Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- bin_best_arch_ensemble/config-model=xgboost_bin_protac-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-task=bin-group=scaffold.yaml +17 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=0_hparams.yaml +60 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=0_state.pt +3 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=10_hparams.yaml +60 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=10_state.pt +3 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=11_hparams.yaml +60 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=11_state.pt +3 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=12_hparams.yaml +60 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=12_state.pt +3 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=13_hparams.yaml +60 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=13_state.pt +3 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=14_hparams.yaml +60 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=14_state.pt +3 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=15_hparams.yaml +60 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=15_state.pt +3 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=16_hparams.yaml +60 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=16_state.pt +3 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=17_hparams.yaml +60 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=17_state.pt +3 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=18_hparams.yaml +60 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=18_state.pt +3 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=19_hparams.yaml +60 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=19_state.pt +3 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=1_hparams.yaml +60 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=1_state.pt +3 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=20_hparams.yaml +60 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=20_state.pt +3 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=21_hparams.yaml +60 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=21_state.pt +3 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=22_hparams.yaml +60 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=22_state.pt +3 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=23_hparams.yaml +60 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=23_state.pt +3 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=24_hparams.yaml +60 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=24_state.pt +3 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=2_hparams.yaml +60 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=2_state.pt +3 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=3_hparams.yaml +60 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=3_state.pt +3 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=4_hparams.yaml +60 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=4_state.pt +3 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=5_hparams.yaml +60 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=5_state.pt +3 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=6_hparams.yaml +60 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=6_state.pt +3 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=7_hparams.yaml +60 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=7_state.pt +3 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=8_hparams.yaml +60 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=8_state.pt +3 -0
- bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=9_hparams.yaml +60 -0
bin_best_arch_ensemble/config-model=xgboost_bin_protac-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-task=bin-group=scaffold.yaml
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
model_config:
|
| 2 |
+
objective: binary:logistic
|
| 3 |
+
tree_method: hist
|
| 4 |
+
n_estimators: 2000
|
| 5 |
+
n_jobs: 8
|
| 6 |
+
seed: 65
|
| 7 |
+
learning_rate: 0.0017541893487450805
|
| 8 |
+
max_depth: 6
|
| 9 |
+
min_child_weight: 1
|
| 10 |
+
subsample: 0.9455922412472693
|
| 11 |
+
colsample_bytree: 0.6293899908000085
|
| 12 |
+
reg_alpha: 0.4467752817973907
|
| 13 |
+
reg_lambda: 0.017654048052495083
|
| 14 |
+
gamma: 0.12030178871154672
|
| 15 |
+
training_config:
|
| 16 |
+
num_boost_round: 2000
|
| 17 |
+
early_stopping_rounds: 30
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-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 |
+
- Activity
|
| 14 |
+
normalize_labels: false
|
| 15 |
+
standardize_labels: false
|
| 16 |
+
impute_labels: false
|
| 17 |
+
fp_size: 512
|
| 18 |
+
radius: 16
|
| 19 |
+
use_fingerprints: true
|
| 20 |
+
use_descriptors: true
|
| 21 |
+
use_relevant_descriptors: false
|
| 22 |
+
selected_descriptors: null
|
| 23 |
+
use_poi_sequence_embedding: false
|
| 24 |
+
use_poi_name_embedding: false
|
| 25 |
+
use_ligase_name_embedding: false
|
| 26 |
+
use_poi_precomputed_embedding: true
|
| 27 |
+
use_ligase_precomputed_embedding: true
|
| 28 |
+
poi_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 29 |
+
poi_embeddings_format: npz
|
| 30 |
+
poi_embeddings_per_residue: false
|
| 31 |
+
poi_residue_pooling: sum
|
| 32 |
+
poi_embeddings_id_type: sequence
|
| 33 |
+
ligase_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 34 |
+
ligase_embeddings_format: npz
|
| 35 |
+
ligase_embeddings_per_residue: false
|
| 36 |
+
ligase_residue_pooling: sum
|
| 37 |
+
ligase_embeddings_id_type: sequence
|
| 38 |
+
use_poi_pca: true
|
| 39 |
+
poi_pca_n_components: 44
|
| 40 |
+
use_ligase_pca: true
|
| 41 |
+
ligase_pca_n_components: 7
|
| 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
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=0_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b52b43984b2601f47fb7c4fd8666b4d2a3084ca59b6d9412129426b8164781af
|
| 3 |
+
size 550881
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-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 |
+
- Activity
|
| 14 |
+
normalize_labels: false
|
| 15 |
+
standardize_labels: false
|
| 16 |
+
impute_labels: false
|
| 17 |
+
fp_size: 512
|
| 18 |
+
radius: 16
|
| 19 |
+
use_fingerprints: true
|
| 20 |
+
use_descriptors: true
|
| 21 |
+
use_relevant_descriptors: false
|
| 22 |
+
selected_descriptors: null
|
| 23 |
+
use_poi_sequence_embedding: false
|
| 24 |
+
use_poi_name_embedding: false
|
| 25 |
+
use_ligase_name_embedding: false
|
| 26 |
+
use_poi_precomputed_embedding: true
|
| 27 |
+
use_ligase_precomputed_embedding: true
|
| 28 |
+
poi_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 29 |
+
poi_embeddings_format: npz
|
| 30 |
+
poi_embeddings_per_residue: false
|
| 31 |
+
poi_residue_pooling: sum
|
| 32 |
+
poi_embeddings_id_type: sequence
|
| 33 |
+
ligase_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 34 |
+
ligase_embeddings_format: npz
|
| 35 |
+
ligase_embeddings_per_residue: false
|
| 36 |
+
ligase_residue_pooling: sum
|
| 37 |
+
ligase_embeddings_id_type: sequence
|
| 38 |
+
use_poi_pca: true
|
| 39 |
+
poi_pca_n_components: 44
|
| 40 |
+
use_ligase_pca: true
|
| 41 |
+
ligase_pca_n_components: 7
|
| 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
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=10_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5247423db1d648cb945a20cfc02ef632a18d7344f405d2cdbc9409881e21130
|
| 3 |
+
size 550823
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-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 |
+
- Activity
|
| 14 |
+
normalize_labels: false
|
| 15 |
+
standardize_labels: false
|
| 16 |
+
impute_labels: false
|
| 17 |
+
fp_size: 512
|
| 18 |
+
radius: 16
|
| 19 |
+
use_fingerprints: true
|
| 20 |
+
use_descriptors: true
|
| 21 |
+
use_relevant_descriptors: false
|
| 22 |
+
selected_descriptors: null
|
| 23 |
+
use_poi_sequence_embedding: false
|
| 24 |
+
use_poi_name_embedding: false
|
| 25 |
+
use_ligase_name_embedding: false
|
| 26 |
+
use_poi_precomputed_embedding: true
|
| 27 |
+
use_ligase_precomputed_embedding: true
|
| 28 |
+
poi_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 29 |
+
poi_embeddings_format: npz
|
| 30 |
+
poi_embeddings_per_residue: false
|
| 31 |
+
poi_residue_pooling: sum
|
| 32 |
+
poi_embeddings_id_type: sequence
|
| 33 |
+
ligase_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 34 |
+
ligase_embeddings_format: npz
|
| 35 |
+
ligase_embeddings_per_residue: false
|
| 36 |
+
ligase_residue_pooling: sum
|
| 37 |
+
ligase_embeddings_id_type: sequence
|
| 38 |
+
use_poi_pca: true
|
| 39 |
+
poi_pca_n_components: 44
|
| 40 |
+
use_ligase_pca: true
|
| 41 |
+
ligase_pca_n_components: 7
|
| 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
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=11_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2981d7de8bd5b5b96a52148c452c94fdce11550f7bf2a902e0cbbc5729191833
|
| 3 |
+
size 551271
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-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 |
+
- Activity
|
| 14 |
+
normalize_labels: false
|
| 15 |
+
standardize_labels: false
|
| 16 |
+
impute_labels: false
|
| 17 |
+
fp_size: 512
|
| 18 |
+
radius: 16
|
| 19 |
+
use_fingerprints: true
|
| 20 |
+
use_descriptors: true
|
| 21 |
+
use_relevant_descriptors: false
|
| 22 |
+
selected_descriptors: null
|
| 23 |
+
use_poi_sequence_embedding: false
|
| 24 |
+
use_poi_name_embedding: false
|
| 25 |
+
use_ligase_name_embedding: false
|
| 26 |
+
use_poi_precomputed_embedding: true
|
| 27 |
+
use_ligase_precomputed_embedding: true
|
| 28 |
+
poi_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 29 |
+
poi_embeddings_format: npz
|
| 30 |
+
poi_embeddings_per_residue: false
|
| 31 |
+
poi_residue_pooling: sum
|
| 32 |
+
poi_embeddings_id_type: sequence
|
| 33 |
+
ligase_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 34 |
+
ligase_embeddings_format: npz
|
| 35 |
+
ligase_embeddings_per_residue: false
|
| 36 |
+
ligase_residue_pooling: sum
|
| 37 |
+
ligase_embeddings_id_type: sequence
|
| 38 |
+
use_poi_pca: true
|
| 39 |
+
poi_pca_n_components: 44
|
| 40 |
+
use_ligase_pca: true
|
| 41 |
+
ligase_pca_n_components: 7
|
| 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
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=12_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2f5c1866f35d1597c2c7461d2ca10df6c746f0bf9f8afb0d3c80ad85b2ad46c5
|
| 3 |
+
size 550951
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-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 |
+
- Activity
|
| 14 |
+
normalize_labels: false
|
| 15 |
+
standardize_labels: false
|
| 16 |
+
impute_labels: false
|
| 17 |
+
fp_size: 512
|
| 18 |
+
radius: 16
|
| 19 |
+
use_fingerprints: true
|
| 20 |
+
use_descriptors: true
|
| 21 |
+
use_relevant_descriptors: false
|
| 22 |
+
selected_descriptors: null
|
| 23 |
+
use_poi_sequence_embedding: false
|
| 24 |
+
use_poi_name_embedding: false
|
| 25 |
+
use_ligase_name_embedding: false
|
| 26 |
+
use_poi_precomputed_embedding: true
|
| 27 |
+
use_ligase_precomputed_embedding: true
|
| 28 |
+
poi_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 29 |
+
poi_embeddings_format: npz
|
| 30 |
+
poi_embeddings_per_residue: false
|
| 31 |
+
poi_residue_pooling: sum
|
| 32 |
+
poi_embeddings_id_type: sequence
|
| 33 |
+
ligase_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 34 |
+
ligase_embeddings_format: npz
|
| 35 |
+
ligase_embeddings_per_residue: false
|
| 36 |
+
ligase_residue_pooling: sum
|
| 37 |
+
ligase_embeddings_id_type: sequence
|
| 38 |
+
use_poi_pca: true
|
| 39 |
+
poi_pca_n_components: 44
|
| 40 |
+
use_ligase_pca: true
|
| 41 |
+
ligase_pca_n_components: 7
|
| 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
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=13_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bfd8212f06eac0b40bd75141766f4cb71ca35df79dd746247e9f7080ebded8af
|
| 3 |
+
size 550951
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-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 |
+
- Activity
|
| 14 |
+
normalize_labels: false
|
| 15 |
+
standardize_labels: false
|
| 16 |
+
impute_labels: false
|
| 17 |
+
fp_size: 512
|
| 18 |
+
radius: 16
|
| 19 |
+
use_fingerprints: true
|
| 20 |
+
use_descriptors: true
|
| 21 |
+
use_relevant_descriptors: false
|
| 22 |
+
selected_descriptors: null
|
| 23 |
+
use_poi_sequence_embedding: false
|
| 24 |
+
use_poi_name_embedding: false
|
| 25 |
+
use_ligase_name_embedding: false
|
| 26 |
+
use_poi_precomputed_embedding: true
|
| 27 |
+
use_ligase_precomputed_embedding: true
|
| 28 |
+
poi_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 29 |
+
poi_embeddings_format: npz
|
| 30 |
+
poi_embeddings_per_residue: false
|
| 31 |
+
poi_residue_pooling: sum
|
| 32 |
+
poi_embeddings_id_type: sequence
|
| 33 |
+
ligase_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 34 |
+
ligase_embeddings_format: npz
|
| 35 |
+
ligase_embeddings_per_residue: false
|
| 36 |
+
ligase_residue_pooling: sum
|
| 37 |
+
ligase_embeddings_id_type: sequence
|
| 38 |
+
use_poi_pca: true
|
| 39 |
+
poi_pca_n_components: 44
|
| 40 |
+
use_ligase_pca: true
|
| 41 |
+
ligase_pca_n_components: 7
|
| 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
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=14_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3bd0f744f89a44f0f5ae926e66acd2f08298ca9c0b28b951ba5441f858658d43
|
| 3 |
+
size 551015
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-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 |
+
- Activity
|
| 14 |
+
normalize_labels: false
|
| 15 |
+
standardize_labels: false
|
| 16 |
+
impute_labels: false
|
| 17 |
+
fp_size: 512
|
| 18 |
+
radius: 16
|
| 19 |
+
use_fingerprints: true
|
| 20 |
+
use_descriptors: true
|
| 21 |
+
use_relevant_descriptors: false
|
| 22 |
+
selected_descriptors: null
|
| 23 |
+
use_poi_sequence_embedding: false
|
| 24 |
+
use_poi_name_embedding: false
|
| 25 |
+
use_ligase_name_embedding: false
|
| 26 |
+
use_poi_precomputed_embedding: true
|
| 27 |
+
use_ligase_precomputed_embedding: true
|
| 28 |
+
poi_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 29 |
+
poi_embeddings_format: npz
|
| 30 |
+
poi_embeddings_per_residue: false
|
| 31 |
+
poi_residue_pooling: sum
|
| 32 |
+
poi_embeddings_id_type: sequence
|
| 33 |
+
ligase_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 34 |
+
ligase_embeddings_format: npz
|
| 35 |
+
ligase_embeddings_per_residue: false
|
| 36 |
+
ligase_residue_pooling: sum
|
| 37 |
+
ligase_embeddings_id_type: sequence
|
| 38 |
+
use_poi_pca: true
|
| 39 |
+
poi_pca_n_components: 44
|
| 40 |
+
use_ligase_pca: true
|
| 41 |
+
ligase_pca_n_components: 7
|
| 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
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=15_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:504d562821cb8d72228c3c5b5658637119d584a7eb2407373dd31de40132a78a
|
| 3 |
+
size 551335
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-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 |
+
- Activity
|
| 14 |
+
normalize_labels: false
|
| 15 |
+
standardize_labels: false
|
| 16 |
+
impute_labels: false
|
| 17 |
+
fp_size: 512
|
| 18 |
+
radius: 16
|
| 19 |
+
use_fingerprints: true
|
| 20 |
+
use_descriptors: true
|
| 21 |
+
use_relevant_descriptors: false
|
| 22 |
+
selected_descriptors: null
|
| 23 |
+
use_poi_sequence_embedding: false
|
| 24 |
+
use_poi_name_embedding: false
|
| 25 |
+
use_ligase_name_embedding: false
|
| 26 |
+
use_poi_precomputed_embedding: true
|
| 27 |
+
use_ligase_precomputed_embedding: true
|
| 28 |
+
poi_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 29 |
+
poi_embeddings_format: npz
|
| 30 |
+
poi_embeddings_per_residue: false
|
| 31 |
+
poi_residue_pooling: sum
|
| 32 |
+
poi_embeddings_id_type: sequence
|
| 33 |
+
ligase_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 34 |
+
ligase_embeddings_format: npz
|
| 35 |
+
ligase_embeddings_per_residue: false
|
| 36 |
+
ligase_residue_pooling: sum
|
| 37 |
+
ligase_embeddings_id_type: sequence
|
| 38 |
+
use_poi_pca: true
|
| 39 |
+
poi_pca_n_components: 44
|
| 40 |
+
use_ligase_pca: true
|
| 41 |
+
ligase_pca_n_components: 7
|
| 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
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=16_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd5d7dd762f313c064d77c87f35c80f213e9d8ad02c50bd2f6fed3b7ff204e10
|
| 3 |
+
size 550823
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-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 |
+
- Activity
|
| 14 |
+
normalize_labels: false
|
| 15 |
+
standardize_labels: false
|
| 16 |
+
impute_labels: false
|
| 17 |
+
fp_size: 512
|
| 18 |
+
radius: 16
|
| 19 |
+
use_fingerprints: true
|
| 20 |
+
use_descriptors: true
|
| 21 |
+
use_relevant_descriptors: false
|
| 22 |
+
selected_descriptors: null
|
| 23 |
+
use_poi_sequence_embedding: false
|
| 24 |
+
use_poi_name_embedding: false
|
| 25 |
+
use_ligase_name_embedding: false
|
| 26 |
+
use_poi_precomputed_embedding: true
|
| 27 |
+
use_ligase_precomputed_embedding: true
|
| 28 |
+
poi_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 29 |
+
poi_embeddings_format: npz
|
| 30 |
+
poi_embeddings_per_residue: false
|
| 31 |
+
poi_residue_pooling: sum
|
| 32 |
+
poi_embeddings_id_type: sequence
|
| 33 |
+
ligase_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 34 |
+
ligase_embeddings_format: npz
|
| 35 |
+
ligase_embeddings_per_residue: false
|
| 36 |
+
ligase_residue_pooling: sum
|
| 37 |
+
ligase_embeddings_id_type: sequence
|
| 38 |
+
use_poi_pca: true
|
| 39 |
+
poi_pca_n_components: 44
|
| 40 |
+
use_ligase_pca: true
|
| 41 |
+
ligase_pca_n_components: 7
|
| 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
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=17_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3137998f036a96f08272aaba02871eaf6bda1baf62bc2cc7dbeb94f99f7fa2ca
|
| 3 |
+
size 550823
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-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 |
+
- Activity
|
| 14 |
+
normalize_labels: false
|
| 15 |
+
standardize_labels: false
|
| 16 |
+
impute_labels: false
|
| 17 |
+
fp_size: 512
|
| 18 |
+
radius: 16
|
| 19 |
+
use_fingerprints: true
|
| 20 |
+
use_descriptors: true
|
| 21 |
+
use_relevant_descriptors: false
|
| 22 |
+
selected_descriptors: null
|
| 23 |
+
use_poi_sequence_embedding: false
|
| 24 |
+
use_poi_name_embedding: false
|
| 25 |
+
use_ligase_name_embedding: false
|
| 26 |
+
use_poi_precomputed_embedding: true
|
| 27 |
+
use_ligase_precomputed_embedding: true
|
| 28 |
+
poi_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 29 |
+
poi_embeddings_format: npz
|
| 30 |
+
poi_embeddings_per_residue: false
|
| 31 |
+
poi_residue_pooling: sum
|
| 32 |
+
poi_embeddings_id_type: sequence
|
| 33 |
+
ligase_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 34 |
+
ligase_embeddings_format: npz
|
| 35 |
+
ligase_embeddings_per_residue: false
|
| 36 |
+
ligase_residue_pooling: sum
|
| 37 |
+
ligase_embeddings_id_type: sequence
|
| 38 |
+
use_poi_pca: true
|
| 39 |
+
poi_pca_n_components: 44
|
| 40 |
+
use_ligase_pca: true
|
| 41 |
+
ligase_pca_n_components: 7
|
| 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
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=18_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6dccd2e95744d37d1049f46219d8ed1e8ecf41beed2e4a3655643dd3d88e49e5
|
| 3 |
+
size 551207
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-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 |
+
- Activity
|
| 14 |
+
normalize_labels: false
|
| 15 |
+
standardize_labels: false
|
| 16 |
+
impute_labels: false
|
| 17 |
+
fp_size: 512
|
| 18 |
+
radius: 16
|
| 19 |
+
use_fingerprints: true
|
| 20 |
+
use_descriptors: true
|
| 21 |
+
use_relevant_descriptors: false
|
| 22 |
+
selected_descriptors: null
|
| 23 |
+
use_poi_sequence_embedding: false
|
| 24 |
+
use_poi_name_embedding: false
|
| 25 |
+
use_ligase_name_embedding: false
|
| 26 |
+
use_poi_precomputed_embedding: true
|
| 27 |
+
use_ligase_precomputed_embedding: true
|
| 28 |
+
poi_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 29 |
+
poi_embeddings_format: npz
|
| 30 |
+
poi_embeddings_per_residue: false
|
| 31 |
+
poi_residue_pooling: sum
|
| 32 |
+
poi_embeddings_id_type: sequence
|
| 33 |
+
ligase_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 34 |
+
ligase_embeddings_format: npz
|
| 35 |
+
ligase_embeddings_per_residue: false
|
| 36 |
+
ligase_residue_pooling: sum
|
| 37 |
+
ligase_embeddings_id_type: sequence
|
| 38 |
+
use_poi_pca: true
|
| 39 |
+
poi_pca_n_components: 44
|
| 40 |
+
use_ligase_pca: true
|
| 41 |
+
ligase_pca_n_components: 7
|
| 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
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=19_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bdf573a91502e9e6993702ca67ff809ce9583fafc907487b14520f194044ce6e
|
| 3 |
+
size 551015
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-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 |
+
- Activity
|
| 14 |
+
normalize_labels: false
|
| 15 |
+
standardize_labels: false
|
| 16 |
+
impute_labels: false
|
| 17 |
+
fp_size: 512
|
| 18 |
+
radius: 16
|
| 19 |
+
use_fingerprints: true
|
| 20 |
+
use_descriptors: true
|
| 21 |
+
use_relevant_descriptors: false
|
| 22 |
+
selected_descriptors: null
|
| 23 |
+
use_poi_sequence_embedding: false
|
| 24 |
+
use_poi_name_embedding: false
|
| 25 |
+
use_ligase_name_embedding: false
|
| 26 |
+
use_poi_precomputed_embedding: true
|
| 27 |
+
use_ligase_precomputed_embedding: true
|
| 28 |
+
poi_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 29 |
+
poi_embeddings_format: npz
|
| 30 |
+
poi_embeddings_per_residue: false
|
| 31 |
+
poi_residue_pooling: sum
|
| 32 |
+
poi_embeddings_id_type: sequence
|
| 33 |
+
ligase_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 34 |
+
ligase_embeddings_format: npz
|
| 35 |
+
ligase_embeddings_per_residue: false
|
| 36 |
+
ligase_residue_pooling: sum
|
| 37 |
+
ligase_embeddings_id_type: sequence
|
| 38 |
+
use_poi_pca: true
|
| 39 |
+
poi_pca_n_components: 44
|
| 40 |
+
use_ligase_pca: true
|
| 41 |
+
ligase_pca_n_components: 7
|
| 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
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=1_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8fb685e5c85facb88c020b20a918aefcfdeb3719b1a096e824a232ecddd6d938
|
| 3 |
+
size 550945
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-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 |
+
- Activity
|
| 14 |
+
normalize_labels: false
|
| 15 |
+
standardize_labels: false
|
| 16 |
+
impute_labels: false
|
| 17 |
+
fp_size: 512
|
| 18 |
+
radius: 16
|
| 19 |
+
use_fingerprints: true
|
| 20 |
+
use_descriptors: true
|
| 21 |
+
use_relevant_descriptors: false
|
| 22 |
+
selected_descriptors: null
|
| 23 |
+
use_poi_sequence_embedding: false
|
| 24 |
+
use_poi_name_embedding: false
|
| 25 |
+
use_ligase_name_embedding: false
|
| 26 |
+
use_poi_precomputed_embedding: true
|
| 27 |
+
use_ligase_precomputed_embedding: true
|
| 28 |
+
poi_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 29 |
+
poi_embeddings_format: npz
|
| 30 |
+
poi_embeddings_per_residue: false
|
| 31 |
+
poi_residue_pooling: sum
|
| 32 |
+
poi_embeddings_id_type: sequence
|
| 33 |
+
ligase_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 34 |
+
ligase_embeddings_format: npz
|
| 35 |
+
ligase_embeddings_per_residue: false
|
| 36 |
+
ligase_residue_pooling: sum
|
| 37 |
+
ligase_embeddings_id_type: sequence
|
| 38 |
+
use_poi_pca: true
|
| 39 |
+
poi_pca_n_components: 44
|
| 40 |
+
use_ligase_pca: true
|
| 41 |
+
ligase_pca_n_components: 7
|
| 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
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=20_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8578d35c4835d889a5008060c4ed46b40c5e51e2cf9919911e1d58f8879c1f59
|
| 3 |
+
size 551079
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-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 |
+
- Activity
|
| 14 |
+
normalize_labels: false
|
| 15 |
+
standardize_labels: false
|
| 16 |
+
impute_labels: false
|
| 17 |
+
fp_size: 512
|
| 18 |
+
radius: 16
|
| 19 |
+
use_fingerprints: true
|
| 20 |
+
use_descriptors: true
|
| 21 |
+
use_relevant_descriptors: false
|
| 22 |
+
selected_descriptors: null
|
| 23 |
+
use_poi_sequence_embedding: false
|
| 24 |
+
use_poi_name_embedding: false
|
| 25 |
+
use_ligase_name_embedding: false
|
| 26 |
+
use_poi_precomputed_embedding: true
|
| 27 |
+
use_ligase_precomputed_embedding: true
|
| 28 |
+
poi_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 29 |
+
poi_embeddings_format: npz
|
| 30 |
+
poi_embeddings_per_residue: false
|
| 31 |
+
poi_residue_pooling: sum
|
| 32 |
+
poi_embeddings_id_type: sequence
|
| 33 |
+
ligase_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 34 |
+
ligase_embeddings_format: npz
|
| 35 |
+
ligase_embeddings_per_residue: false
|
| 36 |
+
ligase_residue_pooling: sum
|
| 37 |
+
ligase_embeddings_id_type: sequence
|
| 38 |
+
use_poi_pca: true
|
| 39 |
+
poi_pca_n_components: 44
|
| 40 |
+
use_ligase_pca: true
|
| 41 |
+
ligase_pca_n_components: 7
|
| 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
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=21_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e30d4b1bc8f1b3f175d5bc1a013f503ca5a32fc28bfe8a854305f254cb0806c0
|
| 3 |
+
size 550823
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-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 |
+
- Activity
|
| 14 |
+
normalize_labels: false
|
| 15 |
+
standardize_labels: false
|
| 16 |
+
impute_labels: false
|
| 17 |
+
fp_size: 512
|
| 18 |
+
radius: 16
|
| 19 |
+
use_fingerprints: true
|
| 20 |
+
use_descriptors: true
|
| 21 |
+
use_relevant_descriptors: false
|
| 22 |
+
selected_descriptors: null
|
| 23 |
+
use_poi_sequence_embedding: false
|
| 24 |
+
use_poi_name_embedding: false
|
| 25 |
+
use_ligase_name_embedding: false
|
| 26 |
+
use_poi_precomputed_embedding: true
|
| 27 |
+
use_ligase_precomputed_embedding: true
|
| 28 |
+
poi_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 29 |
+
poi_embeddings_format: npz
|
| 30 |
+
poi_embeddings_per_residue: false
|
| 31 |
+
poi_residue_pooling: sum
|
| 32 |
+
poi_embeddings_id_type: sequence
|
| 33 |
+
ligase_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 34 |
+
ligase_embeddings_format: npz
|
| 35 |
+
ligase_embeddings_per_residue: false
|
| 36 |
+
ligase_residue_pooling: sum
|
| 37 |
+
ligase_embeddings_id_type: sequence
|
| 38 |
+
use_poi_pca: true
|
| 39 |
+
poi_pca_n_components: 44
|
| 40 |
+
use_ligase_pca: true
|
| 41 |
+
ligase_pca_n_components: 7
|
| 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
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=22_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ff20a907bcbbf76d6d9da52298bca776c7732720f46e1602150f226b153d9c0
|
| 3 |
+
size 551015
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-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 |
+
- Activity
|
| 14 |
+
normalize_labels: false
|
| 15 |
+
standardize_labels: false
|
| 16 |
+
impute_labels: false
|
| 17 |
+
fp_size: 512
|
| 18 |
+
radius: 16
|
| 19 |
+
use_fingerprints: true
|
| 20 |
+
use_descriptors: true
|
| 21 |
+
use_relevant_descriptors: false
|
| 22 |
+
selected_descriptors: null
|
| 23 |
+
use_poi_sequence_embedding: false
|
| 24 |
+
use_poi_name_embedding: false
|
| 25 |
+
use_ligase_name_embedding: false
|
| 26 |
+
use_poi_precomputed_embedding: true
|
| 27 |
+
use_ligase_precomputed_embedding: true
|
| 28 |
+
poi_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 29 |
+
poi_embeddings_format: npz
|
| 30 |
+
poi_embeddings_per_residue: false
|
| 31 |
+
poi_residue_pooling: sum
|
| 32 |
+
poi_embeddings_id_type: sequence
|
| 33 |
+
ligase_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 34 |
+
ligase_embeddings_format: npz
|
| 35 |
+
ligase_embeddings_per_residue: false
|
| 36 |
+
ligase_residue_pooling: sum
|
| 37 |
+
ligase_embeddings_id_type: sequence
|
| 38 |
+
use_poi_pca: true
|
| 39 |
+
poi_pca_n_components: 44
|
| 40 |
+
use_ligase_pca: true
|
| 41 |
+
ligase_pca_n_components: 7
|
| 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
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=23_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aaef3e0c3f55f9f83127cc9934e421f9ee1f245fd6a794e63d51dbfaefe7cd6b
|
| 3 |
+
size 551335
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-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 |
+
- Activity
|
| 14 |
+
normalize_labels: false
|
| 15 |
+
standardize_labels: false
|
| 16 |
+
impute_labels: false
|
| 17 |
+
fp_size: 512
|
| 18 |
+
radius: 16
|
| 19 |
+
use_fingerprints: true
|
| 20 |
+
use_descriptors: true
|
| 21 |
+
use_relevant_descriptors: false
|
| 22 |
+
selected_descriptors: null
|
| 23 |
+
use_poi_sequence_embedding: false
|
| 24 |
+
use_poi_name_embedding: false
|
| 25 |
+
use_ligase_name_embedding: false
|
| 26 |
+
use_poi_precomputed_embedding: true
|
| 27 |
+
use_ligase_precomputed_embedding: true
|
| 28 |
+
poi_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 29 |
+
poi_embeddings_format: npz
|
| 30 |
+
poi_embeddings_per_residue: false
|
| 31 |
+
poi_residue_pooling: sum
|
| 32 |
+
poi_embeddings_id_type: sequence
|
| 33 |
+
ligase_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 34 |
+
ligase_embeddings_format: npz
|
| 35 |
+
ligase_embeddings_per_residue: false
|
| 36 |
+
ligase_residue_pooling: sum
|
| 37 |
+
ligase_embeddings_id_type: sequence
|
| 38 |
+
use_poi_pca: true
|
| 39 |
+
poi_pca_n_components: 44
|
| 40 |
+
use_ligase_pca: true
|
| 41 |
+
ligase_pca_n_components: 7
|
| 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
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=24_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2b35952471f446ceeaf335e23229d8aa2920910566dc027b84c8e72956e87ab
|
| 3 |
+
size 550503
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-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 |
+
- Activity
|
| 14 |
+
normalize_labels: false
|
| 15 |
+
standardize_labels: false
|
| 16 |
+
impute_labels: false
|
| 17 |
+
fp_size: 512
|
| 18 |
+
radius: 16
|
| 19 |
+
use_fingerprints: true
|
| 20 |
+
use_descriptors: true
|
| 21 |
+
use_relevant_descriptors: false
|
| 22 |
+
selected_descriptors: null
|
| 23 |
+
use_poi_sequence_embedding: false
|
| 24 |
+
use_poi_name_embedding: false
|
| 25 |
+
use_ligase_name_embedding: false
|
| 26 |
+
use_poi_precomputed_embedding: true
|
| 27 |
+
use_ligase_precomputed_embedding: true
|
| 28 |
+
poi_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 29 |
+
poi_embeddings_format: npz
|
| 30 |
+
poi_embeddings_per_residue: false
|
| 31 |
+
poi_residue_pooling: sum
|
| 32 |
+
poi_embeddings_id_type: sequence
|
| 33 |
+
ligase_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 34 |
+
ligase_embeddings_format: npz
|
| 35 |
+
ligase_embeddings_per_residue: false
|
| 36 |
+
ligase_residue_pooling: sum
|
| 37 |
+
ligase_embeddings_id_type: sequence
|
| 38 |
+
use_poi_pca: true
|
| 39 |
+
poi_pca_n_components: 44
|
| 40 |
+
use_ligase_pca: true
|
| 41 |
+
ligase_pca_n_components: 7
|
| 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
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=2_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0494ca5b6b39c0b22ba9121ea2048856720254069ec0fefb50d2dc0acb5917f
|
| 3 |
+
size 551201
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-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 |
+
- Activity
|
| 14 |
+
normalize_labels: false
|
| 15 |
+
standardize_labels: false
|
| 16 |
+
impute_labels: false
|
| 17 |
+
fp_size: 512
|
| 18 |
+
radius: 16
|
| 19 |
+
use_fingerprints: true
|
| 20 |
+
use_descriptors: true
|
| 21 |
+
use_relevant_descriptors: false
|
| 22 |
+
selected_descriptors: null
|
| 23 |
+
use_poi_sequence_embedding: false
|
| 24 |
+
use_poi_name_embedding: false
|
| 25 |
+
use_ligase_name_embedding: false
|
| 26 |
+
use_poi_precomputed_embedding: true
|
| 27 |
+
use_ligase_precomputed_embedding: true
|
| 28 |
+
poi_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 29 |
+
poi_embeddings_format: npz
|
| 30 |
+
poi_embeddings_per_residue: false
|
| 31 |
+
poi_residue_pooling: sum
|
| 32 |
+
poi_embeddings_id_type: sequence
|
| 33 |
+
ligase_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 34 |
+
ligase_embeddings_format: npz
|
| 35 |
+
ligase_embeddings_per_residue: false
|
| 36 |
+
ligase_residue_pooling: sum
|
| 37 |
+
ligase_embeddings_id_type: sequence
|
| 38 |
+
use_poi_pca: true
|
| 39 |
+
poi_pca_n_components: 44
|
| 40 |
+
use_ligase_pca: true
|
| 41 |
+
ligase_pca_n_components: 7
|
| 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
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=3_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b474aac81ffbd25d351c168e3dec9b0cabfc09bebf56a5b0f3bc417da1ad0487
|
| 3 |
+
size 551073
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-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 |
+
- Activity
|
| 14 |
+
normalize_labels: false
|
| 15 |
+
standardize_labels: false
|
| 16 |
+
impute_labels: false
|
| 17 |
+
fp_size: 512
|
| 18 |
+
radius: 16
|
| 19 |
+
use_fingerprints: true
|
| 20 |
+
use_descriptors: true
|
| 21 |
+
use_relevant_descriptors: false
|
| 22 |
+
selected_descriptors: null
|
| 23 |
+
use_poi_sequence_embedding: false
|
| 24 |
+
use_poi_name_embedding: false
|
| 25 |
+
use_ligase_name_embedding: false
|
| 26 |
+
use_poi_precomputed_embedding: true
|
| 27 |
+
use_ligase_precomputed_embedding: true
|
| 28 |
+
poi_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 29 |
+
poi_embeddings_format: npz
|
| 30 |
+
poi_embeddings_per_residue: false
|
| 31 |
+
poi_residue_pooling: sum
|
| 32 |
+
poi_embeddings_id_type: sequence
|
| 33 |
+
ligase_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 34 |
+
ligase_embeddings_format: npz
|
| 35 |
+
ligase_embeddings_per_residue: false
|
| 36 |
+
ligase_residue_pooling: sum
|
| 37 |
+
ligase_embeddings_id_type: sequence
|
| 38 |
+
use_poi_pca: true
|
| 39 |
+
poi_pca_n_components: 44
|
| 40 |
+
use_ligase_pca: true
|
| 41 |
+
ligase_pca_n_components: 7
|
| 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
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=4_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b489ce8c7d489d1b80e73851aea16dd9b9bfc3aed7d2b5022ba422db6d9169d5
|
| 3 |
+
size 551073
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-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 |
+
- Activity
|
| 14 |
+
normalize_labels: false
|
| 15 |
+
standardize_labels: false
|
| 16 |
+
impute_labels: false
|
| 17 |
+
fp_size: 512
|
| 18 |
+
radius: 16
|
| 19 |
+
use_fingerprints: true
|
| 20 |
+
use_descriptors: true
|
| 21 |
+
use_relevant_descriptors: false
|
| 22 |
+
selected_descriptors: null
|
| 23 |
+
use_poi_sequence_embedding: false
|
| 24 |
+
use_poi_name_embedding: false
|
| 25 |
+
use_ligase_name_embedding: false
|
| 26 |
+
use_poi_precomputed_embedding: true
|
| 27 |
+
use_ligase_precomputed_embedding: true
|
| 28 |
+
poi_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 29 |
+
poi_embeddings_format: npz
|
| 30 |
+
poi_embeddings_per_residue: false
|
| 31 |
+
poi_residue_pooling: sum
|
| 32 |
+
poi_embeddings_id_type: sequence
|
| 33 |
+
ligase_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 34 |
+
ligase_embeddings_format: npz
|
| 35 |
+
ligase_embeddings_per_residue: false
|
| 36 |
+
ligase_residue_pooling: sum
|
| 37 |
+
ligase_embeddings_id_type: sequence
|
| 38 |
+
use_poi_pca: true
|
| 39 |
+
poi_pca_n_components: 44
|
| 40 |
+
use_ligase_pca: true
|
| 41 |
+
ligase_pca_n_components: 7
|
| 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
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=5_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:87f365f7813f6a7025104e6b407477354ee1af8ee5d9875af104337bcf801a9e
|
| 3 |
+
size 550753
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-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 |
+
- Activity
|
| 14 |
+
normalize_labels: false
|
| 15 |
+
standardize_labels: false
|
| 16 |
+
impute_labels: false
|
| 17 |
+
fp_size: 512
|
| 18 |
+
radius: 16
|
| 19 |
+
use_fingerprints: true
|
| 20 |
+
use_descriptors: true
|
| 21 |
+
use_relevant_descriptors: false
|
| 22 |
+
selected_descriptors: null
|
| 23 |
+
use_poi_sequence_embedding: false
|
| 24 |
+
use_poi_name_embedding: false
|
| 25 |
+
use_ligase_name_embedding: false
|
| 26 |
+
use_poi_precomputed_embedding: true
|
| 27 |
+
use_ligase_precomputed_embedding: true
|
| 28 |
+
poi_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 29 |
+
poi_embeddings_format: npz
|
| 30 |
+
poi_embeddings_per_residue: false
|
| 31 |
+
poi_residue_pooling: sum
|
| 32 |
+
poi_embeddings_id_type: sequence
|
| 33 |
+
ligase_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 34 |
+
ligase_embeddings_format: npz
|
| 35 |
+
ligase_embeddings_per_residue: false
|
| 36 |
+
ligase_residue_pooling: sum
|
| 37 |
+
ligase_embeddings_id_type: sequence
|
| 38 |
+
use_poi_pca: true
|
| 39 |
+
poi_pca_n_components: 44
|
| 40 |
+
use_ligase_pca: true
|
| 41 |
+
ligase_pca_n_components: 7
|
| 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
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=6_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bd34bddc338d2b9e7018d221d5258490358ed624af7f9b9b7890ae10d9327017
|
| 3 |
+
size 551137
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-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 |
+
- Activity
|
| 14 |
+
normalize_labels: false
|
| 15 |
+
standardize_labels: false
|
| 16 |
+
impute_labels: false
|
| 17 |
+
fp_size: 512
|
| 18 |
+
radius: 16
|
| 19 |
+
use_fingerprints: true
|
| 20 |
+
use_descriptors: true
|
| 21 |
+
use_relevant_descriptors: false
|
| 22 |
+
selected_descriptors: null
|
| 23 |
+
use_poi_sequence_embedding: false
|
| 24 |
+
use_poi_name_embedding: false
|
| 25 |
+
use_ligase_name_embedding: false
|
| 26 |
+
use_poi_precomputed_embedding: true
|
| 27 |
+
use_ligase_precomputed_embedding: true
|
| 28 |
+
poi_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 29 |
+
poi_embeddings_format: npz
|
| 30 |
+
poi_embeddings_per_residue: false
|
| 31 |
+
poi_residue_pooling: sum
|
| 32 |
+
poi_embeddings_id_type: sequence
|
| 33 |
+
ligase_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 34 |
+
ligase_embeddings_format: npz
|
| 35 |
+
ligase_embeddings_per_residue: false
|
| 36 |
+
ligase_residue_pooling: sum
|
| 37 |
+
ligase_embeddings_id_type: sequence
|
| 38 |
+
use_poi_pca: true
|
| 39 |
+
poi_pca_n_components: 44
|
| 40 |
+
use_ligase_pca: true
|
| 41 |
+
ligase_pca_n_components: 7
|
| 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
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=7_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:001ec3502fa1310eedd8718aa802d8dcce654e7e530fc291058456d31e68ca08
|
| 3 |
+
size 550561
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-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 |
+
- Activity
|
| 14 |
+
normalize_labels: false
|
| 15 |
+
standardize_labels: false
|
| 16 |
+
impute_labels: false
|
| 17 |
+
fp_size: 512
|
| 18 |
+
radius: 16
|
| 19 |
+
use_fingerprints: true
|
| 20 |
+
use_descriptors: true
|
| 21 |
+
use_relevant_descriptors: false
|
| 22 |
+
selected_descriptors: null
|
| 23 |
+
use_poi_sequence_embedding: false
|
| 24 |
+
use_poi_name_embedding: false
|
| 25 |
+
use_ligase_name_embedding: false
|
| 26 |
+
use_poi_precomputed_embedding: true
|
| 27 |
+
use_ligase_precomputed_embedding: true
|
| 28 |
+
poi_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 29 |
+
poi_embeddings_format: npz
|
| 30 |
+
poi_embeddings_per_residue: false
|
| 31 |
+
poi_residue_pooling: sum
|
| 32 |
+
poi_embeddings_id_type: sequence
|
| 33 |
+
ligase_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 34 |
+
ligase_embeddings_format: npz
|
| 35 |
+
ligase_embeddings_per_residue: false
|
| 36 |
+
ligase_residue_pooling: sum
|
| 37 |
+
ligase_embeddings_id_type: sequence
|
| 38 |
+
use_poi_pca: true
|
| 39 |
+
poi_pca_n_components: 44
|
| 40 |
+
use_ligase_pca: true
|
| 41 |
+
ligase_pca_n_components: 7
|
| 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
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-group=scaffold-fold=8_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92ed3a789e2ffb59280f92e4d1094f459d325e5e7af058b9e1bb72e254a3f57e
|
| 3 |
+
size 550945
|
bin_best_arch_ensemble/datamodule-data=fp512r16_all_desc_poi_emb_lig_emb_cell_text_assay_time_poi_pca44_lig_pca7_labels_Activity-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 |
+
- Activity
|
| 14 |
+
normalize_labels: false
|
| 15 |
+
standardize_labels: false
|
| 16 |
+
impute_labels: false
|
| 17 |
+
fp_size: 512
|
| 18 |
+
radius: 16
|
| 19 |
+
use_fingerprints: true
|
| 20 |
+
use_descriptors: true
|
| 21 |
+
use_relevant_descriptors: false
|
| 22 |
+
selected_descriptors: null
|
| 23 |
+
use_poi_sequence_embedding: false
|
| 24 |
+
use_poi_name_embedding: false
|
| 25 |
+
use_ligase_name_embedding: false
|
| 26 |
+
use_poi_precomputed_embedding: true
|
| 27 |
+
use_ligase_precomputed_embedding: true
|
| 28 |
+
poi_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 29 |
+
poi_embeddings_format: npz
|
| 30 |
+
poi_embeddings_per_residue: false
|
| 31 |
+
poi_residue_pooling: sum
|
| 32 |
+
poi_embeddings_id_type: sequence
|
| 33 |
+
ligase_embeddings_file: /cephyr/users/ribes/Alvis/mimer/stefano/TACK/data/tack/embeddings.npz
|
| 34 |
+
ligase_embeddings_format: npz
|
| 35 |
+
ligase_embeddings_per_residue: false
|
| 36 |
+
ligase_residue_pooling: sum
|
| 37 |
+
ligase_embeddings_id_type: sequence
|
| 38 |
+
use_poi_pca: true
|
| 39 |
+
poi_pca_n_components: 44
|
| 40 |
+
use_ligase_pca: true
|
| 41 |
+
ligase_pca_n_components: 7
|
| 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
|