SYMBOL INDEX (159 symbols across 12 files)

FILE: ChatDrug/TAPE_benchmark/datasets.py
  function dataset_factory (line 16) | def dataset_factory(data_file: Union[str, Path], *args, **kwargs) -> Dat...
  function pad_sequences (line 32) | def pad_sequences(sequences: Sequence, constant_value=0, dtype=None) -> ...
  class LMDBDataset (line 51) | class LMDBDataset(Dataset):
    method __init__ (line 52) | def __init__(self, data_file, in_memory):
    method __len__ (line 67) | def __len__(self):
    method __getitem__ (line 70) | def __getitem__(self, index):
  class DataProcessor (line 83) | class DataProcessor:
    method get_train_examples (line 85) | def get_train_examples(self, data_dir):
    method get_dev_examples (line 89) | def get_dev_examples(self, data_dir):
    method get_test_examples (line 93) | def get_test_examples(self, data_dir):
    method get_labels (line 97) | def get_labels(self):
  class FluorescenceProgress (line 102) | class FluorescenceProgress(DataProcessor):
    method __init__ (line 103) | def __init__(self, tokenizer):
    method get_train_examples (line 107) | def get_train_examples(self, data_dir, in_memory=True):
    method get_dev_examples (line 111) | def get_dev_examples(self, data_dir, in_memory=True):
    method get_test_examples (line 115) | def get_test_examples(self, data_dir, data_cat, in_memory=True):
    method get_labels (line 122) | def get_labels(self):
  class SecondaryStructureProcessor3 (line 126) | class SecondaryStructureProcessor3(DataProcessor):
    method __init__ (line 127) | def __init__(self, tokenizer):
    method get_train_examples (line 131) | def get_train_examples(self, data_dir, in_memory=True):
    method get_dev_examples (line 135) | def get_dev_examples(self, data_dir, in_memory=True):
    method get_test_examples (line 139) | def get_test_examples(self, data_dir, data_cat, in_memory=True):
    method get_labels (line 143) | def get_labels(self):
  class SecondaryStructureProcessor8 (line 147) | class SecondaryStructureProcessor8(DataProcessor):
    method __init__ (line 148) | def __init__(self, tokenizer):
    method get_train_examples (line 152) | def get_train_examples(self, data_dir, in_memory=True):
    method get_dev_examples (line 156) | def get_dev_examples(self, data_dir, in_memory=True):
    method get_test_examples (line 160) | def get_test_examples(self, data_dir, data_cat, in_memory=True):
    method get_labels (line 164) | def get_labels(self):
  class ContactProgress (line 168) | class ContactProgress(DataProcessor):
    method __init__ (line 169) | def __init__(self, tokenizer):
    method get_train_examples (line 173) | def get_train_examples(self, data_dir, in_memory=True):
    method get_dev_examples (line 177) | def get_dev_examples(self, data_dir, in_memory=True):
    method get_test_examples (line 181) | def get_test_examples(self, data_dir, data_cat, in_memory=True):
    method get_labels (line 188) | def get_labels(self):
  class StabilityProgress (line 192) | class StabilityProgress(DataProcessor):
    method __init__ (line 193) | def __init__(self, tokenizer):
    method get_train_examples (line 197) | def get_train_examples(self, data_dir, in_memory=True):
    method get_dev_examples (line 201) | def get_dev_examples(self, data_dir, in_memory=True):
    method get_test_examples (line 205) | def get_test_examples(self, data_dir, data_cat, in_memory=True):
    method get_labels (line 212) | def get_labels(self):
  class RemoteHomologyProgress (line 216) | class RemoteHomologyProgress(DataProcessor):
    method __init__ (line 217) | def __init__(self, tokenizer):
    method get_train_examples (line 221) | def get_train_examples(self, data_dir, in_memory=True):
    method get_dev_examples (line 225) | def get_dev_examples(self, data_dir, in_memory=True):
    method get_test_examples (line 229) | def get_test_examples(self, data_dir, data_cat, in_memory=True):
    method get_labels (line 236) | def get_labels(self):
  class ProteinnetDataset (line 240) | class ProteinnetDataset(Dataset):
    method __init__ (line 242) | def __init__(self,
    method __len__ (line 257) | def __len__(self) -> int:
    method __getitem__ (line 260) | def __getitem__(self, index: int):
    method collate_fn (line 285) | def collate_fn(self, batch):
  class FluorescenceDataset (line 299) | class FluorescenceDataset(Dataset):
    method __init__ (line 300) | def __init__(self, file_path, split, tokenizer):
    method get_data (line 311) | def get_data(self, file):
    method __len__ (line 319) | def __len__(self):
    method __getitem__ (line 322) | def __getitem__(self, index):
    method collate_fn (line 333) | def collate_fn(self, batch):
  class StabilityDataset (line 344) | class StabilityDataset(Dataset):
    method __init__ (line 345) | def __init__(self, file_path, split, tokenizer):
    method get_data (line 356) | def get_data(self, path):
    method __getitem__ (line 364) | def __getitem__(self, index):
    method __len__ (line 375) | def __len__(self):
    method collate_fn (line 378) | def collate_fn(self, batch):
  class RemoteHomologyDataset (line 389) | class RemoteHomologyDataset(Dataset):
    method __init__ (line 390) | def __init__(self, file_path, split, tokenizer):
    method get_data (line 404) | def get_data(self, file):
    method __len__ (line 412) | def __len__(self):
    method __getitem__ (line 415) | def __getitem__(self, index):
    method collate_fn (line 426) | def collate_fn(self, batch):
  class SecondaryStructureDataset3 (line 437) | class SecondaryStructureDataset3(Dataset):
    method __init__ (line 438) | def __init__(
    method __len__ (line 455) | def __len__(self):
    method __getitem__ (line 458) | def __getitem__(self, index: int):
    method collate_fn (line 473) | def collate_fn(self, batch):
  class SecondaryStructureDataset8 (line 486) | class SecondaryStructureDataset8(Dataset):
    method __init__ (line 487) | def __init__(
    method __len__ (line 502) | def __len__(self):
    method __getitem__ (line 505) | def __getitem__(self, index: int):
    method collate_fn (line 520) | def collate_fn(self, batch):

FILE: ChatDrug/TAPE_benchmark/metrics.py
  function accuracy_score_remote (line 10) | def accuracy_score_remote(y_true, y_pred):
  function spearmanr (line 22) | def spearmanr(target: Sequence[float],
  function compute_accuracy_metrics (line 29) | def compute_accuracy_metrics(task_name, preds, labels):
  function compute_spearmanr_metrics (line 38) | def compute_spearmanr_metrics(task_name, preds, labels):
  function simple_accuracy (line 48) | def simple_accuracy(preds, labels):
  function bt_compute_metrics (line 52) | def bt_compute_metrics(task_name, preds, labels):
  function build_compute_metrics_fn (line 62) | def build_compute_metrics_fn(task_name: str, output_type: str) -> Callab...

FILE: ChatDrug/TAPE_benchmark/models.py
  class PairwiseContactPredictionHead (line 9) | class PairwiseContactPredictionHead(nn.Module):
    method __init__ (line 11) | def __init__(self, hidden_size: int, ignore_index=-100):
    method forward (line 17) | def forward(self, inputs, sequence_lengths, targets=None):
    method compute_precision_at_l5 (line 37) | def compute_precision_at_l5(self, sequence_lengths, prediction, labels):
  class BertForOntoProteinContactPrediction (line 56) | class BertForOntoProteinContactPrediction(BertPreTrainedModel):
    method __init__ (line 57) | def __init__(self, config, mean_output):
    method forward (line 68) | def forward(self, input_ids, protein_length, attention_mask=None, labe...
  class BertForSequenceClassification2 (line 83) | class BertForSequenceClassification2(BertPreTrainedModel):
    method __init__ (line 84) | def __init__(self, config, mean_output):
    method forward (line 95) | def forward(
  function load_adam_optimizer_and_scheduler (line 169) | def load_adam_optimizer_and_scheduler(model, args, train_dataset):
  class BertForTokenClassification2 (line 179) | class BertForTokenClassification2(BertPreTrainedModel):
    method __init__ (line 180) | def __init__(self, config, mean_output):
    method forward (line 189) | def forward(

FILE: ChatDrug/TAPE_benchmark/trainer.py
  class OntoProteinTrainer (line 15) | class OntoProteinTrainer(Trainer):
    method prediction_step (line 17) | def prediction_step(
    method prediction_loop (line 58) | def prediction_loop(self, dataloader: DataLoader, description: str, pr...
    method evaluation_loop (line 145) | def evaluation_loop(

FILE: ChatDrug/task_and_evaluation/Conversational_LLMs_utils.py
  function complete (line 9) | def complete(messages, model, tokenizer, conversational_LLM, drug_type, ...
  function complete_chatgpt (line 27) | def complete_chatgpt(messages):
  function complete_galactica_molecule (line 55) | def complete_galactica_molecule(
  function complete_galactica_peptide (line 94) | def complete_galactica_peptide(
  function complete_galactica_protein (line 133) | def complete_galactica_protein(
  function format_tokens (line 179) | def format_tokens(dialogs, tokenizer):
  function complete_llama (line 228) | def complete_llama(

FILE: ChatDrug/task_and_evaluation/__init__.py
  function task_to_drug (line 7) | def task_to_drug(task):
  function get_task_specification_dict (line 18) | def get_task_specification_dict(task):
  function parse (line 29) | def parse(task, input_drug, generated_text, addition_drug=None):
  function evaluate (line 40) | def evaluate(input_drug, generated_drug, task, constraint, threshold_dict):

FILE: ChatDrug/task_and_evaluation/peptide_editing.py
  function parse_peptide (line 56) | def parse_peptide(input_peptide, raw_text, retrieval_sequence):
  function evaluate_peptide (line 77) | def evaluate_peptide(input_peptide_sequence_list, output_peptide_sequenc...
  function load_allele2protein_sequence (line 91) | def load_allele2protein_sequence(file_path):
  function load_selected_allele_list (line 105) | def load_selected_allele_list(file_path):
  function load_raw_allele2peptide (line 113) | def load_raw_allele2peptide(file_path):
  function load_processed_allele2peptide (line 125) | def load_processed_allele2peptide(file_path):

FILE: ChatDrug/task_and_evaluation/protein_editing.py
  function load_ProteinDT_model (line 11) | def load_ProteinDT_model(input_model_path, chache_dir, mean_output, num_...
  function parse_protein (line 46) | def parse_protein(input_protein, raw_text, retrieval_sequence):
  function pad_sequences (line 63) | def pad_sequences(sequences, constant_value=0, dtype=None) -> np.ndarray:
  class ProteinSecondaryStructureDataset (line 82) | class ProteinSecondaryStructureDataset(Dataset):
    method __init__ (line 83) | def __init__(self, data_path, tokenizer, target='ss3'):
    method __len__ (line 124) | def __len__(self):
    method __getitem__ (line 127) | def __getitem__(self, index: int):
    method collate_fn (line 141) | def collate_fn(self, batch):
  function tokenize_one_sequence (line 151) | def tokenize_one_sequence(tokenizer, protein_sequence):
  function tokenize_sequences (line 158) | def tokenize_sequences(tokenizer, sequence_list, labels):
  function evaluate_result (line 179) | def evaluate_result(input_protein_sequence, output_protein_sequence, lab...
  class ProteinListDataset (line 209) | class ProteinListDataset(Dataset):
    method __init__ (line 210) | def __init__(self, protein_sequence_list, tokenizer, task_id):
    method __len__ (line 216) | def __len__(self):
    method __getitem__ (line 219) | def __getitem__(self, index: int):
    method collate_fn (line 228) | def collate_fn(self, batch):
  function evaluate_pairwise_list_result (line 238) | def evaluate_pairwise_list_result(input_protein_list, output_protein_lis...
  function evaluate_fast_protein_dict (line 280) | def evaluate_fast_protein_dict(input_protein_list, task_id, device="cuda"):
  function evaluate_fast_protein (line 318) | def evaluate_fast_protein(input_protein_list, output_protein_list, task_...

FILE: ChatDrug/task_and_evaluation/small_molecule_editing.py
  function parse_molecule (line 70) | def parse_molecule(input_sequence, raw_text, retrieval_sequence):
  function evaluate_molecule (line 87) | def evaluate_molecule(input_SMILES, output_SMILES, task_id, threshold_li...

FILE: main_ChatDrug.py
  function conversation (line 13) | def conversation(messages, model, tokenizer, conversational_LLM, C, roun...
  function ReDF (line 67) | def ReDF(messages, conversational_LLM, round_index, task, drug_type, inp...
  function main (line 102) | def main(args):

FILE: main_InContext.py
  function main (line 9) | def main(args):

FILE: utils.py
  function construct_PDDS_prompt (line 15) | def construct_PDDS_prompt(task_specification_dict, input_drug, drug_type...
  function construct_PDDS_prompt_galactica (line 34) | def construct_PDDS_prompt_galactica(task_specification_dict, input_drug,...
  function construct_prompt_incontext (line 55) | def construct_prompt_incontext(task_specification_dict, input_drug, drug...
  function load_dataset (line 75) | def load_dataset(drug_type, task, task_specification_dict):
  function load_retrieval_DB (line 106) | def load_retrieval_DB(task, seed):
  function load_thredhold (line 176) | def load_thredhold(drug_type):
  function sim_molecule (line 188) | def sim_molecule(smile0, smile1):
  function sim_sequence (line 199) | def sim_sequence(task, SEQ1, SEQ2):
  function retrieve_and_feedback (line 207) | def retrieve_and_feedback(task, DB, input_drug, generated_drug, constrai...
  function retrieve_and_feedback_fast_protein (line 230) | def retrieve_and_feedback_fast_protein(task, sim_DB_dict, test_example_d...
  function generate_retrieval_dict (line 246) | def generate_retrieval_dict(task, input_drug_list, DB, saved_file):
  function fast_protein_dict (line 270) | def fast_protein_dict(task, drug_type, fast_protein, input_drug_list, re...