o ॵiJ@sjdZddlZddlZddlZddlmZmZmZmZm Z ddl m Z ddl m Z dZdZGd d d ZdS) z#Library to run HHblits from Python.N)AnyListMappingOptionalSequence)logging)utilsic@seZdZdZddddddddd eed d ed eed edede dedededede de ededefddZ dede eeeffddZd S)HHBlitsz%Python wrapper of the HHblits binary.gMbP?i@BiiFN) n_cpun_itere_valuemaxseq realign_maxmaxfiltmin_prefilter_hitsall_seqsaltpz binary_path databasesrrrrrrrrrrrc Cs||_||_|jD]}t|dstd|td|q ||_||_||_||_ ||_ ||_ | |_ | |_ | |_| |_| |_dS)aInitializes the Python HHblits wrapper. Args: binary_path: The path to the HHblits executable. databases: A sequence of HHblits database paths. This should be the common prefix for the database files (i.e. up to but not including _hhm.ffindex etc.) n_cpu: The number of CPUs to give HHblits. n_iter: The number of HHblits iterations. e_value: The E-value, see HHblits docs for more details. maxseq: The maximum number of rows in an input alignment. Note that this parameter is only supported in HHBlits version 3.1 and higher. realign_max: Max number of HMM-HMM hits to realign. HHblits default: 500. maxfilt: Max number of hits allowed to pass the 2nd prefilter. HHblits default: 20000. min_prefilter_hits: Min number of hits to pass prefilter. HHblits default: 100. all_seqs: Return all sequences in the MSA / Do not filter the result MSA. HHblits default: False. alt: Show up to this many alternative alignments. p: Minimum Prob for a hit to be included in the output hhr file. HHblits default: 20. z: Hard cap on number of hits reported in the hhr file. HHblits default: 500. NB: The relevant HHblits flag is -Z not -z. Raises: RuntimeError: If HHblits binary not found within the path. z_*z"Could not find HHBlits database %sz Could not find HHBlits database N)rrglobrerror ValueErrorrrrrrrrrrrr)selfrrrrrrrrrrrrr database_pathr g/home/ubuntu/.local/lib/python3.10/site-packages/modelscope/models/science/unifold/msa/tools/hhblits.py__init__ s,-  zHHBlits.__init__input_fasta_pathreturncCs4t}tj|d}g}|jD] }|d||q|jd|dt|j d|dddt|j d t|j d t|j d t|j d t|jd t|jg}|jrS|dg7}|jr_|dt|jg7}|jtkrm|dt|jg7}|jtkr{|dt|jg7}||7}tdd|tj|tjtjd}td|\}} |} Wdn1swY| rtd| d D] } | !rt| !qtdt"d|d| dddft#| } | $} Wdn1swYWdn 1swYt%| || |j |j d}|gS)z#Queries the database using HHblits.z output.a3mz-dz-iz-cpuz-oa3mz-oz /dev/nullz-nz-ez-maxseqz -realign_maxz-maxfiltz-min_prefilter_hitsz-allz-altz-pz-ZzLaunching subprocess "%s" )stdoutstderrz HHblits queryNz%HHblits failed. HHblits stderr begin:zutf-8zHHblits stderr endz&HHblits failed stdout: %s stderr: %s i )a3moutputr'rr)&r tmpdir_managerospathjoinrappendrstrrrrrrrrrrr_HHBLITS_DEFAULT_Pr_HHBLITS_DEFAULT_Zrinfo subprocessPopenPIPEtiming communicatewaitrdecode splitlinesstrip RuntimeErroropenreaddict)rr# query_tmp_dira3m_pathdb_cmddb_pathcmdprocessr&r'retcode error_linefr( raw_outputr r r!querycs               >z HHBlits.query)__name__ __module__ __qualname____doc__r0r1r/rintfloatboolrr"rrrrJr r r r!r sR      "Cr )rNrr+r3typingrrrrrabslrr r0r1r r r r r!s