Functions — github.com/bytedance/dplm

CodeHub MCPcopy Create free account

hub / github.com/bytedance/dplm / functions

Functions1,008 in github.com/bytedance/dplm

⨍ Functions 1,008◇ Types & classes 149↳ Endpoints 2

( self, hidden_states, attention_mask=None, head_mask=None, encoder_hi

src/byprot/models/dplm2/modules/dplm2_bit_modeling_esm.py:230

( self, hidden_states, attention_mask=None, head_mask=None, encoder_hi

src/byprot/models/dplm2/modules/dplm2_bit_modeling_esm.py:279

( self, hidden_states, attention_mask=None, head_mask=None, encoder_hi

src/byprot/models/dplm2/modules/dplm2_bit_modeling_esm.py:367

( self, input_ids: Optional[torch.Tensor] = None, attention_mask: Optional[torch.Tenso

src/byprot/models/dplm2/modules/dplm2_bit_modeling_esm.py:485

( self, input_ids=None, attention_mask=None, type_ids=None, inputs_emb

src/byprot/models/dplm2/modules/dplm2_bit_modeling_esm.py:672

( self, batch, weighting="linear", return_outputs=True, output_encoder

src/byprot/models/dplm/dplm_invfold.py:102

( self, hidden_states: torch.Tensor, attention_mask: Optional[torch.FloatTensor] = Non

src/byprot/models/dplm/modules/dplm_modeling_esm.py:21

( self, input_ids: Optional[torch.Tensor] = None, attention_mask: Optional[torch.Tenso

src/byprot/models/dplm/modules/dplm_modeling_esm.py:170

( self, hidden_states, attention_mask=None, head_mask=None, encoder_hi

src/byprot/models/dplm/modules/dplm_adapter.py:213

(self, batch, output_logits=False, **kwargs)

src/byprot/models/dplm/modules/gvp_transformer_encoder.py:26

Functionfrom_pdb_string

Takes a PDB string and constructs a Protein object. WARNING: All non-standard residue types will be converted into UNK. All non-standard at

src/byprot/datamodules/pdb_dataset/protein.py:72

Functionfrom_prediction

Assembles a protein from a prediction. Args: features: Dictionary holding model inputs. result: Dictionary holding model outputs.

src/byprot/datamodules/pdb_dataset/protein.py:276

Methodfrom_pretrained

( cls, net_name, cfg_override={}, net_override={}, from_huggingface=True )

src/byprot/models/dplm/dplm.py:60

( self, input_tokens, max_iter=None, temperature=1.0, partial_masks=No

src/byprot/models/dplm2/dplm2.py:741

( self, input_tokens, tokenizer=None, max_iter=None, temperature=None,

src/byprot/models/dplm/dplm.py:503

( self, batch, tokenizer=None, max_iter=None, temperature=None,

src/byprot/models/dplm/dplm_invfold.py:399

( self, batch, tokenizer=None, max_iter=None, temperature=None,

src/byprot/models/dplm/modules/dplm_modeling_esm.py:443

Functionget_FASTA_lines

read fasta file from filename. sequence is stored into FASTA_lines * while sequence name is stored into chainID_list. * if ter_opt >=1, only read

analysis/TMalign.cpp:738

Functionget_all_top_samples

(output_dir, csv_fname="*/*/top_sample.csv")

src/byprot/utils/protein/utils.py:138

Functionget_available_device

src/byprot/utils/protein/utils.py:101

Functionget_axial_mask

Helper to convert B x L mask of valid positions to axial mask used in row column attentions. Input: mask: B x L tensor of booleans

src/byprot/models/structok/modules/folding_utils/trunk.py:63

Methodget_codebook_entry

(self, indices, shape)

src/byprot/models/structok/modules/vqvae.py:107

Methodget_codebook_entry

(self, indices, shape)

src/byprot/models/structok/modules/vqvae.py:240

Methodget_codebook_entry

(self, indices, shape=None)

src/byprot/models/structok/modules/vqvae.py:410

Functionget_dataset_cfg

src/byprot/utils/protein/utils.py:384

Functionget_ddp_info

src/byprot/utils/protein/utils.py:272

Methodget_decoder_features

(self, struct_tokens, res_mask, unk_mask)

src/byprot/models/structok/structok_lfq.py:195

Functionget_index_embedding

Creates sine / cosine positional embeddings from a prespecified indices. Args: indices: offsets of size [..., N_edges] of type integer

src/byprot/utils/protein/utils.py:500

Methodget_metadata_lens

src/byprot/datamodules/dataset/uniref_hf.py:233

Functionget_module

(group_name, module_name)

src/byprot/utils/registry.py:14

Methodget_non_special_sym_mask

(self, output_tokens, partial_masks=None)

src/byprot/models/dplm2/modules/dplm2_modeling_esm.py:691

Functionget_pylogger

Initializes multi-GPU-friendly python command line logger.

src/byprot/utils/protein/utils.py:250

Functionget_registered_modules

src/byprot/utils/registry.py:24

Functionget_time_embedding

(timesteps, embedding_dim, max_positions=2000)

src/byprot/utils/protein/utils.py:522

Functionideal_atom_mask

Computes an ideal atom mask. `Protein.atom_mask` typically is defined according to the atoms that are reported in the PDB. This function comp

src/byprot/datamodules/pdb_dataset/protein.py:260

Functionidentity

src/byprot/datamodules/dataset/data_utils.py:379

Methodinfer_pdb

Returns the pdb (file) string from the model given an input sequence.

src/byprot/models/structok/modules/folding_utils/decoder.py:414

Methodinfer_pdb

Returns the pdb (file) string from the model given an input sequence.

src/byprot/models/structok/modules/folding_utils/esmfold.py:341

Methodinference_dir

src/byprot/utils/protein/evaluator_dplm2.py:166

Methodinit_data

(self, raw_batch)

src/byprot/models/structok/structok_lfq.py:265

Methodinit_rbuffers

analysis/TMscore.cpp:1660

Functioninstantiate_from_config2

src/byprot/utils/config.py:143

Methodis_training

src/byprot/datamodules/pdb_dataset/pdb_datamodule.py:208

analysis/TMscore.cpp:1800

analysis/TMscore.cpp:1835

Functionlddt_loss

( logits: torch.Tensor, all_atom_pred_pos: torch.Tensor, all_atom_positions: torch.Tensor, all

src/byprot/models/structok/modules/loss.py:560

Functionload_coords

Args: fpath: filepath to either pdb or cif file chain: the chain id Returns: Tuple (coords, seq) - coords

src/byprot/utils/io.py:109

Methodload_from_ckpt

(self, ckpt_path, not_load=False)

src/byprot/tasks/lm/dplm_invfold.py:114

Functionload_from_experiment

(experiment_save_dir, ckpt="best.ckpt")

src/byprot/utils/__init__.py:62

Functionload_from_pdb

(pdb_path, batch=False)

src/byprot/datamodules/pdb_dataset/pdb_datamodule.py:44

Functionlocal_seed

(seed, enable=True)

src/byprot/utils/__init__.py:399

Functionlog_hyperparameters

Controls which config parts are saved by Lightning loggers. Additionaly saves: - number of model parameters

src/byprot/utils/__init__.py:156

Methodlr_lambda

src/byprot/utils/lr_scheduler.py:101

Methodlr_lambda

src/byprot/utils/lr_scheduler.py:137

Methodlr_lambda

src/byprot/utils/lr_scheduler.py:176

src/byprot/tasks/__init__.py:129

analysis/TMalign.cpp:4686

analysis/TMscore.cpp:6762

Functionmake_atom14_dists_bounds

compute upper and lower bounds for bonds to assess violations.

src/byprot/utils/protein/residue_constants.py:1221

Functionmake_atom14_dists_bounds

compute upper and lower bounds for bonds to assess violations.

src/byprot/datamodules/pdb_dataset/residue_constants.py:1221

Functionmake_config

src/byprot/utils/config.py:38

Functionmask_fill_811

(inputs, masked_indices, mask_id)

src/byprot/models/utils.py:304

Functionmasked_msa_loss

Computes BERT-style masked MSA loss. Implements subsection 1.9.9. Args: logits: [*, N_seq, N_res, 23] predicted residue distribution

src/byprot/models/structok/modules/loss.py:1599

Functionnew_arange

Return a Tensor of `size` filled with a range function on the device of x. If size is empty, using the size of the variable x.

src/byprot/tasks/lm/dplm.py:21

Functionnew_arange

Return a Tensor of `size` filled with a range function on the device of x. If size is empty, using the size of the variable x.

src/byprot/tasks/lm/mlm.py:27

Methodon_after_backward

( self, trainer: pl.Trainer, pl_module: pl.LightningModule )

src/byprot/utils/callbacks.py:333

Methodon_after_training_step

( self, batch, batch_idx, trainer: pl.Trainer, pl_module: pl.Lightning

src/byprot/utils/callbacks.py:311

Methodon_batch_end

(self, trainer, pl_module)

src/byprot/utils/callbacks.py:154

Methodon_batch_end

Check if we should save a checkpoint after every train batch.

src/byprot/utils/callbacks.py:184

Methodon_before_optimizer_step

(self, optimizer)

src/byprot/tasks/lm/dplm.py:76

Methodon_before_optimizer_step

(self, optimizer)

src/byprot/tasks/lm/mlm.py:82

Methodon_before_optimizer_step

(self, optimizer)

src/byprot/tasks/lm/dplm2.py:81

Methodon_predict_epoch_start

src/byprot/tasks/lm/dplm_invfold.py:104

Methodon_test_epoch_end

src/byprot/tasks/__init__.py:200

Methodon_test_epoch_start

src/byprot/tasks/lm/dplm.py:162

Methodon_test_epoch_start

src/byprot/tasks/lm/mlm.py:214

Methodon_test_epoch_start

src/byprot/tasks/lm/dplm_invfold.py:94

Methodon_train_epoch_end

src/byprot/tasks/__init__.py:241

Methodon_train_start

( self, trainer: "pl.Trainer", pl_module: "pl.LightningModule" )

src/byprot/utils/callbacks.py:221

Methodon_validation_epoch_end

src/byprot/tasks/lm/dplm.py:177

Methodon_validation_epoch_end

src/byprot/tasks/lm/mlm.py:231

Methodon_validation_epoch_end

src/byprot/tasks/lm/dplm2.py:241

Methodon_validation_epoch_end

src/byprot/tasks/lm/dplm_invfold.py:380

Methodon_validation_epoch_end

src/byprot/tasks/struct_tokenizer/structok.py:201

* @brief Start a process. * * Calls do_open( @a cmd , @a mode|pstdout ). * * @param cmd a string containing a shell

analysis/TMscore.cpp:645

* @brief Start a process. * * Calls do_open( @a cmd , @a mode|pstdin ). * * @param cmd a string containing a shell c

analysis/TMscore.cpp:803

* @brief Start a process. * * Calls do_open( @a cnd , @a mode ). * * @param cmd a string containing a shell command.

analysis/TMscore.cpp:943

* @brief Start a process. * * Calls do_open( @a cmd , @a mode ). * * @param cmd a string containing a shell command

analysis/TMscore.cpp:1112

analysis/TMscore.cpp:1957

Functionpad_feats

(raw_feats, max_len, use_torch=False)

src/byprot/datamodules/pdb_dataset/utils.py:87

Functionparse_pdb_feats

Args: pdb_name: name of PDB to parse. pdb_path: path to PDB file to read. scale_factor: factor to scale atom positions.

src/byprot/datamodules/pdb_dataset/utils.py:727

Methodpbackfail

analysis/TMscore.cpp:2049

Methodpredict_epoch_end

(self, results: List[Any], log_pref=None)

src/byprot/tasks/__init__.py:212

Methodpredict_step

( self, batch: Any, batch_idx: int, dataloader_idx: int = 0 )

src/byprot/tasks/__init__.py:207

Functionprepare_data

(pdb_path, alphabet, collator, num_seqs, device)

src/byprot/utils/scaffold_utils.py:278

Functionprocess_folded_outputs

(sample_path, folded_output, true_bb_pos=None)

src/byprot/utils/protein/utils.py:624

Functionprocess_mmcif

Processes MMCIF files into usable, smaller pickles. Args: mmcif_path: Path to mmcif file to read. max_resolution: Max resolution

src/byprot/datamodules/pdb_dataset/utils.py:531

Functionprocess_pdb_file

Processes protein file into usable, smaller pickles. Args: file_path: Path to file to read. write_dir: Directory to write pickles

src/byprot/datamodules/pdb_dataset/utils.py:643

Functionprocess_trans_rot_traj

(trans_traj, rots_traj, res_mask)

src/byprot/utils/protein/all_atom.py:284

Functionprocess_trans_rot_traj

(trans_traj, rots_traj, res_mask)

src/byprot/datamodules/pdb_dataset/all_atom.py:284

← previous next →801–900 of 1,008, ranked by callers