o ॵi@s`dZddlZddlZddlmZddlmZddlmZdee de fd d Z Gd d d Z dS) zA Python wrapper for Kalign.N)Sequence)logging)utils sequencesreturncCs^ddtdt|dD}g}t||D]\}}|d|d||dqd|S)z"Converts sequences to an a3m file.cSsg|]}d|qS)z sequence %d).0irrf/home/ubuntu/.local/lib/python3.10/site-packages/modelscope/models/science/unifold/msa/tools/kalign.py sz_to_a3m..r> )rangelenzipappendjoin)rnamesa3msequencenamerrr _to_a3ms  rc@s4eZdZdZdefddZdeedefddZd S) Kalignz$Python wrapper of the Kalign binary. binary_pathcCs ||_dS)zInitializes the Python Kalign wrapper. Args: binary_path: The path to the Kalign binary. Raises: RuntimeError: If Kalign binary not found within the path. N)r)selfrrrr __init__%s zKalign.__init__rrc Cstdt||D]}t|dkrtd|t|fq t}tj|d}tj|d}t |d}| t |Wdn1sGwY|j d|d |d d g}td d |t j|t jt jd}td|\} } |} td| d| dWdn1swY| rtd| d| dft | }|} Wdn1swY| WdS1swYdS)abAligns the sequences and returns the alignment in A3M string. Args: sequences: A list of query sequence strings. The sequences have to be at least 6 residues long (Kalign requires this). Note that the order in which you give the sequences might alter the output slightly as different alignment tree might get constructed. Returns: A string with the alignment in a3m format. Raises: RuntimeError: If Kalign fails. ValueError: If any of the sequences is less than 6 residues long. zAligning %d sequenceszSKalign requires all sequences to be at least 6 residues long. Got %s (%d residues).z input.fastaz output.a3mwNz-iz-oz-formatfastazLaunching subprocess "%s" )stdoutstderrz Kalign queryzKalign stdout: %s stderr: %s zutf-8z%Kalign failed stdout: %s stderr: %s )rinfor ValueErrorrtmpdir_managerospathropenwriterr subprocessPopenPIPEtiming communicatewaitdecode RuntimeErrorread) rrs query_tmp_dirinput_fasta_pathoutput_a3m_pathfcmdprocessr"r#retcoderrrr align0s^           $z Kalign.alignN)__name__ __module__ __qualname____doc__strrrr<rrrr r"s r) r@r'r+typingrabslrrrrArrrrrr s