richiam commited on
Commit
c6d9057
·
verified ·
1 Parent(s): 2926ac7

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=NeuML__pubmedbert-base-embeddings/min=10/t=0.5_ALL_FIELDS.csv.gz +2 -2
  3. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=10/t=0.5_FIELD_CLUSTER_METRICS.csv +13 -13
  4. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=10/t=0.6_ALL_FIELDS.csv.gz +2 -2
  5. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=10/t=0.6_FIELD_CLUSTER_METRICS.csv +13 -13
  6. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=10/t=0.7_ALL_FIELDS.csv.gz +2 -2
  7. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=10/t=0.7_FIELD_CLUSTER_METRICS.csv +13 -13
  8. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=10/t=0.8_ALL_FIELDS.csv.gz +2 -2
  9. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=10/t=0.8_FIELD_CLUSTER_METRICS.csv +13 -13
  10. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=10/t=0.9_ALL_FIELDS.csv.gz +2 -2
  11. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=10/t=0.9_FIELD_CLUSTER_METRICS.csv +13 -13
  12. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=2/t=0.5_ALL_FIELDS.csv.gz +2 -2
  13. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=2/t=0.5_FIELD_CLUSTER_METRICS.csv +13 -13
  14. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=2/t=0.6_ALL_FIELDS.csv.gz +2 -2
  15. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=2/t=0.6_FIELD_CLUSTER_METRICS.csv +13 -13
  16. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=2/t=0.7_ALL_FIELDS.csv.gz +2 -2
  17. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=2/t=0.7_FIELD_CLUSTER_METRICS.csv +13 -13
  18. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=2/t=0.8_ALL_FIELDS.csv.gz +2 -2
  19. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=2/t=0.8_FIELD_CLUSTER_METRICS.csv +13 -13
  20. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=2/t=0.9_ALL_FIELDS.csv.gz +2 -2
  21. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=2/t=0.9_FIELD_CLUSTER_METRICS.csv +13 -13
  22. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=20/t=0.5_ALL_FIELDS.csv.gz +2 -2
  23. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=20/t=0.5_FIELD_CLUSTER_METRICS.csv +13 -13
  24. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=20/t=0.6_ALL_FIELDS.csv.gz +2 -2
  25. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=20/t=0.6_FIELD_CLUSTER_METRICS.csv +13 -13
  26. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=20/t=0.7_ALL_FIELDS.csv.gz +2 -2
  27. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=20/t=0.7_FIELD_CLUSTER_METRICS.csv +13 -13
  28. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=20/t=0.8_ALL_FIELDS.csv.gz +2 -2
  29. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=20/t=0.8_FIELD_CLUSTER_METRICS.csv +13 -13
  30. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=20/t=0.9_ALL_FIELDS.csv.gz +2 -2
  31. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=20/t=0.9_FIELD_CLUSTER_METRICS.csv +13 -13
  32. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=30/t=0.5_ALL_FIELDS.csv.gz +2 -2
  33. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=30/t=0.5_FIELD_CLUSTER_METRICS.csv +13 -13
  34. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=30/t=0.6_ALL_FIELDS.csv.gz +2 -2
  35. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=30/t=0.6_FIELD_CLUSTER_METRICS.csv +13 -13
  36. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=30/t=0.7_ALL_FIELDS.csv.gz +2 -2
  37. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=30/t=0.7_FIELD_CLUSTER_METRICS.csv +13 -13
  38. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=30/t=0.8_ALL_FIELDS.csv.gz +2 -2
  39. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=30/t=0.8_FIELD_CLUSTER_METRICS.csv +13 -13
  40. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=30/t=0.9_ALL_FIELDS.csv.gz +2 -2
  41. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=30/t=0.9_FIELD_CLUSTER_METRICS.csv +13 -13
  42. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=5/t=0.5_ALL_FIELDS.csv.gz +2 -2
  43. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=5/t=0.5_FIELD_CLUSTER_METRICS.csv +13 -13
  44. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=5/t=0.6_ALL_FIELDS.csv.gz +2 -2
  45. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=5/t=0.6_FIELD_CLUSTER_METRICS.csv +13 -13
  46. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=5/t=0.7_ALL_FIELDS.csv.gz +2 -2
  47. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=5/t=0.7_FIELD_CLUSTER_METRICS.csv +13 -13
  48. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=5/t=0.8_ALL_FIELDS.csv.gz +2 -2
  49. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=5/t=0.8_FIELD_CLUSTER_METRICS.csv +13 -13
  50. data/clustering/model=NeuML__pubmedbert-base-embeddings/min=5/t=0.9_ALL_FIELDS.csv.gz +2 -2
.gitattributes CHANGED
@@ -275,3 +275,28 @@ data/clustering/model=sentence-transformers__all-mpnet-base-v2/min=5/t=0.6_ALL_F
275
  data/clustering/model=sentence-transformers__all-mpnet-base-v2/min=5/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
276
  data/clustering/model=sentence-transformers__all-mpnet-base-v2/min=5/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
277
  data/clustering/model=sentence-transformers__all-mpnet-base-v2/min=5/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
275
  data/clustering/model=sentence-transformers__all-mpnet-base-v2/min=5/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
276
  data/clustering/model=sentence-transformers__all-mpnet-base-v2/min=5/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
277
  data/clustering/model=sentence-transformers__all-mpnet-base-v2/min=5/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
278
+ data/clustering/model=NeuML__pubmedbert-base-embeddings/min=10/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
279
+ data/clustering/model=NeuML__pubmedbert-base-embeddings/min=10/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
280
+ data/clustering/model=NeuML__pubmedbert-base-embeddings/min=10/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
281
+ data/clustering/model=NeuML__pubmedbert-base-embeddings/min=10/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
282
+ data/clustering/model=NeuML__pubmedbert-base-embeddings/min=10/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
283
+ data/clustering/model=NeuML__pubmedbert-base-embeddings/min=2/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
284
+ data/clustering/model=NeuML__pubmedbert-base-embeddings/min=2/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
285
+ data/clustering/model=NeuML__pubmedbert-base-embeddings/min=2/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
286
+ data/clustering/model=NeuML__pubmedbert-base-embeddings/min=2/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
287
+ data/clustering/model=NeuML__pubmedbert-base-embeddings/min=2/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
288
+ data/clustering/model=NeuML__pubmedbert-base-embeddings/min=20/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
289
+ data/clustering/model=NeuML__pubmedbert-base-embeddings/min=20/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
290
+ data/clustering/model=NeuML__pubmedbert-base-embeddings/min=20/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
291
+ data/clustering/model=NeuML__pubmedbert-base-embeddings/min=20/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
292
+ data/clustering/model=NeuML__pubmedbert-base-embeddings/min=20/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
293
+ data/clustering/model=NeuML__pubmedbert-base-embeddings/min=30/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
294
+ data/clustering/model=NeuML__pubmedbert-base-embeddings/min=30/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
295
+ data/clustering/model=NeuML__pubmedbert-base-embeddings/min=30/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
296
+ data/clustering/model=NeuML__pubmedbert-base-embeddings/min=30/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
297
+ data/clustering/model=NeuML__pubmedbert-base-embeddings/min=30/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
298
+ data/clustering/model=NeuML__pubmedbert-base-embeddings/min=5/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
299
+ data/clustering/model=NeuML__pubmedbert-base-embeddings/min=5/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
300
+ data/clustering/model=NeuML__pubmedbert-base-embeddings/min=5/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
301
+ data/clustering/model=NeuML__pubmedbert-base-embeddings/min=5/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
302
+ data/clustering/model=NeuML__pubmedbert-base-embeddings/min=5/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
data/clustering/model=NeuML__pubmedbert-base-embeddings/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:d6c1bf6381a8c562433b69b528ed90ed931074d81662ce673e9189b2ca596eca
3
- size 1628215
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f7d966adb985e1ebcd7b6fc820173676a26272a35cbb1846f75d02f6f16d2a8
3
+ size 2531011
data/clustering/model=NeuML__pubmedbert-base-embeddings/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,6292,6031,43,0.7171725630760193,1.3300621518094844,10,0.5
3
- strain,2444,2267,26,0.6957342028617859,1.684334598182741,10,0.5
4
- expression_strain,5677,5602,12,0.6700806617736816,1.2064563826678447,10,0.5
5
- molecular_weight,295,285,2,0.4025617241859436,1.8648349615568287,10,0.5
6
- induction_temperature,3656,3641,13,0.3743528425693512,1.9030132841502945,10,0.5
7
- lysis_buffer,3714,3681,13,0.3627944886684418,2.5478526370321384,10,0.5
8
- elution_buffer,3530,3502,13,0.2114894688129425,2.4060399023229584,10,0.5
9
- inducer,7889,7829,14,0.14916038513183594,2.5754939251632427,10,0.5
10
- desalting_process,3720,3686,19,0.143924742937088,2.628677276959593,10,0.5
11
- plasmid,5480,5300,60,-0.013144510798156261,3.421050857693413,10,0.5
12
- enzyme_name,7975,7044,205,-0.019518611952662468,3.352876814222691,10,0.5
13
- medium_name,4806,4692,50,-0.03975028917193413,2.837953092993161,10,0.5
14
- source_key,8021,8021,1,,,10,0.5
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,9834,9570,56,0.7615697383880615,1.4976458499397836,10,0.5
3
+ expression_strain,8268,8178,12,0.621722936630249,1.1340312281776352,10,0.5
4
+ strain,3834,3654,33,0.5386285185813904,1.821654984523659,10,0.5
5
+ induction_temperature,5383,5354,14,0.3708226978778839,2.035384495170042,10,0.5
6
+ lysis_buffer,5625,5581,20,0.3003097474575043,2.6963525715942467,10,0.5
7
+ molecular_weight,495,490,3,0.2790380120277405,1.7913061347160137,10,0.5
8
+ elution_buffer,5198,5173,20,0.20578496158123016,2.6636752555725485,10,0.5
9
+ desalting_process,5540,5491,21,0.19142979383468628,3.168660307561867,10,0.5
10
+ inducer,11954,11883,19,0.056494686752557755,2.8799831706350774,10,0.5
11
+ enzyme_name,12099,10962,324,-0.0225801020860672,3.254227619516482,10,0.5
12
+ medium_name,7644,7536,60,-0.04811960458755493,3.073055481567714,10,0.5
13
+ plasmid,8217,7989,84,-0.053222816437482834,3.5213158341779045,10,0.5
14
+ source_key,12179,12179,1,,,10,0.5
data/clustering/model=NeuML__pubmedbert-base-embeddings/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:eb05f1d4a6b6bba1aa586409e4e2c159783cbcf978a3699186d70d823655833c
3
- size 1643187
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed04b9757fcdb6f3c7cec289cd3ba1ad536146bb2465ff5ca9742194a3d0b3fd
3
+ size 2551912
data/clustering/model=NeuML__pubmedbert-base-embeddings/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
- organism_source,6292,5893,41,0.8543203473091125,0.9097834240692789,10,0.6
3
- strain,2444,2160,24,0.7831317186355591,1.3148077074787048,10,0.6
4
- expression_strain,5677,5561,10,0.5926868915557861,0.9580993317060009,10,0.6
5
- inducer,7889,7787,20,0.40685126185417175,2.070343314835502,10,0.6
6
- molecular_weight,295,283,4,0.33658844232559204,2.626876057760942,10,0.6
7
- induction_temperature,3656,3598,13,0.2621305286884308,2.341591578964718,10,0.6
8
- lysis_buffer,3714,3634,23,0.24437890946865082,2.658657188764789,10,0.6
9
- elution_buffer,3530,3464,30,0.06870683282613754,2.6044865982821093,10,0.6
10
- enzyme_name,7975,5659,219,0.05873008817434311,2.9639615966522097,10,0.6
11
- desalting_process,3720,3645,45,0.014520445838570595,2.791665275866088,10,0.6
12
- medium_name,4806,4550,69,-0.030361197888851166,2.8861310739086963,10,0.6
13
- plasmid,5480,4974,98,-0.034978628158569336,2.7886352424500354,10,0.6
14
- source_key,8021,8021,1,,,10,0.6
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,9834,9371,48,0.8753162026405334,1.0280659253458087,10,0.6
3
+ strain,3834,3519,30,0.5940209627151489,1.4512132178665553,10,0.6
4
+ expression_strain,8268,8130,15,0.4363784193992615,1.2644504750247094,10,0.6
5
+ molecular_weight,495,469,6,0.25534212589263916,3.124207708103917,10,0.6
6
+ induction_temperature,5383,5322,18,0.23000696301460266,2.5536891800997874,10,0.6
7
+ lysis_buffer,5625,5522,34,0.1936885565519333,2.5842991600706817,10,0.6
8
+ plasmid,8217,7455,161,0.07182153314352036,3.0400522328872635,10,0.6
9
+ elution_buffer,5198,5109,42,0.05227646976709366,2.62938390082572,10,0.6
10
+ enzyme_name,12099,8821,334,0.04834564030170441,2.9351438954082303,10,0.6
11
+ desalting_process,5540,5416,51,0.03008740209043026,2.9996005497390086,10,0.6
12
+ inducer,11954,11831,30,0.008299035020172596,2.7538612263872566,10,0.6
13
+ medium_name,7644,7356,95,-0.04238121211528778,2.8847196929312298,10,0.6
14
+ source_key,12179,12179,1,,,10,0.6
data/clustering/model=NeuML__pubmedbert-base-embeddings/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 sha256:04dbf31f95bb23c734998ab11155a17503406f5373c7add809536ea73d4071a9
3
- size 1626193
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5d11157ba94d423ee2a0928bff036358cfe82960ff8a08dc2fa0f334afd498b
3
+ size 2554955
data/clustering/model=NeuML__pubmedbert-base-embeddings/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,6292,5780,39,0.8789451122283936,0.5829884922336446,10,0.7
3
- strain,2444,1981,21,0.8298354744911194,0.8970115334613118,10,0.7
4
- inducer,7889,7681,21,0.6949065327644348,1.919577455026658,10,0.7
5
- expression_strain,5677,5528,22,0.4839613139629364,1.5826195221754327,10,0.7
6
- molecular_weight,295,262,6,0.3706112802028656,1.5639749538464782,10,0.7
7
- induction_temperature,3656,3550,23,0.26030582189559937,1.8019327697384278,10,0.7
8
- enzyme_name,7975,3640,167,0.22134999930858612,2.347926835241949,10,0.7
9
- source_key,8021,8019,3,0.21271516382694244,3.0899437060478654,10,0.7
10
- plasmid,5480,4095,77,0.2075360119342804,2.3583535055399585,10,0.7
11
- lysis_buffer,3714,3508,37,0.10746237635612488,2.3807513897620978,10,0.7
12
- medium_name,4806,4194,76,0.07306849211454391,2.546934145186119,10,0.7
13
- desalting_process,3720,3448,67,0.012465295381844044,2.6685993576559772,10,0.7
14
- elution_buffer,3530,3349,61,0.002017699182033539,2.7006934755188157,10,0.7
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,9834,9252,46,0.9107958674430847,0.6261080504026256,10,0.7
3
+ inducer,11954,11691,33,0.6622470617294312,1.9836733463715004,10,0.7
4
+ strain,3834,3280,30,0.5066774487495422,1.493732555960024,10,0.7
5
+ expression_strain,8268,8061,35,0.34706929326057434,2.340436215001288,10,0.7
6
+ molecular_weight,495,450,8,0.337075412273407,1.8428757910399602,10,0.7
7
+ source_key,12179,12171,2,0.24367043375968933,3.7147679301950136,10,0.7
8
+ enzyme_name,12099,5589,256,0.2184850424528122,2.3424546014574865,10,0.7
9
+ induction_temperature,5383,5251,29,0.2006305605173111,1.849984083754812,10,0.7
10
+ plasmid,8217,6067,143,0.156584694981575,2.5916997867565916,10,0.7
11
+ lysis_buffer,5625,5342,54,0.09196498990058899,2.8153121079835017,10,0.7
12
+ medium_name,7644,6831,116,0.0626383125782013,2.583941940534267,10,0.7
13
+ desalting_process,5540,5159,91,-0.004914960358291864,2.936972947760685,10,0.7
14
+ elution_buffer,5198,4923,83,-0.048943985253572464,2.908371120742694,10,0.7
data/clustering/model=NeuML__pubmedbert-base-embeddings/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 sha256:60845092b3e0b17f131ce783c83bff0d765ba541d8541935eee0e6f7b2f1fafd
3
- size 1624119
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf549c305e673c52161a10815d803706301433a016605c27f0a1bb8b190d1928
3
+ size 2538537
data/clustering/model=NeuML__pubmedbert-base-embeddings/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
- strain,2444,1808,19,0.9080540537834167,0.732574870725376,10,0.8
3
- organism_source,6292,5655,41,0.8993738293647766,0.3482349020886096,10,0.8
4
- inducer,7889,7569,48,0.6603038311004639,2.1576713916986585,10,0.8
5
- expression_strain,5677,5366,41,0.49226662516593933,1.2984313305786888,10,0.8
6
- induction_temperature,3656,3437,27,0.45856350660324097,1.2769499383269522,10,0.8
7
- enzyme_name,7975,1607,81,0.43394947052001953,1.4479217180002086,10,0.8
8
- plasmid,5480,3063,78,0.31231504678726196,1.725561226721041,10,0.8
9
- medium_name,4806,3505,90,0.1719074547290802,2.121405416567362,10,0.8
10
- molecular_weight,295,199,7,0.16447319090366364,2.4226508467946424,10,0.8
11
- desalting_process,3720,2919,82,0.06523067504167557,2.790574764372148,10,0.8
12
- lysis_buffer,3714,3076,64,0.026585785672068596,2.6148405014786613,10,0.8
13
- source_key,8021,7976,49,-0.004863962531089783,2.757268267615565,10,0.8
14
- elution_buffer,3530,2968,79,-0.033988673239946365,2.5578731835296744,10,0.8
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,9834,9075,47,0.9387332201004028,0.3818010831162047,10,0.8
3
+ inducer,11954,11473,65,0.625816285610199,2.215471272974753,10,0.8
4
+ strain,3834,2977,32,0.5847920775413513,1.3256857348897002,10,0.8
5
+ enzyme_name,12099,2555,138,0.4701145589351654,1.4110658495735788,10,0.8
6
+ induction_temperature,5383,5074,33,0.45667383074760437,1.2811275274278886,10,0.8
7
+ expression_strain,8268,7762,56,0.4375629127025604,1.9229055726285051,10,0.8
8
+ plasmid,8217,4159,107,0.31001371145248413,1.8371514974772403,10,0.8
9
+ medium_name,7644,5686,133,0.1502307653427124,2.282004364236302,10,0.8
10
+ molecular_weight,495,373,11,0.149312362074852,2.0999588382657093,10,0.8
11
+ desalting_process,5540,4366,125,0.009400255978107452,2.8094440906219855,10,0.8
12
+ elution_buffer,5198,4388,106,-0.029768500477075577,2.760990650225249,10,0.8
13
+ lysis_buffer,5625,4757,96,-0.043203383684158325,2.734423878889148,10,0.8
14
+ source_key,12179,12133,73,-0.04763251915574074,2.755080457600837,10,0.8
data/clustering/model=NeuML__pubmedbert-base-embeddings/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 sha256:5e4d852057556e87f5979b4feacc68c09293e67315fadce1f6d3237fc86c9925
3
- size 1564351
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8588c344b542158cdbd331b35fdfc8cf4ad0ad01833567268020744d59b22405
3
+ size 2424868
data/clustering/model=NeuML__pubmedbert-base-embeddings/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
- strain,2444,1626,17,0.9837311506271362,0.3175255077950104,10,0.9
3
- organism_source,6292,5560,37,0.9788530468940735,0.1931223706028745,10,0.9
4
- induction_temperature,3656,3211,37,0.9230761528015137,0.448153998638959,10,0.9
5
- enzyme_name,7975,522,29,0.7515102028846741,0.7553350202223252,10,0.9
6
- inducer,7889,7185,63,0.6551174521446228,1.8185481204961194,10,0.9
7
- expression_strain,5677,4915,56,0.5479424595832825,0.8804435443045874,10,0.9
8
- plasmid,5480,2083,65,0.5256948471069336,0.9193133530880654,10,0.9
9
- molecular_weight,295,80,6,0.5209327936172485,1.1997000912471203,10,0.9
10
- medium_name,4806,2102,76,0.38024479150772095,1.4144364073465854,10,0.9
11
- desalting_process,3720,1324,57,0.33734315633773804,1.7405046316263648,10,0.9
12
- elution_buffer,3530,1743,65,0.1891961544752121,1.9264666877763272,10,0.9
13
- source_key,8021,6053,224,0.1851687878370285,1.9230529273744423,10,0.9
14
- lysis_buffer,3714,1846,79,0.17152932286262512,2.072336001161406,10,0.9
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,9834,8945,44,0.9899806380271912,0.21060236467548013,10,0.9
3
+ induction_temperature,5383,4808,42,0.9428451061248779,0.4645414582638652,10,0.9
4
+ strain,3834,2566,33,0.844353973865509,0.5383923215231834,10,0.9
5
+ enzyme_name,12099,745,46,0.8087031841278076,0.6254054736081194,10,0.9
6
+ inducer,11954,10853,86,0.6490408778190613,1.9402126050937416,10,0.9
7
+ expression_strain,8268,6956,83,0.5155341625213623,0.9797987625551867,10,0.9
8
+ plasmid,8217,2602,78,0.5024995803833008,1.0213756401251533,10,0.9
9
+ molecular_weight,495,154,10,0.4309963881969452,1.3148509163138953,10,0.9
10
+ medium_name,7644,3536,112,0.35585546493530273,1.5212663001719235,10,0.9
11
+ desalting_process,5540,1924,80,0.29242050647735596,1.8569336961032115,10,0.9
12
+ elution_buffer,5198,2501,92,0.17022353410720825,2.1235563814546508,10,0.9
13
+ source_key,12179,9572,331,0.151178240776062,2.003727395092835,10,0.9
14
+ lysis_buffer,5625,2891,116,0.14512041211128235,2.161575818202865,10,0.9
data/clustering/model=NeuML__pubmedbert-base-embeddings/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 sha256:0fb2bba2fe38eb47502f56b85db730d2fe37a5313b2f0d8e716e38348d6303c1
3
- size 1648421
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f5df7b52234ea3149d99068cce3a044766ca7acb6329bc39e086b4b55f05d40
3
+ size 2560101
data/clustering/model=NeuML__pubmedbert-base-embeddings/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,6292,6259,115,0.7014444470405579,1.1186886384988397,2,0.5
3
- strain,2444,2420,83,0.6563694477081299,1.2811940828733883,2,0.5
4
- expression_strain,5677,5672,34,0.639151394367218,1.0753198095917913,2,0.5
5
- induction_temperature,3656,3654,31,0.33753883838653564,1.2848258547062885,2,0.5
6
- molecular_weight,295,295,6,0.3030403256416321,1.980626564490123,2,0.5
7
- lysis_buffer,3714,3711,40,0.2706596553325653,1.5856332095293069,2,0.5
8
- elution_buffer,3530,3527,38,0.14803645014762878,1.5113364745785152,2,0.5
9
- desalting_process,3720,3716,61,0.10539247840642929,1.6319725529873657,2,0.5
10
- inducer,7889,7882,45,-0.0013027563691139221,1.6291838282140598,2,0.5
11
- enzyme_name,7975,7839,807,-0.06183360144495964,2.0900194572659827,2,0.5
12
- medium_name,4806,4796,146,-0.08457455039024353,1.8167264608414597,2,0.5
13
- plasmid,5480,5456,186,-0.09225655347108841,2.257285751191882,2,0.5
14
- source_key,8021,8021,1,,,2,0.5
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,9834,9797,136,0.7439044117927551,1.2191528037393653,2,0.5
3
+ expression_strain,8268,8259,38,0.4872153699398041,1.0934046441151615,2,0.5
4
+ strain,3834,3813,109,0.4225767254829407,1.3406220466072258,2,0.5
5
+ induction_temperature,5383,5382,33,0.35920965671539307,1.5064174285625285,2,0.5
6
+ lysis_buffer,5625,5622,60,0.26706838607788086,1.6602193107097194,2,0.5
7
+ molecular_weight,495,495,7,0.24428516626358032,1.9209211664103287,2,0.5
8
+ elution_buffer,5198,5193,54,0.14284168183803558,1.8030125306701732,2,0.5
9
+ desalting_process,5540,5537,75,0.0932539775967598,1.870438516312756,2,0.5
10
+ enzyme_name,12099,11932,1214,-0.07685815542936325,2.08562192983975,2,0.5
11
+ medium_name,7644,7633,170,-0.08805021643638611,1.8780733266425975,2,0.5
12
+ inducer,11954,11945,63,-0.08944918215274811,1.7467705727193892,2,0.5
13
+ plasmid,8217,8187,264,-0.10545023530721664,2.2654832426845815,2,0.5
14
+ source_key,12179,12179,1,,,2,0.5
data/clustering/model=NeuML__pubmedbert-base-embeddings/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 sha256:759b7339548aa55de067bb941292dd58ee4bc38c4e4d21bf5b3949eace11a952
3
- size 1686179
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6a9d6a435849ea73480b035022186acce9baf2d2070665a71e8584c29bb0256
3
+ size 2612139
data/clustering/model=NeuML__pubmedbert-base-embeddings/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,6292,6232,135,0.8074280619621277,0.8034247731512919,2,0.6
3
- strain,2444,2397,97,0.7322822213172913,1.0540796815933469,2,0.6
4
- expression_strain,5677,5661,37,0.4768998324871063,1.061444229338329,2,0.6
5
- inducer,7889,7870,73,0.30149051547050476,1.351865303108722,2,0.6
6
- molecular_weight,295,292,13,0.21497206389904022,2.220063813211792,2,0.6
7
- induction_temperature,3656,3646,45,0.1668396145105362,1.4859881172235618,2,0.6
8
- lysis_buffer,3714,3701,83,0.1643277108669281,1.4169594465940458,2,0.6
9
- enzyme_name,7975,7511,1153,0.029460951685905457,1.846226318934986,2,0.6
10
- elution_buffer,3530,3520,84,-0.009087025187909603,1.6754271911601184,2,0.6
11
- desalting_process,3720,3699,127,-0.025020558387041092,1.8282613173092361,2,0.6
12
- medium_name,4806,4763,211,-0.05096772685647011,1.7263215266028666,2,0.6
13
- plasmid,5480,5356,372,-0.05536322668194771,1.874561508848513,2,0.6
14
- source_key,8021,8021,1,,,2,0.6
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,9834,9770,162,0.8539462089538574,0.8500965114876793,2,0.6
3
+ strain,3834,3785,117,0.5672385692596436,1.1748075344687035,2,0.6
4
+ expression_strain,8268,8249,49,0.4180246889591217,1.2614960564655195,2,0.6
5
+ molecular_weight,495,493,18,0.22492732107639313,2.1455226710584583,2,0.6
6
+ induction_temperature,5383,5374,54,0.16949604451656342,1.711563126984723,2,0.6
7
+ lysis_buffer,5625,5611,122,0.16610704362392426,1.4688694178359372,2,0.6
8
+ plasmid,8217,8062,613,0.01956109143793583,2.0175676972596372,2,0.6
9
+ elution_buffer,5198,5183,116,0.014184089377522469,1.7863276295993087,2,0.6
10
+ enzyme_name,12099,11439,1699,0.013631418347358704,1.8432373939858895,2,0.6
11
+ medium_name,7644,7596,292,-0.07224320620298386,1.756865338319332,2,0.6
12
+ desalting_process,5540,5507,169,-0.07922038435935974,1.8340331378100736,2,0.6
13
+ inducer,11954,11927,99,-0.09749791771173477,1.5149999095128783,2,0.6
14
+ source_key,12179,12179,1,,,2,0.6
data/clustering/model=NeuML__pubmedbert-base-embeddings/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 sha256:46d9ae409bd1fe06286bfbb0bb50723554de29291f8a5dbedf3b66bd8a6b281c
3
- size 1689720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c57137971343fc7b5208acb9ba0a196794f98711bea79a506f032b28b97c3b09
3
+ size 2649540
data/clustering/model=NeuML__pubmedbert-base-embeddings/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,6292,6213,168,0.8505202531814575,0.5236269551402708,2,0.7
3
- strain,2444,2359,132,0.7275075912475586,0.8558046818061883,2,0.7
4
- inducer,7889,7847,92,0.6559229493141174,1.2627690123156718,2,0.7
5
- expression_strain,5677,5641,72,0.3504142761230469,1.1659953723166698,2,0.7
6
- molecular_weight,295,288,21,0.2413741797208786,1.657396236151921,2,0.7
7
- enzyme_name,7975,6755,1300,0.23069392144680023,1.4930203317765431,2,0.7
8
- induction_temperature,3656,3628,62,0.228397935628891,1.3004781918639166,2,0.7
9
- plasmid,5480,5112,483,0.19534432888031006,1.4863805961353207,2,0.7
10
- source_key,8021,8021,5,0.14175322651863098,2.3214950247758495,2,0.7
11
- medium_name,4806,4677,310,0.09524600952863693,1.4262750485919125,2,0.7
12
- lysis_buffer,3714,3676,158,0.08141886442899704,1.3493395940178483,2,0.7
13
- desalting_process,3720,3650,217,-0.0075378515757620335,1.7191543931338196,2,0.7
14
- elution_buffer,3530,3488,196,-0.02923709526658058,1.6877799313702688,2,0.7
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,9834,9745,189,0.8872775435447693,0.5587345311117136,2,0.7
3
+ inducer,11954,11899,142,0.6303070187568665,1.3955123042404376,2,0.7
4
+ strain,3834,3727,178,0.44678252935409546,0.975660423155321,2,0.7
5
+ expression_strain,8268,8222,103,0.28443560004234314,1.5129573021894551,2,0.7
6
+ enzyme_name,12099,10345,1962,0.22578252851963043,1.4950747363432189,2,0.7
7
+ molecular_weight,495,484,32,0.20864753425121307,1.6593852985768212,2,0.7
8
+ induction_temperature,5383,5346,76,0.17465680837631226,1.365845289669504,2,0.7
9
+ source_key,12179,12179,5,0.15863977372646332,2.2940972784022375,2,0.7
10
+ plasmid,8217,7644,807,0.14851431548595428,1.6048655454786946,2,0.7
11
+ lysis_buffer,5625,5564,211,0.05702400207519531,1.5313272041308745,2,0.7
12
+ medium_name,7644,7487,471,0.04496528580784798,1.5537766557678512,2,0.7
13
+ desalting_process,5540,5431,314,-0.03249683603644371,1.7559429323805293,2,0.7
14
+ elution_buffer,5198,5142,278,-0.07446205615997314,1.7022670052276732,2,0.7
data/clustering/model=NeuML__pubmedbert-base-embeddings/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 sha256:7356e39e2b1521683484423452ff76532cc60db8e5410681b603fe9ab26ccf5e
3
- size 1717664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e2eb9aa4aeedecf3909fdd707acf19a478cadc62ddf54d859ffb7d4b8388e5b
3
+ size 2688863
data/clustering/model=NeuML__pubmedbert-base-embeddings/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,6292,6175,195,0.9014003872871399,0.33777665484431696,2,0.8
3
- strain,2444,2297,157,0.8440360426902771,0.6576135169620141,2,0.8
4
- inducer,7889,7806,175,0.639236569404602,1.1847853429924164,2,0.8
5
- enzyme_name,7975,5543,1404,0.4979456663131714,0.9920201214125276,2,0.8
6
- expression_strain,5677,5593,122,0.45443904399871826,1.027477145077255,2,0.8
7
- induction_temperature,3656,3604,95,0.44411909580230713,0.9441596423292014,2,0.8
8
- plasmid,5480,4658,634,0.384662389755249,1.0534219843893837,2,0.8
9
- medium_name,4806,4483,482,0.21221111714839935,1.241699689173869,2,0.8
10
- molecular_weight,295,275,31,0.17974670231342316,1.6497288810255117,2,0.8
11
- desalting_process,3720,3486,381,0.09097544848918915,1.5278924223889971,2,0.8
12
- lysis_buffer,3714,3588,304,0.045105841010808945,1.3937799480658866,2,0.8
13
- elution_buffer,3530,3372,292,-0.0049078864976763725,1.6557229240638827,2,0.8
14
- source_key,8021,8018,104,-0.0723763257265091,1.8004168732624548,2,0.8
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,9834,9695,228,0.936726987361908,0.3618106368636814,2,0.8
3
+ inducer,11954,11834,255,0.6029758453369141,1.2755873603123677,2,0.8
4
+ strain,3834,3614,228,0.5735137462615967,0.8902447667342013,2,0.8
5
+ enzyme_name,12099,8412,2114,0.5143863558769226,0.9929850508425235,2,0.8
6
+ induction_temperature,5383,5309,125,0.4494137167930603,1.020025008419479,2,0.8
7
+ plasmid,8217,6733,1008,0.36896464228630066,1.1003534713701066,2,0.8
8
+ expression_strain,8268,8140,207,0.36694973707199097,1.3200504459152793,2,0.8
9
+ medium_name,7644,7127,718,0.1908062994480133,1.3030027183378488,2,0.8
10
+ molecular_weight,495,467,51,0.13395041227340698,1.5226552302422034,2,0.8
11
+ desalting_process,5540,5167,562,0.04894699528813362,1.5608691048375192,2,0.8
12
+ lysis_buffer,5625,5443,443,-0.010853772982954979,1.4832942499494235,2,0.8
13
+ elution_buffer,5198,4963,430,-0.03432778641581535,1.6896858479517047,2,0.8
14
+ source_key,12179,12170,140,-0.10041160881519318,1.8736976211033332,2,0.8
data/clustering/model=NeuML__pubmedbert-base-embeddings/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 sha256:33d4cbeb640f3b8125a1ed46fa962cbf2facd8f9c6976ce15e7170ce5c87de42
3
- size 1697638
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62e0d8e5f61e6a3e767128c98b9577c1a1c7acac3dbf068784de72a7727253cb
3
+ size 2637873
data/clustering/model=NeuML__pubmedbert-base-embeddings/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
- organism_source,6292,6153,212,0.9792636632919312,0.21351947298701035,2,0.9
3
- strain,2444,2220,198,0.9549771547317505,0.36182670898560876,2,0.9
4
- induction_temperature,3656,3552,141,0.9214635491371155,0.4176416250816413,2,0.9
5
- enzyme_name,7975,3830,1209,0.7677200436592102,0.5466998347711511,2,0.9
6
- plasmid,5480,3992,710,0.6271998286247253,0.5982124300908573,2,0.9
7
- inducer,7889,7698,285,0.6199725866317749,1.0643471194379739,2,0.9
8
- medium_name,4806,3938,680,0.5441442131996155,0.7554204994550536,2,0.9
9
- desalting_process,3720,2906,615,0.5342471599578857,0.8676093812151201,2,0.9
10
- expression_strain,5677,5487,226,0.497526079416275,0.6948063895049686,2,0.9
11
- molecular_weight,295,220,52,0.4876287877559662,0.9420335883336476,2,0.9
12
- lysis_buffer,3714,3202,589,0.36842986941337585,1.05994317400976,2,0.9
13
- elution_buffer,3530,2887,463,0.3639257252216339,1.0089784345803043,2,0.9
14
- source_key,8021,7839,799,0.29300257563591003,1.1312083683083032,2,0.9
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,9834,9661,252,0.9888184070587158,0.2244173620402013,2,0.9
3
+ induction_temperature,5383,5232,168,0.9362459778785706,0.47432483690142846,2,0.9
4
+ enzyme_name,12099,5854,1881,0.7957338094711304,0.5195820517692754,2,0.9
5
+ strain,3834,3400,306,0.7934702634811401,0.477330260735393,2,0.9
6
+ plasmid,8217,5543,1096,0.6284253001213074,0.6008259520700131,2,0.9
7
+ inducer,11954,11666,451,0.6109368801116943,1.068416408467849,2,0.9
8
+ expression_strain,8268,7907,374,0.49729812145233154,0.7375522952434893,2,0.9
9
+ desalting_process,5540,4244,913,0.49508991837501526,0.9338732145320596,2,0.9
10
+ medium_name,7644,6210,1045,0.4944644272327423,0.7818658521579557,2,0.9
11
+ molecular_weight,495,371,82,0.4239085614681244,1.0004728404743584,2,0.9
12
+ elution_buffer,5198,4173,707,0.3553297817707062,1.0359148335858503,2,0.9
13
+ lysis_buffer,5625,4849,846,0.32853323221206665,1.0852998658348012,2,0.9
14
+ source_key,12179,11931,1163,0.22732694447040558,1.221397279633029,2,0.9
data/clustering/model=NeuML__pubmedbert-base-embeddings/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 sha256:364afc507d2d81a66beb64ff37fd93976aca697259fb02206d4082a54c0f3ca1
3
- size 1607700
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0f7c28d1873fcb5a09749ef5b10275c13ad1d2099e78ba47e8e4ce5c85e1980
3
+ size 2501696
data/clustering/model=NeuML__pubmedbert-base-embeddings/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,6292,5782,21,0.735194981098175,1.2937823886371487,20,0.5
3
- strain,2444,2163,14,0.7030763030052185,1.9577050820317328,20,0.5
4
- expression_strain,5677,5592,9,0.688077449798584,1.242166237039849,20,0.5
5
- molecular_weight,295,293,2,0.42059358954429626,1.781953701391645,20,0.5
6
- lysis_buffer,3714,3654,7,0.3915138244628906,2.5704689725988064,20,0.5
7
- induction_temperature,3656,3624,9,0.39146319031715393,1.814025094815833,20,0.5
8
- elution_buffer,3530,3466,7,0.27233245968818665,1.993423389367861,20,0.5
9
- inducer,7889,7807,7,0.16275009512901306,2.903271835889733,20,0.5
10
- desalting_process,3720,3629,11,0.1507773995399475,2.809677110457744,20,0.5
11
- plasmid,5480,5180,36,0.009570293128490448,3.901686811983883,20,0.5
12
- enzyme_name,7975,6545,108,0.004287067335098982,3.7940350883933616,20,0.5
13
- medium_name,4806,4648,33,-0.033420976251363754,3.1171239292525432,20,0.5
14
- source_key,8021,8021,1,,,20,0.5
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,9834,9235,26,0.7785341739654541,1.4616713675217168,20,0.5
3
+ expression_strain,8268,8163,9,0.6447438597679138,1.1906740378627692,20,0.5
4
+ strain,3834,3522,16,0.530707061290741,2.0478784382765003,20,0.5
5
+ induction_temperature,5383,5335,11,0.3736322224140167,1.8929732031523614,20,0.5
6
+ molecular_weight,495,477,2,0.33558598160743713,2.121664501628384,20,0.5
7
+ lysis_buffer,5625,5560,11,0.31403106451034546,2.8827793579567422,20,0.5
8
+ elution_buffer,5198,5123,11,0.2251083254814148,2.8558418536736787,20,0.5
9
+ desalting_process,5540,5461,14,0.20992392301559448,3.495293224311855,20,0.5
10
+ inducer,11954,11871,12,0.18936003744602203,3.1409212187852096,20,0.5
11
+ enzyme_name,12099,10239,167,0.003437418257817626,3.6593088162725627,20,0.5
12
+ medium_name,7644,7434,37,-0.021134430542588234,3.434160603478347,20,0.5
13
+ plasmid,8217,7876,55,-0.05301554128527641,3.8666288351177123,20,0.5
14
+ source_key,12179,12179,1,,,20,0.5
data/clustering/model=NeuML__pubmedbert-base-embeddings/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 sha256:53b4a3f3e6a7747a2a5e4818d4303f97ea8978c76e88f1fc6369aede1965896f
3
- size 1617384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60a9b923f0ca25159691235020cd108320697511ec86d73ab17a58a323e32195
3
+ size 2509496
data/clustering/model=NeuML__pubmedbert-base-embeddings/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
- organism_source,6292,5666,23,0.8605698347091675,0.955912474893563,20,0.6
3
- strain,2444,2009,12,0.8062338829040527,1.315529553273122,20,0.6
4
- expression_strain,5677,5568,10,0.592525839805603,0.9781723707248797,20,0.6
5
- molecular_weight,295,270,2,0.4220213294029236,1.811233172029535,20,0.6
6
- inducer,7889,7744,10,0.41962286829948425,2.230004698030577,20,0.6
7
- induction_temperature,3656,3574,9,0.3016285002231598,1.9393212768444923,20,0.6
8
- lysis_buffer,3714,3621,15,0.25724831223487854,2.851097937839921,20,0.6
9
- elution_buffer,3530,3437,18,0.09715106338262558,2.7577759623669675,20,0.6
10
- enzyme_name,7975,4696,99,0.07053962349891663,3.4481804402730627,20,0.6
11
- desalting_process,3720,3578,23,0.04440043121576309,3.2165068235727965,20,0.6
12
- medium_name,4806,4406,40,-0.029949339106678963,3.424653171294519,20,0.6
13
- plasmid,5480,4665,50,-0.038508735597133636,3.1442963761538634,20,0.6
14
- source_key,8021,8021,1,,,20,0.6
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,9834,9087,26,0.8830235004425049,1.1165695291231588,20,0.6
3
+ strain,3834,3354,16,0.6785984039306641,1.5158544052796334,20,0.6
4
+ expression_strain,8268,8132,12,0.4982696771621704,1.1354232499096872,20,0.6
5
+ molecular_weight,495,465,4,0.2751835286617279,2.81133643886237,20,0.6
6
+ induction_temperature,5383,5296,12,0.23914796113967896,2.527005219923443,20,0.6
7
+ lysis_buffer,5625,5455,18,0.21630649268627167,2.9510686872136875,20,0.6
8
+ elution_buffer,5198,5052,24,0.07990695536136627,2.8546314370997106,20,0.6
9
+ plasmid,8217,7054,81,0.07900072634220123,3.4793538986837653,20,0.6
10
+ enzyme_name,12099,7357,148,0.06268197298049927,3.397472620208615,20,0.6
11
+ desalting_process,5540,5315,29,0.04242175072431564,3.3741243440556903,20,0.6
12
+ inducer,11954,11793,15,0.040189746767282486,2.7077281158632918,20,0.6
13
+ medium_name,7644,7141,52,-0.03497845679521561,3.4574319962066014,20,0.6
14
+ source_key,12179,12179,1,,,20,0.6
data/clustering/model=NeuML__pubmedbert-base-embeddings/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 sha256:54ac266fc37976e33d7db4defdbbde8f770672872a550574c1766db03e4c153f
3
- size 1595817
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de94f2ea0662162851be86cba4ca7347532036894445b8e9ffc3f14b882384ba
3
+ size 2506650
data/clustering/model=NeuML__pubmedbert-base-embeddings/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
- organism_source,6292,5519,20,0.8825023174285889,0.5438674996232168,20,0.7
3
- strain,2444,1798,7,0.8796408176422119,0.785702038718283,20,0.7
4
- inducer,7889,7616,11,0.7219411134719849,1.7880562592186349,20,0.7
5
- expression_strain,5677,5464,13,0.5166183710098267,1.5064081351007614,20,0.7
6
- molecular_weight,295,220,2,0.5111305713653564,1.4291720689420346,20,0.7
7
- induction_temperature,3656,3512,15,0.29437369108200073,1.647702468672254,20,0.7
8
- source_key,8021,8006,2,0.24682745337486267,2.937016274668573,20,0.7
9
- enzyme_name,7975,2547,62,0.22174155712127686,2.76695160157554,20,0.7
10
- plasmid,5480,3801,44,0.21918685734272003,2.4796455403392668,20,0.7
11
- lysis_buffer,3714,3382,17,0.14324910938739777,2.513262530717553,20,0.7
12
- medium_name,4806,3991,41,0.1003432348370552,2.732768809737927,20,0.7
13
- elution_buffer,3530,3263,33,0.05011225864291191,3.362008711481515,20,0.7
14
- desalting_process,3720,3290,36,0.020936453714966774,3.1925913770033287,20,0.7
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,9834,8932,23,0.9151079654693604,0.5964746158061943,20,0.7
3
+ inducer,11954,11555,16,0.6917601823806763,2.1058904946737504,20,0.7
4
+ strain,3834,3096,14,0.5348719358444214,1.7767301643980187,20,0.7
5
+ expression_strain,8268,8015,26,0.351143479347229,2.2899156120906405,20,0.7
6
+ molecular_weight,495,425,4,0.3420219123363495,2.0175149717479073,20,0.7
7
+ source_key,12179,12171,2,0.24367043375968933,3.7147679301950136,20,0.7
8
+ enzyme_name,12099,3859,92,0.23095601797103882,2.6547389142251423,20,0.7
9
+ induction_temperature,5383,5200,17,0.22961381077766418,1.7982102279974093,20,0.7
10
+ plasmid,8217,5432,68,0.18541210889816284,2.7382221727988205,20,0.7
11
+ lysis_buffer,5625,5180,28,0.10817345231771469,3.136456980706306,20,0.7
12
+ medium_name,7644,6525,61,0.0677177831530571,3.007813533677051,20,0.7
13
+ desalting_process,5540,5019,53,0.006979471538215876,3.3197104967186233,20,0.7
14
+ elution_buffer,5198,4822,42,-0.005928962025791407,3.5586729799911243,20,0.7
data/clustering/model=NeuML__pubmedbert-base-embeddings/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:e9cd08b9b462b741d196e65b0a7ea02bef7dcfbd2de0859243c89e04b85a9d90
3
- size 1590685
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21fc39b7900fe934513e98a2056d68be9077e2df5181ecde914bfa2f1624d639
3
+ size 2473440
data/clustering/model=NeuML__pubmedbert-base-embeddings/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
- strain,2444,1680,9,0.9252917766571045,0.7863057263539988,20,0.8
3
- organism_source,6292,5395,20,0.8976125121116638,0.29818041509171506,20,0.8
4
- inducer,7889,7483,28,0.6750833988189697,2.1403205598019306,20,0.8
5
- expression_strain,5677,5199,26,0.5262196660041809,1.3807528050663365,20,0.8
6
- induction_temperature,3656,3376,21,0.5082316398620605,1.2081381876255726,20,0.8
7
- enzyme_name,7975,809,17,0.4914034307003021,1.5863308888012437,20,0.8
8
- plasmid,5480,2611,36,0.3194701671600342,1.9031310724426298,20,0.8
9
- medium_name,4806,3148,44,0.16938011348247528,2.370099609679877,20,0.8
10
- molecular_weight,295,163,3,0.16934853792190552,2.9878266014677677,20,0.8
11
- desalting_process,3720,2653,41,0.08170177787542343,3.1160726884174177,20,0.8
12
- lysis_buffer,3714,2895,33,0.02566622756421566,3.029961583243971,20,0.8
13
- source_key,8021,7900,32,0.01624436117708683,3.1387229562387264,20,0.8
14
- elution_buffer,3530,2747,44,-0.03809003904461861,3.0397752974839842,20,0.8
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,9834,8771,23,0.938924252986908,0.36797224621020197,20,0.8
3
+ inducer,11954,11301,35,0.6509207487106323,2.534949912183667,20,0.8
4
+ strain,3834,2817,17,0.6261206269264221,1.365658956191383,20,0.8
5
+ enzyme_name,12099,1150,27,0.49713146686553955,1.5209424739216852,20,0.8
6
+ expression_strain,8268,7592,38,0.47017335891723633,1.9616976576244958,20,0.8
7
+ induction_temperature,5383,5014,24,0.4639708995819092,1.3702865047886517,20,0.8
8
+ plasmid,8217,3619,55,0.3057723641395569,1.9234241561432937,20,0.8
9
+ medium_name,7644,5183,66,0.16365016996860504,2.4949198727149304,20,0.8
10
+ molecular_weight,495,310,5,0.15848198533058167,2.255365704067329,20,0.8
11
+ desalting_process,5540,3997,61,0.02356620505452156,3.1754673991645683,20,0.8
12
+ lysis_buffer,5625,4507,52,-0.011230088770389557,3.2367384678680953,20,0.8
13
+ source_key,12179,12048,44,-0.01561005413532257,3.3415879087037537,20,0.8
14
+ elution_buffer,5198,4049,55,-0.028480950742959976,3.229346821205781,20,0.8
data/clustering/model=NeuML__pubmedbert-base-embeddings/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 sha256:828705ebf35ffdeea69be47e1136e24d2c9496229508c2e80efcacd756f670f3
3
- size 1528443
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2220fe4e7da4a36e98ac3e74d1d00c11e0fe34caa75f8ef2b5278fcbdfedcf6f
3
+ size 2368413
data/clustering/model=NeuML__pubmedbert-base-embeddings/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
- strain,2444,1459,5,0.9933634400367737,0.24186252882329193,20,0.9
3
- organism_source,6292,5335,19,0.9785525798797607,0.14007012398338348,20,0.9
4
- induction_temperature,3656,3001,22,0.9284213185310364,0.3816830405773302,20,0.9
5
- enzyme_name,7975,244,7,0.8623812794685364,0.5351190807424206,20,0.9
6
- inducer,7889,6915,28,0.6886938810348511,2.10981207384454,20,0.9
7
- expression_strain,5677,4598,29,0.5656421780586243,0.9521658219192719,20,0.9
8
- plasmid,5480,1664,30,0.5038504600524902,1.007144815570722,20,0.9
9
- medium_name,4806,1501,25,0.34143367409706116,1.7255802843898451,20,0.9
10
- desalting_process,3720,915,19,0.3136816918849945,2.0916765246999804,20,0.9
11
- lysis_buffer,3714,1452,34,0.15363141894340515,2.303142273090867,20,0.9
12
- source_key,8021,4969,108,0.15053826570510864,2.3807024892627044,20,0.9
13
- elution_buffer,3530,1347,26,0.1415809988975525,2.4488828402852585,20,0.9
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
+ organism_source,9834,8626,20,0.9938361048698425,0.16103670092267897,20,0.9
3
+ induction_temperature,5383,4587,26,0.9494100213050842,0.37267225573758805,20,0.9
4
+ enzyme_name,12099,262,8,0.8758740425109863,0.5002421035678462,20,0.9
5
+ strain,3834,2350,17,0.8500778675079346,0.5523310449949227,20,0.9
6
+ inducer,11954,10549,42,0.6832385659217834,2.251596290468062,20,0.9
7
+ expression_strain,8268,6521,46,0.5362691879272461,1.0043557643105574,20,0.9
8
+ plasmid,8217,2107,37,0.48523399233818054,1.0503480791586828,20,0.9
9
+ molecular_weight,495,55,2,0.45945024490356445,1.444658015831849,20,0.9
10
+ medium_name,7644,2717,40,0.35647693276405334,1.7347860739429728,20,0.9
11
+ desalting_process,5540,1370,30,0.2346182018518448,2.489640190339895,20,0.9
12
+ elution_buffer,5198,2001,42,0.14087550342082977,2.4445979040820003,20,0.9
13
+ lysis_buffer,5625,2282,49,0.12215285003185272,2.4339333789699933,20,0.9
14
+ source_key,12179,7955,152,0.11304813623428345,2.4668418347776084,20,0.9
data/clustering/model=NeuML__pubmedbert-base-embeddings/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:cc1746609c0c4a20d5b38762d0bf340b0e538430d29a668f5baff7dd1448a670
3
- size 1595133
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb18a6a49f2cdd584e829e3596b36f6a70457c884ed046beade27f3f580960e2
3
+ size 2480396
data/clustering/model=NeuML__pubmedbert-base-embeddings/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,2444,2047,8,0.7387479543685913,1.6176620947728015,30,0.5
3
- organism_source,6292,5675,16,0.7337491512298584,1.2805200153396772,30,0.5
4
- expression_strain,5677,5504,5,0.7320438623428345,0.8622179763126905,30,0.5
5
- induction_temperature,3656,3610,6,0.4177796542644501,1.5165808856766159,30,0.5
6
- lysis_buffer,3714,3635,5,0.3941906988620758,2.6955585472456605,30,0.5
7
- elution_buffer,3530,3418,4,0.29792332649230957,1.830172123833968,30,0.5
8
- inducer,7889,7778,5,0.26365408301353455,2.425932294029049,30,0.5
9
- desalting_process,3720,3606,8,0.15771904587745667,2.8815674886029545,30,0.5
10
- plasmid,5480,5090,27,0.015603872947394848,4.12098593526514,30,0.5
11
- enzyme_name,7975,6240,75,0.015194298699498177,3.989605049720132,30,0.5
12
- medium_name,4806,4557,23,-0.024534281343221664,2.9712236651650947,30,0.5
13
- molecular_weight,295,273,1,,,30,0.5
14
- source_key,8021,8021,1,,,30,0.5
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,9834,9150,21,0.7791294455528259,1.4477759468248552,30,0.5
3
+ expression_strain,8268,8075,5,0.6921619772911072,0.8667965840372828,30,0.5
4
+ strain,3834,3419,10,0.5555756688117981,1.8614982809730065,30,0.5
5
+ induction_temperature,5383,5323,8,0.3790128529071808,1.873116845780309,30,0.5
6
+ lysis_buffer,5625,5519,8,0.3654744029045105,3.185184999427104,30,0.5
7
+ elution_buffer,5198,5104,7,0.2567848563194275,2.9750041453329206,30,0.5
8
+ inducer,11954,11822,8,0.21633528172969818,2.7414033867330923,30,0.5
9
+ desalting_process,5540,5440,11,0.20191708207130432,3.666878146792581,30,0.5
10
+ enzyme_name,12099,9715,109,0.012620445340871811,3.8950371711186786,30,0.5
11
+ medium_name,7644,7352,27,-0.009268024936318398,3.544363706613604,30,0.5
12
+ plasmid,8217,7682,36,-0.031442999839782715,4.233512828082647,30,0.5
13
+ molecular_weight,495,455,1,,,30,0.5
14
+ source_key,12179,12179,1,,,30,0.5
data/clustering/model=NeuML__pubmedbert-base-embeddings/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 sha256:520ec050a7f7cdc566adb12700ad57fd19a5bbad396cf6e88a1cacecccca2a8e
3
- size 1602511
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de1f8eaf1c841ea752bdb2dbed233312c2db31d0435f370b48fbed2789616e62
3
+ size 2491445
data/clustering/model=NeuML__pubmedbert-base-embeddings/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
- organism_source,6292,5484,15,0.8668153882026672,0.7730055019051398,30,0.6
3
- strain,2444,1901,7,0.841008722782135,1.0243220406899167,30,0.6
4
- expression_strain,5677,5479,6,0.7491251826286316,0.7900202939528994,30,0.6
5
- inducer,7889,7702,7,0.4235774874687195,1.6940218877104485,30,0.6
6
- induction_temperature,3656,3551,8,0.324835866689682,2.028516238050866,30,0.6
7
- lysis_buffer,3714,3561,10,0.267193078994751,2.907467961149611,30,0.6
8
- elution_buffer,3530,3353,12,0.12152472138404846,3.273967766575358,30,0.6
9
- enzyme_name,7975,4121,59,0.07828648388385773,3.8860404480234707,30,0.6
10
- desalting_process,3720,3497,16,0.04973843693733215,3.399378516368765,30,0.6
11
- medium_name,4806,4301,30,-0.024660179391503334,3.599994428303352,30,0.6
12
- plasmid,5480,4500,36,-0.027719631791114807,3.0991341987312744,30,0.6
13
- molecular_weight,295,241,1,,,30,0.6
14
- source_key,8021,8021,1,,,30,0.6
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,9834,8902,18,0.8902947902679443,0.9934629118039536,30,0.6
3
+ strain,3834,3229,9,0.7113696336746216,1.1899187081261464,30,0.6
4
+ expression_strain,8268,8054,8,0.5095241665840149,1.1113402358554922,30,0.6
5
+ molecular_weight,495,429,2,0.4396287500858307,1.4995743814161542,30,0.6
6
+ induction_temperature,5383,5277,9,0.2759968042373657,2.5460505172869734,30,0.6
7
+ lysis_buffer,5625,5389,13,0.21754270792007446,3.1790281252629735,30,0.6
8
+ inducer,11954,11730,10,0.15821345150470734,2.603831730905988,30,0.6
9
+ elution_buffer,5198,4989,16,0.09308198094367981,3.087379055534547,30,0.6
10
+ plasmid,8217,6868,58,0.09213186800479889,3.569814780593335,30,0.6
11
+ enzyme_name,12099,6534,89,0.07088087499141693,3.5974168011349974,30,0.6
12
+ desalting_process,5540,5280,22,0.04958867281675339,3.584399202797272,30,0.6
13
+ medium_name,7644,7084,43,-0.03382620960474014,3.569162558064814,30,0.6
14
+ source_key,12179,12179,1,,,30,0.6
data/clustering/model=NeuML__pubmedbert-base-embeddings/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 sha256:26034d88008554112c23f76310beeceddfd6e2b37b6ca994263c8c79bc4cf713
3
- size 1579390
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:063f9c3940248c0eef59b9dad36587aca5e55c34c5e0c69c2e211144d6c9b485
3
+ size 2471741
data/clustering/model=NeuML__pubmedbert-base-embeddings/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,2444,1777,6,0.8847620487213135,0.7922689371856771,30,0.7
3
- organism_source,6292,5346,13,0.8844028115272522,0.49563055520365673,30,0.7
4
- inducer,7889,7569,7,0.7369444370269775,1.621042199442947,30,0.7
5
- expression_strain,5677,5378,9,0.5242722630500793,1.3177092046250884,30,0.7
6
- induction_temperature,3656,3481,12,0.31392714381217957,1.7224354887187852,30,0.7
7
- source_key,8021,8018,2,0.24789279699325562,3.5119799841196926,30,0.7
8
- enzyme_name,7975,2013,32,0.24377301335334778,2.903724807910372,30,0.7
9
- plasmid,5480,3555,29,0.23242218792438507,2.597081232517982,30,0.7
10
- medium_name,4806,3813,26,0.14467056095600128,2.6248759573739884,30,0.7
11
- lysis_buffer,3714,3266,10,0.1332804262638092,2.852895772076153,30,0.7
12
- elution_buffer,3530,3179,22,0.05641382187604904,3.923859220142157,30,0.7
13
- desalting_process,3720,3233,26,0.028188934549689293,3.6709080869449666,30,0.7
14
- molecular_weight,295,200,1,,,30,0.7
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,9834,8763,16,0.9182670712471008,0.5085039235490207,30,0.7
3
+ inducer,11954,11495,11,0.7005226016044617,2.3228114015590386,30,0.7
4
+ molecular_weight,495,381,2,0.5731660723686218,1.247151217399578,30,0.7
5
+ strain,3834,2990,9,0.5417677760124207,1.8352016057090543,30,0.7
6
+ expression_strain,8268,7919,18,0.3515068590641022,2.6042037613243396,30,0.7
7
+ induction_temperature,5383,5183,14,0.26885658502578735,1.4454062446830407,30,0.7
8
+ source_key,12179,12171,2,0.24367043375968933,3.7147679301950136,30,0.7
9
+ enzyme_name,12099,3093,52,0.2235347032546997,2.9030914657836173,30,0.7
10
+ plasmid,8217,5029,45,0.19218875467777252,2.8904343745180943,30,0.7
11
+ lysis_buffer,5625,5101,21,0.10882223397493362,3.227306334243658,30,0.7
12
+ medium_name,7644,6292,39,0.09153791517019272,3.114028902654882,30,0.7
13
+ desalting_process,5540,4836,35,0.015266909264028072,3.522151339275118,30,0.7
14
+ elution_buffer,5198,4717,30,0.0018493938259780407,3.546002742204452,30,0.7
data/clustering/model=NeuML__pubmedbert-base-embeddings/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 sha256:437cc92a051e516b90452ea9b96940c25d289fb9d84657d9e6afc698a8183ad7
3
- size 1565077
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc7e75c65220f5de864009cbc468dd81738442b50e4cec8ca667f977c0228e17
3
+ size 2443467
data/clustering/model=NeuML__pubmedbert-base-embeddings/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
- strain,2444,1608,6,0.9413581490516663,0.592646380964163,30,0.8
3
- organism_source,6292,5227,13,0.8959501385688782,0.11579256663869128,30,0.8
4
- inducer,7889,7391,17,0.6904475688934326,2.1798036853930842,30,0.8
5
- enzyme_name,7975,608,8,0.572870135307312,1.2970313820823045,30,0.8
6
- expression_strain,5677,5083,16,0.5316421985626221,1.3794505356619733,30,0.8
7
- induction_temperature,3656,3276,15,0.5170644521713257,1.081939158751618,30,0.8
8
- plasmid,5480,2368,22,0.36899977922439575,1.678072712079353,30,0.8
9
- medium_name,4806,2779,24,0.2140057235956192,2.389639294638332,30,0.8
10
- desalting_process,3720,2498,27,0.08945844322443008,3.220827966847268,30,0.8
11
- source_key,8021,7876,26,0.02789880335330963,3.387593788430039,30,0.8
12
- lysis_buffer,3714,2727,22,0.00704045407474041,3.553098837704762,30,0.8
13
- elution_buffer,3530,2599,26,-0.007869563065469265,2.971236202982939,30,0.8
14
- molecular_weight,295,120,1,,,30,0.8
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,9834,8624,17,0.9395735263824463,0.341728002777751,30,0.8
3
+ strain,3834,2684,11,0.6573151350021362,1.3974000012840444,30,0.8
4
+ inducer,11954,11196,25,0.6545769572257996,2.7110422686498463,30,0.8
5
+ induction_temperature,5383,4846,15,0.5279124975204468,1.132034360101091,30,0.8
6
+ enzyme_name,12099,915,17,0.481136679649353,1.8009718610500374,30,0.8
7
+ expression_strain,8268,7493,30,0.48008450865745544,2.0225401443188447,30,0.8
8
+ plasmid,8217,3094,30,0.3073803782463074,2.056085316328521,30,0.8
9
+ medium_name,7644,4763,42,0.18330636620521545,2.682429181202671,30,0.8
10
+ molecular_weight,495,274,3,0.1697501689195633,2.5461231664047994,30,0.8
11
+ desalting_process,5540,3865,45,0.03669217973947525,3.2035690263949257,30,0.8
12
+ source_key,12179,11935,33,-0.0027732085436582565,3.5835435920679073,30,0.8
13
+ elution_buffer,5198,3908,36,-0.003017418785020709,3.4280277546621956,30,0.8
14
+ lysis_buffer,5625,4324,35,-0.00987998116761446,3.5164518979389565,30,0.8
data/clustering/model=NeuML__pubmedbert-base-embeddings/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:b0046b85233e0fc6e7332a794306199dd3daeff1be27e2ff3047bfe636fc0104
3
- size 1514264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fe0588b52a29926c6ee3006deaeb06249b058e8722d41893b8d73a2e149a372
3
+ size 2343510
data/clustering/model=NeuML__pubmedbert-base-embeddings/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
- strain,2444,1416,3,0.995725154876709,0.16641304118982256,30,0.9
3
- organism_source,6292,5187,13,0.9861152768135071,0.04018051741415145,30,0.9
4
- induction_temperature,3656,2925,19,0.9314102530479431,0.33886886334171623,30,0.9
5
- enzyme_name,7975,144,3,0.8892529010772705,0.48788499726560675,30,0.9
6
- inducer,7889,6790,19,0.7142660021781921,2.0925406759894005,30,0.9
7
- expression_strain,5677,4372,19,0.5599997639656067,0.9283359022462655,30,0.9
8
- plasmid,5480,1445,19,0.4889703392982483,1.115912554124196,30,0.9
9
- medium_name,4806,1380,18,0.3426302671432495,1.8141656386084861,30,0.9
10
- desalting_process,3720,746,11,0.317225843667984,2.2521487281420423,30,0.9
11
- source_key,8021,4174,61,0.15622453391551971,2.5787232127140687,30,0.9
12
- lysis_buffer,3714,1169,18,0.15555055439472198,2.4968517444864924,30,0.9
13
- elution_buffer,3530,1159,16,0.1403721123933792,2.546139276363924,30,0.9
14
- molecular_weight,295,0,0,,,30,0.9
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,9834,8526,16,0.9944865107536316,0.038593039102208945,30,0.9
3
+ induction_temperature,5383,4432,20,0.9501296281814575,0.37128622461922217,30,0.9
4
+ enzyme_name,12099,136,3,0.8890537023544312,0.4895897888291401,30,0.9
5
+ strain,3834,2263,13,0.8528121709823608,0.6055389848763332,30,0.9
6
+ inducer,11954,10323,29,0.7009783983230591,2.29827036197951,30,0.9
7
+ expression_strain,8268,6183,30,0.5316296219825745,1.0170404708325742,30,0.9
8
+ plasmid,8217,1884,26,0.49713292717933655,1.0363180768761346,30,0.9
9
+ medium_name,7644,2472,26,0.3699890375137329,1.7814427995432671,30,0.9
10
+ desalting_process,5540,1061,16,0.26339101791381836,2.5199229436257844,30,0.9
11
+ elution_buffer,5198,1743,25,0.14168211817741394,2.668497619311455,30,0.9
12
+ lysis_buffer,5625,2019,32,0.12870806455612183,2.6613808609245706,30,0.9
13
+ source_key,12179,7023,98,0.10604915022850037,2.7326270549435856,30,0.9
14
+ molecular_weight,495,0,0,,,30,0.9
data/clustering/model=NeuML__pubmedbert-base-embeddings/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 sha256:43ce877355929dd269a7375e645adb1302dfe7f6c8084c8ea6076b92f9b72a9a
3
- size 1641642
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05abce3a0668f75c272f6e6678e29b5bef1d8e34dbfd6fc64a72610199a0ff00
3
+ size 2550097
data/clustering/model=NeuML__pubmedbert-base-embeddings/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,6292,6152,65,0.7116084694862366,1.2776319927001494,5,0.5
3
- strain,2444,2341,46,0.6651964783668518,1.5154119349243513,5,0.5
4
- expression_strain,5677,5635,18,0.6643050909042358,1.2710638164484551,5,0.5
5
- molecular_weight,295,292,3,0.3724769353866577,2.3800510724609887,5,0.5
6
- induction_temperature,3656,3651,22,0.34683331847190857,1.5956831416893904,5,0.5
7
- lysis_buffer,3714,3685,19,0.33203479647636414,2.265500853194448,5,0.5
8
- elution_buffer,3530,3519,21,0.18799574673175812,2.025847339852486,5,0.5
9
- desalting_process,3720,3705,32,0.13077065348625183,2.140481767642444,5,0.5
10
- inducer,7889,7869,24,0.040928199887275696,2.1315596783071995,5,0.5
11
- enzyme_name,7975,7486,386,-0.032286837697029114,2.787813201840156,5,0.5
12
- plasmid,5480,5386,99,-0.04223800078034401,2.9716109209671746,5,0.5
13
- medium_name,4806,4764,88,-0.07344536483287811,2.3772258858006903,5,0.5
14
- source_key,8021,8021,1,,,5,0.5
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,9834,9694,82,0.7597892880439758,1.3828830326928037,5,0.5
3
+ strain,3834,3718,56,0.5236640572547913,1.7111298468277762,5,0.5
4
+ expression_strain,8268,8231,24,0.4971255362033844,1.31600135483574,5,0.5
5
+ induction_temperature,5383,5377,23,0.36087438464164734,1.6547958599789643,5,0.5
6
+ lysis_buffer,5625,5607,34,0.2816701829433441,2.292734734277252,5,0.5
7
+ molecular_weight,495,491,4,0.2635747194290161,1.9656868028226644,5,0.5
8
+ elution_buffer,5198,5182,30,0.1773126721382141,2.3567062751472365,5,0.5
9
+ desalting_process,5540,5521,38,0.1456826776266098,2.6653441784947915,5,0.5
10
+ inducer,11954,11933,36,-0.007892987690865993,2.1939853783949292,5,0.5
11
+ enzyme_name,12099,11472,584,-0.042914800345897675,2.7585474269404515,5,0.5
12
+ plasmid,8217,8108,140,-0.07483965903520584,3.0067603941790333,5,0.5
13
+ medium_name,7644,7589,98,-0.07718747109174728,2.5033854884802262,5,0.5
14
+ source_key,12179,12179,1,,,5,0.5
data/clustering/model=NeuML__pubmedbert-base-embeddings/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:e2da2946f9835894d728532999864112edb65da36649f30c29413b18bced1b0c
3
- size 1667396
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4a84c916b1e503476318407ae8aeaa21c0a7fe61af374be5885113fb54f1354
3
+ size 2586417
data/clustering/model=NeuML__pubmedbert-base-embeddings/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,6292,6053,65,0.8506341576576233,0.8762573591589932,5,0.6
3
- strain,2444,2268,43,0.7561348676681519,1.232902500283271,5,0.6
4
- expression_strain,5677,5618,20,0.5712189078330994,1.2344710419009868,5,0.6
5
- inducer,7889,7840,37,0.3981858789920807,1.8112936476973818,5,0.6
6
- molecular_weight,295,288,8,0.2509263753890991,2.6015992217309556,5,0.6
7
- induction_temperature,3656,3634,26,0.22644540667533875,1.995524172814541,5,0.6
8
- lysis_buffer,3714,3662,38,0.20235462486743927,2.170020576657856,5,0.6
9
- enzyme_name,7975,6566,480,0.04579773172736168,2.474849264581452,5,0.6
10
- elution_buffer,3530,3494,48,0.03527271747589111,2.206144199418986,5,0.6
11
- desalting_process,3720,3666,71,-0.011856835335493088,2.437033611863743,5,0.6
12
- medium_name,4806,4678,124,-0.04384743049740791,2.2406051611874065,5,0.6
13
- plasmid,5480,5134,165,-0.052219994366168976,2.4566962912067374,5,0.6
14
- source_key,8021,8021,1,,,5,0.6
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,9834,9578,83,0.8651096820831299,0.9726462897076272,5,0.6
3
+ strain,3834,3635,53,0.5794798135757446,1.4682415173756225,5,0.6
4
+ expression_strain,8268,8207,30,0.4250609278678894,1.4161182917559691,5,0.6
5
+ molecular_weight,495,484,11,0.23443005979061127,2.7096647790884156,5,0.6
6
+ induction_temperature,5383,5360,34,0.20033273100852966,2.164715478835619,5,0.6
7
+ lysis_buffer,5625,5552,55,0.18812385201454163,2.120200548183522,5,0.6
8
+ elution_buffer,5198,5148,65,0.03931543603539467,2.3402916755387584,5,0.6
9
+ plasmid,8217,7734,286,0.03893932327628136,2.677174856343722,5,0.6
10
+ enzyme_name,12099,10115,714,0.03464433178305626,2.4732477269679216,5,0.6
11
+ inducer,11954,11890,51,-0.0010591204045340419,2.0789740490354345,5,0.6
12
+ medium_name,7644,7478,159,-0.05557246878743172,2.3789068228104893,5,0.6
13
+ desalting_process,5540,5465,87,-0.05897752195596695,2.5009961246932493,5,0.6
14
+ source_key,12179,12179,1,,,5,0.6
data/clustering/model=NeuML__pubmedbert-base-embeddings/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 sha256:7a9525468b8bcda39aab8905f109a5af03ce177b93c0c077c0abfb2cc5932a86
3
- size 1654577
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:864b8d823d3f839fc332c6a5714f8a2c0959ee6b19e513ab1a98a0ee7f9bb76c
3
+ size 2605089
data/clustering/model=NeuML__pubmedbert-base-embeddings/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,6292,5952,67,0.8556991219520569,0.5686428941764288,5,0.7
3
- strain,2444,2142,47,0.747120201587677,0.9946439017044285,5,0.7
4
- inducer,7889,7789,45,0.6830241680145264,1.8402158765543684,5,0.7
5
- expression_strain,5677,5549,32,0.39044469594955444,1.3788925864711792,5,0.7
6
- molecular_weight,295,273,9,0.322784960269928,2.0106841047612996,5,0.7
7
- induction_temperature,3656,3581,33,0.23405320942401886,1.6747121825152123,5,0.7
8
- enzyme_name,7975,4977,427,0.21938377618789673,1.94449823999632,5,0.7
9
- plasmid,5480,4499,168,0.1913851499557495,2.0670183165479945,5,0.7
10
- source_key,8021,8021,4,0.1677163541316986,2.5406642940100594,5,0.7
11
- lysis_buffer,3714,3577,70,0.08887837082147598,1.9886834723886047,5,0.7
12
- medium_name,4806,4420,144,0.08617504686117172,1.9819755571376518,5,0.7
13
- desalting_process,3720,3537,110,0.0009430046193301678,2.30734582182165,5,0.7
14
- elution_buffer,3530,3407,101,-0.0039037021342664957,2.353557274602187,5,0.7
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,9834,9470,81,0.8951528668403625,0.6156095080857287,5,0.7
3
+ inducer,11954,11826,72,0.6433972716331482,1.970590292526747,5,0.7
4
+ strain,3834,3478,66,0.47240424156188965,1.308255793173933,5,0.7
5
+ expression_strain,8268,8123,52,0.3175680935382843,2.061992168194414,5,0.7
6
+ molecular_weight,495,460,12,0.28010037541389465,2.036210495644249,5,0.7
7
+ enzyme_name,12099,7694,667,0.2181576043367386,1.968635041744093,5,0.7
8
+ source_key,12179,12176,3,0.21569623053073883,3.271537154662449,5,0.7
9
+ induction_temperature,5383,5294,42,0.17363622784614563,1.7750479205165324,5,0.7
10
+ plasmid,8217,6687,293,0.1395067274570465,2.241273912410873,5,0.7
11
+ lysis_buffer,5625,5442,99,0.06963126361370087,2.2921407990779303,5,0.7
12
+ medium_name,7644,7153,225,0.040841925889253616,2.138664139453662,5,0.7
13
+ desalting_process,5540,5285,156,-0.021950973197817802,2.471027340645969,5,0.7
14
+ elution_buffer,5198,5048,149,-0.05791900306940079,2.2865845299518153,5,0.7
data/clustering/model=NeuML__pubmedbert-base-embeddings/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:a7d40afbec0a7be578c85597cf1f6de89f56dc9d1d37dcc80abe614224af327d
3
- size 1661818
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b05f6a1c5a353838d57e7f5aa80e2aac55774c65c817fd2f547fb261c69ec242
3
+ size 2595713
data/clustering/model=NeuML__pubmedbert-base-embeddings/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,6292,5860,73,0.899277925491333,0.35284450468743145,5,0.8
3
- strain,2444,2024,52,0.8691732883453369,0.7565188359562189,5,0.8
4
- inducer,7889,7646,78,0.6505777835845947,1.7906389296664111,5,0.8
5
- expression_strain,5677,5453,60,0.4677024185657501,1.2558169361042266,5,0.8
6
- enzyme_name,7975,2935,302,0.46385183930397034,1.2801573710331045,5,0.8
7
- induction_temperature,3656,3479,38,0.43915894627571106,1.3012482233503062,5,0.8
8
- plasmid,5480,3580,172,0.3323499858379364,1.4610948716959313,5,0.8
9
- molecular_weight,295,247,15,0.1836349070072174,1.9589420199936334,5,0.8
10
- medium_name,4806,3877,182,0.17937305569648743,1.7794366370269679,5,0.8
11
- desalting_process,3720,3124,154,0.044300515204668045,2.262571166488856,5,0.8
12
- lysis_buffer,3714,3299,126,0.009192639030516148,2.0764094673347175,5,0.8
13
- elution_buffer,3530,3128,137,-0.022425707429647446,2.2018447701177277,5,0.8
14
- source_key,8021,8008,74,-0.03492216393351555,2.2838507364297627,5,0.8
 
1
  field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,9834,9340,88,0.9368722438812256,0.3937709444869219,5,0.8
3
+ inducer,11954,11598,114,0.6096725463867188,1.8174811253394179,5,0.8
4
+ strain,3834,3228,72,0.5731325149536133,1.1530990348346448,5,0.8
5
+ enzyme_name,12099,4414,451,0.48379701375961304,1.2906890754806173,5,0.8
6
+ induction_temperature,5383,5141,46,0.4491744935512543,1.3720869180322595,5,0.8
7
+ expression_strain,8268,7935,95,0.41298651695251465,1.7339211252411244,5,0.8
8
+ plasmid,8217,4991,260,0.3145831525325775,1.5375510941258081,5,0.8
9
+ medium_name,7644,6257,274,0.15979766845703125,1.8752252957491684,5,0.8
10
+ molecular_weight,495,425,22,0.1351013332605362,2.0026006130416776,5,0.8
11
+ desalting_process,5540,4642,226,0.0035786216612905264,2.315476695967539,5,0.8
12
+ elution_buffer,5198,4624,193,-0.03157674893736839,2.345602868217775,5,0.8
13
+ lysis_buffer,5625,5051,187,-0.03582679107785225,2.17319799885268,5,0.8
14
+ source_key,12179,12155,98,-0.0664583295583725,2.335495687717003,5,0.8
data/clustering/model=NeuML__pubmedbert-base-embeddings/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:acdd5ecafa938a624d9d96f3fc7e1f960ebb3258b9f5548dceb4da2b21c15c84
3
- size 1610020
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35ef07bfb0f1dfe807cb8863ef3925656f000c28bedf3d842d1adda1738b6ed4
3
+ size 2493097