PROTAC
drug-discovery
xgboost
cheminformatics
ribesstefano commited on
Commit
310450e
·
verified ·
1 Parent(s): 5fd1493

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. dmax_best_arch_ensemble/config-model=xgboost_dmax_protac-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-task=dmax-group=scaffold.yaml +18 -0
  2. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=0_hparams.yaml +60 -0
  3. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=0_state.pt +3 -0
  4. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=10_hparams.yaml +60 -0
  5. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=10_state.pt +3 -0
  6. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=11_hparams.yaml +60 -0
  7. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=11_state.pt +3 -0
  8. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=12_hparams.yaml +60 -0
  9. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=12_state.pt +3 -0
  10. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=13_hparams.yaml +60 -0
  11. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=13_state.pt +3 -0
  12. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=14_hparams.yaml +60 -0
  13. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=14_state.pt +3 -0
  14. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=15_hparams.yaml +60 -0
  15. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=15_state.pt +3 -0
  16. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=16_hparams.yaml +60 -0
  17. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=16_state.pt +3 -0
  18. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=17_hparams.yaml +60 -0
  19. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=17_state.pt +3 -0
  20. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=18_hparams.yaml +60 -0
  21. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=18_state.pt +3 -0
  22. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=19_hparams.yaml +60 -0
  23. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=19_state.pt +3 -0
  24. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=1_hparams.yaml +60 -0
  25. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=1_state.pt +3 -0
  26. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=20_hparams.yaml +60 -0
  27. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=20_state.pt +3 -0
  28. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=21_hparams.yaml +60 -0
  29. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=21_state.pt +3 -0
  30. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=22_hparams.yaml +60 -0
  31. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=22_state.pt +3 -0
  32. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=23_hparams.yaml +60 -0
  33. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=23_state.pt +3 -0
  34. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=24_hparams.yaml +60 -0
  35. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=24_state.pt +3 -0
  36. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=2_hparams.yaml +60 -0
  37. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=2_state.pt +3 -0
  38. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=3_hparams.yaml +60 -0
  39. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=3_state.pt +3 -0
  40. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=4_hparams.yaml +60 -0
  41. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=4_state.pt +3 -0
  42. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=5_hparams.yaml +60 -0
  43. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=5_state.pt +3 -0
  44. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=6_hparams.yaml +60 -0
  45. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=6_state.pt +3 -0
  46. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=7_hparams.yaml +60 -0
  47. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=7_state.pt +3 -0
  48. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=8_hparams.yaml +60 -0
  49. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=8_state.pt +3 -0
  50. dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=9_hparams.yaml +60 -0
dmax_best_arch_ensemble/config-model=xgboost_dmax_protac-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-task=dmax-group=scaffold.yaml ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ model_config:
2
+ objective: reg:squarederror
3
+ base_score: 0.0
4
+ tree_method: hist
5
+ n_estimators: 2000
6
+ n_jobs: 8
7
+ seed: 65
8
+ learning_rate: 0.015930522616241012
9
+ max_depth: 7
10
+ min_child_weight: 1
11
+ subsample: 0.9819459112971965
12
+ colsample_bytree: 0.9162213204002109
13
+ reg_alpha: 0.0070689749506246055
14
+ reg_lambda: 0.005337032762603957
15
+ gamma: 0.00541524411940254
16
+ training_config:
17
+ num_boost_round: 2000
18
+ early_stopping_rounds: 30
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=0_hparams.yaml ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ smiles_col: SMILES
2
+ ligase_col: Ligase_Name
3
+ ligase_sequence_col: Ligase_Sequence
4
+ poi_col: POI_Name
5
+ poi_sequence_col: POI_Sequence
6
+ cell_line_col: Cell_Line_ID
7
+ assay_type_col: Assay
8
+ treatment_time_col: Assay_Time
9
+ treatment_time_dmax_col: Assay_Time
10
+ treatment_time_dc50_col: Assay_Time
11
+ treatment_time_ic50_col: Treatment Time (h) (Cellular activities, IC50)
12
+ labels:
13
+ - Dmax
14
+ normalize_labels: true
15
+ standardize_labels: false
16
+ impute_labels: true
17
+ fp_size: 512
18
+ radius: 16
19
+ use_fingerprints: false
20
+ use_descriptors: true
21
+ use_relevant_descriptors: false
22
+ selected_descriptors: null
23
+ use_poi_sequence_embedding: true
24
+ use_poi_name_embedding: false
25
+ use_ligase_name_embedding: true
26
+ use_poi_precomputed_embedding: false
27
+ use_ligase_precomputed_embedding: false
28
+ poi_embeddings_file: null
29
+ poi_embeddings_format: npz
30
+ poi_embeddings_per_residue: true
31
+ poi_residue_pooling: sum
32
+ poi_embeddings_id_type: sequence
33
+ ligase_embeddings_file: null
34
+ ligase_embeddings_format: npz
35
+ ligase_embeddings_per_residue: true
36
+ ligase_residue_pooling: sum
37
+ ligase_embeddings_id_type: sequence
38
+ use_poi_pca: false
39
+ poi_pca_n_components: null
40
+ use_ligase_pca: false
41
+ ligase_pca_n_components: null
42
+ use_cell_description_embedding: true
43
+ use_cell_name_embedding: false
44
+ use_tokenizer: false
45
+ tokenizer_name: google-bert/bert-base-cased
46
+ max_length: 512
47
+ prompt_template: null
48
+ label_task_col: Value_Type
49
+ degrader_type_col: null
50
+ default_degrader_type: PROTAC
51
+ include_prompt: false
52
+ is_bert_multitask: false
53
+ use_assay_type_encoding: true
54
+ use_treatment_time: true
55
+ batch_size: 32
56
+ num_workers: 0
57
+ num_proc: 1
58
+ verbose: 0
59
+ sort_features: true
60
+ categorical_encoding: onehot
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=0_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d856d52331bdf6b3e6678d3b6b9bf593ca6834b752acd05ca600b8cde81510cb
3
+ size 169169
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=10_hparams.yaml ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ smiles_col: SMILES
2
+ ligase_col: Ligase_Name
3
+ ligase_sequence_col: Ligase_Sequence
4
+ poi_col: POI_Name
5
+ poi_sequence_col: POI_Sequence
6
+ cell_line_col: Cell_Line_ID
7
+ assay_type_col: Assay
8
+ treatment_time_col: Assay_Time
9
+ treatment_time_dmax_col: Assay_Time
10
+ treatment_time_dc50_col: Assay_Time
11
+ treatment_time_ic50_col: Treatment Time (h) (Cellular activities, IC50)
12
+ labels:
13
+ - Dmax
14
+ normalize_labels: true
15
+ standardize_labels: false
16
+ impute_labels: true
17
+ fp_size: 512
18
+ radius: 16
19
+ use_fingerprints: false
20
+ use_descriptors: true
21
+ use_relevant_descriptors: false
22
+ selected_descriptors: null
23
+ use_poi_sequence_embedding: true
24
+ use_poi_name_embedding: false
25
+ use_ligase_name_embedding: true
26
+ use_poi_precomputed_embedding: false
27
+ use_ligase_precomputed_embedding: false
28
+ poi_embeddings_file: null
29
+ poi_embeddings_format: npz
30
+ poi_embeddings_per_residue: true
31
+ poi_residue_pooling: sum
32
+ poi_embeddings_id_type: sequence
33
+ ligase_embeddings_file: null
34
+ ligase_embeddings_format: npz
35
+ ligase_embeddings_per_residue: true
36
+ ligase_residue_pooling: sum
37
+ ligase_embeddings_id_type: sequence
38
+ use_poi_pca: false
39
+ poi_pca_n_components: null
40
+ use_ligase_pca: false
41
+ ligase_pca_n_components: null
42
+ use_cell_description_embedding: true
43
+ use_cell_name_embedding: false
44
+ use_tokenizer: false
45
+ tokenizer_name: google-bert/bert-base-cased
46
+ max_length: 512
47
+ prompt_template: null
48
+ label_task_col: Value_Type
49
+ degrader_type_col: null
50
+ default_degrader_type: PROTAC
51
+ include_prompt: false
52
+ is_bert_multitask: false
53
+ use_assay_type_encoding: true
54
+ use_treatment_time: true
55
+ batch_size: 32
56
+ num_workers: 0
57
+ num_proc: 1
58
+ verbose: 0
59
+ sort_features: true
60
+ categorical_encoding: onehot
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=10_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be6ba69794e1812b38e1b29a1916ad017f655d2701995ef2bbb3c04c52614954
3
+ size 169239
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=11_hparams.yaml ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ smiles_col: SMILES
2
+ ligase_col: Ligase_Name
3
+ ligase_sequence_col: Ligase_Sequence
4
+ poi_col: POI_Name
5
+ poi_sequence_col: POI_Sequence
6
+ cell_line_col: Cell_Line_ID
7
+ assay_type_col: Assay
8
+ treatment_time_col: Assay_Time
9
+ treatment_time_dmax_col: Assay_Time
10
+ treatment_time_dc50_col: Assay_Time
11
+ treatment_time_ic50_col: Treatment Time (h) (Cellular activities, IC50)
12
+ labels:
13
+ - Dmax
14
+ normalize_labels: true
15
+ standardize_labels: false
16
+ impute_labels: true
17
+ fp_size: 512
18
+ radius: 16
19
+ use_fingerprints: false
20
+ use_descriptors: true
21
+ use_relevant_descriptors: false
22
+ selected_descriptors: null
23
+ use_poi_sequence_embedding: true
24
+ use_poi_name_embedding: false
25
+ use_ligase_name_embedding: true
26
+ use_poi_precomputed_embedding: false
27
+ use_ligase_precomputed_embedding: false
28
+ poi_embeddings_file: null
29
+ poi_embeddings_format: npz
30
+ poi_embeddings_per_residue: true
31
+ poi_residue_pooling: sum
32
+ poi_embeddings_id_type: sequence
33
+ ligase_embeddings_file: null
34
+ ligase_embeddings_format: npz
35
+ ligase_embeddings_per_residue: true
36
+ ligase_residue_pooling: sum
37
+ ligase_embeddings_id_type: sequence
38
+ use_poi_pca: false
39
+ poi_pca_n_components: null
40
+ use_ligase_pca: false
41
+ ligase_pca_n_components: null
42
+ use_cell_description_embedding: true
43
+ use_cell_name_embedding: false
44
+ use_tokenizer: false
45
+ tokenizer_name: google-bert/bert-base-cased
46
+ max_length: 512
47
+ prompt_template: null
48
+ label_task_col: Value_Type
49
+ degrader_type_col: null
50
+ default_degrader_type: PROTAC
51
+ include_prompt: false
52
+ is_bert_multitask: false
53
+ use_assay_type_encoding: true
54
+ use_treatment_time: true
55
+ batch_size: 32
56
+ num_workers: 0
57
+ num_proc: 1
58
+ verbose: 0
59
+ sort_features: true
60
+ categorical_encoding: onehot
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=11_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c66e7ab098d34bb6100073f39c3fc025cf45b0a98352e807746ecc5f26468c8
3
+ size 169239
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=12_hparams.yaml ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ smiles_col: SMILES
2
+ ligase_col: Ligase_Name
3
+ ligase_sequence_col: Ligase_Sequence
4
+ poi_col: POI_Name
5
+ poi_sequence_col: POI_Sequence
6
+ cell_line_col: Cell_Line_ID
7
+ assay_type_col: Assay
8
+ treatment_time_col: Assay_Time
9
+ treatment_time_dmax_col: Assay_Time
10
+ treatment_time_dc50_col: Assay_Time
11
+ treatment_time_ic50_col: Treatment Time (h) (Cellular activities, IC50)
12
+ labels:
13
+ - Dmax
14
+ normalize_labels: true
15
+ standardize_labels: false
16
+ impute_labels: true
17
+ fp_size: 512
18
+ radius: 16
19
+ use_fingerprints: false
20
+ use_descriptors: true
21
+ use_relevant_descriptors: false
22
+ selected_descriptors: null
23
+ use_poi_sequence_embedding: true
24
+ use_poi_name_embedding: false
25
+ use_ligase_name_embedding: true
26
+ use_poi_precomputed_embedding: false
27
+ use_ligase_precomputed_embedding: false
28
+ poi_embeddings_file: null
29
+ poi_embeddings_format: npz
30
+ poi_embeddings_per_residue: true
31
+ poi_residue_pooling: sum
32
+ poi_embeddings_id_type: sequence
33
+ ligase_embeddings_file: null
34
+ ligase_embeddings_format: npz
35
+ ligase_embeddings_per_residue: true
36
+ ligase_residue_pooling: sum
37
+ ligase_embeddings_id_type: sequence
38
+ use_poi_pca: false
39
+ poi_pca_n_components: null
40
+ use_ligase_pca: false
41
+ ligase_pca_n_components: null
42
+ use_cell_description_embedding: true
43
+ use_cell_name_embedding: false
44
+ use_tokenizer: false
45
+ tokenizer_name: google-bert/bert-base-cased
46
+ max_length: 512
47
+ prompt_template: null
48
+ label_task_col: Value_Type
49
+ degrader_type_col: null
50
+ default_degrader_type: PROTAC
51
+ include_prompt: false
52
+ is_bert_multitask: false
53
+ use_assay_type_encoding: true
54
+ use_treatment_time: true
55
+ batch_size: 32
56
+ num_workers: 0
57
+ num_proc: 1
58
+ verbose: 0
59
+ sort_features: true
60
+ categorical_encoding: onehot
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=12_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a8ffea24fcace78effc9e6a6811253203b395e3ed032bfd9f05009122da35b9
3
+ size 169239
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=13_hparams.yaml ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ smiles_col: SMILES
2
+ ligase_col: Ligase_Name
3
+ ligase_sequence_col: Ligase_Sequence
4
+ poi_col: POI_Name
5
+ poi_sequence_col: POI_Sequence
6
+ cell_line_col: Cell_Line_ID
7
+ assay_type_col: Assay
8
+ treatment_time_col: Assay_Time
9
+ treatment_time_dmax_col: Assay_Time
10
+ treatment_time_dc50_col: Assay_Time
11
+ treatment_time_ic50_col: Treatment Time (h) (Cellular activities, IC50)
12
+ labels:
13
+ - Dmax
14
+ normalize_labels: true
15
+ standardize_labels: false
16
+ impute_labels: true
17
+ fp_size: 512
18
+ radius: 16
19
+ use_fingerprints: false
20
+ use_descriptors: true
21
+ use_relevant_descriptors: false
22
+ selected_descriptors: null
23
+ use_poi_sequence_embedding: true
24
+ use_poi_name_embedding: false
25
+ use_ligase_name_embedding: true
26
+ use_poi_precomputed_embedding: false
27
+ use_ligase_precomputed_embedding: false
28
+ poi_embeddings_file: null
29
+ poi_embeddings_format: npz
30
+ poi_embeddings_per_residue: true
31
+ poi_residue_pooling: sum
32
+ poi_embeddings_id_type: sequence
33
+ ligase_embeddings_file: null
34
+ ligase_embeddings_format: npz
35
+ ligase_embeddings_per_residue: true
36
+ ligase_residue_pooling: sum
37
+ ligase_embeddings_id_type: sequence
38
+ use_poi_pca: false
39
+ poi_pca_n_components: null
40
+ use_ligase_pca: false
41
+ ligase_pca_n_components: null
42
+ use_cell_description_embedding: true
43
+ use_cell_name_embedding: false
44
+ use_tokenizer: false
45
+ tokenizer_name: google-bert/bert-base-cased
46
+ max_length: 512
47
+ prompt_template: null
48
+ label_task_col: Value_Type
49
+ degrader_type_col: null
50
+ default_degrader_type: PROTAC
51
+ include_prompt: false
52
+ is_bert_multitask: false
53
+ use_assay_type_encoding: true
54
+ use_treatment_time: true
55
+ batch_size: 32
56
+ num_workers: 0
57
+ num_proc: 1
58
+ verbose: 0
59
+ sort_features: true
60
+ categorical_encoding: onehot
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=13_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f965bb03e287d1d7bd1cce59e636dbd48e0a22642cb01981e223a03310e8a04
3
+ size 169239
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=14_hparams.yaml ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ smiles_col: SMILES
2
+ ligase_col: Ligase_Name
3
+ ligase_sequence_col: Ligase_Sequence
4
+ poi_col: POI_Name
5
+ poi_sequence_col: POI_Sequence
6
+ cell_line_col: Cell_Line_ID
7
+ assay_type_col: Assay
8
+ treatment_time_col: Assay_Time
9
+ treatment_time_dmax_col: Assay_Time
10
+ treatment_time_dc50_col: Assay_Time
11
+ treatment_time_ic50_col: Treatment Time (h) (Cellular activities, IC50)
12
+ labels:
13
+ - Dmax
14
+ normalize_labels: true
15
+ standardize_labels: false
16
+ impute_labels: true
17
+ fp_size: 512
18
+ radius: 16
19
+ use_fingerprints: false
20
+ use_descriptors: true
21
+ use_relevant_descriptors: false
22
+ selected_descriptors: null
23
+ use_poi_sequence_embedding: true
24
+ use_poi_name_embedding: false
25
+ use_ligase_name_embedding: true
26
+ use_poi_precomputed_embedding: false
27
+ use_ligase_precomputed_embedding: false
28
+ poi_embeddings_file: null
29
+ poi_embeddings_format: npz
30
+ poi_embeddings_per_residue: true
31
+ poi_residue_pooling: sum
32
+ poi_embeddings_id_type: sequence
33
+ ligase_embeddings_file: null
34
+ ligase_embeddings_format: npz
35
+ ligase_embeddings_per_residue: true
36
+ ligase_residue_pooling: sum
37
+ ligase_embeddings_id_type: sequence
38
+ use_poi_pca: false
39
+ poi_pca_n_components: null
40
+ use_ligase_pca: false
41
+ ligase_pca_n_components: null
42
+ use_cell_description_embedding: true
43
+ use_cell_name_embedding: false
44
+ use_tokenizer: false
45
+ tokenizer_name: google-bert/bert-base-cased
46
+ max_length: 512
47
+ prompt_template: null
48
+ label_task_col: Value_Type
49
+ degrader_type_col: null
50
+ default_degrader_type: PROTAC
51
+ include_prompt: false
52
+ is_bert_multitask: false
53
+ use_assay_type_encoding: true
54
+ use_treatment_time: true
55
+ batch_size: 32
56
+ num_workers: 0
57
+ num_proc: 1
58
+ verbose: 0
59
+ sort_features: true
60
+ categorical_encoding: onehot
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=14_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbf8bac8d41725656bf3a5fa1044eadda6631a683070e8b8f5356ea8cec6b354
3
+ size 169175
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=15_hparams.yaml ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ smiles_col: SMILES
2
+ ligase_col: Ligase_Name
3
+ ligase_sequence_col: Ligase_Sequence
4
+ poi_col: POI_Name
5
+ poi_sequence_col: POI_Sequence
6
+ cell_line_col: Cell_Line_ID
7
+ assay_type_col: Assay
8
+ treatment_time_col: Assay_Time
9
+ treatment_time_dmax_col: Assay_Time
10
+ treatment_time_dc50_col: Assay_Time
11
+ treatment_time_ic50_col: Treatment Time (h) (Cellular activities, IC50)
12
+ labels:
13
+ - Dmax
14
+ normalize_labels: true
15
+ standardize_labels: false
16
+ impute_labels: true
17
+ fp_size: 512
18
+ radius: 16
19
+ use_fingerprints: false
20
+ use_descriptors: true
21
+ use_relevant_descriptors: false
22
+ selected_descriptors: null
23
+ use_poi_sequence_embedding: true
24
+ use_poi_name_embedding: false
25
+ use_ligase_name_embedding: true
26
+ use_poi_precomputed_embedding: false
27
+ use_ligase_precomputed_embedding: false
28
+ poi_embeddings_file: null
29
+ poi_embeddings_format: npz
30
+ poi_embeddings_per_residue: true
31
+ poi_residue_pooling: sum
32
+ poi_embeddings_id_type: sequence
33
+ ligase_embeddings_file: null
34
+ ligase_embeddings_format: npz
35
+ ligase_embeddings_per_residue: true
36
+ ligase_residue_pooling: sum
37
+ ligase_embeddings_id_type: sequence
38
+ use_poi_pca: false
39
+ poi_pca_n_components: null
40
+ use_ligase_pca: false
41
+ ligase_pca_n_components: null
42
+ use_cell_description_embedding: true
43
+ use_cell_name_embedding: false
44
+ use_tokenizer: false
45
+ tokenizer_name: google-bert/bert-base-cased
46
+ max_length: 512
47
+ prompt_template: null
48
+ label_task_col: Value_Type
49
+ degrader_type_col: null
50
+ default_degrader_type: PROTAC
51
+ include_prompt: false
52
+ is_bert_multitask: false
53
+ use_assay_type_encoding: true
54
+ use_treatment_time: true
55
+ batch_size: 32
56
+ num_workers: 0
57
+ num_proc: 1
58
+ verbose: 0
59
+ sort_features: true
60
+ categorical_encoding: onehot
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=15_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a17a84b212e23f13cd82f7dc7769f22671274df446f8345dce523de4ec2e548
3
+ size 169239
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=16_hparams.yaml ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ smiles_col: SMILES
2
+ ligase_col: Ligase_Name
3
+ ligase_sequence_col: Ligase_Sequence
4
+ poi_col: POI_Name
5
+ poi_sequence_col: POI_Sequence
6
+ cell_line_col: Cell_Line_ID
7
+ assay_type_col: Assay
8
+ treatment_time_col: Assay_Time
9
+ treatment_time_dmax_col: Assay_Time
10
+ treatment_time_dc50_col: Assay_Time
11
+ treatment_time_ic50_col: Treatment Time (h) (Cellular activities, IC50)
12
+ labels:
13
+ - Dmax
14
+ normalize_labels: true
15
+ standardize_labels: false
16
+ impute_labels: true
17
+ fp_size: 512
18
+ radius: 16
19
+ use_fingerprints: false
20
+ use_descriptors: true
21
+ use_relevant_descriptors: false
22
+ selected_descriptors: null
23
+ use_poi_sequence_embedding: true
24
+ use_poi_name_embedding: false
25
+ use_ligase_name_embedding: true
26
+ use_poi_precomputed_embedding: false
27
+ use_ligase_precomputed_embedding: false
28
+ poi_embeddings_file: null
29
+ poi_embeddings_format: npz
30
+ poi_embeddings_per_residue: true
31
+ poi_residue_pooling: sum
32
+ poi_embeddings_id_type: sequence
33
+ ligase_embeddings_file: null
34
+ ligase_embeddings_format: npz
35
+ ligase_embeddings_per_residue: true
36
+ ligase_residue_pooling: sum
37
+ ligase_embeddings_id_type: sequence
38
+ use_poi_pca: false
39
+ poi_pca_n_components: null
40
+ use_ligase_pca: false
41
+ ligase_pca_n_components: null
42
+ use_cell_description_embedding: true
43
+ use_cell_name_embedding: false
44
+ use_tokenizer: false
45
+ tokenizer_name: google-bert/bert-base-cased
46
+ max_length: 512
47
+ prompt_template: null
48
+ label_task_col: Value_Type
49
+ degrader_type_col: null
50
+ default_degrader_type: PROTAC
51
+ include_prompt: false
52
+ is_bert_multitask: false
53
+ use_assay_type_encoding: true
54
+ use_treatment_time: true
55
+ batch_size: 32
56
+ num_workers: 0
57
+ num_proc: 1
58
+ verbose: 0
59
+ sort_features: true
60
+ categorical_encoding: onehot
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=16_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4f0d31bc875d15f676069c5f4e1f0ef8435e62e20bee0cdefe2d09a1bf19d21
3
+ size 169175
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=17_hparams.yaml ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ smiles_col: SMILES
2
+ ligase_col: Ligase_Name
3
+ ligase_sequence_col: Ligase_Sequence
4
+ poi_col: POI_Name
5
+ poi_sequence_col: POI_Sequence
6
+ cell_line_col: Cell_Line_ID
7
+ assay_type_col: Assay
8
+ treatment_time_col: Assay_Time
9
+ treatment_time_dmax_col: Assay_Time
10
+ treatment_time_dc50_col: Assay_Time
11
+ treatment_time_ic50_col: Treatment Time (h) (Cellular activities, IC50)
12
+ labels:
13
+ - Dmax
14
+ normalize_labels: true
15
+ standardize_labels: false
16
+ impute_labels: true
17
+ fp_size: 512
18
+ radius: 16
19
+ use_fingerprints: false
20
+ use_descriptors: true
21
+ use_relevant_descriptors: false
22
+ selected_descriptors: null
23
+ use_poi_sequence_embedding: true
24
+ use_poi_name_embedding: false
25
+ use_ligase_name_embedding: true
26
+ use_poi_precomputed_embedding: false
27
+ use_ligase_precomputed_embedding: false
28
+ poi_embeddings_file: null
29
+ poi_embeddings_format: npz
30
+ poi_embeddings_per_residue: true
31
+ poi_residue_pooling: sum
32
+ poi_embeddings_id_type: sequence
33
+ ligase_embeddings_file: null
34
+ ligase_embeddings_format: npz
35
+ ligase_embeddings_per_residue: true
36
+ ligase_residue_pooling: sum
37
+ ligase_embeddings_id_type: sequence
38
+ use_poi_pca: false
39
+ poi_pca_n_components: null
40
+ use_ligase_pca: false
41
+ ligase_pca_n_components: null
42
+ use_cell_description_embedding: true
43
+ use_cell_name_embedding: false
44
+ use_tokenizer: false
45
+ tokenizer_name: google-bert/bert-base-cased
46
+ max_length: 512
47
+ prompt_template: null
48
+ label_task_col: Value_Type
49
+ degrader_type_col: null
50
+ default_degrader_type: PROTAC
51
+ include_prompt: false
52
+ is_bert_multitask: false
53
+ use_assay_type_encoding: true
54
+ use_treatment_time: true
55
+ batch_size: 32
56
+ num_workers: 0
57
+ num_proc: 1
58
+ verbose: 0
59
+ sort_features: true
60
+ categorical_encoding: onehot
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=17_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f77429d44432534b39a8dfdc2fbd8db93e2a3d6189cb94eca8bf1284defa23b
3
+ size 169303
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=18_hparams.yaml ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ smiles_col: SMILES
2
+ ligase_col: Ligase_Name
3
+ ligase_sequence_col: Ligase_Sequence
4
+ poi_col: POI_Name
5
+ poi_sequence_col: POI_Sequence
6
+ cell_line_col: Cell_Line_ID
7
+ assay_type_col: Assay
8
+ treatment_time_col: Assay_Time
9
+ treatment_time_dmax_col: Assay_Time
10
+ treatment_time_dc50_col: Assay_Time
11
+ treatment_time_ic50_col: Treatment Time (h) (Cellular activities, IC50)
12
+ labels:
13
+ - Dmax
14
+ normalize_labels: true
15
+ standardize_labels: false
16
+ impute_labels: true
17
+ fp_size: 512
18
+ radius: 16
19
+ use_fingerprints: false
20
+ use_descriptors: true
21
+ use_relevant_descriptors: false
22
+ selected_descriptors: null
23
+ use_poi_sequence_embedding: true
24
+ use_poi_name_embedding: false
25
+ use_ligase_name_embedding: true
26
+ use_poi_precomputed_embedding: false
27
+ use_ligase_precomputed_embedding: false
28
+ poi_embeddings_file: null
29
+ poi_embeddings_format: npz
30
+ poi_embeddings_per_residue: true
31
+ poi_residue_pooling: sum
32
+ poi_embeddings_id_type: sequence
33
+ ligase_embeddings_file: null
34
+ ligase_embeddings_format: npz
35
+ ligase_embeddings_per_residue: true
36
+ ligase_residue_pooling: sum
37
+ ligase_embeddings_id_type: sequence
38
+ use_poi_pca: false
39
+ poi_pca_n_components: null
40
+ use_ligase_pca: false
41
+ ligase_pca_n_components: null
42
+ use_cell_description_embedding: true
43
+ use_cell_name_embedding: false
44
+ use_tokenizer: false
45
+ tokenizer_name: google-bert/bert-base-cased
46
+ max_length: 512
47
+ prompt_template: null
48
+ label_task_col: Value_Type
49
+ degrader_type_col: null
50
+ default_degrader_type: PROTAC
51
+ include_prompt: false
52
+ is_bert_multitask: false
53
+ use_assay_type_encoding: true
54
+ use_treatment_time: true
55
+ batch_size: 32
56
+ num_workers: 0
57
+ num_proc: 1
58
+ verbose: 0
59
+ sort_features: true
60
+ categorical_encoding: onehot
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=18_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9ffbdf09557d6833237c87e7055e736e614ef9f9ae16317721dd8ef8a419237
3
+ size 169303
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=19_hparams.yaml ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ smiles_col: SMILES
2
+ ligase_col: Ligase_Name
3
+ ligase_sequence_col: Ligase_Sequence
4
+ poi_col: POI_Name
5
+ poi_sequence_col: POI_Sequence
6
+ cell_line_col: Cell_Line_ID
7
+ assay_type_col: Assay
8
+ treatment_time_col: Assay_Time
9
+ treatment_time_dmax_col: Assay_Time
10
+ treatment_time_dc50_col: Assay_Time
11
+ treatment_time_ic50_col: Treatment Time (h) (Cellular activities, IC50)
12
+ labels:
13
+ - Dmax
14
+ normalize_labels: true
15
+ standardize_labels: false
16
+ impute_labels: true
17
+ fp_size: 512
18
+ radius: 16
19
+ use_fingerprints: false
20
+ use_descriptors: true
21
+ use_relevant_descriptors: false
22
+ selected_descriptors: null
23
+ use_poi_sequence_embedding: true
24
+ use_poi_name_embedding: false
25
+ use_ligase_name_embedding: true
26
+ use_poi_precomputed_embedding: false
27
+ use_ligase_precomputed_embedding: false
28
+ poi_embeddings_file: null
29
+ poi_embeddings_format: npz
30
+ poi_embeddings_per_residue: true
31
+ poi_residue_pooling: sum
32
+ poi_embeddings_id_type: sequence
33
+ ligase_embeddings_file: null
34
+ ligase_embeddings_format: npz
35
+ ligase_embeddings_per_residue: true
36
+ ligase_residue_pooling: sum
37
+ ligase_embeddings_id_type: sequence
38
+ use_poi_pca: false
39
+ poi_pca_n_components: null
40
+ use_ligase_pca: false
41
+ ligase_pca_n_components: null
42
+ use_cell_description_embedding: true
43
+ use_cell_name_embedding: false
44
+ use_tokenizer: false
45
+ tokenizer_name: google-bert/bert-base-cased
46
+ max_length: 512
47
+ prompt_template: null
48
+ label_task_col: Value_Type
49
+ degrader_type_col: null
50
+ default_degrader_type: PROTAC
51
+ include_prompt: false
52
+ is_bert_multitask: false
53
+ use_assay_type_encoding: true
54
+ use_treatment_time: true
55
+ batch_size: 32
56
+ num_workers: 0
57
+ num_proc: 1
58
+ verbose: 0
59
+ sort_features: true
60
+ categorical_encoding: onehot
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=19_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48e2cacb9462112811c5cde0dd13fdee56682a97dbc253ee33d2ef09de981fe3
3
+ size 169303
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=1_hparams.yaml ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ smiles_col: SMILES
2
+ ligase_col: Ligase_Name
3
+ ligase_sequence_col: Ligase_Sequence
4
+ poi_col: POI_Name
5
+ poi_sequence_col: POI_Sequence
6
+ cell_line_col: Cell_Line_ID
7
+ assay_type_col: Assay
8
+ treatment_time_col: Assay_Time
9
+ treatment_time_dmax_col: Assay_Time
10
+ treatment_time_dc50_col: Assay_Time
11
+ treatment_time_ic50_col: Treatment Time (h) (Cellular activities, IC50)
12
+ labels:
13
+ - Dmax
14
+ normalize_labels: true
15
+ standardize_labels: false
16
+ impute_labels: true
17
+ fp_size: 512
18
+ radius: 16
19
+ use_fingerprints: false
20
+ use_descriptors: true
21
+ use_relevant_descriptors: false
22
+ selected_descriptors: null
23
+ use_poi_sequence_embedding: true
24
+ use_poi_name_embedding: false
25
+ use_ligase_name_embedding: true
26
+ use_poi_precomputed_embedding: false
27
+ use_ligase_precomputed_embedding: false
28
+ poi_embeddings_file: null
29
+ poi_embeddings_format: npz
30
+ poi_embeddings_per_residue: true
31
+ poi_residue_pooling: sum
32
+ poi_embeddings_id_type: sequence
33
+ ligase_embeddings_file: null
34
+ ligase_embeddings_format: npz
35
+ ligase_embeddings_per_residue: true
36
+ ligase_residue_pooling: sum
37
+ ligase_embeddings_id_type: sequence
38
+ use_poi_pca: false
39
+ poi_pca_n_components: null
40
+ use_ligase_pca: false
41
+ ligase_pca_n_components: null
42
+ use_cell_description_embedding: true
43
+ use_cell_name_embedding: false
44
+ use_tokenizer: false
45
+ tokenizer_name: google-bert/bert-base-cased
46
+ max_length: 512
47
+ prompt_template: null
48
+ label_task_col: Value_Type
49
+ degrader_type_col: null
50
+ default_degrader_type: PROTAC
51
+ include_prompt: false
52
+ is_bert_multitask: false
53
+ use_assay_type_encoding: true
54
+ use_treatment_time: true
55
+ batch_size: 32
56
+ num_workers: 0
57
+ num_proc: 1
58
+ verbose: 0
59
+ sort_features: true
60
+ categorical_encoding: onehot
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=1_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce2db97ff55fa1c54ca0891752ceeed521407a0159f6ea45a678fa083ff6796f
3
+ size 169297
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=20_hparams.yaml ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ smiles_col: SMILES
2
+ ligase_col: Ligase_Name
3
+ ligase_sequence_col: Ligase_Sequence
4
+ poi_col: POI_Name
5
+ poi_sequence_col: POI_Sequence
6
+ cell_line_col: Cell_Line_ID
7
+ assay_type_col: Assay
8
+ treatment_time_col: Assay_Time
9
+ treatment_time_dmax_col: Assay_Time
10
+ treatment_time_dc50_col: Assay_Time
11
+ treatment_time_ic50_col: Treatment Time (h) (Cellular activities, IC50)
12
+ labels:
13
+ - Dmax
14
+ normalize_labels: true
15
+ standardize_labels: false
16
+ impute_labels: true
17
+ fp_size: 512
18
+ radius: 16
19
+ use_fingerprints: false
20
+ use_descriptors: true
21
+ use_relevant_descriptors: false
22
+ selected_descriptors: null
23
+ use_poi_sequence_embedding: true
24
+ use_poi_name_embedding: false
25
+ use_ligase_name_embedding: true
26
+ use_poi_precomputed_embedding: false
27
+ use_ligase_precomputed_embedding: false
28
+ poi_embeddings_file: null
29
+ poi_embeddings_format: npz
30
+ poi_embeddings_per_residue: true
31
+ poi_residue_pooling: sum
32
+ poi_embeddings_id_type: sequence
33
+ ligase_embeddings_file: null
34
+ ligase_embeddings_format: npz
35
+ ligase_embeddings_per_residue: true
36
+ ligase_residue_pooling: sum
37
+ ligase_embeddings_id_type: sequence
38
+ use_poi_pca: false
39
+ poi_pca_n_components: null
40
+ use_ligase_pca: false
41
+ ligase_pca_n_components: null
42
+ use_cell_description_embedding: true
43
+ use_cell_name_embedding: false
44
+ use_tokenizer: false
45
+ tokenizer_name: google-bert/bert-base-cased
46
+ max_length: 512
47
+ prompt_template: null
48
+ label_task_col: Value_Type
49
+ degrader_type_col: null
50
+ default_degrader_type: PROTAC
51
+ include_prompt: false
52
+ is_bert_multitask: false
53
+ use_assay_type_encoding: true
54
+ use_treatment_time: true
55
+ batch_size: 32
56
+ num_workers: 0
57
+ num_proc: 1
58
+ verbose: 0
59
+ sort_features: true
60
+ categorical_encoding: onehot
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=20_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af93f411109d99375dca334bb4ca64ebb2991be4fde08f79fa436316478d9ff2
3
+ size 169303
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=21_hparams.yaml ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ smiles_col: SMILES
2
+ ligase_col: Ligase_Name
3
+ ligase_sequence_col: Ligase_Sequence
4
+ poi_col: POI_Name
5
+ poi_sequence_col: POI_Sequence
6
+ cell_line_col: Cell_Line_ID
7
+ assay_type_col: Assay
8
+ treatment_time_col: Assay_Time
9
+ treatment_time_dmax_col: Assay_Time
10
+ treatment_time_dc50_col: Assay_Time
11
+ treatment_time_ic50_col: Treatment Time (h) (Cellular activities, IC50)
12
+ labels:
13
+ - Dmax
14
+ normalize_labels: true
15
+ standardize_labels: false
16
+ impute_labels: true
17
+ fp_size: 512
18
+ radius: 16
19
+ use_fingerprints: false
20
+ use_descriptors: true
21
+ use_relevant_descriptors: false
22
+ selected_descriptors: null
23
+ use_poi_sequence_embedding: true
24
+ use_poi_name_embedding: false
25
+ use_ligase_name_embedding: true
26
+ use_poi_precomputed_embedding: false
27
+ use_ligase_precomputed_embedding: false
28
+ poi_embeddings_file: null
29
+ poi_embeddings_format: npz
30
+ poi_embeddings_per_residue: true
31
+ poi_residue_pooling: sum
32
+ poi_embeddings_id_type: sequence
33
+ ligase_embeddings_file: null
34
+ ligase_embeddings_format: npz
35
+ ligase_embeddings_per_residue: true
36
+ ligase_residue_pooling: sum
37
+ ligase_embeddings_id_type: sequence
38
+ use_poi_pca: false
39
+ poi_pca_n_components: null
40
+ use_ligase_pca: false
41
+ ligase_pca_n_components: null
42
+ use_cell_description_embedding: true
43
+ use_cell_name_embedding: false
44
+ use_tokenizer: false
45
+ tokenizer_name: google-bert/bert-base-cased
46
+ max_length: 512
47
+ prompt_template: null
48
+ label_task_col: Value_Type
49
+ degrader_type_col: null
50
+ default_degrader_type: PROTAC
51
+ include_prompt: false
52
+ is_bert_multitask: false
53
+ use_assay_type_encoding: true
54
+ use_treatment_time: true
55
+ batch_size: 32
56
+ num_workers: 0
57
+ num_proc: 1
58
+ verbose: 0
59
+ sort_features: true
60
+ categorical_encoding: onehot
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=21_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c03364af7e9c87fa4548a878d249e06178e25b34ff1b77475ca6f7d44c57be5e
3
+ size 169303
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=22_hparams.yaml ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ smiles_col: SMILES
2
+ ligase_col: Ligase_Name
3
+ ligase_sequence_col: Ligase_Sequence
4
+ poi_col: POI_Name
5
+ poi_sequence_col: POI_Sequence
6
+ cell_line_col: Cell_Line_ID
7
+ assay_type_col: Assay
8
+ treatment_time_col: Assay_Time
9
+ treatment_time_dmax_col: Assay_Time
10
+ treatment_time_dc50_col: Assay_Time
11
+ treatment_time_ic50_col: Treatment Time (h) (Cellular activities, IC50)
12
+ labels:
13
+ - Dmax
14
+ normalize_labels: true
15
+ standardize_labels: false
16
+ impute_labels: true
17
+ fp_size: 512
18
+ radius: 16
19
+ use_fingerprints: false
20
+ use_descriptors: true
21
+ use_relevant_descriptors: false
22
+ selected_descriptors: null
23
+ use_poi_sequence_embedding: true
24
+ use_poi_name_embedding: false
25
+ use_ligase_name_embedding: true
26
+ use_poi_precomputed_embedding: false
27
+ use_ligase_precomputed_embedding: false
28
+ poi_embeddings_file: null
29
+ poi_embeddings_format: npz
30
+ poi_embeddings_per_residue: true
31
+ poi_residue_pooling: sum
32
+ poi_embeddings_id_type: sequence
33
+ ligase_embeddings_file: null
34
+ ligase_embeddings_format: npz
35
+ ligase_embeddings_per_residue: true
36
+ ligase_residue_pooling: sum
37
+ ligase_embeddings_id_type: sequence
38
+ use_poi_pca: false
39
+ poi_pca_n_components: null
40
+ use_ligase_pca: false
41
+ ligase_pca_n_components: null
42
+ use_cell_description_embedding: true
43
+ use_cell_name_embedding: false
44
+ use_tokenizer: false
45
+ tokenizer_name: google-bert/bert-base-cased
46
+ max_length: 512
47
+ prompt_template: null
48
+ label_task_col: Value_Type
49
+ degrader_type_col: null
50
+ default_degrader_type: PROTAC
51
+ include_prompt: false
52
+ is_bert_multitask: false
53
+ use_assay_type_encoding: true
54
+ use_treatment_time: true
55
+ batch_size: 32
56
+ num_workers: 0
57
+ num_proc: 1
58
+ verbose: 0
59
+ sort_features: true
60
+ categorical_encoding: onehot
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=22_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de5ef50a73a80d03deac6701914ef1b0792917bff1fd68b05ea3514891420a3c
3
+ size 169303
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=23_hparams.yaml ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ smiles_col: SMILES
2
+ ligase_col: Ligase_Name
3
+ ligase_sequence_col: Ligase_Sequence
4
+ poi_col: POI_Name
5
+ poi_sequence_col: POI_Sequence
6
+ cell_line_col: Cell_Line_ID
7
+ assay_type_col: Assay
8
+ treatment_time_col: Assay_Time
9
+ treatment_time_dmax_col: Assay_Time
10
+ treatment_time_dc50_col: Assay_Time
11
+ treatment_time_ic50_col: Treatment Time (h) (Cellular activities, IC50)
12
+ labels:
13
+ - Dmax
14
+ normalize_labels: true
15
+ standardize_labels: false
16
+ impute_labels: true
17
+ fp_size: 512
18
+ radius: 16
19
+ use_fingerprints: false
20
+ use_descriptors: true
21
+ use_relevant_descriptors: false
22
+ selected_descriptors: null
23
+ use_poi_sequence_embedding: true
24
+ use_poi_name_embedding: false
25
+ use_ligase_name_embedding: true
26
+ use_poi_precomputed_embedding: false
27
+ use_ligase_precomputed_embedding: false
28
+ poi_embeddings_file: null
29
+ poi_embeddings_format: npz
30
+ poi_embeddings_per_residue: true
31
+ poi_residue_pooling: sum
32
+ poi_embeddings_id_type: sequence
33
+ ligase_embeddings_file: null
34
+ ligase_embeddings_format: npz
35
+ ligase_embeddings_per_residue: true
36
+ ligase_residue_pooling: sum
37
+ ligase_embeddings_id_type: sequence
38
+ use_poi_pca: false
39
+ poi_pca_n_components: null
40
+ use_ligase_pca: false
41
+ ligase_pca_n_components: null
42
+ use_cell_description_embedding: true
43
+ use_cell_name_embedding: false
44
+ use_tokenizer: false
45
+ tokenizer_name: google-bert/bert-base-cased
46
+ max_length: 512
47
+ prompt_template: null
48
+ label_task_col: Value_Type
49
+ degrader_type_col: null
50
+ default_degrader_type: PROTAC
51
+ include_prompt: false
52
+ is_bert_multitask: false
53
+ use_assay_type_encoding: true
54
+ use_treatment_time: true
55
+ batch_size: 32
56
+ num_workers: 0
57
+ num_proc: 1
58
+ verbose: 0
59
+ sort_features: true
60
+ categorical_encoding: onehot
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=23_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da014958a5eaa63d05db394caa0f5441e0cda8784ad504bec47eb1d76d945da8
3
+ size 169367
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=24_hparams.yaml ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ smiles_col: SMILES
2
+ ligase_col: Ligase_Name
3
+ ligase_sequence_col: Ligase_Sequence
4
+ poi_col: POI_Name
5
+ poi_sequence_col: POI_Sequence
6
+ cell_line_col: Cell_Line_ID
7
+ assay_type_col: Assay
8
+ treatment_time_col: Assay_Time
9
+ treatment_time_dmax_col: Assay_Time
10
+ treatment_time_dc50_col: Assay_Time
11
+ treatment_time_ic50_col: Treatment Time (h) (Cellular activities, IC50)
12
+ labels:
13
+ - Dmax
14
+ normalize_labels: true
15
+ standardize_labels: false
16
+ impute_labels: true
17
+ fp_size: 512
18
+ radius: 16
19
+ use_fingerprints: false
20
+ use_descriptors: true
21
+ use_relevant_descriptors: false
22
+ selected_descriptors: null
23
+ use_poi_sequence_embedding: true
24
+ use_poi_name_embedding: false
25
+ use_ligase_name_embedding: true
26
+ use_poi_precomputed_embedding: false
27
+ use_ligase_precomputed_embedding: false
28
+ poi_embeddings_file: null
29
+ poi_embeddings_format: npz
30
+ poi_embeddings_per_residue: true
31
+ poi_residue_pooling: sum
32
+ poi_embeddings_id_type: sequence
33
+ ligase_embeddings_file: null
34
+ ligase_embeddings_format: npz
35
+ ligase_embeddings_per_residue: true
36
+ ligase_residue_pooling: sum
37
+ ligase_embeddings_id_type: sequence
38
+ use_poi_pca: false
39
+ poi_pca_n_components: null
40
+ use_ligase_pca: false
41
+ ligase_pca_n_components: null
42
+ use_cell_description_embedding: true
43
+ use_cell_name_embedding: false
44
+ use_tokenizer: false
45
+ tokenizer_name: google-bert/bert-base-cased
46
+ max_length: 512
47
+ prompt_template: null
48
+ label_task_col: Value_Type
49
+ degrader_type_col: null
50
+ default_degrader_type: PROTAC
51
+ include_prompt: false
52
+ is_bert_multitask: false
53
+ use_assay_type_encoding: true
54
+ use_treatment_time: true
55
+ batch_size: 32
56
+ num_workers: 0
57
+ num_proc: 1
58
+ verbose: 0
59
+ sort_features: true
60
+ categorical_encoding: onehot
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=24_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d899c0332b8c3bb7be65ccd7ba2a47277d8925e653d13e1294c3f5a2fe7e52e
3
+ size 169303
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=2_hparams.yaml ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ smiles_col: SMILES
2
+ ligase_col: Ligase_Name
3
+ ligase_sequence_col: Ligase_Sequence
4
+ poi_col: POI_Name
5
+ poi_sequence_col: POI_Sequence
6
+ cell_line_col: Cell_Line_ID
7
+ assay_type_col: Assay
8
+ treatment_time_col: Assay_Time
9
+ treatment_time_dmax_col: Assay_Time
10
+ treatment_time_dc50_col: Assay_Time
11
+ treatment_time_ic50_col: Treatment Time (h) (Cellular activities, IC50)
12
+ labels:
13
+ - Dmax
14
+ normalize_labels: true
15
+ standardize_labels: false
16
+ impute_labels: true
17
+ fp_size: 512
18
+ radius: 16
19
+ use_fingerprints: false
20
+ use_descriptors: true
21
+ use_relevant_descriptors: false
22
+ selected_descriptors: null
23
+ use_poi_sequence_embedding: true
24
+ use_poi_name_embedding: false
25
+ use_ligase_name_embedding: true
26
+ use_poi_precomputed_embedding: false
27
+ use_ligase_precomputed_embedding: false
28
+ poi_embeddings_file: null
29
+ poi_embeddings_format: npz
30
+ poi_embeddings_per_residue: true
31
+ poi_residue_pooling: sum
32
+ poi_embeddings_id_type: sequence
33
+ ligase_embeddings_file: null
34
+ ligase_embeddings_format: npz
35
+ ligase_embeddings_per_residue: true
36
+ ligase_residue_pooling: sum
37
+ ligase_embeddings_id_type: sequence
38
+ use_poi_pca: false
39
+ poi_pca_n_components: null
40
+ use_ligase_pca: false
41
+ ligase_pca_n_components: null
42
+ use_cell_description_embedding: true
43
+ use_cell_name_embedding: false
44
+ use_tokenizer: false
45
+ tokenizer_name: google-bert/bert-base-cased
46
+ max_length: 512
47
+ prompt_template: null
48
+ label_task_col: Value_Type
49
+ degrader_type_col: null
50
+ default_degrader_type: PROTAC
51
+ include_prompt: false
52
+ is_bert_multitask: false
53
+ use_assay_type_encoding: true
54
+ use_treatment_time: true
55
+ batch_size: 32
56
+ num_workers: 0
57
+ num_proc: 1
58
+ verbose: 0
59
+ sort_features: true
60
+ categorical_encoding: onehot
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=2_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9ab3caf0b9215753907f82b1530ec1668823a78aa0d8802043822e4bce75e99
3
+ size 169297
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=3_hparams.yaml ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ smiles_col: SMILES
2
+ ligase_col: Ligase_Name
3
+ ligase_sequence_col: Ligase_Sequence
4
+ poi_col: POI_Name
5
+ poi_sequence_col: POI_Sequence
6
+ cell_line_col: Cell_Line_ID
7
+ assay_type_col: Assay
8
+ treatment_time_col: Assay_Time
9
+ treatment_time_dmax_col: Assay_Time
10
+ treatment_time_dc50_col: Assay_Time
11
+ treatment_time_ic50_col: Treatment Time (h) (Cellular activities, IC50)
12
+ labels:
13
+ - Dmax
14
+ normalize_labels: true
15
+ standardize_labels: false
16
+ impute_labels: true
17
+ fp_size: 512
18
+ radius: 16
19
+ use_fingerprints: false
20
+ use_descriptors: true
21
+ use_relevant_descriptors: false
22
+ selected_descriptors: null
23
+ use_poi_sequence_embedding: true
24
+ use_poi_name_embedding: false
25
+ use_ligase_name_embedding: true
26
+ use_poi_precomputed_embedding: false
27
+ use_ligase_precomputed_embedding: false
28
+ poi_embeddings_file: null
29
+ poi_embeddings_format: npz
30
+ poi_embeddings_per_residue: true
31
+ poi_residue_pooling: sum
32
+ poi_embeddings_id_type: sequence
33
+ ligase_embeddings_file: null
34
+ ligase_embeddings_format: npz
35
+ ligase_embeddings_per_residue: true
36
+ ligase_residue_pooling: sum
37
+ ligase_embeddings_id_type: sequence
38
+ use_poi_pca: false
39
+ poi_pca_n_components: null
40
+ use_ligase_pca: false
41
+ ligase_pca_n_components: null
42
+ use_cell_description_embedding: true
43
+ use_cell_name_embedding: false
44
+ use_tokenizer: false
45
+ tokenizer_name: google-bert/bert-base-cased
46
+ max_length: 512
47
+ prompt_template: null
48
+ label_task_col: Value_Type
49
+ degrader_type_col: null
50
+ default_degrader_type: PROTAC
51
+ include_prompt: false
52
+ is_bert_multitask: false
53
+ use_assay_type_encoding: true
54
+ use_treatment_time: true
55
+ batch_size: 32
56
+ num_workers: 0
57
+ num_proc: 1
58
+ verbose: 0
59
+ sort_features: true
60
+ categorical_encoding: onehot
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=3_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:290e6d91c99cd3c177c1fde2499d3c07bae368ac181de3a0694777c05c80828e
3
+ size 169297
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=4_hparams.yaml ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ smiles_col: SMILES
2
+ ligase_col: Ligase_Name
3
+ ligase_sequence_col: Ligase_Sequence
4
+ poi_col: POI_Name
5
+ poi_sequence_col: POI_Sequence
6
+ cell_line_col: Cell_Line_ID
7
+ assay_type_col: Assay
8
+ treatment_time_col: Assay_Time
9
+ treatment_time_dmax_col: Assay_Time
10
+ treatment_time_dc50_col: Assay_Time
11
+ treatment_time_ic50_col: Treatment Time (h) (Cellular activities, IC50)
12
+ labels:
13
+ - Dmax
14
+ normalize_labels: true
15
+ standardize_labels: false
16
+ impute_labels: true
17
+ fp_size: 512
18
+ radius: 16
19
+ use_fingerprints: false
20
+ use_descriptors: true
21
+ use_relevant_descriptors: false
22
+ selected_descriptors: null
23
+ use_poi_sequence_embedding: true
24
+ use_poi_name_embedding: false
25
+ use_ligase_name_embedding: true
26
+ use_poi_precomputed_embedding: false
27
+ use_ligase_precomputed_embedding: false
28
+ poi_embeddings_file: null
29
+ poi_embeddings_format: npz
30
+ poi_embeddings_per_residue: true
31
+ poi_residue_pooling: sum
32
+ poi_embeddings_id_type: sequence
33
+ ligase_embeddings_file: null
34
+ ligase_embeddings_format: npz
35
+ ligase_embeddings_per_residue: true
36
+ ligase_residue_pooling: sum
37
+ ligase_embeddings_id_type: sequence
38
+ use_poi_pca: false
39
+ poi_pca_n_components: null
40
+ use_ligase_pca: false
41
+ ligase_pca_n_components: null
42
+ use_cell_description_embedding: true
43
+ use_cell_name_embedding: false
44
+ use_tokenizer: false
45
+ tokenizer_name: google-bert/bert-base-cased
46
+ max_length: 512
47
+ prompt_template: null
48
+ label_task_col: Value_Type
49
+ degrader_type_col: null
50
+ default_degrader_type: PROTAC
51
+ include_prompt: false
52
+ is_bert_multitask: false
53
+ use_assay_type_encoding: true
54
+ use_treatment_time: true
55
+ batch_size: 32
56
+ num_workers: 0
57
+ num_proc: 1
58
+ verbose: 0
59
+ sort_features: true
60
+ categorical_encoding: onehot
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=4_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c70b656aadece6f184d3f187ecaa8220692d6d531b0346eb5c316d4c0d817775
3
+ size 169169
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=5_hparams.yaml ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ smiles_col: SMILES
2
+ ligase_col: Ligase_Name
3
+ ligase_sequence_col: Ligase_Sequence
4
+ poi_col: POI_Name
5
+ poi_sequence_col: POI_Sequence
6
+ cell_line_col: Cell_Line_ID
7
+ assay_type_col: Assay
8
+ treatment_time_col: Assay_Time
9
+ treatment_time_dmax_col: Assay_Time
10
+ treatment_time_dc50_col: Assay_Time
11
+ treatment_time_ic50_col: Treatment Time (h) (Cellular activities, IC50)
12
+ labels:
13
+ - Dmax
14
+ normalize_labels: true
15
+ standardize_labels: false
16
+ impute_labels: true
17
+ fp_size: 512
18
+ radius: 16
19
+ use_fingerprints: false
20
+ use_descriptors: true
21
+ use_relevant_descriptors: false
22
+ selected_descriptors: null
23
+ use_poi_sequence_embedding: true
24
+ use_poi_name_embedding: false
25
+ use_ligase_name_embedding: true
26
+ use_poi_precomputed_embedding: false
27
+ use_ligase_precomputed_embedding: false
28
+ poi_embeddings_file: null
29
+ poi_embeddings_format: npz
30
+ poi_embeddings_per_residue: true
31
+ poi_residue_pooling: sum
32
+ poi_embeddings_id_type: sequence
33
+ ligase_embeddings_file: null
34
+ ligase_embeddings_format: npz
35
+ ligase_embeddings_per_residue: true
36
+ ligase_residue_pooling: sum
37
+ ligase_embeddings_id_type: sequence
38
+ use_poi_pca: false
39
+ poi_pca_n_components: null
40
+ use_ligase_pca: false
41
+ ligase_pca_n_components: null
42
+ use_cell_description_embedding: true
43
+ use_cell_name_embedding: false
44
+ use_tokenizer: false
45
+ tokenizer_name: google-bert/bert-base-cased
46
+ max_length: 512
47
+ prompt_template: null
48
+ label_task_col: Value_Type
49
+ degrader_type_col: null
50
+ default_degrader_type: PROTAC
51
+ include_prompt: false
52
+ is_bert_multitask: false
53
+ use_assay_type_encoding: true
54
+ use_treatment_time: true
55
+ batch_size: 32
56
+ num_workers: 0
57
+ num_proc: 1
58
+ verbose: 0
59
+ sort_features: true
60
+ categorical_encoding: onehot
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=5_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6097d0342175683eac418852d6ffbbcbd26ca5ff488e441a297a6110a4c5c763
3
+ size 169233
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=6_hparams.yaml ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ smiles_col: SMILES
2
+ ligase_col: Ligase_Name
3
+ ligase_sequence_col: Ligase_Sequence
4
+ poi_col: POI_Name
5
+ poi_sequence_col: POI_Sequence
6
+ cell_line_col: Cell_Line_ID
7
+ assay_type_col: Assay
8
+ treatment_time_col: Assay_Time
9
+ treatment_time_dmax_col: Assay_Time
10
+ treatment_time_dc50_col: Assay_Time
11
+ treatment_time_ic50_col: Treatment Time (h) (Cellular activities, IC50)
12
+ labels:
13
+ - Dmax
14
+ normalize_labels: true
15
+ standardize_labels: false
16
+ impute_labels: true
17
+ fp_size: 512
18
+ radius: 16
19
+ use_fingerprints: false
20
+ use_descriptors: true
21
+ use_relevant_descriptors: false
22
+ selected_descriptors: null
23
+ use_poi_sequence_embedding: true
24
+ use_poi_name_embedding: false
25
+ use_ligase_name_embedding: true
26
+ use_poi_precomputed_embedding: false
27
+ use_ligase_precomputed_embedding: false
28
+ poi_embeddings_file: null
29
+ poi_embeddings_format: npz
30
+ poi_embeddings_per_residue: true
31
+ poi_residue_pooling: sum
32
+ poi_embeddings_id_type: sequence
33
+ ligase_embeddings_file: null
34
+ ligase_embeddings_format: npz
35
+ ligase_embeddings_per_residue: true
36
+ ligase_residue_pooling: sum
37
+ ligase_embeddings_id_type: sequence
38
+ use_poi_pca: false
39
+ poi_pca_n_components: null
40
+ use_ligase_pca: false
41
+ ligase_pca_n_components: null
42
+ use_cell_description_embedding: true
43
+ use_cell_name_embedding: false
44
+ use_tokenizer: false
45
+ tokenizer_name: google-bert/bert-base-cased
46
+ max_length: 512
47
+ prompt_template: null
48
+ label_task_col: Value_Type
49
+ degrader_type_col: null
50
+ default_degrader_type: PROTAC
51
+ include_prompt: false
52
+ is_bert_multitask: false
53
+ use_assay_type_encoding: true
54
+ use_treatment_time: true
55
+ batch_size: 32
56
+ num_workers: 0
57
+ num_proc: 1
58
+ verbose: 0
59
+ sort_features: true
60
+ categorical_encoding: onehot
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=6_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e169a517b2287d1556a88aac032bf0b79c3d9a7e03a0002d6d01e71113144683
3
+ size 169233
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=7_hparams.yaml ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ smiles_col: SMILES
2
+ ligase_col: Ligase_Name
3
+ ligase_sequence_col: Ligase_Sequence
4
+ poi_col: POI_Name
5
+ poi_sequence_col: POI_Sequence
6
+ cell_line_col: Cell_Line_ID
7
+ assay_type_col: Assay
8
+ treatment_time_col: Assay_Time
9
+ treatment_time_dmax_col: Assay_Time
10
+ treatment_time_dc50_col: Assay_Time
11
+ treatment_time_ic50_col: Treatment Time (h) (Cellular activities, IC50)
12
+ labels:
13
+ - Dmax
14
+ normalize_labels: true
15
+ standardize_labels: false
16
+ impute_labels: true
17
+ fp_size: 512
18
+ radius: 16
19
+ use_fingerprints: false
20
+ use_descriptors: true
21
+ use_relevant_descriptors: false
22
+ selected_descriptors: null
23
+ use_poi_sequence_embedding: true
24
+ use_poi_name_embedding: false
25
+ use_ligase_name_embedding: true
26
+ use_poi_precomputed_embedding: false
27
+ use_ligase_precomputed_embedding: false
28
+ poi_embeddings_file: null
29
+ poi_embeddings_format: npz
30
+ poi_embeddings_per_residue: true
31
+ poi_residue_pooling: sum
32
+ poi_embeddings_id_type: sequence
33
+ ligase_embeddings_file: null
34
+ ligase_embeddings_format: npz
35
+ ligase_embeddings_per_residue: true
36
+ ligase_residue_pooling: sum
37
+ ligase_embeddings_id_type: sequence
38
+ use_poi_pca: false
39
+ poi_pca_n_components: null
40
+ use_ligase_pca: false
41
+ ligase_pca_n_components: null
42
+ use_cell_description_embedding: true
43
+ use_cell_name_embedding: false
44
+ use_tokenizer: false
45
+ tokenizer_name: google-bert/bert-base-cased
46
+ max_length: 512
47
+ prompt_template: null
48
+ label_task_col: Value_Type
49
+ degrader_type_col: null
50
+ default_degrader_type: PROTAC
51
+ include_prompt: false
52
+ is_bert_multitask: false
53
+ use_assay_type_encoding: true
54
+ use_treatment_time: true
55
+ batch_size: 32
56
+ num_workers: 0
57
+ num_proc: 1
58
+ verbose: 0
59
+ sort_features: true
60
+ categorical_encoding: onehot
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=7_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:382fbf3752c6439f532d687aac02d4dcc589bac663c63bc70c45805e2f68ff28
3
+ size 169233
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=8_hparams.yaml ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ smiles_col: SMILES
2
+ ligase_col: Ligase_Name
3
+ ligase_sequence_col: Ligase_Sequence
4
+ poi_col: POI_Name
5
+ poi_sequence_col: POI_Sequence
6
+ cell_line_col: Cell_Line_ID
7
+ assay_type_col: Assay
8
+ treatment_time_col: Assay_Time
9
+ treatment_time_dmax_col: Assay_Time
10
+ treatment_time_dc50_col: Assay_Time
11
+ treatment_time_ic50_col: Treatment Time (h) (Cellular activities, IC50)
12
+ labels:
13
+ - Dmax
14
+ normalize_labels: true
15
+ standardize_labels: false
16
+ impute_labels: true
17
+ fp_size: 512
18
+ radius: 16
19
+ use_fingerprints: false
20
+ use_descriptors: true
21
+ use_relevant_descriptors: false
22
+ selected_descriptors: null
23
+ use_poi_sequence_embedding: true
24
+ use_poi_name_embedding: false
25
+ use_ligase_name_embedding: true
26
+ use_poi_precomputed_embedding: false
27
+ use_ligase_precomputed_embedding: false
28
+ poi_embeddings_file: null
29
+ poi_embeddings_format: npz
30
+ poi_embeddings_per_residue: true
31
+ poi_residue_pooling: sum
32
+ poi_embeddings_id_type: sequence
33
+ ligase_embeddings_file: null
34
+ ligase_embeddings_format: npz
35
+ ligase_embeddings_per_residue: true
36
+ ligase_residue_pooling: sum
37
+ ligase_embeddings_id_type: sequence
38
+ use_poi_pca: false
39
+ poi_pca_n_components: null
40
+ use_ligase_pca: false
41
+ ligase_pca_n_components: null
42
+ use_cell_description_embedding: true
43
+ use_cell_name_embedding: false
44
+ use_tokenizer: false
45
+ tokenizer_name: google-bert/bert-base-cased
46
+ max_length: 512
47
+ prompt_template: null
48
+ label_task_col: Value_Type
49
+ degrader_type_col: null
50
+ default_degrader_type: PROTAC
51
+ include_prompt: false
52
+ is_bert_multitask: false
53
+ use_assay_type_encoding: true
54
+ use_treatment_time: true
55
+ batch_size: 32
56
+ num_workers: 0
57
+ num_proc: 1
58
+ verbose: 0
59
+ sort_features: true
60
+ categorical_encoding: onehot
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=8_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d38b8cd8e34e7729b5ce645f1c6475ac08157b0a3e34d4200383659003e9e5c
3
+ size 169361
dmax_best_arch_ensemble/datamodule-data=all_desc_poi_vec_lig_onehot_cell_text_assay_time_norm_labels_Dmax-group=scaffold-fold=9_hparams.yaml ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ smiles_col: SMILES
2
+ ligase_col: Ligase_Name
3
+ ligase_sequence_col: Ligase_Sequence
4
+ poi_col: POI_Name
5
+ poi_sequence_col: POI_Sequence
6
+ cell_line_col: Cell_Line_ID
7
+ assay_type_col: Assay
8
+ treatment_time_col: Assay_Time
9
+ treatment_time_dmax_col: Assay_Time
10
+ treatment_time_dc50_col: Assay_Time
11
+ treatment_time_ic50_col: Treatment Time (h) (Cellular activities, IC50)
12
+ labels:
13
+ - Dmax
14
+ normalize_labels: true
15
+ standardize_labels: false
16
+ impute_labels: true
17
+ fp_size: 512
18
+ radius: 16
19
+ use_fingerprints: false
20
+ use_descriptors: true
21
+ use_relevant_descriptors: false
22
+ selected_descriptors: null
23
+ use_poi_sequence_embedding: true
24
+ use_poi_name_embedding: false
25
+ use_ligase_name_embedding: true
26
+ use_poi_precomputed_embedding: false
27
+ use_ligase_precomputed_embedding: false
28
+ poi_embeddings_file: null
29
+ poi_embeddings_format: npz
30
+ poi_embeddings_per_residue: true
31
+ poi_residue_pooling: sum
32
+ poi_embeddings_id_type: sequence
33
+ ligase_embeddings_file: null
34
+ ligase_embeddings_format: npz
35
+ ligase_embeddings_per_residue: true
36
+ ligase_residue_pooling: sum
37
+ ligase_embeddings_id_type: sequence
38
+ use_poi_pca: false
39
+ poi_pca_n_components: null
40
+ use_ligase_pca: false
41
+ ligase_pca_n_components: null
42
+ use_cell_description_embedding: true
43
+ use_cell_name_embedding: false
44
+ use_tokenizer: false
45
+ tokenizer_name: google-bert/bert-base-cased
46
+ max_length: 512
47
+ prompt_template: null
48
+ label_task_col: Value_Type
49
+ degrader_type_col: null
50
+ default_degrader_type: PROTAC
51
+ include_prompt: false
52
+ is_bert_multitask: false
53
+ use_assay_type_encoding: true
54
+ use_treatment_time: true
55
+ batch_size: 32
56
+ num_workers: 0
57
+ num_proc: 1
58
+ verbose: 0
59
+ sort_features: true
60
+ categorical_encoding: onehot