Commit
·
284f956
1
Parent(s):
850dfb5
cleaned data
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- training_data/hemo-negative.npz +2 -2
- training_data/hemo-positive.npz +2 -2
- training_data/nf-negative.npz +2 -2
- training_data/nf-positive.npz +2 -2
- training_data_cleaned/hemolysis/hemo_meta_with_split.csv +3 -0
- training_data_cleaned/hemolysis/hemo_smiles_meta_with_split.csv +3 -0
- training_data_cleaned/hemolysis/hemo_smiles_with_embeddings/dataset_dict.json +1 -0
- training_data_cleaned/hemolysis/hemo_smiles_with_embeddings/train/data-00000-of-00001.arrow +3 -0
- training_data_cleaned/hemolysis/hemo_smiles_with_embeddings/train/dataset_info.json +23 -0
- training_data_cleaned/hemolysis/hemo_smiles_with_embeddings/train/state.json +13 -0
- training_data_cleaned/hemolysis/hemo_smiles_with_embeddings/val/data-00000-of-00001.arrow +3 -0
- training_data_cleaned/hemolysis/hemo_smiles_with_embeddings/val/dataset_info.json +23 -0
- training_data_cleaned/hemolysis/hemo_smiles_with_embeddings/val/state.json +13 -0
- training_data_cleaned/hemolysis/hemo_wt_with_embeddings/dataset_dict.json +1 -0
- training_data_cleaned/hemolysis/hemo_wt_with_embeddings/train/data-00000-of-00001.arrow +3 -0
- training_data_cleaned/hemolysis/hemo_wt_with_embeddings/train/dataset_info.json +23 -0
- training_data_cleaned/hemolysis/hemo_wt_with_embeddings/train/state.json +13 -0
- training_data_cleaned/hemolysis/hemo_wt_with_embeddings/val/data-00000-of-00001.arrow +3 -0
- training_data_cleaned/hemolysis/hemo_wt_with_embeddings/val/dataset_info.json +23 -0
- training_data_cleaned/hemolysis/hemo_wt_with_embeddings/val/state.json +13 -0
- training_data_cleaned/nf/nf_meta_with_split.csv +3 -0
- training_data_cleaned/nf/nf_smiles_meta_with_split.csv +3 -0
- training_data_cleaned/nf/nf_smiles_with_embeddings/dataset_dict.json +1 -0
- training_data_cleaned/nf/nf_smiles_with_embeddings/train/data-00000-of-00001.arrow +3 -0
- training_data_cleaned/nf/nf_smiles_with_embeddings/train/dataset_info.json +23 -0
- training_data_cleaned/nf/nf_smiles_with_embeddings/train/state.json +13 -0
- training_data_cleaned/nf/nf_smiles_with_embeddings/val/data-00000-of-00001.arrow +3 -0
- training_data_cleaned/nf/nf_smiles_with_embeddings/val/dataset_info.json +23 -0
- training_data_cleaned/nf/nf_smiles_with_embeddings/val/state.json +13 -0
- training_data_cleaned/nf/nf_wt_with_embeddings/dataset_dict.json +1 -0
- training_data_cleaned/nf/nf_wt_with_embeddings/train/data-00000-of-00001.arrow +3 -0
- training_data_cleaned/nf/nf_wt_with_embeddings/train/dataset_info.json +23 -0
- training_data_cleaned/nf/nf_wt_with_embeddings/train/state.json +13 -0
- training_data_cleaned/nf/nf_wt_with_embeddings/val/data-00000-of-00001.arrow +3 -0
- training_data_cleaned/nf/nf_wt_with_embeddings/val/dataset_info.json +23 -0
- training_data_cleaned/nf/nf_wt_with_embeddings/val/state.json +13 -0
- training_data_cleaned/permeability_caco2/caco2_meta_with_split.csv +3 -0
- training_data_cleaned/permeability_caco2/caco2_smiles_with_embeddings/dataset_dict.json +1 -0
- training_data_cleaned/permeability_caco2/caco2_smiles_with_embeddings/train/data-00000-of-00001.arrow +3 -0
- training_data_cleaned/permeability_caco2/caco2_smiles_with_embeddings/train/dataset_info.json +23 -0
- training_data_cleaned/permeability_caco2/caco2_smiles_with_embeddings/train/state.json +13 -0
- training_data_cleaned/permeability_caco2/caco2_smiles_with_embeddings/val/data-00000-of-00001.arrow +3 -0
- training_data_cleaned/permeability_caco2/caco2_smiles_with_embeddings/val/dataset_info.json +23 -0
- training_data_cleaned/permeability_caco2/caco2_smiles_with_embeddings/val/state.json +13 -0
- training_data_cleaned/permeability_pampa/pampa_meta_with_split.csv +3 -0
- training_data_cleaned/permeability_pampa/pampa_smiles_with_embeddings/dataset_dict.json +1 -0
- training_data_cleaned/permeability_pampa/pampa_smiles_with_embeddings/train/data-00000-of-00001.arrow +3 -0
- training_data_cleaned/permeability_pampa/pampa_smiles_with_embeddings/train/dataset_info.json +23 -0
- training_data_cleaned/permeability_pampa/pampa_smiles_with_embeddings/train/state.json +13 -0
- training_data_cleaned/permeability_pampa/pampa_smiles_with_embeddings/val/data-00000-of-00001.arrow +3 -0
training_data/hemo-negative.npz
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bcf254803d7f5a809153007989de42b9ca9030c3a45b1f4048f40b289d010012
|
| 3 |
+
size 11385064
|
training_data/hemo-positive.npz
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c4dd8a83ebf887e285bd5d10e3cee919452d8ddf97463e02f52ee51789aebb41
|
| 3 |
+
size 2775784
|
training_data/nf-negative.npz
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:697db57ca3cf2366caabc000b69019e3b84fe88fea5da98de3fd75b3c9920aeb
|
| 3 |
+
size 21736264
|
training_data/nf-positive.npz
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d49dea7969a0e408dfede599f165746bb45c83dc5bac1cc1a7d14e32de13406
|
| 3 |
+
size 5760264
|
training_data_cleaned/hemolysis/hemo_meta_with_split.csv
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0326835d831524088e84ab86b1555cac366219fb5982fca7ac9ddddfc43b1b0
|
| 3 |
+
size 233220
|
training_data_cleaned/hemolysis/hemo_smiles_meta_with_split.csv
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e521d4f4344bebdce1b5aa57f9e7fb1c6dc848319cb980baec38574573f079f
|
| 3 |
+
size 4726077
|
training_data_cleaned/hemolysis/hemo_smiles_with_embeddings/dataset_dict.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"splits": ["train", "val"]}
|
training_data_cleaned/hemolysis/hemo_smiles_with_embeddings/train/data-00000-of-00001.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1af97dd02933072c0522101cb6c382703093fcdeee3185e509c6edd6fc070b8a
|
| 3 |
+
size 16876472
|
training_data_cleaned/hemolysis/hemo_smiles_with_embeddings/train/dataset_info.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"citation": "",
|
| 3 |
+
"description": "",
|
| 4 |
+
"features": {
|
| 5 |
+
"sequence": {
|
| 6 |
+
"dtype": "string",
|
| 7 |
+
"_type": "Value"
|
| 8 |
+
},
|
| 9 |
+
"embedding": {
|
| 10 |
+
"feature": {
|
| 11 |
+
"dtype": "float32",
|
| 12 |
+
"_type": "Value"
|
| 13 |
+
},
|
| 14 |
+
"_type": "List"
|
| 15 |
+
},
|
| 16 |
+
"label": {
|
| 17 |
+
"dtype": "int64",
|
| 18 |
+
"_type": "Value"
|
| 19 |
+
}
|
| 20 |
+
},
|
| 21 |
+
"homepage": "",
|
| 22 |
+
"license": ""
|
| 23 |
+
}
|
training_data_cleaned/hemolysis/hemo_smiles_with_embeddings/train/state.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_data_files": [
|
| 3 |
+
{
|
| 4 |
+
"filename": "data-00000-of-00001.arrow"
|
| 5 |
+
}
|
| 6 |
+
],
|
| 7 |
+
"_fingerprint": "48acc3da44ca47b8",
|
| 8 |
+
"_format_columns": null,
|
| 9 |
+
"_format_kwargs": {},
|
| 10 |
+
"_format_type": null,
|
| 11 |
+
"_output_all_columns": false,
|
| 12 |
+
"_split": null
|
| 13 |
+
}
|
training_data_cleaned/hemolysis/hemo_smiles_with_embeddings/val/data-00000-of-00001.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:40cb576c6993d53b26152f4cd954ba372c2b7817811ee4da9513036e9d2cc573
|
| 3 |
+
size 4157120
|
training_data_cleaned/hemolysis/hemo_smiles_with_embeddings/val/dataset_info.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"citation": "",
|
| 3 |
+
"description": "",
|
| 4 |
+
"features": {
|
| 5 |
+
"sequence": {
|
| 6 |
+
"dtype": "string",
|
| 7 |
+
"_type": "Value"
|
| 8 |
+
},
|
| 9 |
+
"embedding": {
|
| 10 |
+
"feature": {
|
| 11 |
+
"dtype": "float32",
|
| 12 |
+
"_type": "Value"
|
| 13 |
+
},
|
| 14 |
+
"_type": "List"
|
| 15 |
+
},
|
| 16 |
+
"label": {
|
| 17 |
+
"dtype": "int64",
|
| 18 |
+
"_type": "Value"
|
| 19 |
+
}
|
| 20 |
+
},
|
| 21 |
+
"homepage": "",
|
| 22 |
+
"license": ""
|
| 23 |
+
}
|
training_data_cleaned/hemolysis/hemo_smiles_with_embeddings/val/state.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_data_files": [
|
| 3 |
+
{
|
| 4 |
+
"filename": "data-00000-of-00001.arrow"
|
| 5 |
+
}
|
| 6 |
+
],
|
| 7 |
+
"_fingerprint": "fd2db53d34e0b66a",
|
| 8 |
+
"_format_columns": null,
|
| 9 |
+
"_format_kwargs": {},
|
| 10 |
+
"_format_type": null,
|
| 11 |
+
"_output_all_columns": false,
|
| 12 |
+
"_split": null
|
| 13 |
+
}
|
training_data_cleaned/hemolysis/hemo_wt_with_embeddings/dataset_dict.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"splits": ["train", "val"]}
|
training_data_cleaned/hemolysis/hemo_wt_with_embeddings/train/data-00000-of-00001.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b790e2b015c19f7e0af6b8c412543677d3cdb792591952c98717f5a38eb62fc
|
| 3 |
+
size 25054912
|
training_data_cleaned/hemolysis/hemo_wt_with_embeddings/train/dataset_info.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"citation": "",
|
| 3 |
+
"description": "",
|
| 4 |
+
"features": {
|
| 5 |
+
"sequence": {
|
| 6 |
+
"dtype": "string",
|
| 7 |
+
"_type": "Value"
|
| 8 |
+
},
|
| 9 |
+
"embedding": {
|
| 10 |
+
"feature": {
|
| 11 |
+
"dtype": "float32",
|
| 12 |
+
"_type": "Value"
|
| 13 |
+
},
|
| 14 |
+
"_type": "List"
|
| 15 |
+
},
|
| 16 |
+
"label": {
|
| 17 |
+
"dtype": "int64",
|
| 18 |
+
"_type": "Value"
|
| 19 |
+
}
|
| 20 |
+
},
|
| 21 |
+
"homepage": "",
|
| 22 |
+
"license": ""
|
| 23 |
+
}
|
training_data_cleaned/hemolysis/hemo_wt_with_embeddings/train/state.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_data_files": [
|
| 3 |
+
{
|
| 4 |
+
"filename": "data-00000-of-00001.arrow"
|
| 5 |
+
}
|
| 6 |
+
],
|
| 7 |
+
"_fingerprint": "e02b995aa75a9a40",
|
| 8 |
+
"_format_columns": null,
|
| 9 |
+
"_format_kwargs": {},
|
| 10 |
+
"_format_type": null,
|
| 11 |
+
"_output_all_columns": false,
|
| 12 |
+
"_split": null
|
| 13 |
+
}
|
training_data_cleaned/hemolysis/hemo_wt_with_embeddings/val/data-00000-of-00001.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:29ace9ae3f6248785f08e15fff28be45e2d4832aaf929008470b055d60b3a523
|
| 3 |
+
size 6268920
|
training_data_cleaned/hemolysis/hemo_wt_with_embeddings/val/dataset_info.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"citation": "",
|
| 3 |
+
"description": "",
|
| 4 |
+
"features": {
|
| 5 |
+
"sequence": {
|
| 6 |
+
"dtype": "string",
|
| 7 |
+
"_type": "Value"
|
| 8 |
+
},
|
| 9 |
+
"embedding": {
|
| 10 |
+
"feature": {
|
| 11 |
+
"dtype": "float32",
|
| 12 |
+
"_type": "Value"
|
| 13 |
+
},
|
| 14 |
+
"_type": "List"
|
| 15 |
+
},
|
| 16 |
+
"label": {
|
| 17 |
+
"dtype": "int64",
|
| 18 |
+
"_type": "Value"
|
| 19 |
+
}
|
| 20 |
+
},
|
| 21 |
+
"homepage": "",
|
| 22 |
+
"license": ""
|
| 23 |
+
}
|
training_data_cleaned/hemolysis/hemo_wt_with_embeddings/val/state.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_data_files": [
|
| 3 |
+
{
|
| 4 |
+
"filename": "data-00000-of-00001.arrow"
|
| 5 |
+
}
|
| 6 |
+
],
|
| 7 |
+
"_fingerprint": "b7d24c190523afa3",
|
| 8 |
+
"_format_columns": null,
|
| 9 |
+
"_format_kwargs": {},
|
| 10 |
+
"_format_type": null,
|
| 11 |
+
"_output_all_columns": false,
|
| 12 |
+
"_split": null
|
| 13 |
+
}
|
training_data_cleaned/nf/nf_meta_with_split.csv
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bcce644701612db54d5f3505dce201c351234837e3685739b2fde68d53c8cf5e
|
| 3 |
+
size 1756049
|
training_data_cleaned/nf/nf_smiles_meta_with_split.csv
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e36214670d615dca1a48df6500c203707cdbf31c88261bf719f7d7c1eabc201c
|
| 3 |
+
size 57456921
|
training_data_cleaned/nf/nf_smiles_with_embeddings/dataset_dict.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"splits": ["train", "val"]}
|
training_data_cleaned/nf/nf_smiles_with_embeddings/train/data-00000-of-00001.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d682c81cf7d3c0ce5f1f11ebf2b097d7f100f2d2a78a8ad8a40b1f38b94cc5a
|
| 3 |
+
size 23581248
|
training_data_cleaned/nf/nf_smiles_with_embeddings/train/dataset_info.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"citation": "",
|
| 3 |
+
"description": "",
|
| 4 |
+
"features": {
|
| 5 |
+
"sequence": {
|
| 6 |
+
"dtype": "string",
|
| 7 |
+
"_type": "Value"
|
| 8 |
+
},
|
| 9 |
+
"embedding": {
|
| 10 |
+
"feature": {
|
| 11 |
+
"dtype": "float32",
|
| 12 |
+
"_type": "Value"
|
| 13 |
+
},
|
| 14 |
+
"_type": "List"
|
| 15 |
+
},
|
| 16 |
+
"label": {
|
| 17 |
+
"dtype": "int64",
|
| 18 |
+
"_type": "Value"
|
| 19 |
+
}
|
| 20 |
+
},
|
| 21 |
+
"homepage": "",
|
| 22 |
+
"license": ""
|
| 23 |
+
}
|
training_data_cleaned/nf/nf_smiles_with_embeddings/train/state.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_data_files": [
|
| 3 |
+
{
|
| 4 |
+
"filename": "data-00000-of-00001.arrow"
|
| 5 |
+
}
|
| 6 |
+
],
|
| 7 |
+
"_fingerprint": "fb6f5e1e2e124220",
|
| 8 |
+
"_format_columns": null,
|
| 9 |
+
"_format_kwargs": {},
|
| 10 |
+
"_format_type": null,
|
| 11 |
+
"_output_all_columns": false,
|
| 12 |
+
"_split": null
|
| 13 |
+
}
|
training_data_cleaned/nf/nf_smiles_with_embeddings/val/data-00000-of-00001.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd5724627360561f961366f3c57b8de1ed0f6187bbf670bd3a4254da1d0ba571
|
| 3 |
+
size 57618824
|
training_data_cleaned/nf/nf_smiles_with_embeddings/val/dataset_info.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"citation": "",
|
| 3 |
+
"description": "",
|
| 4 |
+
"features": {
|
| 5 |
+
"sequence": {
|
| 6 |
+
"dtype": "string",
|
| 7 |
+
"_type": "Value"
|
| 8 |
+
},
|
| 9 |
+
"embedding": {
|
| 10 |
+
"feature": {
|
| 11 |
+
"dtype": "float32",
|
| 12 |
+
"_type": "Value"
|
| 13 |
+
},
|
| 14 |
+
"_type": "List"
|
| 15 |
+
},
|
| 16 |
+
"label": {
|
| 17 |
+
"dtype": "int64",
|
| 18 |
+
"_type": "Value"
|
| 19 |
+
}
|
| 20 |
+
},
|
| 21 |
+
"homepage": "",
|
| 22 |
+
"license": ""
|
| 23 |
+
}
|
training_data_cleaned/nf/nf_smiles_with_embeddings/val/state.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_data_files": [
|
| 3 |
+
{
|
| 4 |
+
"filename": "data-00000-of-00001.arrow"
|
| 5 |
+
}
|
| 6 |
+
],
|
| 7 |
+
"_fingerprint": "51b64b0e80ee5ffd",
|
| 8 |
+
"_format_columns": null,
|
| 9 |
+
"_format_kwargs": {},
|
| 10 |
+
"_format_type": null,
|
| 11 |
+
"_output_all_columns": false,
|
| 12 |
+
"_split": null
|
| 13 |
+
}
|
training_data_cleaned/nf/nf_wt_with_embeddings/dataset_dict.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"splits": ["train", "val"]}
|
training_data_cleaned/nf/nf_wt_with_embeddings/train/data-00000-of-00001.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f8f13aa3f2a7dadafc529956ed192be52d9aa20e592ae9f99ee298f6f22748f
|
| 3 |
+
size 71732104
|
training_data_cleaned/nf/nf_wt_with_embeddings/train/dataset_info.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"citation": "",
|
| 3 |
+
"description": "",
|
| 4 |
+
"features": {
|
| 5 |
+
"sequence": {
|
| 6 |
+
"dtype": "string",
|
| 7 |
+
"_type": "Value"
|
| 8 |
+
},
|
| 9 |
+
"embedding": {
|
| 10 |
+
"feature": {
|
| 11 |
+
"dtype": "float32",
|
| 12 |
+
"_type": "Value"
|
| 13 |
+
},
|
| 14 |
+
"_type": "List"
|
| 15 |
+
},
|
| 16 |
+
"label": {
|
| 17 |
+
"dtype": "int64",
|
| 18 |
+
"_type": "Value"
|
| 19 |
+
}
|
| 20 |
+
},
|
| 21 |
+
"homepage": "",
|
| 22 |
+
"license": ""
|
| 23 |
+
}
|
training_data_cleaned/nf/nf_wt_with_embeddings/train/state.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_data_files": [
|
| 3 |
+
{
|
| 4 |
+
"filename": "data-00000-of-00001.arrow"
|
| 5 |
+
}
|
| 6 |
+
],
|
| 7 |
+
"_fingerprint": "7e9e61eb2e38bf25",
|
| 8 |
+
"_format_columns": null,
|
| 9 |
+
"_format_kwargs": {},
|
| 10 |
+
"_format_type": null,
|
| 11 |
+
"_output_all_columns": false,
|
| 12 |
+
"_split": null
|
| 13 |
+
}
|
training_data_cleaned/nf/nf_wt_with_embeddings/val/data-00000-of-00001.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:480c6294956397a18619267bc07d880e29e96532fe9a9618a052dec3969b46cc
|
| 3 |
+
size 17930608
|
training_data_cleaned/nf/nf_wt_with_embeddings/val/dataset_info.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"citation": "",
|
| 3 |
+
"description": "",
|
| 4 |
+
"features": {
|
| 5 |
+
"sequence": {
|
| 6 |
+
"dtype": "string",
|
| 7 |
+
"_type": "Value"
|
| 8 |
+
},
|
| 9 |
+
"embedding": {
|
| 10 |
+
"feature": {
|
| 11 |
+
"dtype": "float32",
|
| 12 |
+
"_type": "Value"
|
| 13 |
+
},
|
| 14 |
+
"_type": "List"
|
| 15 |
+
},
|
| 16 |
+
"label": {
|
| 17 |
+
"dtype": "int64",
|
| 18 |
+
"_type": "Value"
|
| 19 |
+
}
|
| 20 |
+
},
|
| 21 |
+
"homepage": "",
|
| 22 |
+
"license": ""
|
| 23 |
+
}
|
training_data_cleaned/nf/nf_wt_with_embeddings/val/state.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_data_files": [
|
| 3 |
+
{
|
| 4 |
+
"filename": "data-00000-of-00001.arrow"
|
| 5 |
+
}
|
| 6 |
+
],
|
| 7 |
+
"_fingerprint": "52fcbc4e0da87fa3",
|
| 8 |
+
"_format_columns": null,
|
| 9 |
+
"_format_kwargs": {},
|
| 10 |
+
"_format_type": null,
|
| 11 |
+
"_output_all_columns": false,
|
| 12 |
+
"_split": null
|
| 13 |
+
}
|
training_data_cleaned/permeability_caco2/caco2_meta_with_split.csv
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa8f0fb32da50e69eafd3e585d68c7876710951fc54c20dd85c2501745dbb38c
|
| 3 |
+
size 233334
|
training_data_cleaned/permeability_caco2/caco2_smiles_with_embeddings/dataset_dict.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"splits": ["train", "val"]}
|
training_data_cleaned/permeability_caco2/caco2_smiles_with_embeddings/train/data-00000-of-00001.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b1ee6d2739e733de4465bc3b3229614c02efd9397c10178b2aac1509a9878b68
|
| 3 |
+
size 1592344
|
training_data_cleaned/permeability_caco2/caco2_smiles_with_embeddings/train/dataset_info.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"citation": "",
|
| 3 |
+
"description": "",
|
| 4 |
+
"features": {
|
| 5 |
+
"sequence": {
|
| 6 |
+
"dtype": "string",
|
| 7 |
+
"_type": "Value"
|
| 8 |
+
},
|
| 9 |
+
"embedding": {
|
| 10 |
+
"feature": {
|
| 11 |
+
"dtype": "float32",
|
| 12 |
+
"_type": "Value"
|
| 13 |
+
},
|
| 14 |
+
"_type": "List"
|
| 15 |
+
},
|
| 16 |
+
"label": {
|
| 17 |
+
"dtype": "float64",
|
| 18 |
+
"_type": "Value"
|
| 19 |
+
}
|
| 20 |
+
},
|
| 21 |
+
"homepage": "",
|
| 22 |
+
"license": ""
|
| 23 |
+
}
|
training_data_cleaned/permeability_caco2/caco2_smiles_with_embeddings/train/state.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_data_files": [
|
| 3 |
+
{
|
| 4 |
+
"filename": "data-00000-of-00001.arrow"
|
| 5 |
+
}
|
| 6 |
+
],
|
| 7 |
+
"_fingerprint": "b67b8e734ab59271",
|
| 8 |
+
"_format_columns": null,
|
| 9 |
+
"_format_kwargs": {},
|
| 10 |
+
"_format_type": null,
|
| 11 |
+
"_output_all_columns": false,
|
| 12 |
+
"_split": null
|
| 13 |
+
}
|
training_data_cleaned/permeability_caco2/caco2_smiles_with_embeddings/val/data-00000-of-00001.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e534dfe6744d9fbb89ecea63e54aeac9fcd319dd018f0c7939dfad856eb9599d
|
| 3 |
+
size 392528
|
training_data_cleaned/permeability_caco2/caco2_smiles_with_embeddings/val/dataset_info.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"citation": "",
|
| 3 |
+
"description": "",
|
| 4 |
+
"features": {
|
| 5 |
+
"sequence": {
|
| 6 |
+
"dtype": "string",
|
| 7 |
+
"_type": "Value"
|
| 8 |
+
},
|
| 9 |
+
"embedding": {
|
| 10 |
+
"feature": {
|
| 11 |
+
"dtype": "float32",
|
| 12 |
+
"_type": "Value"
|
| 13 |
+
},
|
| 14 |
+
"_type": "List"
|
| 15 |
+
},
|
| 16 |
+
"label": {
|
| 17 |
+
"dtype": "float64",
|
| 18 |
+
"_type": "Value"
|
| 19 |
+
}
|
| 20 |
+
},
|
| 21 |
+
"homepage": "",
|
| 22 |
+
"license": ""
|
| 23 |
+
}
|
training_data_cleaned/permeability_caco2/caco2_smiles_with_embeddings/val/state.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_data_files": [
|
| 3 |
+
{
|
| 4 |
+
"filename": "data-00000-of-00001.arrow"
|
| 5 |
+
}
|
| 6 |
+
],
|
| 7 |
+
"_fingerprint": "c5abdd50b2a6a84c",
|
| 8 |
+
"_format_columns": null,
|
| 9 |
+
"_format_kwargs": {},
|
| 10 |
+
"_format_type": null,
|
| 11 |
+
"_output_all_columns": false,
|
| 12 |
+
"_split": null
|
| 13 |
+
}
|
training_data_cleaned/permeability_pampa/pampa_meta_with_split.csv
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d04d3767f03a4846003f404db6d03f8392ef9ad73830546064769beded3cfa80
|
| 3 |
+
size 2180806
|
training_data_cleaned/permeability_pampa/pampa_smiles_with_embeddings/dataset_dict.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"splits": ["train", "val"]}
|
training_data_cleaned/permeability_pampa/pampa_smiles_with_embeddings/train/data-00000-of-00001.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac8d9409bc3e1f8ea60bf13881e59b431b494093d8cb211ecad75d9940ee9957
|
| 3 |
+
size 16838472
|
training_data_cleaned/permeability_pampa/pampa_smiles_with_embeddings/train/dataset_info.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"citation": "",
|
| 3 |
+
"description": "",
|
| 4 |
+
"features": {
|
| 5 |
+
"sequence": {
|
| 6 |
+
"dtype": "string",
|
| 7 |
+
"_type": "Value"
|
| 8 |
+
},
|
| 9 |
+
"embedding": {
|
| 10 |
+
"feature": {
|
| 11 |
+
"dtype": "float32",
|
| 12 |
+
"_type": "Value"
|
| 13 |
+
},
|
| 14 |
+
"_type": "List"
|
| 15 |
+
},
|
| 16 |
+
"label": {
|
| 17 |
+
"dtype": "float64",
|
| 18 |
+
"_type": "Value"
|
| 19 |
+
}
|
| 20 |
+
},
|
| 21 |
+
"homepage": "",
|
| 22 |
+
"license": ""
|
| 23 |
+
}
|
training_data_cleaned/permeability_pampa/pampa_smiles_with_embeddings/train/state.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_data_files": [
|
| 3 |
+
{
|
| 4 |
+
"filename": "data-00000-of-00001.arrow"
|
| 5 |
+
}
|
| 6 |
+
],
|
| 7 |
+
"_fingerprint": "b3fc67db512e6dff",
|
| 8 |
+
"_format_columns": null,
|
| 9 |
+
"_format_kwargs": {},
|
| 10 |
+
"_format_type": null,
|
| 11 |
+
"_output_all_columns": false,
|
| 12 |
+
"_split": null
|
| 13 |
+
}
|
training_data_cleaned/permeability_pampa/pampa_smiles_with_embeddings/val/data-00000-of-00001.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93ce6ce347c39cc97353985efbd9d57a18fa61c0cec0c258293008d06d04a1fe
|
| 3 |
+
size 5412880
|