o Rŀge @s<dZddlZddlmZddlmZddlmZddlmZddlmZdZ e d Z d Z e e Z e e Ze d Ze d Ze d Zdefdefdefdefdefdefdefdefdefdefd ZdZdZdZdZd(ddZddZd d!ZGd"d#d#ZGd$d%d%eZed&krdd'l m!Z!e!dSdS))a(Bio.SearchIO support for Bill Pearson's FASTA tools. This module adds support for parsing FASTA outputs. FASTA is a suite of programs that finds regions of local or global similarity between protein or nucleotide sequences, either by searching databases or identifying local duplications. Bio.SearchIO.FastaIO was tested on the following FASTA flavors and versions: - flavors: fasta, ssearch, tfastx - versions: 35, 36 Other flavors and/or versions may introduce some bugs. Please file a bug report if you see such problems to Biopython's bug tracker. More information on FASTA are available through these links: - Website: http://fasta.bioch.virginia.edu/fasta_www2/fasta_list2.shtml - User guide: http://fasta.bioch.virginia.edu/fasta_www2/fasta_guide.pdf Supported Formats ================= Bio.SearchIO.FastaIO supports parsing and indexing FASTA outputs triggered by the -m 10 flag. Other formats that mimic other programs (e.g. the BLAST tabular format using the -m 8 flag) may be parseable but using SearchIO's other parsers (in this case, using the 'blast-tab' parser). fasta-m10 ========= Note that in FASTA -m 10 outputs, HSPs from different strands are considered to be from different hits. They are listed as two separate entries in the hit table. FastaIO recognizes this and will group HSPs with the same hit ID into a single Hit object, regardless of strand. FASTA also sometimes output extra sequences adjacent to the HSP match. These extra sequences are discarded by FastaIO. Only regions containing the actual sequence match are extracted. The following object attributes are provided: +-----------------+-------------------------+----------------------------------+ | Object | Attribute | Value | +=================+=========================+==================================+ | QueryResult | description | query sequence description | | +-------------------------+----------------------------------+ | | id | query sequence ID | | +-------------------------+----------------------------------+ | | program | FASTA flavor | | +-------------------------+----------------------------------+ | | seq_len | full length of query sequence | | +-------------------------+----------------------------------+ | | target | target search database | | +-------------------------+----------------------------------+ | | version | FASTA version | +-----------------+-------------------------+----------------------------------+ | Hit | seq_len | full length of the hit sequence | +-----------------+-------------------------+----------------------------------+ | HSP | bitscore | \*_bits line | | +-------------------------+----------------------------------+ | | evalue | \*_expect line | | +-------------------------+----------------------------------+ | | ident_pct | \*_ident line | | +-------------------------+----------------------------------+ | | init1_score | \*_init1 line | | +-------------------------+----------------------------------+ | | initn_score | \*_initn line | | +-------------------------+----------------------------------+ | | opt_score | \*_opt line, \*_s-w opt line | | +-------------------------+----------------------------------+ | | pos_pct | \*_sim line | | +-------------------------+----------------------------------+ | | sw_score | \*_score line | | +-------------------------+----------------------------------+ | | z_score | \*_z-score line | +-----------------+-------------------------+----------------------------------+ | HSPFragment | aln_annotation | al_cons block, if present | | (also via HSP) +-------------------------+----------------------------------+ | | hit | hit sequence | | +-------------------------+----------------------------------+ | | hit_end | hit sequence end coordinate | | +-------------------------+----------------------------------+ | | hit_start | hit sequence start coordinate | | +-------------------------+----------------------------------+ | | hit_strand | hit sequence strand | | +-------------------------+----------------------------------+ | | query | query sequence | | +-------------------------+----------------------------------+ | | query_end | query sequence end coordinate | | +-------------------------+----------------------------------+ | | query_start | query sequence start coordinate | | +-------------------------+----------------------------------+ | | query_strand | query sequence strand | +-----------------+-------------------------+----------------------------------+ N) SearchIndexer)Hit)HSP) HSPFragment) QueryResult)FastaM10ParserFastaM10Indexerz2t?fast[afmsxy]|pr[sf][sx]|lalign|[gs]?[glso]searchz'>>>(.+?)\s+(.*?) *- (\d+) (?:aa|nt)\s*$z^; [a-z]+(_[ \w-]+):\s+(.*)$z^-*z-*$ initn_score init1_score opt_scorez_scorebitscoreevaluesw_score ident_pctpos_pct) _initn_init1_optz_s-w optz_z-score_bits_expect_score_ident_simcCsP|D]#}|dd\}}||vr%t||j}t|g}t|g}||q|S)z;Append Hits without alignments into QueryResults (PRIVATE). r)splitridrrappend)qresulthit_rowshit_rowhit_id remainderfraghsphitrrH/var/www/html/myenv/lib/python3.10/site-packages/Bio/SearchIO/FastaIO.py_set_qresult_hitss    r+c Cs d}dD]@}d|vrD||}t|\}}ttt|dd}ttt|dd}||}|||}|d||||d<qt|ddt|ddkritdt|ddt|ddfd|jvr|jd|d |jd<t|jdt|ddksJ|dd |dd ksJ|dd } | d krd nd } t |j d| dD]]}t ||d}t ||d} t |j |dt || dt |j |dt || t |j |||d| d kr|| krt |j |ddqt |j |ddqt |j |ddqd S)aSet HSPs sequences (PRIVATE). :param hsp: HSP whose properties will be set :type hsp: HSP :param parsed: parsed values of the HSP attributes :type parsed: dictionary {string: object} :param program: program name :type program: string r)r)querytfastseqr,r)zLength mismatch: %r %r similarityN_typeDDNAprotein molecule_type_start_stopr_end_strand)_get_aln_slice_coordslenresearch _RE_START_EXCgroup _RE_END_EXC ValueErroraln_annotationsetattrfragmentintminmax) r(parsedprogramstartseq_typepseqstop start_adjstop_adjtype_valr4endrrr* _set_hsp_seqssH     "  rRcCs|d}|d}t|d}t|d}t|d}||kr*||}||d}n ||}||d}||d7}d|krI||krI|t|ksStd||||f||fS) a)Get HSPs sequences (PRIVATE). To get the actual pairwise alignment sequences, we must first translate the un-gapped sequence based coordinates into positions in the gapped sequence (which may have a flanking region shown using leading - characters). To date, I have never seen any trailing flanking region shown in the m10 file, but the following code should also cope with that. Note that this code seems to work fine even when the "sq_offset" entries are present as a result of using the -X command line option. r.-_display_startr5r6rrz.Problem with sequence start/stop, %s[%i:%i] %s)striprEcountr;rA) parsed_hspr. seq_stripped disp_startrJrMrrr*r:s$      r:c@sBeZdZdZdddZddZddZd d Zd d Zd dZ dS)rz5Parser for Bill Pearson's FASTA suite's -m 10 output.FcCs||_||_dSzInitialize the class.N)handle_parse_preamble _preamble)selfr[ _FastaM10Parser__parse_hit_tablerrr*__init__szFastaM10Parser.__init__ccs"|D] }|j|_|VqdS)z8Iterate over FastaM10Parser object yields query results.N)_parse_qresult description)r^r"rrr*__iter__s  zFastaM10Parser.__iter__cCshi} |j}|drn!|dr|dd|d<ntt|}|r.|d|d<q||_ |S) z@Parse the Fasta preamble for Fasta flavor and version (PRIVATE).TQueryz versionrrversionrrI) r[readline startswithrr<match _RE_FLAVSlowerr?line)r^preamblerk flav_matchrrr*r\s    zFastaM10Parser._parse_preamblecCs4g} |j}|r|rn|dq||_|S)zParse hit table rows.T)r[rfrUr!rk)r^r#rkrrr*__parse_hit_table0s   z FastaM10Parser.__parse_hit_tableccs d}g}d}d}d}d}|j} |dr|}n'|dks!|s$|}n|d s0d |vr0|}n|d r>|d kr>|}nd}|dur||krS|}|j}n||kr^t||Vn||kr|durlt||Vtt |} | d} | d} | d } t | d }t | |_ |j}d d|dDd|_| dur| |_|jD] \} }t|| |q|j}nN||kr|dd|jsJ||| D],\}}|j|_|j|_|j|vr||q|jD]}||jksJ||j|qq|j}n|j}q||_dS)zParse query result (PRIVATE).NrrTzThe best scores are:>>>///>>>>>><<psz1FastaM10Parser._parse_qresult..r)rkrgrUr_r[rfr+r<r=_RE_ID_DESC_SEQLENr?rrEseq_lenrtargetrbr]itemsrCr _parse_hitquery_descriptionr!hsps query_strand)r^r"r#state_QRES_NEWstate_QRES_HITTABstate_QRES_CONTENTstate_QRES_ENDrk qres_stateregxquery_idrydesckeyvaluer)strandr(rrr*ra<sr                   DzFastaM10Parser._parse_qresultccs  |j}|dr nqt}d}g}d}d}d}d} |j|_|jdvs5|jdsrd|jvrr|tkrF|dd|7<n|tkrV|jd|d 7<t |||j d t |} || _ | | _ | |fVg}dS|dr|rt |||j d t |} || _ | | _ | |fVg}z|d dd d \} }Wnty|d dd d d} d}Ynwt| |} t| g}||t}iid}n-|drt |||j d t| |} t| g}||t}iid}n|drF|tkr'||d dd dst|d|t}d|dd<n|tkrE| |d dd ds=Jt}d|dd<n|drUt}d|jjd<n|drtt|} | d }| d }|tkr|tvrt|\}}|tur||}|dvr|d9}t|||nl|tkr||d|<n`|tkr|dkrt|} nQ||d|<nJtd|d|vsJ|tkr|dd|7<n+|tkr|dd|7<n|tkr|jjd|d 7<ntd||j}q)z(Parse hit on query identifier (PRIVATE).Tz>>N)rtrrrsr)r.r/z rIrrrrrn)r,r)z>-->z vs r,z ; al_cons;)rrd_lenzUnexpected line: %r)r[rfrg _STATE_NONErkrU_STATE_HIT_BLOCK_STATE_CONS_BLOCKrBrRr]rrbryrrArrr!_STATE_QUERY_BLOCKrDr<r=_RE_ATTRr? _HSP_ATTR_MAPstrrCrE)r^rrkstaterhsp_listr(rWhit_descryr)r%r'rnamer attr_namecasterrrr*r|s                    "                    zFastaM10Parser._parse_hitN)F) __name__ __module__ __qualname____doc__r`rcr\r_rar|rrrr*r s  Src@s,eZdZdZeZddZddZddZdS) rz>>Tr) _handleseektellrfrgr<r=_RE_ID_DESC_SEQLEN_IDXr?decoder;)r^r[ start_offset qresult_key query_markrk end_offsetrrrr*rcs0   zFastaM10Indexer.__iter__cCs|j}d}d}|d|} ||7}|}||s#||vr#nq|||} |s5 |dS||7}|}||sK||vrK |dSq.)z6Return the raw record from the file as a bytes string.rrTs>>><<< )rrrfrg)r^offsetr[ qresult_rawrrkrrr*get_raw5s.   zFastaM10Indexer.get_rawN) rrrrr_parserr`rcrrrrr*rs  r__main__) run_doctest)r)"rr<Bio.SearchIO._indexrBio.SearchIO._modelrrrr__all__compileri_PTR_ID_DESC_SEQLENrxencoderrr>r@rEfloatrrrrrr+rRr:rrr Bio._utilsrrrrr*sRd           ?"G