ó Y_Sc@`sëdZddlmZmZddlmZddlmZmZddlm Z m Z ddd d d d d ddddddddddd gZ de fd„ƒYZ e d8d8ƒZe deddƒƒZe deddƒƒZe dedd ƒƒZe d!ed"d#ƒƒZe d$ed%d&ƒƒZe d'ed(d)ƒƒZe d*ed+d*ƒƒZe d,ed-d,ƒƒZe d.ed/d0ƒƒZe d1d2ƒZdefd3„ƒYZd efd4„ƒYZd5„Zd6„Z d7„Z!d8S(9sê Alphabetic sequences and associated tools and data. Seq is a subclass of a python string with additional annotation and an alphabet. The characters in string must be contained in the alphabet. Various standard alphabets are provided. Classes : Alphabet -- A subset of non-null ascii characters Seq -- An alphabetic string SeqList -- A collection of Seq's Alphabets : o generic_alphabet -- A generic alphabet. Any printable ASCII character. o protein_alphabet -- IUCAP/IUB Amino Acid one letter codes. o nucleic_alphabet -- IUPAC/IUB Nucleic Acid codes 'ACGTURYSWKMBDHVN-' o dna_alphabet -- Same as nucleic_alphabet, with 'U' (Uracil) an alternative for 'T' (Thymidine). o rna_alphabet -- Same as nucleic_alphabet, with 'T' (Thymidine) an alternative for 'U' (Uracil). o reduced_nucleic_alphabet -- All ambiguous codes in 'nucleic_alphabet' are alternative to 'N' (aNy) o reduced_protein_alphabet -- All ambiguous ('BZJ') and non-canonical amino acids codes ( 'U', Selenocysteine and 'O', Pyrrolysine) in 'protein_alphabet' are alternative to 'X'. o unambiguous_dna_alphabet -- 'ACGT' o unambiguous_rna_alphabet -- 'ACGU' o unambiguous_protein_alphabet -- The twenty canonical amino acid one letter codes, in alphabetic order, 'ACDEFGHIKLMNPQRSTVWY' Amino Acid Codes: Code Alt. Meaning ----------------- A Alanine B Aspartic acid or Asparagine C Cysteine D Aspartate E Glutamate F Phenylalanine G Glycine H Histidine I Isoleucine J Leucine or Isoleucine K Lysine L Leucine M Methionine N Asparagine O Pyrrolysine P Proline Q Glutamine R Arginine S Serine T Threonine U Selenocysteine V Valine W Tryptophan Y Tyrosine Z Glutamate or Glutamine X ? any * translation stop - .~ gap Nucleotide Codes: Code Alt. Meaning ------------------------------ A Adenosine C Cytidine G Guanine T Thymidine U Uracil R G A (puRine) Y T C (pYrimidine) K G T (Ketone) M A C (aMino group) S G C (Strong interaction) W A T (Weak interaction) B G T C (not A) (B comes after A) D G A T (not C) (D comes after C) H A C T (not G) (H comes after G) V G C A (not T, not U) (V comes after U) N X? A G C T (aNy) - .~ A gap Refs: http://www.chem.qmw.ac.uk/iupac/AminoAcid/A2021.html http://www.chem.qmw.ac.uk/iubmb/misc/naseq.html Status: Beta Authors: GEC 2004,2005 i(tabsolute_importtdivision(tarrayi(targmaxtsqrt(t maketranst _as_bytestAlphabettSeqtrnatdnatproteintSeqListtgeneric_alphabettprotein_alphabettnucleic_alphabett dna_alphabett rna_alphabettreduced_nucleic_alphabettreduced_protein_alphabettunambiguous_dna_alphabettunambiguous_rna_alphabettunambiguous_protein_alphabetcB`sÎeZdZddddgZdd„Zd„Zd„Zd„Zd „Z d „Z d „Z d „Z d „Z d„Zd„Zd„Zd„Zd„Zd„Zd„Zd„Zedd„ƒZRS(spAn ordered subset of printable ascii characters. Status: Beta Authors: - GEC 2005 t_letterst _alternativest _ord_tablet _chr_tablecC`stj|ƒ}djgtddƒD]}t|ƒ^q%ƒ}|d krU|}n||_tddƒ}|d kr‚|}ntdgdƒ}xjt |ƒD]\\}} t | ƒ} | dkrÕt d ƒ‚n|| dkrôt d ƒ‚n||| |j}x.t|ƒD] }|t|ƒdkrtSqWtS(s:True if all characters of the string are in this alphabet.iÿ(RtstrR'tFalsetTrue(R/tstringttablets((s5/home/psgendb/BIRCHDEV/pkg/weblogo-3.4/corebio/seq.pyt alphabeticñs  cC`s |j|S(s9 The n'th character in the alphabet (zero indexed) or \0 (R(R/R6((s5/home/psgendb/BIRCHDEV/pkg/weblogo-3.4/corebio/seq.pyR"ùscC`s|jt|ƒS(sgThe ordinal position of the character c in this alphabet, or 255 if no such character. (RR'(R/R:((s5/home/psgendb/BIRCHDEV/pkg/weblogo-3.4/corebio/seq.pyR'ýscC`s<g|D]}|j|^q}dj|ƒ}t||ƒS(s9Convert a sequence of ordinals into an alphabetic string.R(RR R(R/tsequence_of_intsR6R:RA((s5/home/psgendb/BIRCHDEV/pkg/weblogo-3.4/corebio/seq.pytchrss cC`s7t|ƒ}|j|jƒ}tdt|ƒƒ}|S(s;Convert an alphabetic string into a byte array of ordinals.tB(R<t translateRRR(R/R?RAR5((s5/home/psgendb/BIRCHDEV/pkg/weblogo-3.4/corebio/seq.pytords s cC`s4|j|ƒstdƒ‚n|j|j|ƒƒS(s€Normalize an alphabetic string by converting all alternative symbols to the canonical equivalent in 'letters'. sNot an alphabetic string.(RBR(RDRG(R/R?((s5/home/psgendb/BIRCHDEV/pkg/weblogo-3.4/corebio/seq.pyt normalizescC`s t|ƒS(s% Letters of the alphabet as a string.(R<(R/((s5/home/psgendb/BIRCHDEV/pkg/weblogo-3.4/corebio/seq.pyR-scC`sJg}|j|jƒx$|jD]\}}|j|ƒq Wdj|ƒS(s- All allowed letters, including alternatives.R(R)RRR (R/tlettkeytvalue((s5/home/psgendb/BIRCHDEV/pkg/weblogo-3.4/corebio/seq.pyt _all_letterss cC`s d|jdt|jƒdS(Ns Alphabet( 's', zips )(RtreprR(R/((s5/home/psgendb/BIRCHDEV/pkg/weblogo-3.4/corebio/seq.pyt__repr__%scC`s t|jƒS(N(R<R(R/((s5/home/psgendb/BIRCHDEV/pkg/weblogo-3.4/corebio/seq.pyt__str__(scC`s t|jƒS(N(tlenR(R/((s5/home/psgendb/BIRCHDEV/pkg/weblogo-3.4/corebio/seq.pyt__len__+scC`s#t|dƒstS|j|jkS(NR(thasattrR=R(R/tother((s5/home/psgendb/BIRCHDEV/pkg/weblogo-3.4/corebio/seq.pyt__eq__.scC`s|j|ƒ S(N(RT(R/RS((s5/home/psgendb/BIRCHDEV/pkg/weblogo-3.4/corebio/seq.pyt__ne__2scC`s t|jƒS(N(titerR(R/((s5/home/psgendb/BIRCHDEV/pkg/weblogo-3.4/corebio/seq.pyt__iter__5scC`s |j|S(N(R(R/RJ((s5/home/psgendb/BIRCHDEV/pkg/weblogo-3.4/corebio/seq.pyt __getitem__8scC`stt|jƒƒS(N(thashttupleR(R/((s5/home/psgendb/BIRCHDEV/pkg/weblogo-3.4/corebio/seq.pyt__hash__;scC`sˆ|dkrtttf}nddl}g|D].}t|j|ƒƒ|jt|ƒƒ^q1}|j t |ƒƒ}||}|S(sœ Returns the most appropriate unambiguous protein, RNA or DNA alphabet for a Seq or SeqList. If a list of alphabets is supplied, then the best alphabet is selected from that list. The heuristic is to count the occurrences of letters for each alphabet and downweight longer alphabets by the log of the alphabet length. Ties go to the first alphabet in the list. iN( R#RRRtmathtsumttallytlogRPtindextmax(tseqst alphabetsR\R5tscoretbest((s5/home/psgendb/BIRCHDEV/pkg/weblogo-3.4/corebio/seq.pytwhich>s   ; N(t__name__t __module__t__doc__t __slots__R#RRBR"R'RDRGRHR-RLRNRORQRTRURWRXR[t staticmethodRf(((s5/home/psgendb/BIRCHDEV/pkg/weblogo-3.4/corebio/seq.pyRžs* H                sACDEFGHIKLMNOPQRSTUVWYBJZX*-sacdefghiklmnopqrstuvwybjzx?.~sACDEFGHIKLMNOPQRSTUVWYBJZXX--sACGTURYSWKMBDHVN-sacgturyswkmbdhvnXx?.~sACGTURYSWKMBDHVNNNN--sACGTRYSWKMBDHVN-sacgtryswkmbdhvnXx?.~UusACGTRYSWKMBDHVNNNN--TTsACGURYSWKMBDHVN-sacguryswkmbdhvnXx?.~TtsACGURYSWKMBDHVNNNN--UUsACGTN-s acgtryswkmbdhvnXx?.~TtRYSWKMBDHVs ACGTNNNNNNNNNNNNNN--TTNNNNNNNNNNsACDEFGHIKLMNPQRSTVWYX*-sacdefghiklmnpqrstvwyx?.~BbZzUusACDEFGHIKLMNPQRSTVWYXX--XXXXCCtACGTtacgttACGUtacgutACDEFGHIKLMNPQRSTVWYtacdefghiklmnopqrstuvwytACDEFGHIKLMNOPQRSTUVWYs&ACGTRYSWKMBDHVN-acgtUuryswkmbdhvnXx?.~s&TGCAYRSWMKVHDBN-tgcaAayrswmkvhdbnXx?.~cB`seZdZeddd„Zed„ƒZd„Zdd„Z d„Z d„Z d„Z d„Z d „Zd „Zd „Zd „Zd „Zd„Zd„Zd„Zd„Zddd„Zd„Zd„Zd„Zd„Zdd„Zdd„ZRS(sd An alphabetic string. A subclass of "str" consisting solely of letters from the same alphabet. Attributes: alphabet -- A string or Alphabet of allowed characters. name -- A short string used to identify the sequence. description -- A string describing the sequence Authors : GEC 2005 cC`sŒtj||ƒ}|dkr't}nt|tƒsEt|ƒ}n|j|ƒsmtd||fƒ‚n||_||_ ||_ |S(Ns Sequence not alphabetic %s, '%s'( R<RR#R t isinstanceRRBR(t _alphabettnamet description(R,tobjtalphabetRuRvR/((s5/home/psgendb/BIRCHDEV/pkg/weblogo-3.4/corebio/seq.pyR’s     cC`s|jS(N(Rt(R/((s5/home/psgendb/BIRCHDEV/pkg/weblogo-3.4/corebio/seq.pyRx§scC`s|jj|ƒS(s] Convert sequence to an array of integers in the range [0, len(alphabet) ) (RxRG(R/((s5/home/psgendb/BIRCHDEV/pkg/weblogo-3.4/corebio/seq.pyRG®scC`sn|s|j}nt|ƒ}dg|}|j|ƒ}x-|D]%}||krA||cd7s(R{R R<RFRRx(R/R‰R,tcleanseq((R‰s5/home/psgendb/BIRCHDEV/pkg/weblogo-3.4/corebio/seq.pyR„þs %cC`s7|j}tddƒ}|t|ƒj|ƒ|jƒS(s*Return a lower case copy of the sequence. RR(R{RR<RFRx(R/R,ttrans((s5/home/psgendb/BIRCHDEV/pkg/weblogo-3.4/corebio/seq.pytlowers cC`s7|j}tddƒ}|t|ƒj|ƒ|jƒS(s*Return a lower case copy of the sequence. RR(R{RR<RFRx(R/R,R‹((s5/home/psgendb/BIRCHDEV/pkg/weblogo-3.4/corebio/seq.pytupper s RtXcC`snt|ƒ}t|ƒdkr-tdƒ‚n||}t||ƒ}|j}|t|ƒj|ƒ|jƒS(s‡Replace all occurrences of letters with the mask character. The default is to replace all lower case letters with 'X'. isMask should be single character(RPR(RR{R<RFRx(R/R-tmasktLLttoR‹R,((s5/home/psgendb/BIRCHDEV/pkg/weblogo-3.4/corebio/seq.pyRs   cC`s#ddlm}|jƒj|ƒS(sðTranslate a nucleotide sequence to a polypeptide using full IUPAC ambiguities in DNA/RNA and amino acid codes, using the standard genetic code. See corebio.transform.GeneticCode for details and more options. i(t GeneticCode(t transformR’tstdRF(R/R’((s5/home/psgendb/BIRCHDEV/pkg/weblogo-3.4/corebio/seq.pyRFscC`s#ddlm}|jƒj|ƒS(s¬Translate a protein sequence back into coding DNA, using the standard genetic code. See corebio.transform.GeneticCode for details and more options. i(R’(R“R’R”tback_translate(R/R’((s5/home/psgendb/BIRCHDEV/pkg/weblogo-3.4/corebio/seq.pyR•)scC`s|jƒjƒS(sqReturns reversed complementary nucleic acid sequence (i.e. the other strand of a DNA sequence.) (Rƒt complement(R/((s5/home/psgendb/BIRCHDEV/pkg/weblogo-3.4/corebio/seq.pytreverse_complement2scC`sXtj|jƒs!tdƒ‚ntj|tƒ}|j}|||j|j|j ƒS(s,Returns complementary nucleic acid sequence.sIncompatable alphabets( RRBRxR(R<RFt_complement_tableR{RuRv(R/RAR,((s5/home/psgendb/BIRCHDEV/pkg/weblogo-3.4/corebio/seq.pyR–8s  cc`sŽt|ƒ|krdS|jj|ƒjƒ}xYtdt|ƒ|dƒD]:}||||!}|dks~|j|ƒrL|VqLqLWdS(sûReturn an iteration over all subwords of length k in the sequence. If an optional alphabet is provided, only words from that alphabet are returned. >>> list(Seq("abcabc").words(3)) ['abc', 'bca', 'cab', 'abc'] Nii(RPRxRHR‚R!R#RB(R/tkRxtseqR4tword((s5/home/psgendb/BIRCHDEV/pkg/weblogo-3.4/corebio/seq.pytwords@s$cC`s2ddlm}t|j||ƒƒ}||ƒS(s¼Return a count of all subwords in the sequence. >>> from corebio.seq import * >>> Seq("abcabc").word_count(3) [('abc', 2), ('bca', 1), ('cab', 1)] i(t group_count(tutilsRtsortedRœ(R/R™RxRRœ((s5/home/psgendb/BIRCHDEV/pkg/weblogo-3.4/corebio/seq.pyt word_countSsN(RgRhRiR R#RtpropertyRxRGR^R|RXR~RR RTRUR‚RƒR…R„RŒRRRFR•R—R–RœR (((s5/home/psgendb/BIRCHDEV/pkg/weblogo-3.4/corebio/seq.pyRƒs4                 cB`s_eZdZdddgZgd d d d„Zd„Zd d„Zd d„Zd d„Z RS( s A list of sequences. RxRuRvcC`s/tj||ƒ||_||_||_dS(N(tlistt__init__RxRuRv(R/talistRxRuRv((s5/home/psgendb/BIRCHDEV/pkg/weblogo-3.4/corebio/seq.pyR£hs  cC`s‰t|ƒdkrtS|j}|dkr;|dj}nt|dƒ}x7|D]/}t|ƒ|krntS|j|krRtSqRWtS(s2Are all sequences of the same length and alphabet?iN(RPR>RxR#R=(R/tARyRA((s5/home/psgendb/BIRCHDEV/pkg/weblogo-3.4/corebio/seq.pyt isalignedss   cC`sX|s|j}n|s'tdƒ‚ng}x$|D]}|j|j|ƒƒq4W|S(s< Convert sequence list into a 2D array of ordinals. s No alphabet(RxR(R)RG(R/RxR™RA((s5/home/psgendb/BIRCHDEV/pkg/weblogo-3.4/corebio/seq.pyRGs  cC`sl|s|j}n|s'tdƒ‚ngtg|D]}|j|ƒ^q4ŒD]}t|ƒ^qP}|S(sÓCounts the occurrences of alphabetic characters. Arguments: - alphabet -- an optional alternative alphabet Returns : A list of character counts in alphabetic order. s No alphabet(RxR(R$R^R](R/RxRAR:Rz((s5/home/psgendb/BIRCHDEV/pkg/weblogo-3.4/corebio/seq.pyR^‹s  Ac C`s |s|j}n|s'tdƒ‚nt|ƒ}|j|ƒ}t|dƒ}gtd|ƒD]}dg|^qb}xo|D]g}t|ƒ|kr©tdƒ‚nx=t|ƒD]/\}} | |kr¶||| cd7ysh   »        ßP