o RŀgR@sdZddlmZddlmZddlmZddlmZddlm Z ddlm Z dd l m Z d e d eefd d Z Gddde ZedkrNddlmZedSdS)aBio.SeqIO support for the "phd" file format. PHD files are output by PHRED and used by PHRAP and CONSED. You are expected to use this module via the Bio.SeqIO functions, under the format name "phd". See also the underlying Bio.Sequencing.Phd module. For example, using Bio.SeqIO we can read in one of the example PHRED files from the Biopython unit tests: >>> from Bio import SeqIO >>> for record in SeqIO.parse("Phd/phd1", "phd"): ... print(record.id) ... print("%s..." % record.seq[:10]) ... print("%s..." % record.letter_annotations["phred_quality"][:10]) 34_222_(80-A03-19).b.ab1 ctccgtcgga... [9, 9, 10, 19, 22, 37, 28, 28, 24, 22]... 425_103_(81-A03-19).g.ab1 cgggatccca... [14, 17, 22, 10, 10, 10, 15, 8, 8, 9]... 425_7_(71-A03-19).b.ab1 acataaatca... [10, 10, 10, 10, 8, 8, 6, 6, 6, 6]... Since PHRED files contain quality scores, you can save them as FASTQ or as QUAL files, for example using Bio.SeqIO.write(...), or simply with the format method of the SeqRecord object: >>> print(record[:50].format("fastq")) @425_7_(71-A03-19).b.ab1 acataaatcaaattactnaccaacacacaaaccngtctcgcgtagtggag + ++++))'''')(''')$!$''')''''(+.''$!$))))+)))''''''' Or, >>> print(record[:50].format("qual")) >425_7_(71-A03-19).b.ab1 10 10 10 10 8 8 6 6 6 6 8 7 6 6 6 8 3 0 3 6 6 6 8 6 6 6 6 7 10 13 6 6 3 0 3 8 8 8 8 10 8 8 8 6 6 6 6 6 6 6 Note these examples only show the first 50 bases to keep the output short. )Iterator) SeqRecord)Phd) _IOSource) _TextIOSource)SequenceWriter)_get_phred_qualitysourcereturnc cst|}|D]C}|jddd}t|j|||jd}|j|_d|jd<dd|jD|j d <z d d|jD|j d <Wn t yGYnw|VqdS) zReturn SeqRecord objects from a PHD file. Arguments: - source - input stream opened in text mode, or a path to a file This uses the Bio.Sequencing.Phd module to do the hard work. Nrr)idname descriptionDNA molecule_typecSg|]}t|dqS)rint.0siterC/var/www/html/myenv/lib/python3.10/site-packages/Bio/SeqIO/PhdIO.py Y zPhdIterator.. phred_qualitycSr)rrrrrr]r peak_location) rparse file_namesplitrseqcomments annotationssitesletter_annotations IndexError)r phd_records phd_recordr seq_recordrrr PhdIteratorBs*     r*cs2eZdZdZdeddffdd ZddZZS) PhdWriterz Class to write Phd format files.handler Ncst|dS)zInitialize the class.N)super__init__)selfr, __class__rrr.kszPhdWriter.__init__c Cs|jsJdt|}|jd}t|jt|krtd|r-t|jt|kr-tdd|vr5td|j|jdrC|j}n |jd|j}|j d| |d d d t j DD]B}d}|d krw|jd rvd |jd }n|dkr|jdr|jdd}n|j|}|s|dkr|j |d|dqa|j dt|jD]&\}}|r|j d|t||||fq|j d|t||fq|j ddS)z&Write a single Phd record to the file.z No sequence present in SeqRecordrz>Number of phd quality scores does not match length of sequencez@Number of peak location scores does not match length of sequenceNz!A quality value of None was found zBEGIN_SEQUENCE z BEGIN_COMMENT cSsg|]}|qSr)lower)rkrrrrsz*PhdWriter.write_record..trimz %s %s %.4ftrace_peak_area_ratioz.4frz:  zEND_COMMENT BEGIN_DNA z %s %i %i z%s %i zEND_DNA END_SEQUENCE )r!r r%getlen ValueErrorr startswithr r,writecleanr CKEYWORDSr#upper enumerateround) r/recordphred_qualitiespeak_locationstitleannotvalueirrrr write_recordosP      zPhdWriter.write_record)__name__ __module__ __qualname____doc__rr.rI __classcell__rrr0rr+hsr+__main__) run_doctestN)rMcollections.abcr Bio.SeqRecordrBio.Sequencingr Interfacesrrr QualityIOr r*r+rJ Bio._utilsrPrrrrs /      &8