- plasmid,5480,2047,67,0.6324900388717651,0.8686349458151417,10,0.8
9
- desalting_process,3720,810,42,0.5361937284469604,1.2976182096692501,10,0.8
10
- expression_strain,5677,4865,58,0.5254154205322266,0.9224448623130759,10,0.8
11
- medium_name,4806,2038,81,0.39642706513404846,1.4370769285536718,10,0.8
12
- elution_buffer,3530,1087,57,0.3246791362762451,1.6533586916098384,10,0.8
13
- lysis_buffer,3714,1570,81,0.22845757007598877,2.00430615980288,10,0.8
14
- molecular_weight,295,10,1,,,10,0.8
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,9834,9038,46,0.9917417764663696,0.40713114583426063,10,0.8
3
+ strain,3834,2487,32,0.8847610950469971,0.6013888771995686,10,0.8
4
+ induction_temperature,5383,4821,32,0.8460920453071594,0.6250858111925388,10,0.8
5
+ inducer,11954,10367,123,0.6703124046325684,1.9484352616885738,10,0.8
6
+ source_key,12179,3534,248,0.6622770428657532,1.0208572414815842,10,0.8
7
+ enzyme_name,12099,836,49,0.6385555863380432,1.065326651924217,10,0.8
8
+ plasmid,8217,2639,88,0.5960489511489868,0.9959376550261058,10,0.8
9
+ desalting_process,5540,1101,57,0.5167031288146973,1.409257816202528,10,0.8
10
+ expression_strain,8268,6721,78,0.5065197348594666,1.002864831687617,10,0.8
11
+ medium_name,7644,3330,110,0.37134140729904175,1.64247449182673,10,0.8
12
+ elution_buffer,5198,1601,79,0.29947522282600403,1.789764588587713,10,0.8
13
+ lysis_buffer,5625,2331,107,0.18839938938617706,2.10128452575196,10,0.8
14
+ molecular_weight,495,10,1,,,10,0.8
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=10/t=0.9_ALL_FIELDS.csv.gz CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dab6c87fa0742c7e78512dfa2a4278364dd63319e26bce6e49c592c5dfa5c998
3
- size 1495033
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96c4d8a99c656b38ab81b4e43795a174a8004c058f4324e00553a4823305dd2b
3
+ size 2312140
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=10/t=0.9_FIELD_CLUSTER_METRICS.csv CHANGED
@@ -1,14 +1,14 @@
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
- induction_temperature,3656,3130,36,0.9994598627090454,0.1598977747630751,10,0.9
3
- organism_source,6292,5544,37,0.9994490146636963,0.16579063872248295,10,0.9
4
- enzyme_name,7975,158,10,0.9979529976844788,0.038391667993584455,10,0.9
5
- strain,2444,1574,17,0.9973907470703125,0.17012588673646756,10,0.9
6
- source_key,8021,1173,89,0.9934604167938232,0.1675002353004377,10,0.9
7
- plasmid,5480,1531,62,0.9283315539360046,0.2736388925939326,10,0.9
8
- desalting_process,3720,377,25,0.9199746251106262,0.35025741841179203,10,0.9
9
- inducer,7889,5908,76,0.896723747253418,0.9295681879117219,10,0.9
10
- lysis_buffer,3714,444,33,0.8245513439178467,0.583100777929201,10,0.9
11
- elution_buffer,3530,373,25,0.7746942043304443,0.6386139132462056,10,0.9
12
- expression_strain,5677,4555,69,0.6772974133491516,0.6400915704142556,10,0.9
13
- medium_name,4806,1155,53,0.6625632047653198,0.7878992788324822,10,0.9
14
- molecular_weight,295,10,1,,,10,0.9
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ induction_temperature,5383,4695,40,0.9995632767677307,0.1774096292479364,10,0.9
3
+ organism_source,9834,8928,45,0.9990827441215515,0.21129299717511354,10,0.9
4
+ enzyme_name,12099,330,22,0.9921022653579712,0.1891561011264982,10,0.9
5
+ source_key,12179,1621,123,0.9812606573104858,0.26394673416001385,10,0.9
6
+ strain,3834,2354,36,0.9812034368515015,0.27305567145001625,10,0.9
7
+ desalting_process,5540,503,32,0.9546884298324585,0.30908473361018685,10,0.9
8
+ plasmid,8217,1809,72,0.9347535371780396,0.3112191042150386,10,0.9
9
+ inducer,11954,8961,104,0.8782563209533691,1.1053978590505338,10,0.9
10
+ lysis_buffer,5625,643,45,0.7976125478744507,0.5979926328129845,10,0.9
11
+ elution_buffer,5198,578,35,0.7535232901573181,0.7173428637904252,10,0.9
12
+ expression_strain,8268,6275,88,0.6845119595527649,0.6286888483142167,10,0.9
13
+ medium_name,7644,2016,79,0.6611666083335876,0.9188101393506772,10,0.9
14
+ molecular_weight,495,10,1,,,10,0.9
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=2/t=0.5_ALL_FIELDS.csv.gz CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b31358d269f031334d480532bb988368c53473ba3917c763f8223697a4379258
3
- size 1710112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2925d67931b483c0a89de3b5f536337395593b37537f9b100cf8d1030864c6f7
3
+ size 2709142
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=2/t=0.5_FIELD_CLUSTER_METRICS.csv CHANGED
@@ -1,14 +1,14 @@
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
- organism_source,6292,6251,120,0.7359616160392761,1.181714929032349,2,0.5
3
- strain,2444,2393,129,0.6301724314689636,1.4046663400574038,2,0.5
4
- expression_strain,5677,5655,93,0.24549226462841034,1.52794236330288,2,0.5
5
- inducer,7889,7864,127,0.233584925532341,1.7430825349585015,2,0.5
6
- induction_temperature,3656,3644,55,0.10356168448925018,1.5492199536085371,2,0.5
7
- lysis_buffer,3714,3684,129,0.0684572383761406,1.4843066037442114,2,0.5
8
- molecular_weight,295,275,42,0.024247264489531517,2.0222289343348954,2,0.5
9
- desalting_process,3720,3643,252,0.023925328627228737,1.7031714766522172,2,0.5
10
- plasmid,5480,5386,470,0.021125968545675278,2.0921226508851802,2,0.5
11
- elution_buffer,3530,3484,210,0.003627642523497343,1.6897520320245834,2,0.5
12
- enzyme_name,7975,7749,1114,-0.06914626061916351,2.230431267218011,2,0.5
13
- medium_name,4806,4753,245,-0.06954880803823471,1.6505925915314352,2,0.5
14
- source_key,8021,8020,34,-0.0712493360042572,2.7397064264415487,2,0.5
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,9834,9791,137,0.7704284191131592,1.2501697301968293,2,0.5
3
+ expression_strain,8268,8241,150,0.24290937185287476,1.7150252913558683,2,0.5
4
+ inducer,11954,11923,193,0.17136798799037933,1.743002022446186,2,0.5
5
+ strain,3834,3777,208,0.15669627487659454,1.505547946544373,2,0.5
6
+ induction_temperature,5383,5373,74,0.03545905649662018,1.752249976611971,2,0.5
7
+ lysis_buffer,5625,5574,177,0.03139469027519226,1.5529810781662363,2,0.5
8
+ desalting_process,5540,5443,380,-0.0002556914114393294,1.7851687421827864,2,0.5
9
+ elution_buffer,5198,5149,278,-0.011876239441335201,1.760481524990134,2,0.5
10
+ molecular_weight,495,469,67,-0.018874559551477432,1.9965740382522092,2,0.5
11
+ plasmid,8217,8095,745,-0.025197332724928856,2.1926350320168777,2,0.5
12
+ medium_name,7644,7570,340,-0.059237558394670486,1.7310688452219993,2,0.5
13
+ enzyme_name,12099,11775,1643,-0.07552535086870193,2.2334835924948346,2,0.5
14
+ source_key,12179,12179,44,-0.09427706152200699,2.639501277092732,2,0.5
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=2/t=0.6_ALL_FIELDS.csv.gz CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c1f1ce76f95693ee02ba3b06f9c4cbb3d0cce180bb2c332cf3b3e39b0e19d9af
3
- size 1743425
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c9c1443612bfff6bdb1a0b11fb8e45a9555111fd281b35c9912c4596fe5f76f
3
+ size 2726496
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=2/t=0.6_FIELD_CLUSTER_METRICS.csv CHANGED
@@ -1,14 +1,14 @@
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
- organism_source,6292,6214,156,0.8042559623718262,0.7408389867080667,2,0.6
3
- strain,2444,2315,164,0.7870423197746277,0.8584690378739643,2,0.6
4
- inducer,7889,7836,204,0.524699866771698,1.573576424497548,2,0.6
5
- expression_strain,5677,5603,133,0.4494732618331909,1.2963580596715796,2,0.6
6
- molecular_weight,295,249,48,0.22060450911521912,1.4634350113588142,2,0.6
7
- induction_temperature,3656,3624,78,0.18628351390361786,1.2893443441870371,2,0.6
8
- plasmid,5480,5088,627,0.12096375226974487,1.5976979804074654,2,0.6
9
- medium_name,4806,4648,384,0.12037362158298492,1.5880109350843041,2,0.6
10
- enzyme_name,7975,7037,1432,0.09422920644283295,1.7338125264231143,2,0.6
11
- desalting_process,3720,3508,385,0.08089420199394226,1.6312461880619276,2,0.6
12
- elution_buffer,3530,3398,316,0.059726908802986145,1.6285720785632896,2,0.6
13
- lysis_buffer,3714,3638,206,0.02915474958717823,1.527254027060754,2,0.6
14
- source_key,8021,8018,175,-0.12275737524032593,2.1070661758304765,2,0.6
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,9834,9748,184,0.839300274848938,0.8359968641942924,2,0.6
3
+ strain,3834,3647,248,0.5075187683105469,1.1932810964143985,2,0.6
4
+ inducer,11954,11873,290,0.4907238781452179,1.6220588200475619,2,0.6
5
+ expression_strain,8268,8176,253,0.3542380630970001,1.5048741930455165,2,0.6
6
+ induction_temperature,5383,5339,98,0.2064398229122162,1.308228853501364,2,0.6
7
+ molecular_weight,495,433,85,0.09952028840780258,1.5739863446543545,2,0.6
8
+ medium_name,7644,7413,526,0.0954468846321106,1.6789956216088666,2,0.6
9
+ enzyme_name,12099,10782,2087,0.08467531204223633,1.7630898202220566,2,0.6
10
+ plasmid,8217,7601,981,0.07050518691539764,1.7315854654345106,2,0.6
11
+ desalting_process,5540,5215,560,0.061758555471897125,1.6893683436157534,2,0.6
12
+ elution_buffer,5198,5028,412,0.012021989561617374,1.7179146756846502,2,0.6
13
+ lysis_buffer,5625,5499,291,-0.013728567399084568,1.6005080143435026,2,0.6
14
+ source_key,12179,12174,244,-0.14928416907787323,2.0591890117296145,2,0.6
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=2/t=0.7_ALL_FIELDS.csv.gz CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:372c8ad0b9a248ece143e35ab00401d3c696c0af72269c3418854f34708c99fe
3
- size 1749154
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f76ed876f726d17238daa9c86fb728ccae616bebe5ee02136bd0a877be000d8f
3
+ size 2745302
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=2/t=0.7_FIELD_CLUSTER_METRICS.csv CHANGED
@@ -1,14 +1,14 @@
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
- organism_source,6292,6185,177,0.9244288802146912,0.5123129776684122,2,0.7
3
- strain,2444,2272,183,0.8965273499488831,0.6384774801002754,2,0.7
4
- inducer,7889,7775,294,0.5697078108787537,1.3747385547864301,2,0.7
5
- molecular_weight,295,211,50,0.5260589122772217,0.9766324181448153,2,0.7
6
- expression_strain,5677,5554,178,0.407649964094162,1.0115625528322254,2,0.7
7
- induction_temperature,3656,3591,110,0.4044451415538788,0.8898753305491555,2,0.7
8
- plasmid,5480,4633,714,0.3942432701587677,1.0990658686295904,2,0.7
9
- enzyme_name,7975,5802,1480,0.3440663516521454,1.2574927880380684,2,0.7
10
- desalting_process,3720,3171,519,0.3052557110786438,1.2599141026652554,2,0.7
11
- medium_name,4806,4412,550,0.23887693881988525,1.3061334257338666,2,0.7
12
- elution_buffer,3530,3158,472,0.2113880217075348,1.4638544819853032,2,0.7
13
- source_key,8021,7950,674,0.10563254356384277,1.5440591831062185,2,0.7
14
- lysis_buffer,3714,3502,379,0.09377645701169968,1.4373119018318188,2,0.7
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,9834,9712,212,0.9428121447563171,0.6241720529072671,2,0.7
3
+ strain,3834,3491,293,0.6721920967102051,0.836816569858886,2,0.7
4
+ inducer,11954,11770,434,0.5642595291137695,1.414326074412011,2,0.7
5
+ molecular_weight,495,347,84,0.475884348154068,0.9424701654907065,2,0.7
6
+ induction_temperature,5383,5296,134,0.44137969613075256,0.983055153047712,2,0.7
7
+ expression_strain,8268,8030,336,0.3884178102016449,1.0919365744676077,2,0.7
8
+ plasmid,8217,6772,1131,0.3349080979824066,1.2177228247538248,2,0.7
9
+ enzyme_name,12099,8895,2153,0.32166555523872375,1.289564419825727,2,0.7
10
+ desalting_process,5540,4639,778,0.2751881778240204,1.307125018189765,2,0.7
11
+ medium_name,7644,7022,818,0.1876334846019745,1.374892266610774,2,0.7
12
+ elution_buffer,5198,4660,672,0.18267036974430084,1.5228708847163748,2,0.7
13
+ lysis_buffer,5625,5315,569,0.062071043998003006,1.5161862326795996,2,0.7
14
+ source_key,12179,12099,990,0.04957820475101471,1.6299819272418739,2,0.7
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=2/t=0.8_ALL_FIELDS.csv.gz CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8afb9c67304d1e1c7ab763880c75a8e651247e7110e897e2f057adee339b7f5
3
- size 1693771
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98fe753e0cd9b25061de97b02a3d688e470c6ad95f6a0f4f9910762fcfd9672b
3
+ size 2633275
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=2/t=0.8_FIELD_CLUSTER_METRICS.csv CHANGED
@@ -1,14 +1,14 @@
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
- organism_source,6292,6161,196,0.9871184229850769,0.40763664563497176,2,0.8
3
- strain,2444,2219,206,0.9496977925300598,0.4302512151572753,2,0.8
4
- molecular_weight,295,171,56,0.8738483786582947,0.49033222226921264,2,0.8
5
- source_key,8021,7458,1555,0.8493194580078125,0.6596555103699607,2,0.8
6
- induction_temperature,3656,3559,131,0.8182914853096008,0.5516981997621985,2,0.8
7
- desalting_process,3720,2704,666,0.6945850849151611,0.7790529022894463,2,0.8
8
- inducer,7889,7632,400,0.6783764958381653,1.0916827657846424,2,0.8
9
- enzyme_name,7975,4078,1305,0.655800998210907,0.7837910979194758,2,0.8
10
- plasmid,5480,4069,744,0.6508817672729492,0.7131719435646066,2,0.8
11
- elution_buffer,3530,2699,598,0.5654290914535522,0.87955478396106,2,0.8
12
- medium_name,4806,3956,729,0.5421817302703857,0.8380413127526829,2,0.8
13
- expression_strain,5677,5483,250,0.5199859738349915,0.6746388336660916,2,0.8
14
- lysis_buffer,3714,3152,634,0.43792206048965454,1.0593182708537643,2,0.8
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,9834,9675,232,0.9871939420700073,0.41423139991444985,2,0.8
3
+ molecular_weight,495,288,87,0.8654143214225769,0.5092237635845475,2,0.8
4
+ strain,3834,3348,316,0.8594660758972168,0.5194915098734986,2,0.8
5
+ induction_temperature,5383,5238,162,0.8264345526695251,0.479628293760092,2,0.8
6
+ source_key,12179,11343,2282,0.7697919607162476,0.7494020962317138,2,0.8
7
+ desalting_process,5540,3866,1005,0.6931871175765991,0.8031729133538142,2,0.8
8
+ enzyme_name,12099,6359,1981,0.6523424386978149,0.8135544160412623,2,0.8
9
+ inducer,11954,11540,580,0.6523213982582092,1.098152974380361,2,0.8
10
+ plasmid,8217,5724,1168,0.631205141544342,0.7459274466257438,2,0.8
11
+ elution_buffer,5198,3878,871,0.5466943383216858,0.9030539261740668,2,0.8
12
+ expression_strain,8268,7834,425,0.4981157183647156,0.7290515304055276,2,0.8
13
+ medium_name,7644,6252,1093,0.49031388759613037,0.9029494417032765,2,0.8
14
+ lysis_buffer,5625,4714,939,0.41990897059440613,1.0630915276773931,2,0.8
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=2/t=0.9_ALL_FIELDS.csv.gz CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:98dfe2ef46412eea67c265c3ed3939c11a2b037efb6552dc25a876627e63608a
3
- size 1644932
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d893314c79c6a66f45b6784cfec2cd04f67686ed2b30932e71d04b5be609217
3
+ size 2548126
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=2/t=0.9_FIELD_CLUSTER_METRICS.csv CHANGED
@@ -1,14 +1,14 @@
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
- molecular_weight,295,142,49,0.9999998807907104,5.184469437610214e-07,2,0.9
3
- organism_source,6292,6141,211,0.9985463619232178,0.19276997667080423,2,0.9
4
- induction_temperature,3656,3527,152,0.9982514977455139,0.17912158313851584,2,0.9
5
- source_key,8021,7217,1742,0.9953441023826599,0.24073583298038487,2,0.9
6
- strain,2444,2164,206,0.9901585578918457,0.25285042093249843,2,0.9
7
- desalting_process,3720,2402,713,0.9532882571220398,0.3236402956013293,2,0.9
8
- plasmid,5480,3546,736,0.9246120452880859,0.33677715956687676,2,0.9
9
- enzyme_name,7975,2539,906,0.9176825881004333,0.3723740436841698,2,0.9
10
- lysis_buffer,3714,2681,776,0.8995020985603333,0.44118849965644563,2,0.9
11
- elution_buffer,3530,2321,660,0.8951386213302612,0.4043604880176693,2,0.9
12
- inducer,7889,7404,531,0.8646087050437927,0.6126176495524824,2,0.9
13
- medium_name,4806,3577,837,0.8121472597122192,0.45963750715300056,2,0.9
14
- expression_strain,5677,5382,306,0.6984133720397949,0.4627520690822105,2,0.9
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ molecular_weight,495,250,85,0.9999998211860657,5.681546931635111e-07,2,0.9
3
+ induction_temperature,5383,5190,186,0.9983040690422058,0.20138673914730879,2,0.9
4
+ organism_source,9834,9647,253,0.997991681098938,0.2103376142676233,2,0.9
5
+ source_key,12179,10842,2706,0.9870166182518005,0.2836417395730608,2,0.9
6
+ strain,3834,3249,326,0.9719149470329285,0.2705146872943898,2,0.9
7
+ desalting_process,5540,3398,1044,0.9576654434204102,0.3272160789823375,2,0.9
8
+ plasmid,8217,4748,1070,0.9294074773788452,0.3416671696525665,2,0.9
9
+ enzyme_name,12099,4086,1428,0.9290539026260376,0.3556194508980408,2,0.9
10
+ elution_buffer,5198,3292,946,0.8923376202583313,0.4178643375220069,2,0.9
11
+ lysis_buffer,5625,4005,1165,0.890524685382843,0.44114747951147765,2,0.9
12
+ inducer,11954,11175,779,0.8426512479782104,0.6559040293450579,2,0.9
13
+ medium_name,7644,5601,1264,0.8092308640480042,0.4543970898029418,2,0.9
14
+ expression_strain,8268,7663,501,0.7144708037376404,0.4570312623285555,2,0.9
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=20/t=0.5_ALL_FIELDS.csv.gz CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:34c6a34db9e26f8af7c9c67c4b21fdacbf0baa1f0c700744ef887abf74ae7f52
3
- size 1620638
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4c9a2605d81a12811c87172d68c5b862afe2045513a1a87c0f05e0121b55c67
3
+ size 2577408
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=20/t=0.5_FIELD_CLUSTER_METRICS.csv CHANGED
@@ -1,14 +1,14 @@
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
- organism_source,6292,5890,25,0.7503998875617981,1.412051211361173,20,0.5
3
- strain,2444,1909,13,0.7046726942062378,1.9641575436735057,20,0.5
4
- expression_strain,5677,5489,22,0.35810378193855286,2.234774507282118,20,0.5
5
- inducer,7889,7669,26,0.3461412489414215,3.1487951266514353,20,0.5
6
- lysis_buffer,3714,3440,16,0.1226840689778328,3.130491517019406,20,0.5
7
- induction_temperature,3656,3576,20,0.11875562369823456,2.0472911478467433,20,0.5
8
- molecular_weight,295,146,4,0.1064641922712326,3.0329216874363865,20,0.5
9
- plasmid,5480,4568,76,0.0591772198677063,3.3401350373044885,20,0.5
10
- elution_buffer,3530,3185,33,0.05365007370710373,3.1841766404334133,20,0.5
11
- desalting_process,3720,3217,32,0.042665764689445496,3.6417904915043997,20,0.5
12
- enzyme_name,7975,5683,128,0.017951760441064835,3.970489532942838,20,0.5
13
- source_key,8021,8004,18,-0.0020853711757808924,4.061182762730637,20,0.5
14
- medium_name,4806,4259,42,-0.08588773012161255,3.172504799031956,20,0.5
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,9834,9405,31,0.7828075885772705,1.6501868512035238,20,0.5
3
+ expression_strain,8268,7996,30,0.2769909203052521,2.8060146090868168,20,0.5
4
+ inducer,11954,11717,38,0.2556192874908447,3.146519952105198,20,0.5
5
+ strain,3834,3201,24,0.1363760083913803,2.630279081479377,20,0.5
6
+ lysis_buffer,5625,5224,21,0.09983358532190323,3.4301458577057127,20,0.5
7
+ molecular_weight,495,319,8,0.07148878276348114,3.2466990622174934,20,0.5
8
+ induction_temperature,5383,5273,23,0.06485782563686371,2.268416673491494,20,0.5
9
+ elution_buffer,5198,4719,42,0.028079677373170853,3.2742072116557415,20,0.5
10
+ desalting_process,5540,4890,54,0.026684945449233055,3.61437887516177,20,0.5
11
+ plasmid,8217,7026,129,0.01730905845761299,3.5806924023810667,20,0.5
12
+ enzyme_name,12099,8930,195,0.008942244574427605,4.04923273748927,20,0.5
13
+ source_key,12179,12124,19,-0.0040798853151500225,4.384408009734411,20,0.5
14
+ medium_name,7644,6941,56,-0.035881176590919495,3.4146118623634587,20,0.5
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=20/t=0.6_ALL_FIELDS.csv.gz CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c9673de061656b377cbfb1752bfd43ad87fbc7ebc95e76b4415e1d5dbf8fb11
3
- size 1607537
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c50e3eb137b954471b0bc9b418a5bef0ddc7db7b1dbcb644ea1a3a89c38c8cd
3
+ size 2521398
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=20/t=0.6_FIELD_CLUSTER_METRICS.csv CHANGED
@@ -1,14 +1,14 @@
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
- strain,2444,1630,8,0.8813602328300476,1.1830246301662362,20,0.6
3
- organism_source,6292,5675,25,0.8370367288589478,0.9336707082033557,20,0.6
4
- inducer,7889,7478,36,0.5766865611076355,2.6992117465588303,20,0.6
5
- expression_strain,5677,5249,28,0.489561527967453,1.8145193455926454,20,0.6
6
- induction_temperature,3656,3429,17,0.21010009944438934,1.62299214748714,20,0.6
7
- molecular_weight,295,77,3,0.20079904794692993,2.488450737935613,20,0.6
8
- enzyme_name,7975,2882,70,0.14786164462566376,2.9217208068418423,20,0.6
9
- plasmid,5480,3332,56,0.12614291906356812,2.5673927998255954,20,0.6
10
- medium_name,4806,3720,50,0.09682820737361908,3.1286267960650203,20,0.6
11
- desalting_process,3720,2618,40,0.04840308055281639,3.5885319645475113,20,0.6
12
- lysis_buffer,3714,3165,25,0.03675231337547302,3.4388532933976967,20,0.6
13
- elution_buffer,3530,2689,40,0.03268149495124817,3.2986390760344206,20,0.6
14
- source_key,8021,7854,66,-0.029732568189501762,3.530863032595723,20,0.6
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,9834,9061,26,0.874016523361206,0.9642766492499072,20,0.6
3
+ strain,3834,2746,19,0.560074508190155,1.7834888512102718,20,0.6
4
+ inducer,11954,11384,49,0.5477119088172913,2.79315595208321,20,0.6
5
+ expression_strain,8268,7675,50,0.3993888199329376,2.2191893789291943,20,0.6
6
+ induction_temperature,5383,5080,21,0.2806701362133026,1.5839896908548716,20,0.6
7
+ molecular_weight,495,143,4,0.13977301120758057,2.754454061493555,20,0.6
8
+ enzyme_name,12099,4896,114,0.12135324627161026,3.0846206483151617,20,0.6
9
+ plasmid,8217,4943,90,0.09129977971315384,2.851638215216592,20,0.6
10
+ medium_name,7644,6233,76,0.08944616466760635,3.2933215547428523,20,0.6
11
+ desalting_process,5540,3997,58,0.03805313631892204,3.6089786189227784,20,0.6
12
+ lysis_buffer,5625,4863,36,0.016103604808449745,3.6785158176479067,20,0.6
13
+ elution_buffer,5198,4099,55,-0.0024938161950558424,3.374269833140706,20,0.6
14
+ source_key,12179,11939,90,-0.04484950751066208,3.44433740415082,20,0.6
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=20/t=0.7_ALL_FIELDS.csv.gz CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cac59176c9712e61c09a5d572c49914603ebb29c831034fb5eadb137decae0ab
3
- size 1572963
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d1d94cf616b0678e9e386d9ac61ed824eab46f40431099ce910b702b46495e5
3
+ size 2462849
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=20/t=0.7_FIELD_CLUSTER_METRICS.csv CHANGED
@@ -1,14 +1,14 @@
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
- strain,2444,1528,6,0.955305814743042,0.7091875076994215,20,0.7
3
- organism_source,6292,5458,21,0.9531962275505066,0.5181467351865382,20,0.7
4
- inducer,7889,7121,42,0.6300966143608093,2.428079947639936,20,0.7
5
- induction_temperature,3656,3237,21,0.4609184265136719,1.1529742222004016,20,0.7
6
- expression_strain,5677,4951,32,0.4195638597011566,1.3579367179560307,20,0.7
7
- enzyme_name,7975,1012,26,0.398987740278244,1.6896747373772538,20,0.7
8
- plasmid,5480,2151,36,0.3418406844139099,1.7288504104155615,20,0.7
9
- medium_name,4806,2754,46,0.1722477674484253,2.6118940546184355,20,0.7
10
- desalting_process,3720,1561,27,0.14235807955265045,2.908586553818619,20,0.7
11
- source_key,8021,6094,155,0.08303676545619965,2.6021573001207474,20,0.7
12
- elution_buffer,3530,1704,36,0.07601241767406464,3.2330573868291492,20,0.7
13
- lysis_buffer,3714,2429,35,0.019434064626693726,3.3336463985386593,20,0.7
14
- molecular_weight,295,0,0,,,20,0.7
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,9834,8905,27,0.9649766683578491,0.5953940198236635,20,0.7
3
+ strain,3834,2450,19,0.6681674122810364,1.133644883404909,20,0.7
4
+ inducer,11954,10848,65,0.6065726280212402,2.5098096493877198,20,0.7
5
+ induction_temperature,5383,4808,21,0.4768288731575012,1.1681998586684266,20,0.7
6
+ expression_strain,8268,7011,48,0.4091379940509796,1.4788282643605033,20,0.7
7
+ enzyme_name,12099,2013,48,0.33695027232170105,2.0105331363159045,20,0.7
8
+ plasmid,8217,2952,50,0.28714099526405334,1.9129089744672816,20,0.7
9
+ desalting_process,5540,2260,35,0.13907232880592346,3.0857738250251114,20,0.7
10
+ medium_name,7644,4612,66,0.11902673542499542,2.937801309084376,20,0.7
11
+ elution_buffer,5198,2683,58,0.053476929664611816,3.3844487130784358,20,0.7
12
+ source_key,12179,9630,221,0.044089656323194504,2.7554174836371654,20,0.7
13
+ lysis_buffer,5625,3799,58,-0.002129903994500637,3.534695609790234,20,0.7
14
+ molecular_weight,495,20,1,,,20,0.7
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=20/t=0.8_ALL_FIELDS.csv.gz CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:77923c0d4af2ec3ee16d1d3984dd2a51f958fc0fee9cd44798bac3b25272ec90
3
- size 1502113
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c58a348e2c669ee3a43dc72b75c3a19791871f582061354831bfed5a170b3af
3
+ size 2330436
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=20/t=0.8_FIELD_CLUSTER_METRICS.csv CHANGED
@@ -1,14 +1,14 @@
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
- organism_source,6292,5392,21,0.9926964044570923,0.37455294163170266,20,0.8
3
- strain,2444,1467,5,0.9782355427742004,0.4072372774625528,20,0.8
4
- induction_temperature,3656,3086,18,0.867624819278717,0.5778048890213031,20,0.8
5
- source_key,8021,305,13,0.8017788529396057,0.7195722948229245,20,0.8
6
- inducer,7889,6441,44,0.7338472008705139,1.9623813184610825,20,0.8
7
- enzyme_name,7975,185,6,0.6508431434631348,1.1559015606063803,20,0.8
8
- plasmid,5480,1607,31,0.6495945453643799,0.829491345489685,20,0.8
9
- expression_strain,5677,4537,30,0.538157045841217,0.9610951439799056,20,0.8
10
- desalting_process,3720,470,12,0.5163097977638245,1.513031823193578,20,0.8
11
- medium_name,4806,1462,30,0.3894849121570587,1.6498554932807283,20,0.8
12
- elution_buffer,3530,646,17,0.19492991268634796,2.3035049192966897,20,0.8
13
- lysis_buffer,3714,986,28,0.16803999245166779,2.326535204168088,20,0.8
14
- molecular_weight,295,0,0,,,20,0.8
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,9834,8791,26,0.9927010536193848,0.4153560808145941,20,0.8
3
+ strain,3834,2277,16,0.9038386940956116,0.6186001987224603,20,0.8
4
+ induction_temperature,5383,4644,19,0.8813338279724121,0.5578173039182678,20,0.8
5
+ inducer,11954,9783,62,0.695711076259613,2.2263294895317642,20,0.8
6
+ enzyme_name,12099,361,12,0.6748945713043213,1.0304951358060286,20,0.8
7
+ source_key,12179,695,29,0.624921441078186,1.114993567025615,20,0.8
8
+ plasmid,8217,2015,37,0.6215651631355286,0.958589052652611,20,0.8
9
+ expression_strain,8268,6385,46,0.5254905223846436,1.0265913400823838,20,0.8
10
+ desalting_process,5540,600,15,0.5153481364250183,1.610155211607981,20,0.8
11
+ medium_name,7644,2678,49,0.38099217414855957,1.7161080374910473,20,0.8
12
+ elution_buffer,5198,1023,26,0.21529993414878845,2.3483609503330687,20,0.8
13
+ lysis_buffer,5625,1627,43,0.13791300356388092,2.4391386081071245,20,0.8
14
+ molecular_weight,495,0,0,,,20,0.8
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=20/t=0.9_ALL_FIELDS.csv.gz CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:93084a271360438b5ad0679605cbe382ddacd1feb97a6a34e200bd7bdeda48e0
3
- size 1475540
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a804d0d0614f1c1ba34ca998d3d529ceeeff4b83dd6a09807d3bc94b3d27b0e
3
+ size 2283622
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=20/t=0.9_FIELD_CLUSTER_METRICS.csv CHANGED
@@ -1,14 +1,14 @@
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
- enzyme_name,7975,49,2,0.9999998211860657,5.367938782260942e-07,20,0.9
3
- induction_temperature,3656,2965,24,0.9999995231628418,4.7277720493779304e-06,20,0.9
4
- organism_source,6292,5314,19,0.9998162388801575,0.008617838265056231,20,0.9
5
- strain,2444,1420,5,0.9989898204803467,0.028742681438578305,20,0.9
6
- source_key,8021,116,5,0.9831867814064026,0.16748777303524934,20,0.9
7
- desalting_process,3720,121,3,0.9629573225975037,0.32746048823200496,20,0.9
8
- inducer,7889,5288,27,0.9372491240501404,0.9905408670230594,20,0.9
9
- plasmid,5480,1059,24,0.9341457486152649,0.309102090188955,20,0.9
10
- lysis_buffer,3714,78,3,0.8617530465126038,0.47276638111393515,20,0.9
11
- expression_strain,5677,4016,30,0.6727377772331238,0.7853666214835181,20,0.9
12
- medium_name,4806,703,15,0.6586852669715881,0.9881778878308529,20,0.9
13
- elution_buffer,3530,89,3,0.5853481888771057,1.1578433187640458,20,0.9
14
- molecular_weight,295,0,0,,,20,0.9
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ enzyme_name,12099,75,3,0.9999998807907104,6.238960108995635e-07,20,0.9
3
+ induction_temperature,5383,4540,28,0.9999993443489075,7.929783618856911e-06,20,0.9
4
+ organism_source,9834,8603,20,0.9998865127563477,0.00847393240479874,20,0.9
5
+ desalting_process,5540,154,3,0.9922242760658264,0.11600631619661278,20,0.9
6
+ source_key,12179,135,6,0.9855530858039856,0.16215790693650875,20,0.9
7
+ strain,3834,2052,15,0.9810547232627869,0.2994589533038894,20,0.9
8
+ plasmid,8217,1252,27,0.9282448887825012,0.3152117406453656,20,0.9
9
+ inducer,11954,8240,46,0.9123760461807251,1.0839200078558637,20,0.9
10
+ elution_buffer,5198,243,8,0.7607119679450989,0.7819716510808115,20,0.9
11
+ lysis_buffer,5625,164,6,0.7255371809005737,0.747816082177125,20,0.9
12
+ expression_strain,8268,5728,48,0.6845447421073914,0.7162779213562122,20,0.9
13
+ medium_name,7644,1418,26,0.6683018803596497,1.0372546396325335,20,0.9
14
+ molecular_weight,495,0,0,,,20,0.9
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=30/t=0.5_ALL_FIELDS.csv.gz CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c27197498d46f6c79546542e3dc647c004e43f9684f544ee0631e3c5aef9a01e
3
- size 1600185
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31438fba63c34a938d87c489b6632d02bdf85d223e0cef8d3d163e562f42bae1
3
+ size 2542442
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=30/t=0.5_FIELD_CLUSTER_METRICS.csv CHANGED
@@ -1,14 +1,14 @@
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
- strain,2444,1777,7,0.7601905465126038,2.0356520157495352,30,0.5
3
- organism_source,6292,5754,17,0.7594259977340698,1.4800336618897305,30,0.5
4
- expression_strain,5677,5393,15,0.36399152874946594,2.561622158353512,30,0.5
5
- inducer,7889,7685,22,0.3545350432395935,3.1008249148543006,30,0.5
6
- molecular_weight,295,102,2,0.12454235553741455,3.5041937249663886,30,0.5
7
- lysis_buffer,3714,3303,8,0.12067686766386032,3.635269864487448,30,0.5
8
- induction_temperature,3656,3515,15,0.11761916428804398,1.909834654242092,30,0.5
9
- plasmid,5480,4250,50,0.0631290152668953,3.6093783702943982,30,0.5
10
- elution_buffer,3530,3059,22,0.056219808757305145,3.540187709172764,30,0.5
11
- desalting_process,3720,3147,25,0.04758177325129509,3.7871875357248648,30,0.5
12
- enzyme_name,7975,5134,80,0.03458671271800995,4.177221271458485,30,0.5
13
- source_key,8021,7962,15,0.0021563819609582424,4.404232310170288,30,0.5
14
- medium_name,4806,4122,28,-0.0808965265750885,3.492084549443644,30,0.5
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,9834,9257,21,0.7871121764183044,1.6828715123878908,30,0.5
3
+ inducer,11954,11609,25,0.31908541917800903,3.2552853418456364,30,0.5
4
+ expression_strain,8268,7881,21,0.3189159631729126,3.1515476510207314,30,0.5
5
+ strain,3834,3050,14,0.14052380621433258,2.548295840419977,30,0.5
6
+ molecular_weight,495,241,4,0.10911101847887039,3.277023733572661,30,0.5
7
+ lysis_buffer,5625,5158,15,0.10623012483119965,3.8422257443494057,30,0.5
8
+ induction_temperature,5383,5217,18,0.08123978227376938,2.188011117057695,30,0.5
9
+ elution_buffer,5198,4641,29,0.05189056321978569,3.4778350919279375,30,0.5
10
+ desalting_process,5540,4741,37,0.03482285141944885,3.9263772940211923,30,0.5
11
+ plasmid,8217,6692,85,0.030402911826968193,3.8590032117072672,30,0.5
12
+ enzyme_name,12099,8184,127,0.01676197350025177,4.305529025661993,30,0.5
13
+ source_key,12179,12113,17,0.0014261760516092181,4.52505700045992,30,0.5
14
+ medium_name,7644,6841,41,-0.04064856469631195,3.776426762552451,30,0.5
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=30/t=0.6_ALL_FIELDS.csv.gz CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9d11ff360beffe92ae3c5b60dc7cad28e036256472fcb14d02e21844a23c8fa
3
- size 1584794
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2cf2a55b6b11fac09ff9f88fa31fa34e4beb92f16e0b7a3b79f5c1eaa0a7f42
3
+ size 2478527
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=30/t=0.6_FIELD_CLUSTER_METRICS.csv CHANGED
@@ -1,14 +1,14 @@
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
- strain,2444,1589,6,0.8902954459190369,1.1249316528951407,30,0.6
3
- organism_source,6292,5410,14,0.8541831374168396,0.69426034005274,30,0.6
4
- inducer,7889,7479,27,0.5830671191215515,2.6656896609191927,30,0.6
5
- expression_strain,5677,5158,20,0.5152678489685059,1.9236220969671713,30,0.6
6
- induction_temperature,3656,3383,13,0.2262950837612152,1.57448412450708,30,0.6
7
- enzyme_name,7975,2357,41,0.17569437623023987,2.8539145106818347,30,0.6
8
- plasmid,5480,2953,36,0.13402360677719116,2.667810688494559,30,0.6
9
- medium_name,4806,3536,37,0.0896327868103981,3.3675858899493836,30,0.6
10
- desalting_process,3720,2465,27,0.0675622746348381,3.8099595797500374,30,0.6
11
- elution_buffer,3530,2458,24,0.04150938615202904,3.5922749073597173,30,0.6
12
- lysis_buffer,3714,2984,14,0.028299733996391296,3.962441893353738,30,0.6
13
- source_key,8021,7694,48,-0.015119753777980804,3.9088511378551765,30,0.6
14
- molecular_weight,295,35,1,,,30,0.6
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,9834,8873,17,0.8821169137954712,0.980691628466982,30,0.6
3
+ strain,3834,2609,12,0.579774022102356,1.833075326993843,30,0.6
4
+ inducer,11954,11201,32,0.5656386017799377,2.9075599810763553,30,0.6
5
+ expression_strain,8268,7467,35,0.41454482078552246,2.282331948005401,30,0.6
6
+ induction_temperature,5383,5025,16,0.2838282585144043,1.6878056683648623,30,0.6
7
+ molecular_weight,495,98,2,0.24707865715026855,2.326901876956492,30,0.6
8
+ enzyme_name,12099,4006,62,0.14768752455711365,3.1906444349421763,30,0.6
9
+ plasmid,8217,4436,59,0.09777848422527313,2.884134034637122,30,0.6
10
+ medium_name,7644,5930,51,0.09196951240301132,3.5583906688299147,30,0.6
11
+ desalting_process,5540,3753,38,0.05648096278309822,3.812738555930874,30,0.6
12
+ lysis_buffer,5625,4680,23,0.017936868593096733,4.0911708360045695,30,0.6
13
+ elution_buffer,5198,3861,35,0.00085125130135566,3.680704304190067,30,0.6
14
+ source_key,12179,11765,67,-0.02997599169611931,3.7745478149420304,30,0.6
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=30/t=0.7_ALL_FIELDS.csv.gz CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:990bcb33f4c06439fb7e8d0f6248f10114adeca3a4580a99196495abc50eee48
3
- size 1547700
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:444107df073563cb8da301ecc391805b67207b06630b823f6f4387f7b2f3b5e1
3
+ size 2424652
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=30/t=0.7_FIELD_CLUSTER_METRICS.csv CHANGED
@@ -1,14 +1,14 @@
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
- strain,2444,1475,4,0.9668060541152954,0.5971053780422806,30,0.7
3
- organism_source,6292,5279,14,0.9561777114868164,0.37108685210930076,30,0.7
4
- inducer,7889,7016,30,0.6428833603858948,2.529069002009106,30,0.7
5
- induction_temperature,3656,3126,16,0.47053536772727966,1.1590148187832128,30,0.7
6
- expression_strain,5677,4808,22,0.4504583477973938,1.3385516672798392,30,0.7
7
- enzyme_name,7975,678,12,0.39817237854003906,1.7394242357170695,30,0.7
8
- plasmid,5480,1894,24,0.33989858627319336,1.700609141090778,30,0.7
9
- medium_name,4806,2402,29,0.18661107122898102,2.800113533468319,30,0.7
10
- desalting_process,3720,1409,19,0.14845167100429535,3.1510688825028357,30,0.7
11
- elution_buffer,3530,1498,22,0.0831158459186554,3.2854719884284935,30,0.7
12
- source_key,8021,5201,97,0.07545509934425354,2.8085928800998294,30,0.7
13
- lysis_buffer,3714,2182,21,0.013289880007505417,3.6829335707638675,30,0.7
14
- molecular_weight,295,0,0,,,30,0.7
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,9834,8686,18,0.9690663814544678,0.49416959935751975,30,0.7
3
+ strain,3834,2363,15,0.6613224148750305,1.2696086410498202,30,0.7
4
+ inducer,11954,10609,42,0.6262892484664917,2.665603147709915,30,0.7
5
+ induction_temperature,5383,4720,17,0.47667407989501953,1.2154238817361875,30,0.7
6
+ expression_strain,8268,6751,32,0.4221341907978058,1.4854111887048762,30,0.7
7
+ enzyme_name,12099,1569,25,0.3997960388660431,1.6637648825828482,30,0.7
8
+ plasmid,8217,2624,34,0.2947281301021576,1.8651212374142847,30,0.7
9
+ desalting_process,5540,2015,23,0.12687595188617706,3.4274700964759908,30,0.7
10
+ medium_name,7644,4336,48,0.1263047456741333,2.993386027965799,30,0.7
11
+ elution_buffer,5198,2514,39,0.0532039999961853,3.5749883646674756,30,0.7
12
+ source_key,12179,8684,153,0.05140596255660057,2.8916783039197913,30,0.7
13
+ lysis_buffer,5625,3522,38,0.007223394699394703,3.6849383220449843,30,0.7
14
+ molecular_weight,495,0,0,,,30,0.7
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=30/t=0.8_ALL_FIELDS.csv.gz CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c020bec537cb11075966d161e6b412097f75dff06130c25fd84e187cb32566b1
3
- size 1487802
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d402a64515eaadf35550378bf075cb927f4360237c09db08eb28a5fc31c020df
3
+ size 2305097
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=30/t=0.8_FIELD_CLUSTER_METRICS.csv CHANGED
@@ -1,14 +1,14 @@
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
- organism_source,6292,5218,14,0.9949008226394653,0.03301672129835328,30,0.8
3
- strain,2444,1418,3,0.9830803275108337,0.2771625290949223,30,0.8
4
- induction_temperature,3656,3038,16,0.869080662727356,0.5693434786628196,30,0.8
5
- inducer,7889,6221,30,0.7540117502212524,2.074816351431419,30,0.8
6
- enzyme_name,7975,136,4,0.720913827419281,0.8713917697434361,30,0.8
7
- plasmid,5480,1311,18,0.6430783271789551,0.8793216179066483,30,0.8
8
- desalting_process,3720,353,7,0.5619339346885681,1.5085356223998132,30,0.8
9
- expression_strain,5677,4318,19,0.5276784300804138,1.1271989138262453,30,0.8
10
- medium_name,4806,1091,12,0.4316490590572357,1.7260581690631833,30,0.8
11
- lysis_buffer,3714,737,15,0.1815847009420395,2.4391545512526904,30,0.8
12
- elution_buffer,3530,521,10,0.15386579930782318,2.5492569373781953,30,0.8
13
- molecular_weight,295,0,0,,,30,0.8
14
- source_key,8021,31,1,,,30,0.8
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,9834,8584,18,0.9963101148605347,0.2476773570018303,30,0.8
3
+ strain,3834,2179,12,0.9092528223991394,0.5559086172544124,30,0.8
4
+ induction_temperature,5383,4594,17,0.8829489946365356,0.5557169777450153,30,0.8
5
+ enzyme_name,12099,224,6,0.7428946495056152,0.8116901849988282,30,0.8
6
+ inducer,11954,9513,44,0.7162615656852722,2.355611187874636,30,0.8
7
+ plasmid,8217,1697,24,0.6328004598617554,0.9021751331897937,30,0.8
8
+ desalting_process,5540,423,7,0.5758087635040283,1.5680657046201663,30,0.8
9
+ expression_strain,8268,6061,32,0.5163628458976746,1.1331682717434426,30,0.8
10
+ medium_name,7644,2025,20,0.4025120139122009,2.071290219273964,30,0.8
11
+ elution_buffer,5198,822,14,0.21012786030769348,2.492118751844664,30,0.8
12
+ lysis_buffer,5625,1245,23,0.1685381978750229,2.339804423114242,30,0.8
13
+ molecular_weight,495,0,0,,,30,0.8
14
+ source_key,12179,31,1,,,30,0.8
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=30/t=0.9_ALL_FIELDS.csv.gz CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6dfc397dcdf19c467b0a8d5529d0168b74b8bfed796274fee838cac28ef80d2e
3
- size 1470133
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52209bc1f027e0b3f4ee0761f0a01c4bbbfe71b735abc18b25f34981cf04dcd3
3
+ size 2274056
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=30/t=0.9_FIELD_CLUSTER_METRICS.csv CHANGED
@@ -1,14 +1,14 @@
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
- induction_temperature,3656,2882,20,0.999999463558197,4.828185438724473e-06,30,0.9
3
- organism_source,6292,5187,14,0.9998118281364441,0.008704258637822647,30,0.9
4
- strain,2444,1369,3,0.9991834163665771,0.031065958418081106,30,0.9
5
- desalting_process,3720,97,2,0.9899388551712036,0.10697688565120202,30,0.9
6
- inducer,7889,5039,16,0.9553627967834473,0.8892303998489335,30,0.9
7
- plasmid,5480,709,10,0.9160519242286682,0.36837472979956426,30,0.9
8
- medium_name,4806,533,7,0.7428325414657593,0.9052838747514003,30,0.9
9
- expression_strain,5677,3833,22,0.6627251505851746,0.8736693123459319,30,0.9
10
- elution_buffer,3530,64,2,0.6592882871627808,0.9666971911933472,30,0.9
11
- enzyme_name,7975,0,0,,,30,0.9
12
- lysis_buffer,3714,34,1,,,30,0.9
13
- molecular_weight,295,0,0,,,30,0.9
14
- source_key,8021,0,0,,,30,0.9
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ induction_temperature,5383,4343,20,0.9999993443489075,8.24550311609219e-06,30,0.9
3
+ organism_source,9834,8524,17,0.9998854398727417,0.008537653623878332,30,0.9
4
+ desalting_process,5540,134,2,0.9910764694213867,0.11929147822822574,30,0.9
5
+ strain,3834,1988,12,0.9838135242462158,0.28635429684411456,30,0.9
6
+ lysis_buffer,5625,76,2,0.9545453786849976,0.20249275577935133,30,0.9
7
+ inducer,11954,7717,23,0.939956784248352,0.9808835500060076,30,0.9
8
+ plasmid,8217,930,14,0.937159538269043,0.32184708517141297,30,0.9
9
+ elution_buffer,5198,135,3,0.7920598983764648,0.7313228330356937,30,0.9
10
+ medium_name,7644,1160,14,0.7130675315856934,0.9856003774290217,30,0.9
11
+ expression_strain,8268,5329,31,0.6680899858474731,0.8593234006140654,30,0.9
12
+ enzyme_name,12099,0,0,,,30,0.9
13
+ molecular_weight,495,0,0,,,30,0.9
14
+ source_key,12179,0,0,,,30,0.9
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=5/t=0.5_ALL_FIELDS.csv.gz CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6fc97ea0be85dba35c656e942aa4defaa71ee266ddddbb5b5497fd389f6532c1
3
- size 1687746
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eca6f09ff087d46ccbb298f8c7e0c52c3430d0f6ac9862687fdfc6c450a70331
3
+ size 2679581
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=5/t=0.5_FIELD_CLUSTER_METRICS.csv CHANGED
@@ -1,14 +1,14 @@
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
- organism_source,6292,6158,66,0.7369772791862488,1.5109565951300286,5,0.5
3
- strain,2444,2238,55,0.6431707143783569,1.7863081312876716,5,0.5
4
- inducer,7889,7818,71,0.2819422483444214,2.3123612554224264,5,0.5
5
- expression_strain,5677,5598,55,0.2558070421218872,1.8378732163774283,5,0.5
6
- induction_temperature,3656,3625,34,0.10276639461517334,1.9065303834591827,5,0.5
7
- lysis_buffer,3714,3589,55,0.08504025638103485,2.194626692719605,5,0.5
8
- molecular_weight,295,250,22,0.058413852006196976,2.497611335060404,5,0.5
9
- plasmid,5480,5147,253,0.032580193132162094,2.6718073240168065,5,0.5
10
- desalting_process,3720,3549,130,0.025134488940238953,2.379950440493697,5,0.5
11
- elution_buffer,3530,3400,108,0.007596910931169987,2.2751471258200913,5,0.5
12
- enzyme_name,7975,7141,515,-0.02839156612753868,2.9560051131480503,5,0.5
13
- source_key,8021,8017,27,-0.03761657327413559,3.2725116870641577,5,0.5
14
- medium_name,4806,4596,115,-0.07634414732456207,2.3329825144052223,5,0.5
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,9834,9703,81,0.7686113119125366,1.5501178244753393,5,0.5
3
+ expression_strain,8268,8169,82,0.2533850073814392,2.165116847971109,5,0.5
4
+ inducer,11954,11880,110,0.21536536514759064,2.293331068694035,5,0.5
5
+ strain,3834,3599,92,0.1474076509475708,2.0059751289581693,5,0.5
6
+ lysis_buffer,5625,5468,81,0.0555686354637146,2.2062309385103474,5,0.5
7
+ induction_temperature,5383,5336,45,0.03529872000217438,2.0214911901689177,5,0.5
8
+ molecular_weight,495,441,34,0.01630842685699463,2.6590552452949434,5,0.5
9
+ desalting_process,5540,5301,184,0.014933527447283268,2.474148427108015,5,0.5
10
+ elution_buffer,5198,5036,143,-0.0041691018268466,2.394718652830333,5,0.5
11
+ plasmid,8217,7773,377,-0.005889321677386761,2.8888110263099973,5,0.5
12
+ enzyme_name,12099,10997,771,-0.03694867342710495,2.994189839306161,5,0.5
13
+ medium_name,7644,7360,165,-0.055366382002830505,2.4027466380069717,5,0.5
14
+ source_key,12179,12178,36,-0.07051427662372589,3.108890248114516,5,0.5
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=5/t=0.6_ALL_FIELDS.csv.gz CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:114eb82786fc282dae057f38f8070d5f3bae228f657a354a39567761ce4bdb78
3
- size 1698871
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a97cacc14b8f40a19a5828c338b55b973185f0cf2df2ca144717d56863f9763a
3
+ size 2655623
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=5/t=0.6_FIELD_CLUSTER_METRICS.csv CHANGED
@@ -1,14 +1,14 @@
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
- organism_source,6292,5997,67,0.834170401096344,0.8426107290356327,5,0.6
3
- strain,2444,2048,55,0.7932126522064209,1.097719910165116,5,0.6
4
- inducer,7889,7723,113,0.5368948578834534,2.0533374310031993,5,0.6
5
- expression_strain,5677,5485,73,0.44874265789985657,1.579939037811718,5,0.6
6
- molecular_weight,295,187,19,0.25550034642219543,1.6523803787674807,5,0.6
7
- induction_temperature,3656,3557,40,0.18242205679416656,1.6504973675677728,5,0.6
8
- plasmid,5480,4436,246,0.12075365334749222,2.106117794022432,5,0.6
9
- enzyme_name,7975,5321,478,0.09901222586631775,2.322744785460987,5,0.6
10
- medium_name,4806,4300,172,0.09585053473711014,2.2682416945285575,5,0.6
11
- desalting_process,3720,3178,161,0.04695821925997734,2.3380085094756344,5,0.6
12
- elution_buffer,3530,3196,154,0.042584601789712906,2.1599144954315013,5,0.6
13
- lysis_buffer,3714,3451,90,0.01560107059776783,2.2444476456644002,5,0.6
14
- source_key,8021,7988,127,-0.08309346437454224,2.5900562693870364,5,0.6
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,9834,9481,77,0.8611820936203003,1.0187423050405497,5,0.6
3
+ inducer,11954,11728,155,0.502535879611969,2.1342184019256254,5,0.6
4
+ strain,3834,3292,92,0.4966259002685547,1.5407900592839325,5,0.6
5
+ expression_strain,8268,8006,132,0.36851269006729126,1.9361413302701713,5,0.6
6
+ induction_temperature,5383,5270,56,0.2282114177942276,1.656320803809004,5,0.6
7
+ molecular_weight,495,334,30,0.14809328317642212,2.0167128337079396,5,0.6
8
+ enzyme_name,12099,8388,725,0.09567771852016449,2.3274709939942433,5,0.6
9
+ medium_name,7644,6942,244,0.08346405625343323,2.344643971203277,5,0.6
10
+ plasmid,8217,6620,386,0.06769412010908127,2.334190833733779,5,0.6
11
+ desalting_process,5540,4730,228,0.03761005774140358,2.4289960021721257,5,0.6
12
+ elution_buffer,5198,4723,197,0.0021206364035606384,2.3074658289120573,5,0.6
13
+ lysis_buffer,5625,5256,129,-0.0013870709808543324,2.3545264059509488,5,0.6
14
+ source_key,12179,12155,180,-0.11603152006864548,2.493498303340163,5,0.6
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=5/t=0.7_ALL_FIELDS.csv.gz CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2fc37c52208ffa289c1633bb57d7b57752aa469bcd604b24860ade3c39448c79
3
- size 1672923
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd085c4d00ec935025a2126d135aa968ca9c87309eeede88cbc8689b175238f3
3
+ size 2628190
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=5/t=0.7_FIELD_CLUSTER_METRICS.csv CHANGED
@@ -1,14 +1,14 @@
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
- organism_source,6292,5922,73,0.9443482756614685,0.5718148400891157,5,0.7
3
- strain,2444,1937,52,0.9165727496147156,0.7367410516866768,5,0.7
4
- inducer,7889,7538,142,0.5760037302970886,1.9561916236448726,5,0.7
5
- molecular_weight,295,121,15,0.48770323395729065,1.2671526293820528,5,0.7
6
- expression_strain,5677,5350,91,0.41914400458335876,1.2029687199113022,5,0.7
7
- induction_temperature,3656,3451,50,0.40973272919654846,1.0671727401581919,5,0.7
8
- plasmid,5480,3476,209,0.3558383285999298,1.4542716466540218,5,0.7
9
- enzyme_name,7975,3166,330,0.31110891699790955,1.6896226078563858,5,0.7
10
- desalting_process,3720,2423,165,0.21211960911750793,1.849798305431841,5,0.7
11
- medium_name,4806,3702,205,0.17596539855003357,1.903979460950627,5,0.7
12
- elution_buffer,3530,2575,193,0.16288751363754272,2.0289683427751326,5,0.7
13
- source_key,8021,7620,437,0.09377432614564896,1.933075330391653,5,0.7
14
- lysis_buffer,3714,3076,153,0.044689636677503586,2.1446177352547293,5,0.7
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,9834,9394,84,0.9586203098297119,0.6932934264603977,5,0.7
3
+ strain,3834,2974,83,0.6667201519012451,0.9786764939561241,5,0.7
4
+ inducer,11954,11420,207,0.5662036538124084,1.993024168821524,5,0.7
5
+ induction_temperature,5383,5121,60,0.43788406252861023,1.1674032734295239,5,0.7
6
+ molecular_weight,495,201,23,0.4239448308944702,1.2955572225474554,5,0.7
7
+ expression_strain,8268,7618,147,0.3990951478481293,1.3734072972482345,5,0.7
8
+ plasmid,8217,4936,325,0.29726678133010864,1.591988152947234,5,0.7
9
+ enzyme_name,12099,5207,514,0.2843882441520691,1.7491814450514838,5,0.7
10
+ desalting_process,5540,3538,242,0.1878713220357895,1.9084698094456174,5,0.7
11
+ medium_name,7644,6011,312,0.13277573883533478,2.0395695365561,5,0.7
12
+ elution_buffer,5198,3856,269,0.12419383227825165,2.1418327689374417,5,0.7
13
+ source_key,12179,11709,650,0.04634162783622742,2.0152894973803885,5,0.7
14
+ lysis_buffer,5625,4723,238,0.01871468871831894,2.2440021032823334,5,0.7
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=5/t=0.8_ALL_FIELDS.csv.gz CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc856a2ec3e0b8cd48d399e175c151264e006d09540f48582d597722dc573d0d
3
- size 1586186
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57cf5c9bb0d2a3a807067151adae1557a3fce747856af13f3e51005fcd0b119d
3
+ size 2462086
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=5/t=0.8_FIELD_CLUSTER_METRICS.csv CHANGED
@@ -1,14 +1,14 @@
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
- organism_source,6292,5842,73,0.9895585179328918,0.38770667328252695,5,0.8
3
- strain,2444,1820,49,0.964370608329773,0.4516839941438964,5,0.8
4
- molecular_weight,295,47,7,0.8723016381263733,0.5413751282354026,5,0.8
5
- induction_temperature,3656,3360,50,0.8276402950286865,0.6596679305619388,5,0.8
6
- source_key,8021,4779,572,0.8137261271476746,0.7445287491257055,5,0.8
7
- inducer,7889,7149,162,0.6820428967475891,1.5501571044914741,5,0.8
8
- enzyme_name,7975,1398,181,0.6420785188674927,0.9470737681517927,5,0.8
9
- plasmid,5480,2648,163,0.6175456643104553,0.8761456862166952,5,0.8
10
- desalting_process,3720,1486,155,0.6002575755119324,1.0671082690686162,5,0.8
11
- expression_strain,5677,5149,109,0.5193809270858765,0.7807080071844968,5,0.8
12
- elution_buffer,3530,1650,158,0.44272565841674805,1.2451076627710072,5,0.8
13
- medium_name,4806,2677,191,0.4377133548259735,1.186113551511221,5,0.8
14
- lysis_buffer,3714,2129,193,0.3151301145553589,1.5724141341390625,5,0.8
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,9834,9314,89,0.9897955060005188,0.40416840727744713,5,0.8
3
+ strain,3834,2732,72,0.8750402331352234,0.5323326288557207,5,0.8
4
+ molecular_weight,495,125,19,0.8459687232971191,0.5993856121140724,5,0.8
5
+ induction_temperature,5383,4982,57,0.8358964323997498,0.5692409919607223,5,0.8
6
+ source_key,12179,7467,859,0.7220664024353027,0.8749807766114311,5,0.8
7
+ inducer,11954,10827,231,0.6547908186912537,1.6242625752307254,5,0.8
8
+ enzyme_name,12099,2263,279,0.6237987875938416,0.9989491815051269,5,0.8
9
+ desalting_process,5540,1986,212,0.5910636186599731,1.1164249349800648,5,0.8
10
+ plasmid,8217,3480,230,0.5902198553085327,0.9479290142248349,5,0.8
11
+ expression_strain,8268,7180,158,0.4972711205482483,0.8517285852905733,5,0.8
12
+ medium_name,7644,4360,295,0.40150269865989685,1.3212613564754254,5,0.8
13
+ elution_buffer,5198,2310,209,0.3961767256259918,1.3378489226099453,5,0.8
14
+ lysis_buffer,5625,3163,266,0.27621254324913025,1.617919922001649,5,0.8
data/clustering/model=kamalkraj__BioSimCSE-BioLinkBERT-BASE/min=5/t=0.9_ALL_FIELDS.csv.gz CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a6fc94336c4c4e7a88316dad7e2330ee0dae47efcea854e11471d283ebda315
3
- size 1532603
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e4204fcb1757a984e118b5aa1eba1e367c689df5bf59304fb146063423a23fc
3
+ size 2370636