deepfold.data.multimer.msa_pairing

Pairing logic for multimer data pipeline.

Functions

block_diag(*arrs[, pad_value])	Like scipy.linalg.block_diag but with an optional padding value.
create_paired_features(chains)	Returns the original chains with paired NUM_SEQ features.
deduplicate_unpaired_sequences(np_chains)	Removes unpaired sequences which duplicate a paired sequence.
merge_chain_features(np_chains_list, ...)	Merges features for multiple chains to single FeatureDict.
pad_features(feature, feature_name)	Add a 'padding' row at the end of the features list.
pair_sequences(examples)	Returns indices for paired MSA sequences across chains.
reorder_paired_rows(all_paired_msa_rows_dict)	Creates a list of indices of paired MSA rows across chains.