o RŀgM(@shdZddlmZddlmZddlmZddZGdddeZGd d d Z Gd d d Z d dZ dS)aASTRAL RAF (Rapid Access Format) Sequence Maps. The ASTRAL RAF Sequence Maps record the relationship between the PDB SEQRES records (representing the sequence of the molecule used in an experiment) to the ATOM records (representing the atoms experimentally observed). This data is derived from the Protein Data Bank CIF files. Known errors in the CIF files are corrected manually, with the original PDB file serving as the final arbiter in case of discrepancies. Residues are referenced by residue ID. This consists of a the PDB residue sequence number (up to 4 digits) and an optional PDB insertion code (an ascii alphabetic character, a-z, A-Z). e.g. "1", "10A", "1010b", "-1" See "ASTRAL RAF Sequence Maps":http://astral.stanford.edu/raf.html Dictionary `protein_letters_3to1_extended` provides a mapping from the 3-letter amino acid codes found in PDB files to 1-letter codes. The 3-letter codes include chemically modified residues. )copy)protein_letters_3to1_extended)ResiduescCs|dkrdS|S)zConvert RAF one-letter amino acid codes into IUPAC standard codes. Letters are uppercased, and "." ("Unknown") is converted to "X". .X)upper)one_letter_coder @/var/www/html/myenv/lib/python3.10/site-packages/Bio/SCOP/Raf.pynormalize_letters!sr c@s(eZdZdZddZddZddZdS) SeqMapIndexaIAn RAF file index. The RAF file itself is about 50 MB. This index provides rapid, random access of RAF records without having to load the entire file into memory. The index key is a concatenation of the PDB ID and chain ID. e.g "2drcA", ``"155c_"``. RAF uses an underscore to indicate blank chain IDs. cCszt|||_t|j&}d} |}|sn|dd}|dur&|||<|}qWddS1s6wYdS)zfInitialize the RAF file index. Arguments: - filename -- The file to index rTN)dict__init__filenameopenreadlinetell)selfrfpositionlinekeyr r r r7s   "zSeqMapIndex.__init__cCsVt||}t|j}|||}t|}Wd|S1s$wY|S)z%Return an item from the indexed file.N)r __getitem__rrseekrSeqMap)rrrrrrecordr r r rLs     zSeqMapIndex.__getitem__c Cst|tr t|}|j}|j}|sd}d}|D]J}|d}|dvr#d}||}||}d} t|j} |dr@t||d|} |drPt||d|d} || | }|dur]|}q||7}q|S)zGet the sequence map for a collection of residues. Arguments: - residues -- A Residues instance, or a string that can be converted into a Residues instance. ))_rNr)r- rr) isinstancestrrpdbid fragmentslenresintindex) rresiduesr%fragsseqMapfragchainididsmstartendr r r getSeqMapVs0    zSeqMapIndex.getSeqMapN)__name__ __module__ __qualname____doc__rrr4r r r r r ,s   r c@s\eZdZdZdddZddZddd Zd d Zd d ZddZ ddZ ddZ ddZ dS)raAn ASTRAL RAF (Rapid Access Format) Sequence Map. This is a list like object; You can find the location of particular residues with index(), slice this SeqMap into fragments, and glue fragments back together with extend(). Attributes: - pdbid -- The PDB 4 character ID - pdb_datestamp -- From the PDB file - version -- The RAF format version. e.g. 0.01 - flags -- RAF flags. (See release notes for more information.) - res -- A list of Res objects, one for each residue in this sequence map NcCs4d|_d|_d|_d|_g|_|r||dSdSzInitialize the class.rN)r% pdb_datestampversionflagsr(_process)rrr r r rszSeqMap.__init__cCsd}|}t||krtd||dd|_|dd}|dd|_|jdkr7|jd kr7td |j|d d |_|d d|_t|t|dD]?}|||d}t|dkretd|dt}||_ |dd |_ t |dd|_ t |dd|_|j|qMdS)z2Parse a RAF record into a SeqMap object (PRIVATE).&zIncomplete header: rr  z0.01z0.02zIncompatible RAF version: zCorrupt Field: ()N)rstripr' ValueErrorr%r;r:r<rangeResr/stripresidr atomseqresr(append)rr header_lenr/irrr r r r=s,    zSeqMap._processrcCsLtt|jD]}|j|j|kr|j|j|kr|Sqtd||)z?Return the index of the SeqMap for the given resid and chainid.zNo such residue )rJr'r(rMr/KeyError)rrMr/rRr r r r*s  z SeqMap.indexcCs&t|tstt|}|j||_|S)z,Extract a single Res object from the SeqMap.)r#sliceNotImplementedErrorrr()rr*sr r r rs  zSeqMap.__getitem__cCs|j|dS)zs    U$