MCPcopy Create free account

hub / github.com/PharMolix/SToFM / functions

Functions139 in github.com/PharMolix/SToFM

Method_convert_token_to_id_with_added_voc
(self, token)
model/utils.py:18
Method_get_train_sampler
(self)
geneformer_001/geneformer/pretrainer.py:624
Method_init_weights
Initialize the weights
model/se2transformer.py:371
Method_missing_
(cls, value)
geneformer_001/geneformer/collator_for_classification.py:39
Method_missing_
(cls, value)
geneformer_001/geneformer/pretrainer.py:65
Method_prepare_batch
(self, features)
geneformer_001/geneformer/collator_for_classification.py:589
Method_prepare_batch
(self, features)
model/utils.py:33
Methodconvert_ids_to_tokens
(self,value)
geneformer_001/geneformer/pretrainer.py:124
Methodconvert_tokens_to_ids
Converts a token string (or a sequence of tokens) in a single integer id (or a sequence of ids), using the vocabulary. Args:
geneformer_001/geneformer/collator_for_classification.py:492
Methodconvert_tokens_to_ids
Converts a token string (or a sequence of tokens) in a single integer id (or a sequence of ids), using the vocabulary. Args:
geneformer_001/geneformer/pretrainer.py:565
Methodextract_embs
Extract embeddings from input data and save as results in output_directory. Parameters ---------- model_directory :
geneformer_001/geneformer/emb_extractor.py:327
Functionfilter_data_by_criteria
(example)
geneformer_001/geneformer/in_silico_perturber.py:50
Methodfilter_for_origin
(example)
geneformer_001/geneformer/in_silico_perturber.py:970
Functionfilter_states
(example)
geneformer_001/geneformer/in_silico_perturber.py:266
Methodforward
(self, hidden_states: torch.Tensor)
get_embeddings.py:56
Methodforward
( self, x: torch.Tensor, # [bs, n_node, n_node] )
model/se2transformer.py:43
Methodforward
( self, query: torch.LongTensor, # [n_node, bs, dim] key: Optional[torch.Tensor],
model/se2transformer.py:101
Methodforward
( self, input_nodes: torch.Tensor, # [n_node, bs, dim] self_attn_bias: Optional[torch.
model/se2transformer.py:238
Methodforward
( self, # input_nodes: torch.LongTensor, attn_bias: torch.Tensor, # [bs, n_head, n_nod
model/se2transformer.py:307
Methodforward
( self, token_embeddings: Optional[torch.Tensor], # [bs, n_node, dim] attn_bias: torch
model/se2transformer.py:431
Methodforward
( self, # input_nodes: torch.LongTensor, token_embeddings: Optional[torch.Tensor], # [
model/se2transformer.py:475
Functiongather_graphs
(local_rank, world_size, graphs)
model/extraction.py:14
Methodget_special_tokens_mask
Retrieves sequence ids from a token list that has no special tokens added. This method is called when adding special tokens using the
geneformer_001/geneformer/collator_for_classification.py:463
Methodget_special_tokens_mask
Retrieves sequence ids from a token list that has no special tokens added. This method is called when adding special tokens using the
geneformer_001/geneformer/pretrainer.py:531
Methodget_stats
Get stats for in silico perturbation data and save as results in output_directory. Parameters ---------- input_data_
geneformer_001/geneformer/in_silico_perturber_stats.py:602
Methodif_has_tokens_to_perturb
(example)
geneformer_001/geneformer/in_silico_perturber.py:996
Methodinit_params
(self, module: Union[nn.Linear, nn.Embedding, MultiheadAttention])
model/se2transformer.py:357
Functionload_data_debug
(data_path, spatial_path=None, emb_path=None, new_emb=False, model=None, model_input_path=None,
model/extraction.py:281
Methodmake_group_perturbation_batch
(example)
geneformer_001/geneformer/in_silico_perturber.py:1034
Functionmeasure_length
(example)
geneformer_001/geneformer/in_silico_perturber.py:94
Methodmeasure_length
(example)
geneformer_001/geneformer/tokenizer.py:227
Functionoverexpress_indices
(example)
geneformer_001/geneformer/in_silico_perturber.py:140
Functionpad_or_trunc_example
(example)
geneformer_001/geneformer/in_silico_perturber.py:356
Methodperturb_data
Perturb genes in input data and save as results in output_directory. Parameters ---------- model_directory : Path
geneformer_001/geneformer/in_silico_perturber.py:924
Functionperturb_emb_by_index
(emb, indices)
geneformer_001/geneformer/in_silico_perturber.py:126
Methodplot_embs
Plot embeddings, coloring by provided labels. Parameters ---------- embs : pandas.core.frame.DataFrame P
geneformer_001/geneformer/emb_extractor.py:365
Methodreset_output_layer_parameters
(self)
model/se2transformer.py:428
Methodtokenize_data
Tokenize .loom files in loom_data_directory and save as tokenized .dataset in output_directory. Parameters ----------
geneformer_001/geneformer/tokenizer.py:95
Methodtruncate
(example)
geneformer_001/geneformer/tokenizer.py:220
← previous101–139 of 139, ranked by callers