ó –°Ic@sídZddd„ƒYZddd„ƒYZddd„ƒYZddd„ƒYZd efd „ƒYZd efd „ƒYZd efd„ƒYZdefd„ƒYZdefd„ƒYZ defd„ƒYZ ddd„ƒYZ dS(sÕRepresent a Sequence Feature holding info about a part of a sequence. This is heavily modeled after the Biocorba SeqFeature objects, and may be pretty biased towards GenBank stuff since I'm writing it for the GenBank parser output... What's here: Base class to hold a Feature. ---------------------------- classes: o SeqFeature Hold information about a Reference. ---------------------------------- This is an attempt to create a General class to hold Reference type information. classes: o Reference Specify locations of a feature on a Sequence. --------------------------------------------- This aims to handle, in Ewan's words, 'the dreaded fuzziness issue' in much the same way as Biocorba. This has the advantages of allowing us to handle fuzzy stuff in case anyone needs it, and also be compatible with Biocorba. classes: o FeatureLocation - Specify the start and end location of a feature. o ExactPosition - Specify the position as being exact. o WithinPosition - Specify a position occuring within some range. o BetweenPosition - Specify a position occuring between a range. o BeforePosition - Specify the position as being found before some base. o AfterPosition - Specify the position as being found after some base. t SeqFeaturec BsMeZdZdddddigddd„ Zd„Zd„Zd„ZRS(sÒRepresent a Sequence Feature on an object. Attributes: o location - the location of the feature on the sequence o type - the specified type of the feature (ie. CDS, exon, repeat...) o location_operator - a string specifying how this SeqFeature may be related to others. For example, in the example GenBank feature shown below, the location_operator would be "join" o strand - A value specifying on which strand (of a DNA sequence, for instance) the feature deals with. 1 indicates the plus strand, -1 indicates the minus strand, 0 indicates both strands, and None indicates that strand doesn't apply (ie. for proteins) or is not known. o id - A string identifier for the feature. o ref - A reference to another sequence. This could be an accession number for some different sequence. o ref_db - A different database for the reference accession number. o qualifier - A dictionary of qualifiers on the feature. These are analagous to the qualifiers from a GenBank feature table. The keys of the dictionary are qualifier names, the values are the qualifier values. o sub_features - Additional SeqFeatures which fall under this 'parent' feature. For instance, if we having something like: CDS join(1..10,30..40,50..60) The the top level feature would be a CDS from 1 to 60, and the sub features would be of 'CDS_join' type and would be from 1 to 10, 30 to 40 and 50 to 60, respectively. ts c CsU||_||_||_||_||_i|_g|_||_| |_dS(s/Initialize a SeqFeature on a Sequence. N( tlocationttypetlocation_operatortstrandtidt qualifierst sub_featurestreftref_db( tselfRRRRRRRR R ((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyt__init__Gs        cCs d|jt|jƒf}|jr?|dt|jƒ7}n|jrb|dt|jƒ7}n|jr…|dt|jƒ7}n|jr·|jdkr·|dt|jƒ7}n|jrÚ|dt|jƒ7}n|jrý|dt|jƒ7}n|d 7}|S( s4A string representation of the record for debugging.s%s(%ss , type=%ss, location_operator=%ss , strand=%ss s, id=%ss, ref=%ss , ref_db=%st)( t __class__treprRRRRRR R (R tanswer((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyt__repr__\s      cCsàd|j}|d|j7}|d|j|jf7}|d|j7}|d7}|jjƒ}|jƒx)|D]!}|d||j|f7}qsWt|j ƒdkrÜ|d7}x"|j D]}|d |7}qÁWn|S( sLA readable summary of the feature intended to be printed to screen. s type: %s s location: %s s ref: %s:%s s strand: %s s qualifiers: s Key: %s, Value: %s is Sub-Features s%s ( RRR R RRtkeystsorttlenR(R touttqualifier_keystqual_keyt sub_feature((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyt__str__ns      cCs•td|jj|ƒd|jd|jd|jd|jd|jd|jƒ}g|j D]}|j|ƒ^q[|_ t |j j ƒƒ|_ |S(sqReturns a copy of the feature with its location shifted (PRIVATE). The annotation qaulifiers are copied.RRRRRR R ( RRt_shiftRRRRR R RtdictRt iteritems(R toffsetRtf((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyR‚s      (N(t__name__t __module__t__doc__tNoneR RRR(((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyR)s   t ReferencecBs eZdZd„Zd„ZRS(sfRepresent a Generic Reference object. Attributes: o location - A list of Location objects specifying regions of the sequence that the references correspond to. If no locations are specified, the entire sequence is assumed. o authors - A big old string, or a list split by author, of authors for the reference. o title - The title of the reference. o journal - Journal the reference was published in. o medline_id - A medline reference for the article. o pubmed_id - A pubmed reference for the article. o comment - A place to stick any comments about the reference. cCsLg|_d|_d|_d|_d|_d|_d|_d|_dS(NR(Rtauthorstconsrtmttitletjournalt medline_idt pubmed_idtcomment(R ((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyR ¦s       cCs¯d}x|jD]}|d|7}qW|d|j7}|jrV|d|j7}n|d|j7}|d|j7}|d|j7}|d|j7}|d |j7}|S( s4Output an informative string for debugging. Rs location: %s s authors: %s s consrtm: %s s title: %s s journal: %s smedline id: %s spubmed id: %s s comment: %s (RR$R%R&R'R(R)R*(R Rtsingle_location((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyR°s (RR R!R R(((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyR#—s tFeatureLocationcBs;eZdZd„Zd„Zd„Zd„Zd„ZRS(sSpecify the location of a feature along a sequence. This attempts to deal with fuzziness of position ends, but also make it easy to get the start and end in the 'normal' case (no fuzziness). You should access the start and end attributes with your_location.start and your_location.end. If the start and end are exact, this will return the positions, if not, we'll return the approriate Fuzzy class with info about the position and fuzziness. Note that the start and end location numbering follow Python's scheme, thus a GenBank entry of 123..150 (one based counting) becomes a location of [122:150] (zero based counting). cCsXt|tƒr||_nt|ƒ|_t|tƒrE||_nt|ƒ|_dS(sãSpecify the start and end of a sequence feature. start and end arguments specify the values where the feature begins and ends. These can either by any of the *Position objects that inherit from AbstractPosition, or can just be integers specifying the position. In the case of integers, the values are assumed to be exact and are converted in ExactPosition arguments. This is meant to make it easy to deal with non-fuzzy ends. N(t isinstancetAbstractPositiont_startt ExactPositiont_end(R tstarttend((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyR Ós   cCsd|j|jfS(sôReturns a representation of the location (with python counting). For the simple case this uses the python splicing syntax, [122:150] (zero based counting) which GenBank would call 123..150 (one based counting). s[%s:%s](R/R1(R ((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyRçscCs&d|jt|jƒt|jƒfS(s6A string representation of the location for debugging.s %s(%s,%s)(RRR2R3(R ((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyRðscCs+td|jj|ƒd|jj|ƒƒS(s?Returns a copy of the location shifted by the offset (PRIVATE).R2R3(R,R/RR1(R R((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyRõscCsú|dkr|jS|dkr&|jS|dkr†|j|jkr`t|jtƒr`|jjSt|jj|jj|jjƒSnp|dkræ|j|jkrÀt|jtƒrÀ|jjSt|jj|jj|jjƒSntd|ƒ‚dS(s»Make it easy to get non-fuzzy starts and ends. We override get_attribute here so that in non-fuzzy cases we can just return the start and end position without any hassle. To get fuzzy start and ends, just ask for item.start and item.end. To get non-fuzzy attributes (ie. the position only) ask for 'item.nofuzzy_start', 'item.nofuzzy_end'. These should return the largest range of the fuzzy position. So something like: (10.20)..(30.40) should return 10 for start, and 40 for end. The special tricky case where is when we have a single between position argument like 2^3 for the range. We want nofuzzy_start and nofuzzy_end to give a reasonable approximation of what this really means, which is an empty string -- so the same position for both. Doing a special case here sucks, but there is really not a general rule you can apply to this. R2R3t nofuzzy_startt nofuzzy_endsCannot evaluate attribute %s.N( R/R1R-tBetweenPositiontpositiontmint extensiontmaxtAttributeError(R tattr((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyt __getattr__ús"          (RR R!R RRRR=(((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyR,Ãs    R.cBs2eZdZd„Zd„Zd„Zd„ZRS(s1Abstract base class representing a position. cCs||_||_dS(N(R7R9(R R7R9((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyR 's cCs&d|jt|jƒt|jƒfS(s4String representation of the location for debugging.s %s(%s,%s)(RRR7R9(R ((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyR+scCs.t|tƒstdƒ‚t|j|jƒS(sA simple comparison function for positions. This is very simple-minded and just compares the position attribute of the features; extensions are not considered at all. This could potentially be expanded to try to take advantage of extensions. s>We can only do comparisons between Biopython Position objects.(R-R.tAssertionErrortcmpR7(R tother((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyt__cmp__0s cCs|j|j||jƒS(N(RR7R9(R R((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyR<s(RR R!R RRAR(((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyR.$s    R0cBs,eZdZdd„Zd„Zd„ZRS(soSpecify the specific position of a boundary. o position - The position of the boundary. o extension - An optional argument which must be zero since we don't have an extension. The argument is provided so that the same number of arguments can be passed to all position types. In this case, there is no fuzziness associated with the position. icCs6|dkrtd|ƒ‚ntj||dƒdS(Nis)Non-zero extension %s for exact position.(R;R.R (R R7R9((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyR Js  cCs/|jdkst‚d|jt|jƒfS(sBString representation of the ExactPosition location for debugging.is%s(%s)(R9R>RRR7(R ((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyRPscCs t|jƒS(N(tstrR7(R ((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyRUs(RR R!R RR(((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyR0@s   tWithinPositioncBs#eZdZdd„Zd„ZRS(s§Specify the position of a boundary within some coordinates. Arguments: o position - The start position of the boundary o extension - The range to which the boundary can extend. This allows dealing with a position like ((1.4)..100). This indicates that the start of the sequence is somewhere between 1 and 4. To represent that with this class we would set position as 1 and extension as 3. icCstj|||ƒdS(N(R.R (R R7R9((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyR dscCsd|j|j|jfS(Ns(%s.%s)(R7R9(R ((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyRgs(RR R!R R(((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyRCXs  R6cBs#eZdZdd„Zd„ZRS(s©Specify the position of a boundary between two coordinates. Arguments: o position - The start position of the boundary. o extension - The range to the other position of a boundary. This specifies a coordinate which is found between the two positions. So this allows us to deal with a position like ((1^2)..100). To represent that with this class we set position as 1 and the extension as 1. icCstj|||ƒdS(N(R.R (R R7R9((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyR vscCsd|j|j|jfS(Ns(%s^%s)(R7R9(R ((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyRys(RR R!R R(((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyR6js  tBeforePositioncBs,eZdZdd„Zd„Zd„ZRS(sÒSpecify a position where the actual location occurs before it. Arguments: o position - The upper boundary of where the location can occur. o extension - An optional argument which must be zero since we don't have an extension. The argument is provided so that the same number of arguments can be passed to all position types. This is used to specify positions like (<10..100) where the location occurs somewhere before position 10. icCs6|dkrtd|ƒ‚ntj||dƒdS(Nis)Non-zero extension %s for exact position.(R;R.R (R R7R9((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyR ˆs  cCs/|jdkst‚d|jt|jƒfS(s6A string representation of the location for debugging.is%s(%s)(R9R>RRR7(R ((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyRŽscCs d|jS(Ns<%s(R7(R ((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyR“s(RR R!R RR(((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyRD|s   t AfterPositioncBs,eZdZdd„Zd„Zd„ZRS(sÒSpecify a position where the actual location is found after it. Arguments: o position - The lower boundary of where the location can occur. o extension - An optional argument which must be zero since we don't have an extension. The argument is provided so that the same number of arguments can be passed to all position types. This is used to specify positions like (>10..100) where the location occurs somewhere after position 10. icCs6|dkrtd|ƒ‚ntj||dƒdS(Nis)Non-zero extension %s for exact position.(R;R.R (R R7R9((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyR ¢s  cCs/|jdkst‚d|jt|jƒfS(s6A string representation of the location for debugging.is%s(%s)(R9R>RRR7(R ((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyR¨scCs d|jS(Ns>%s(R7(R ((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyR­s(RR R!R RR(((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyRE–s   t OneOfPositioncBs)eZdZd„Zd„Zd„ZRS(sISpecify a position where the location can be multiple positions. This models the GenBank 'one-of(1888,1901)' function, and tries to make this fit within the Biopython Position models. In our case the position of the "one-of" is set as the lowest choice, and the extension is the range to the highest choice. cCsÆ||_d}d}x“|jD]ˆ}t|tƒsDtd|ƒ‚|dkrq|dkrq|j}|j}q|j|krŒ|j}q|j|kr|j}qqWtj||||ƒdS(s£Initialize with a set of posssible positions. position_list is a list of AbstractPosition derived objects, specifying possible locations. s!Expected position objects, got %rN(tposition_choicesR"R-R.R>R7R (R t position_listtsmallesttlargesttposition_choice((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyR ¸s     cCsd|jt|jƒfS(sBString representation of the OneOfPosition location for debugging.s%s(%s)(RRRG(R ((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyRÐscCs:d}x|jD]}|d|7}qW|d d}|S(Nsone-of(s%s,iÿÿÿÿR (RG(R RR7((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyRÔs (RR R!R RR(((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyRF°s  t PositionGapcBs)eZdZd„Zd„Zd„ZRS(sDSimple class to hold information about a gap between positions. cCs ||_dS(sIIntialize with a position object containing the gap information. N(tgap_size(R RM((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyR ßscCsd|jt|jƒfS(s:A string representation of the position gap for debugging.s%s(%s)(RRRM(R ((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyRäscCsd|j}|S(Nsgap(%s)(RM(R R((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyRès (RR R!R RR(((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyRLÜs  N(((((( R!RR#R,R.R0RCR6RDRERFRL(((s/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/Bio/SeqFeature.pyt'sn,a,