o RŀgAF@sdZddlZddlZddlZddlZddlmZddlmZddl m Z ddl m Z ddl mZddlmZdd lmZd d d d ddddddddddddZeZdefddZGdddZGdd d eZGd!d"d"eZGd#d$d$eZGd%d&d&eZGd'd(d(eZGd)d*d*eZGd+d,d,eZGd-d.d.eZGd/d0d0eZ Gd1d2d2eZ!Gd3d4d4eZ"Gd5d6d6eZ#Gd7d8d8eZ$Gd9d:d:eZ%Gd;d<dd>eZ'Gd?d@d@eZ(GdAdBdBeZ)GdCdDdDe*Z+edEZ,e+Z-GdFdGdGe+eZ.e+Z/e+Z0e1D]7\Z2\Z3Z4e5dHdIe3DZ6e7ed e6iZ8e4D]Z9e8e9e6e e9Z:e:;r?e/e0dJdKe=DZ?e@>eAeBe?e=dLe5e?ZC[9[4[2[3[6[?dS)MaRestriction Enzyme classes. Notes about the diverses class of the restriction enzyme implementation:: RestrictionType is the type of all restriction enzymes. ----------------------------------------------------------------------- AbstractCut implements some methods that are common to all enzymes. ----------------------------------------------------------------------- NoCut, OneCut,TwoCuts represent the number of double strand cuts produced by the enzyme. they correspond to the 4th field of the rebase record emboss_e.NNN. 0->NoCut : the enzyme is not characterised. 2->OneCut : the enzyme produce one double strand cut. 4->TwoCuts : two double strand cuts. ----------------------------------------------------------------------- Meth_Dep, Meth_Undep represent the methylation susceptibility to the enzyme. Not implemented yet. ----------------------------------------------------------------------- Palindromic, if the site is palindromic or not. NotPalindromic allow some optimisations of the code. No need to check the reverse strand with palindromic sites. ----------------------------------------------------------------------- Unknown, Blunt, represent the overhang. Ov5, Ov3 Unknown is here for symmetry reasons and correspond to enzymes that are not characterised in rebase. ----------------------------------------------------------------------- Defined, Ambiguous, represent the sequence of the overhang. NotDefined NotDefined is for enzymes not characterised in rebase. Defined correspond to enzymes that display a constant overhang whatever the sequence. ex : EcoRI. G^AATTC -> overhang :AATT CTTAA^G Ambiguous : the overhang varies with the sequence restricted. Typically enzymes which cut outside their restriction site or (but not always) inside an ambiguous site. ex: AcuI CTGAAG(22/20) -> overhang : NN AasI GACNNN^NNNGTC -> overhang : NN CTGN^NNNNNCAG note : these 3 classes refers to the overhang not the site. So the enzyme ApoI (RAATTY) is defined even if its restriction site is ambiguous. ApoI R^AATTY -> overhang : AATT -> Defined YTTAA^R Accordingly, blunt enzymes are always Defined even when they cut outside their restriction site. ----------------------------------------------------------------------- Not_available, as found in rebase file emboss_r.NNN files. Commercially_available allow the selection of the enzymes according to their suppliers to reduce the quantity of results. Also will allow the implementation of buffer compatibility tables. Not implemented yet. the list of suppliers is extracted from emboss_s.NNN ----------------------------------------------------------------------- N)BiopythonWarning) PrintFormat) rest_dict) suppliers)typedict) MutableSeq)SeqARWMHVDNCYSMHBVNGRSKBVDNTYWKHBDN ABDGHKMNSRWV CBDHKMNSTWVY ABDHKMNRTWVY CBDGHKMNSRVY ACBDHMNSRWVY BDGHKNSRTWVYACBDHKMNSRTWVYCBDGHKMNSRTWVYACBDGHKMNSRWVYABDGHKMNSRTWVYACBDGHKMNSRTWVY)ACGTRYWSMKHBVDNreturncCs>td}tdtd}dD] }|||<||||<qt|S)NrasABCDGHKMNRSTVWY) bytearrayordbytes)tableupper_to_lowercr0O/var/www/html/myenv/lib/python3.10/site-packages/Bio/Restriction/Restriction.py_make_FormattedSeq_tablews r2c@seZdZdZejejZe Z dddZ ddZ ddZ d d Zd d Zd dZddZddZddZddZddZdS) FormattedSeqaA linear or circular sequence object for restriction analysis. Translates a Bio.Seq into a formatted sequence to be used with Restriction. Roughly: remove anything which is not IUPAC alphabet and then add a space in front of the sequence to get a biological index instead of a python index (i.e. index of the first base is 1 not 0). Retains information about the shape of the molecule linear (default) or circular. Restriction sites are search over the edges of circular sequence. TcCst|ttfr:||_t|}|j|j|jd|_ d|j vr(t d| d|j d|_ ||_ |j |_dSt|trQ|j|_|j |_ |j |_ |j|_dSt dt|)aInitialize ``FormattedSeq`` with sequence and topology (optional). ``seq`` is either a ``Bio.Seq``, ``Bio.MutableSeq`` or a ``FormattedSeq``. If ``seq`` is a ``FormattedSeq``, ``linear`` will have no effect on the shape of the sequence. )deleterzInvalid character found in  ASCIIz expected Seq or MutableSeq, got N) isinstancerrislowerlowerr, translate_table _remove_charsdata TypeErrordecodelinear __class__klassr3type)selfseqr@r=r0r0r1__init__s     zFormattedSeq.__init__cCst|jdS)zkReturn length of ``FormattedSeq``. ``FormattedSeq`` has a leading space, thus subtract 1. )lenr=rDr0r0r1__len__zFormattedSeq.__len__cCsd|ddd|jdS)z-Represent ``FormattedSeq`` class as a string.z FormattedSeq(rGNz , linear=)r@rIr0r0r1__repr__szFormattedSeq.__repr__cCs&t|trt|t|krdSdSdS)z8Implement equality operator for ``FormattedSeq`` object.TF)r7r3reprrDotherr0r0r1__eq__s zFormattedSeq.__eq__cC d|_dS)zCircularise sequence in place.FNrMrIr0r0r1 circularise zFormattedSeq.circularisecCrS)zLinearise sequence in place.TNrMrIr0r0r1 lineariserUzFormattedSeq.linearisecC||}d|_|S)z*Make a new instance of sequence as linear.TrAr@rDnewr0r0r1 to_linear zFormattedSeq.to_linearcCrW)z,Make a new instance of sequence as circular.FrXrYr0r0r1 to_circularr\zFormattedSeq.to_circularcC|jS)z8Return if sequence is linear (True) or circular (False).rMrIr0r0r1 is_linearzFormattedSeq.is_linearcCs:|r|j}n |j|jd|}ddt||DS)anReturn a list of a given pattern which occurs in the sequence. The list is made of tuple (location, pattern.group). The latter is used with non palindromic sites. Pattern is the regular expression pattern corresponding to the enzyme restriction site. Size is the size of the restriction enzyme recognition-site size. rGcSsg|] }||jfqSr0)startgroup.0ir0r0r1 z)FormattedSeq.finditer..)r_r=refinditer)rDpatternsizer=r0r0r1ris zFormattedSeq.finditercCs*|jr ||j|S||j|S)aReturn substring of ``FormattedSeq``. The class of the returned object is the class of the respective sequence. Note that due to the leading space, indexing is 1-based: >>> from Bio.Seq import Seq >>> from Bio.Restriction.Restriction import FormattedSeq >>> f_seq = FormattedSeq(Seq('ATGCATGC')) >>> f_seq[1] Seq('A') )r9rBr=)rDrer0r0r1 __getitem__s zFormattedSeq.__getitem__NT)__name__ __module__ __qualname____doc__string whitespaceencodedigitsr<r2r;rFrJrNrRrTrVr[r]r_rirlr0r0r0r1r3s    r3c@seZdZdZd)ddZddZd d Zd d Zd dZddZ ddZ ddZ ddZ ddZ ddZddZddZdd Zd!d"Zd#d$Zd%d&Zd'd(ZdS)*RestrictionTypezjRestrictionType. Type from which all enzyme classes are derived. Implement the operator methods. r0NcCsbd|vr td|dz t|j|_WdSty YdSty0td|jddw)zInitialize RestrictionType instance. Not intended to be used in normal operation. The enzymes are instantiated when importing the module. See below. -zProblem with hyphen in z as enzyme namez-Problem with regular expression, re.compiled(rLN) ValueErrorrhcompilecompsiteAttributeError Exception)clsnamebasesdctr0r0r1rFs   zRestrictionType.__init__cCs.t|tr t||gSt|tr||St)zAdd restriction enzyme to a RestrictionBatch(). If other is an enzyme returns a batch of the two enzymes. If other is already a RestrictionBatch add enzyme to it. )r7rvRestrictionBatch add_nocheckr>r~rQr0r0r1__add__s    zRestrictionType.__add__cC ||S)zOverride '/' operator to use as search method. >>> from Bio.Restriction import EcoRI >>> EcoRI/Seq('GAATTC') [2] Returns RE.search(other). searchrr0r0r1 __truediv__! zRestrictionType.__truediv__cCr)zOverride division with reversed operands to use as search method. >>> from Bio.Restriction import EcoRI >>> Seq('GAATTC')/EcoRI [2] Returns RE.search(other). rrr0r0r1 __rtruediv__,rzRestrictionType.__rtruediv__cCr)zOverride '//' operator to use as catalyse method. >>> from Bio.Restriction import EcoRI >>> EcoRI//Seq('GAATTC') (Seq('G'), Seq('AATTC')) Returns RE.catalyse(other). catalyserr0r0r1 __floordiv__7rzRestrictionType.__floordiv__cCr)zAs __floordiv__, with reversed operands. >>> from Bio.Restriction import EcoRI >>> Seq('GAATTC')//EcoRI (Seq('G'), Seq('AATTC')) Returns RE.catalyse(other). rrr0r0r1 __rfloordiv__BrzRestrictionType.__rfloordiv__cCr^)z(Return the name of the enzyme as string.rnr~r0r0r1__str__Mr`zRestrictionType.__str__cCs|jS)z\Implement repr method. Used with eval or exec will instantiate the enzyme. rrr0r0r1rNQszRestrictionType.__repr__cCsz|jWStyYdSw)z3Return length of recognition site of enzyme as int.r)rkr|rr0r0r1rJXs  zRestrictionType.__len__cCst|S)zImplement ``hash()`` method for ``RestrictionType``. Python default is to use ``id(...)`` This is consistent with the ``__eq__`` implementation idrr0r0r1__hash__czRestrictionType.__hash__cCst|t|kS)zOverride '==' operator. True if RE and other are the same enzyme. Specifically this checks they are the same Python object. rrr0r0r1rRkszRestrictionType.__eq__cCs"t|tsdS|j|jkrdSdS)aeOverride '!=' operator. Isoschizomer strict (same recognition site, same restriction) -> False All the other-> True WARNING - This is not the inverse of the __eq__ method >>> from Bio.Restriction import SacI, SstI >>> SacI != SstI # true isoschizomers False >>> SacI == SstI False TF)r7rvcharacrr0r0r1__ne__us  zRestrictionType.__ne__cCs.t|tsdS|j|jkr|j|jkrdSdS)a0Override '>>' operator to test for neoschizomers. neoschizomer : same recognition site, different restriction. -> True all the others : -> False >>> from Bio.Restriction import SmaI, XmaI >>> SmaI >> XmaI True FT)r7rvsiterrr0r0r1 __rshift__s zRestrictionType.__rshift__cCs(t|tstdt|d||S)zOverride '%' operator to test for compatible overhangs. True if a and b have compatible overhang. >>> from Bio.Restriction import XhoI, SalI >>> XhoI % SalI True zexpected RestrictionType, got  instead)r7rvr>rC_mod1rr0r0r1__mod__s  zRestrictionType.__mod__cCsDt|tstt|t|krdS|jt|kr |j|jkr dSdS)aCompare length of recognition site of two enzymes. Override '>='. a is greater or equal than b if the a site is longer than b site. If their site have the same length sort by alphabetical order of their names. >>> from Bio.Restriction import EcoRI, EcoRV >>> EcoRI.size 6 >>> EcoRV.size 6 >>> EcoRI >= EcoRV False TFr7rvNotImplementedErrorrHrkrnrr0r0r1__ge__s zRestrictionType.__ge__cCsDt|tstt|t|krdS|jt|kr |j|jkr dSdS)zCompare length of recognition site of two enzymes. Override '>'. Sorting order: 1. size of the recognition site. 2. if equal size, alphabetical order of the names. TFrrr0r0r1__gt__s zRestrictionType.__gt__cCsFt|tstt|t|krdSt|t|kr!|j|jkr!dSdS)zCompare length of recognition site of two enzymes. Override '<='. Sorting order: 1. size of the recognition site. 2. if equal size, alphabetical order of the names. TFr7rvrrHrnrr0r0r1__le__ zRestrictionType.__le__cCsFt|tstt|t|krdSt|t|kr!|j|jkr!dSdS)zCompare length of recognition site of two enzymes. Override '<'. Sorting order: 1. size of the recognition site. 2. if equal size, alphabetical order of the names. TFrrr0r0r1__lt__rzRestrictionType.__lt__)rwr0N)rnrorprqrFrrrrrrrNrJrrRrrrrrrrr0r0r0r1rvs(          rvc@seZdZdZedddZeddZeddZed d Zed d Z ed dZ edddZ edddZ edddZ eddZdS) AbstractCutzImplement the methods that are common to all restriction enzymes. All the methods are classmethod. For internal use only. Not meant to be instantiated. TcCs,t|tr ||_|St|||_|S)aReturn a list of cutting sites of the enzyme in the sequence. Compensate for circular sequences and so on. dna must be a Bio.Seq.Seq instance or a Bio.Seq.MutableSeq instance. If linear is False, the restriction sites that span over the boundaries will be included. The positions are the first base of the 3' fragment, i.e. the first base after the position the enzyme will cut. )r7r3dna_searchr~rr@r0r0r1rs  zAbstractCut.searchcstjjrfddfddjD_dStjD]\}}|dkr5j|7<q#tjdddD]\}}|krUj|d 8<q@dSdS)Remove cuts that are outsite of the sequence (PRIVATE). For internal use only. Drop the site that are situated outside the sequence in linear sequence. Modify the index for site in circular sequences. cs:|j}d|koknod|kokSS)NrG)ovhg) cut_on_watson cut_on_crick)r~lengthr0r1filtering_function's 0z-AbstractCut._drop..filtering_functioncsg|]}|r|qSr0r0)rdcut)rr0r1rf+z%AbstractCut._drop..rGN)rHrr_results enumerate)r~indexlocationr0)r~rrr1_drops zAbstractCut._dropcCs(tddtD}td|dS)z.Print all the suppliers of restriction enzyme.css|]}|dVqdSrNr0rdxr0r0r1 ;z,AbstractCut.all_suppliers..z, N)sortedsuppliers_dictvaluesprintjoinr~supplyr0r0r1 all_suppliers8zAbstractCut.all_supplierscCs ||k S)aoTest for real isoschizomer. True if other is an isoschizomer of RE, but not an neoschizomer, else False. Equischizomer: same site, same position of restriction. >>> from Bio.Restriction import SacI, SstI, SmaI, XmaI >>> SacI.is_equischizomer(SstI) True >>> SmaI.is_equischizomer(XmaI) False r0rr0r0r1is_equischizomer>s zAbstractCut.is_equischizomercCs||?S)zTest for neoschizomer. True if other is an isoschizomer of RE, else False. Neoschizomer: same site, different position of restriction. r0rr0r0r1is_neoschizomerPszAbstractCut.is_neoschizomercCs||k p||?S)a5Test for same recognition site. True if other has the same recognition site, else False. Isoschizomer: same site. >>> from Bio.Restriction import SacI, SstI, SmaI, XmaI >>> SacI.is_isoschizomer(SstI) True >>> SmaI.is_isoschizomer(XmaI) True r0rr0r0r1is_isoschizomerYszAbstractCut.is_isoschizomerNc6|st}fdd|D}|}||=||S)zList equischizomers of the enzyme. Return a tuple of all the isoschizomers of RE. If batch is supplied it is used instead of the default AllEnzymes. Equischizomer: same site, same position of restriction. csg|]}|ks|qSr0r0rrr0r1rfurz.AbstractCut.equischizomers.. AllEnzymesrsortr~batchrrer0rr1equischizomersjs  zAbstractCut.equischizomerscs"|st}tfdd|D}|S)zList neoschizomers of the enzyme. Return a tuple of all the neoschizomers of RE. If batch is supplied it is used instead of the default AllEnzymes. Neoschizomer: same site, different position of restriction. c3s|] }|?r|VqdSNr0rrr0r1rz,AbstractCut.neoschizomers..)rrr~rrr0rr1 neoschizomers{s zAbstractCut.neoschizomerscr)zList all isoschizomers of the enzyme. Return a tuple of all the equischizomers and neoschizomers of RE. If batch is supplied it is used instead of the default AllEnzymes. cs g|] }|?s |ks|qSr0r0rrr0r1rf z-AbstractCut.isoschizomers..rrr0rr1 isoschizomerss zAbstractCut.isoschizomerscCr^)zReturn the theoretically cutting frequency of the enzyme. Frequency of the site, given as 'one cut per x bases' (int). )freqrr0r0r1 frequencyszAbstractCut.frequencyrmr)rnrorprq classmethodrrrrrrrrrrr0r0r0r1rs,         rc@LeZdZdZeddZeddZeddZedd Zed d Z d S) NoCutafImplement the methods specific to the enzymes that do not cut. These enzymes are generally enzymes that have been only partially characterised and the way they cut the DNA is unknown or enzymes for which the pattern of cut is to complex to be recorded in Rebase (ncuts values of 0 in emboss_e.###). When using search() with these enzymes the values returned are at the start of the restriction site. Their catalyse() method returns a TypeError. Unknown and NotDefined are also part of the base classes of these enzymes. Internal use only. Not meant to be instantiated. cCdSyReturn if the cutting pattern has one cut. True if the enzyme cut the sequence one time on each strand. Fr0rr0r0r1cut_oncezNoCut.cut_oncecCrwReturn if the cutting pattern has two cuts. True if the enzyme cut the sequence twice on each strand. Fr0rr0r0r1 cut_twicerzNoCut.cut_twicecc |VdS)aReturn a generator that moves the cutting position by 1 (PRIVATE). For internal use only. location is an integer corresponding to the location of the match for the enzyme pattern in the sequence. _modify returns the real place where the enzyme will cut. Example:: EcoRI pattern : GAATTC EcoRI will cut after the G. so in the sequence: ______ GAATACACGGAATTCGA | 10 dna.finditer(GAATTC, 6) will return 10 as G is the 10th base EcoRI cut after the G so: EcoRI._modify(10) -> 11. If the enzyme cut twice _modify will returns two integer corresponding to each cutting site. Nr0r~rr0r0r1_modifys z NoCut._modifyccr)zReturn a generator that moves the cutting position by 1 (PRIVATE). For internal use only. As _modify for site situated on the antiparallel strand when the enzyme is not palindromic. Nr0rr0r0r1 _rev_modifys zNoCut._rev_modifycCsdddd|jfS)Return a list of the enzyme's characteristics as tuple. the tuple contains the attributes: - fst5 -> first 5' cut ((current strand) or None - fst3 -> first 3' cut (complementary strand) or None - scd5 -> second 5' cut (current strand) or None - scd5 -> second 3' cut (complementary strand) or None - site -> recognition site. Nrrr0r0r1characteristics zNoCut.characteristicN rnrorprqrrrrrrr0r0r0r1rs     rc@r) OneCutzImplement the methods for enzymes that cut the DNA only once. Correspond to ncuts values of 2 in emboss_e.### Internal use only. Not meant to be instantiated. cCr)rTr0rr0r0r1rrzOneCut.cut_oncecCrrr0rr0r0r1r rzOneCut.cut_twiceccs||jVdS)aReturn a generator that moves the cutting position by 1 (PRIVATE). For internal use only. location is an integer corresponding to the location of the match for the enzyme pattern in the sequence. _modify returns the real place where the enzyme will cut. Example:: EcoRI pattern : GAATTC EcoRI will cut after the G. so in the sequence: ______ GAATACACGGAATTCGA | 10 dna.finditer(GAATTC, 6) will return 10 as G is the 10th base EcoRI cut after the G so: EcoRI._modify(10) -> 11. if the enzyme cut twice _modify will returns two integer corresponding to each cutting site. N)fst5rr0r0r1rszOneCut._modifyccs||jVdS)zReturn a generator that moves the cutting position by 1 (PRIVATE). For internal use only. As _modify for site situated on the antiparallel strand when the enzyme is not palindromic N)fst3rr0r0r1r.s zOneCut._rev_modifycCs|j|jdd|jfS)aReturn a list of the enzyme's characteristics as tuple. The tuple contains the attributes: - fst5 -> first 5' cut ((current strand) or None - fst3 -> first 3' cut (complementary strand) or None - scd5 -> second 5' cut (current strand) or None - scd5 -> second 3' cut (complementary strand) or None - site -> recognition site. N)rrrrr0r0r1r9s zOneCut.characteristicNrr0r0r0r1rs     rc@r) TwoCutszImplement the methods for enzymes that cut the DNA twice. Correspond to ncuts values of 4 in emboss_e.### Internal use only. Not meant to be instantiated. cCrrr0rr0r0r1rQrzTwoCuts.cut_oncecCr)rTr0rr0r0r1rYrzTwoCuts.cut_twiceccs||jV||jVdS)aReturn a generator that moves the cutting position by 1 (PRIVATE). For internal use only. location is an integer corresponding to the location of the match for the enzyme pattern in the sequence. _modify returns the real place where the enzyme will cut. example:: EcoRI pattern : GAATTC EcoRI will cut after the G. so in the sequence: ______ GAATACACGGAATTCGA | 10 dna.finditer(GAATTC, 6) will return 10 as G is the 10th base EcoRI cut after the G so: EcoRI._modify(10) -> 11. if the enzyme cut twice _modify will returns two integer corresponding to each cutting site. N)rscd5rr0r0r1ras zTwoCuts._modifyccs||jV||jVdS)zReturn a generator that moves the cutting position by 1 (PRIVATE). for internal use only. as _modify for site situated on the antiparallel strand when the enzyme is not palindromic N)rscd3rr0r0r1r~s zTwoCuts._rev_modifycCs|j|j|j|j|jfS)r)rrrrrrr0r0r1rs zTwoCuts.characteristicNrr0r0r0r1rIs     rc@eZdZdZeddZdS)Meth_DepzpImplement the information about methylation. Enzymes of this class possess a site which is methylable. cCr)mReturn if recognition site can be methylated. True if the recognition site is a methylable. Tr0rr0r0r1 is_methylablerzMeth_Dep.is_methylableNrnrorprqrrr0r0r0r1rrc@r) Meth_UndepzwImplement information about methylation sensitibility. Enzymes of this class are not sensible to methylation. cCr)rFr0rr0r0r1rrzMeth_Undep.is_methylableNrr0r0r0r1rrrc@(eZdZdZeddZeddZdS) PalindromicaImplement methods for enzymes with palindromic recognition sites. palindromic means : the recognition site and its reverse complement are identical. Remarks : an enzyme with a site CGNNCG is palindromic even if some of the sites that it will recognise are not. for example here : CGAACG Internal use only. Not meant to be instantiated. cs:jjj}fdd|D_jrjS)zReturn a list of cutting sites of the enzyme in the sequence (PRIVATE). For internal use only. Implement the search method for palindromic enzymes. cs$g|]\}}|D]}|q qSr0)r)rdsgrrr0r1rf$z'Palindromic._search..)rrir{rkrr)r~sitelocr0rr1rs zPalindromic._searchcCr)8Return if the enzyme has a palindromic recognition site.Tr0rr0r0r1is_palindromiczPalindromic.is_palindromicNrnrorprqrrrr0r0r0r1rs   rc@r)NonPalindromiczImplement methods for enzymes with non-palindromic recognition sites. Palindromic means : the recognition site and its reverse complement are identical. Internal use only. Not meant to be instantiated. cCs|j|j|j}g|_|j}|j}t|}g|_|D]\}}||r/|jt ||7_q|jt ||7_q|j|j7_|jrO|j | |jS)zReturn a list of cutting sites of the enzyme in the sequence (PRIVATE). For internal use only. Implement the search method for non palindromic enzymes. ) rrir{rkrrrstron_minuslistrr)r~iteratormodifrevmodifrrarbr0r0r1rs  zNonPalindromic._searchcCr)rFr0rr0r0r1rrzNonPalindromic.is_palindromicNrr0r0r0r1rs  rc@sjeZdZdZedddZeZeddZeddZed d Z ed d Z ed dZ eddZ dS)UnknownzImplement methods for enzymes that produce unknown overhangs. These enzymes are also NotDefined and NoCut. Internal use only. Not meant to be instantiated. TcCst|jd)iList the sequence fragments after cutting dna with enzyme. Return a tuple of dna as will be produced by using RE to restrict the dna. dna must be a Bio.Seq.Seq instance or a Bio.Seq.MutableSeq instance. If linear is False, the sequence is considered to be circular and the output will be modified accordingly. z restriction is unknown.)rrnrr0r0r1r s zUnknown.catalysecCrReturn if the enzyme produces blunt ends. True if the enzyme produces blunt end. Related methods: - RE.is_3overhang() - RE.is_5overhang() - RE.is_unknown() Fr0rr0r0r1is_blunt zUnknown.is_bluntcCrReturn if the enzymes produces 5' overhanging ends. True if the enzyme produces 5' overhang sticky end. Related methods: - RE.is_3overhang() - RE.is_blunt() - RE.is_unknown() Fr0rr0r0r1 is_5overhang)rzUnknown.is_5overhangcCrReturn if the enzyme produces 3' overhanging ends. True if the enzyme produces 3' overhang sticky end. Related methods: - RE.is_5overhang() - RE.is_blunt() - RE.is_unknown() Fr0rr0r0r1 is_3overhang8rzUnknown.is_3overhangcCr)~Return the type of the enzyme's overhang as string. Can be "3' overhang", "5' overhang", "blunt", "unknown". unknownr0rr0r0r1overhangGrzUnknown.overhangcCgS)=List all enzymes that produce compatible ends for the enzyme.r0rr0r0r1compatible_endOrzUnknown.compatible_endcCrTest if other enzyme produces compatible ends for enzyme (PRIVATE). For internal use only. Test for the compatibility of restriction ending of RE and other. Fr0rr0r0r1rTsz Unknown._mod1Nrm rnrorprqrrcatalyzerrrrrrr0r0r0r1r s"       r c@sleZdZdZedddZeZeddZeddZed d Z ed d Z edddZ e ddZ d S)BluntzImplement methods for enzymes that produce blunt ends. The enzyme cuts the + strand and the - strand of the DNA at the same place. Internal use only. Not meant to be instantiated. Tc||||jsddfSg}td}rH|dd|r9|fddt|D7}|ddt|S|dddd|sat|S|fddt|D7}t|S)r rGNrc$g|]}||dqSrGr0rdrr0r1rfrz"Blunt.catalyse..rcr"r#r0rr$r0r1rfrrrrHr_appendrangetupler~rr@ fragmentsrr0r$r1rh"  &zBlunt.catalysecCr)r Tr0rr0r0r1rrzBlunt.is_bluntcCrrr0rr0r0r1rrzBlunt.is_5overhangcCrrr0rr0r0r1rrzBlunt.is_3overhangcCr)rbluntr0rr0r0r1rrzBlunt.overhangNcCs"|st}tddttD}|S)rcss|] }|r|VqdSrrrr0r0r1rrz'Blunt.compatible_end..rriterrr0r0r1rszBlunt.compatible_endcCs t|tS)zTest if other enzyme produces compatible ends for enzyme (PRIVATE). For internal use only Test for the compatibility of restriction ending of RE and other. ) issubclassr )rQr0r0r1rs z Blunt._mod1rmr)rnrorprqrrrrrrrr staticmethodrr0r0r0r1r _s" /     r c@leZdZdZedddZeZeddZeddZed d Z ed d Z edddZ eddZ d S)Ov5zImplement methods for enzymes that produce 5' overhanging ends. The enzyme cuts the + strand after the - strand of the DNA. Internal use only. Not meant to be instantiated. Tcs||||jsddfStd}g}rH|dd|r9|fddt|D7}|ddt|S|dddd|sat|S|fddt|D7}t|S)r rGNrcr"r#r0rr$r0r1rfrz Ov5.catalyse..rcr"r#r0rr$r0r1rfrr&)r~rr@rr+r0r$r1rs"  &z Ov5.catalysecCrr r0rr0r0r1rrz Ov5.is_bluntcCr)rTr0rr0r0r1r+rzOv5.is_5overhangcCrrr0rr0r0r1r:rzOv5.is_3overhangcCr)rz 5' overhangr0rr0r0r1rIrz Ov5.overhangNc&|st}tfddttD}|S)rc3$|] }|r|r|VqdSrrrrr0r1rV"z%Ov5.compatible_end..r/rr0rr1rQzOv5.compatible_endcCt|tr ||SdSr)r1r4_mod2rr0r0r1rYs  z Ov5._mod1rmrrr0r0r0r1r4" /     r4c@r3)Ov3zImplement methods for enzymes that produce 3' overhanging ends. The enzyme cuts the - strand after the + strand of the DNA. Internal use only. Not meant to be instantiated. Tcr!)r rGNrcr"r#r0rr$r0r1rfrz Ov3.catalyse..rcr"r#r0rr$r0r1rfrr&r*r0r$r1ror,z Ov3.catalysecCrr r0rr0r0r1rrz Ov3.is_bluntcCrrr0rr0r0r1rrzOv3.is_5overhangcCr)rTr0rr0r0r1rrzOv3.is_3overhangcCr)rz 3' overhangr0rr0r0r1rrz Ov3.overhangNcr5)rc3r6rrrrr0r1rr8z%Ov3.compatible_end..r/rr0rr1rr9zOv3.compatible_endcCr:r)r1r=r;rr0r0r1rs z Ov3._mod1rmrrr0r0r0r1r=gr<r=c@r) DefinedajImplement methods for enzymes with defined recognition site and cut. Typical example : EcoRI -> G^AATT_C The overhang will always be AATT Notes: Blunt enzymes are always defined. Even if their site is GGATCCNNN^_N Their overhang is always the same : blunt! Internal use only. Not meant to be instantiated. cCr)-Return if recognition sequence and cut are defined. True if the sequence recognised and cut is constant, i.e. the recognition site is not degenerated AND the enzyme cut inside the site. Related methods: - RE.is_ambiguous() - RE.is_unknown() Tr0rr0r0r1 is_definedzDefined.is_definedcCr1Return if recognition sequence and cut may be ambiguous. True if the sequence recognised and cut is ambiguous, i.e. the recognition site is degenerated AND/OR the enzyme cut outside the site. Related methods: - RE.is_defined() - RE.is_unknown() Fr0rr0r0r1 is_ambiguous rBzDefined.is_ambiguouscCrReturn if recognition sequence is unknown. True if the sequence is unknown, i.e. the recognition site has not been characterised yet. Related methods: - RE.is_defined() - RE.is_ambiguous() Fr0rr0r0r1 is_unknownrzDefined.is_unknowncCs0|j}|j}|j}|rd}|S|rX||krdkr*nn d|jd}|S|dkr@|d|d||dd}|S|d|d|||d||d}|S|rl|d|d||d}|S||krvdkrnnd |d }|S|d|d|||d||d}|S) aEReturn a string representing the recognition site and cuttings. Return a representation of the site with the cut on the (+) strand represented as '^' and the cut on the (-) strand as '_'. ie: >>> from Bio.Restriction import EcoRI, KpnI, EcoRV, SnaI >>> EcoRI.elucidate() # 5' overhang 'G^AATT_C' >>> KpnI.elucidate() # 3' overhang 'G_GTAC^C' >>> EcoRV.elucidate() # blunt 'GAT^_ATC' >>> SnaI.elucidate() # NotDefined, cut profile unknown. '? GTATAC ?' >>> %cut twice, not yet implemented sorry.rN^_NN^_z^_N_^N)rrrrrr)r~f5f3rrhr0r0r1 elucidate*s.   , ,zDefined.elucidatecCs(|j|jkrdSt|tr||SdS)rTF)ovhgseqr1 Ambiguousr;rr0r0r1r;Ss   z Defined._mod2N) rnrorprqrrArErHrRr;r0r0r0r1r?s    (r?c@r) rTaxImplement methods for enzymes that produce variable overhangs. Typical example : BstXI -> CCAN_NNNN^NTGG The overhang can be any sequence of 4 bases. Notes: Blunt enzymes are always defined. Even if their site is GGATCCNNN^_N Their overhang is always the same : blunt! Internal use only. Not meant to be instantiated. cCrr@Fr0rr0r0r1rAtrBzAmbiguous.is_definedcCr)rDTr0rr0r0r1rErBzAmbiguous.is_ambiguouscCrrFr0rr0r0r1rHrzAmbiguous.is_unknowncCst|jt|jkr dS|j}|D]'}|dvr |dvr$d|d}|dvr8dt|d}|||}qt||jrBdSdS) rFATCGr&. RYWMSKHDBV[]T)rHrSrsplitmatchingrhmatch)r~rQsebaseexpandr0r0r1r;s zAmbiguous._mod2cCs|j}|j}t|}|j}|rd}|S|r||kr#dkr-nnd|d}|Sd|kr7|kr_nn&d||krE|kr_nn|d|d|||d||d}|Sd|kri|krnn|d|d||d|dd}|Sd||kr|krnndt|d|d|d||d}|S||dkrdt|ddt||d|}|S||kr|||dd|||dd}|Sdt|d||dd}|S|r|dkrd t|d|}|S||kr|||dd }|Std |j |f|dkr?|dkr1d |d }|S|d||dd }|Sd||krM|krunn&d|kr[|krunn|d|d|||d||d}|Sd||kr|krnn|d|d||d||dd }|Sd|kr|krnnd d|||d|d||d}|S|dkr||dd|||dd }|S|dkrd t|||ddt|d|}|Sd t||d|||dd }|S)FReturn a string representing the recognition site and cuttings. Return a representation of the site with the cut on the (+) strand represented as '^' and the cut on the (-) strand as '_'. ie: >>> from Bio.Restriction import EcoRI, KpnI, EcoRV, SnaI >>> EcoRI.elucidate() # 5' overhang 'G^AATT_C' >>> KpnI.elucidate() # 3' overhang 'G_GTAC^C' >>> EcoRV.elucidate() # blunt 'GAT^_ATC' >>> SnaI.elucidate() # NotDefined, cut profile unknown. '? GTATAC ?' >>> rIrrJrKNrLrMr&zN^_z^_Nz%s.easyrepr() : error f5=%irNrO) rrrHrrrabsrryr)r~rPrQrrrhr0r0r1rRsv) &4,$(", ((       <, , , $ ,(zAmbiguous.elucidateN) rnrorprqrrArErHr;rRr0r0r0r1rTfs    rTcs`eZdZdZefddZeddZeddZedd Zed d Z ed d Z Z S) NotDefinedzImplement methods for enzymes with non-characterized overhangs. Correspond to NoCut and Unknown. Internal use only. Not meant to be instantiated. cs|jrdStdS)rN)rr_superrrrAr0r1r s zNotDefined._dropcCrrUr0rr0r0r1rArBzNotDefined.is_definedcCrrCr0rr0r0r1rE*rBzNotDefined.is_ambiguouscCr)rGTr0rr0r0r1rH:rzNotDefined.is_unknowncCstdt|t|t|f)rz0%s.mod2(%s), %s : NotDefined. pas glop pas glop!)ryrrr0r0r1r;Is zNotDefined._mod2cCsd|jdS)raz? z ?rrr0r0r1rR]szNotDefined.elucidate) rnrorprqrrrArErHr;rR __classcell__r0r0rer1rcs    rcc@s@eZdZdZeddZeddZeddZedd Zd S) Commercially_availablezzImplement methods for enzymes which are commercially available. Internal use only. Not meant to be instantiated. cCs$|jD] }tt|ddqdS)(Print a list of suppliers of the enzyme.r,N)supplrr)r~rr0r0r1rs z Commercially_available.supplierscsfddtDS))Return a list of suppliers of the enzyme.cs"g|] \}}|jvr|dqSr)rjrdkvrr0r1rf"z8Commercially_available.supplier_list..ritemsrr0rr1 supplier_listsz$Commercially_available.supplier_listcCr)eReturn the recommended buffer of the supplier for this enzyme. Not implemented yet. Nr0r~supplierr0r0r1buffersszCommercially_available.bufferscCr)WReturn if enzyme is commercially available. True if RE has suppliers. Tr0rr0r0r1is_commrzCommercially_available.is_commN) rnrorprqrrrsrwryr0r0r0r1rgts   rgc@s@eZdZdZeddZeddZeddZedd Z d S) Not_availablez~Implement methods for enzymes which are not commercially available. Internal use only. Not meant to be instantiated. cCr)rhNr0r0r0r0r1rrzNot_available.supplierscCr)rkr0rr0r0r1rsrzNot_available.supplier_listcCstd)rtz"Enzyme not commercially available.)r>rur0r0r1rwrzNot_available.bufferscCr)rxFr0rr0r0r1ryrzNot_available.is_commN) rnrorprqr2rrrsrwryr0r0r0r1rzs   rzc@seZdZdZd8ddZddZddZd d Zd d Zd dZ ddZ ddZ d9ddZ ddZ ddZddZddZddZd d!Zd"d#Zd$d%Zd&d'Zd(d)Zd*d+Zd,d-Zd.d/Zed0d1Zed2d3Zd:d5d6Zd7S);rz-Class for operations on more than one enzyme.r0csVfdd|D}|dd|D7}t|t_d_dd|D_dS)z=Initialize empty RB or pre-fill with enzymes (from supplier).csg|]}|qSr0)formatrrIr0r1rfz-RestrictionBatch.__init__..cSs&g|]}t|dD]}t|q qSr#)reval)rdnrr0r0r1rfs&NcSsg|]}|tvr|qSr0rrr0r0r1rfr)setrFdictfromkeysmappingalready_mappedr)rDfirstrr0rIr1rFs   zRestrictionBatch.__init__cCsLt|dkr d|Sdd|ddd|ddfS)z=Return a readable representation of the ``RestrictionBatch``.+z...N)rHrelementsrIr0r0r1rs *zRestrictionBatch.__str__cCsd|dS)z?Represent ``RestrictionBatch`` class as a string for debugging.zRestrictionBatch(rL)rrIr0r0r1rNszRestrictionBatch.__repr__cCs0z||}Wn tyYdSwt||S)z*Implement ``in`` for ``RestrictionBatch``.F)r{ryr __contains__rPr0r0r1rs   zRestrictionBatch.__contains__cCr)z.Override '/' operator to use as search method.rrPr0r0r1__div__rUzRestrictionBatch.__div__cCr)zAOverride division with reversed operands to use as search method.rrPr0r0r1__rdiv__rUzRestrictionBatch.__rdiv__cCr)z\Override Python 3 division operator to use as search method. Like __div__. rrPr0r0r1r zRestrictionBatch.__truediv__cCr)zIAs __truediv___, with reversed operands. Like __rdiv__. rrPr0r0r1rrzRestrictionBatch.__rtruediv__FcCs:||}||vr |S|r|||Std|jd)a3Check if enzyme is in batch and return it. If add is True and enzyme is not in batch add enzyme to batch. If add is False (which is the default) only return enzyme. If enzyme is not a RestrictionType or can not be evaluated to a RestrictionType, raise a ValueError. zenzyme z is not in RestrictionBatch)r{addryrn)rDenzymerer0r0r1gets  zRestrictionBatch.getcCs2tt||}t}tt|dgt||_|S)zFilter enzymes in batch with supplied function. The new batch will contain only the enzymes for which func return True. TrfilterrrziprH_data)rDfuncr%rZr0r0r1 lambdasplit szRestrictionBatch.lambdasplitcCs4t|}|j||dD] }|t|qdS)zAdd all enzymes from a given supplier to batch. letter represents the suppliers as defined in the dictionary RestrictionDictionary.suppliers Returns None. Raise a KeyError if letter is not a supplier code. rGN)rrr'rr})rDletterrvrr0r0r1 add_suppliers   zRestrictionBatch.add_suppliercCstdd|jD}|S)zList the current suppliers for the restriction batch. Return a sorted list of the suppliers which have been used to create the batch. css|] }t|dVqdSrrrr0r0r1r(rz5RestrictionBatch.current_suppliers..)rr)rD suppl_listr0r0r1current_suppliers"sz"RestrictionBatch.current_supplierscCs|||S)ziOverride '+=' for use with sets. b += other -> add other to b, check the type of other. )rrPr0r0r1__iadd__+s zRestrictionBatch.__iadd__cCs||}|||S)zTOverride '+' for use with sets. b + other -> new RestrictionBatch. )rAr)rDrQrZr0r0r1r3s  zRestrictionBatch.__add__cCt|||S)a&Remove enzyme from restriction batch. Safe set.remove method. Verify that other is a RestrictionType or can be evaluated to a RestrictionType. Raise a ValueError if other can not be evaluated to a RestrictionType. Raise a KeyError if other is not in B. )rremover{rPr0r0r1r<szRestrictionBatch.removecCr)aAdd a restriction enzyme to the restriction batch. Safe set.add method. Verify that other is a RestrictionType or can be evaluated to a RestrictionType. Raise a ValueError if other can not be evaluated to a RestrictionType. )rrr{rPr0r0r1rFszRestrictionBatch.addcCs t||S)z:Add restriction enzyme to batch without checking its type.)rrrPr0r0r1rOs zRestrictionBatch.add_nocheckc CsXzt|tr |WSttt|trt|WSWn ttfy#Ynwt|jd)zEvaluate enzyme (name) and return it (as RestrictionType). If y is a RestrictionType return y. If y can be evaluated to a RestrictionType return eval(y). Raise a ValueError in all other case. z is not a RestrictionType)r7rvr}r NameError SyntaxErrorryrArDyr0r0r1r{Ss  zRestrictionBatch.formatcCst|tp ttt|tS)zgReturn if enzyme (name) is a known enzyme. True if y or eval(y) is a RestrictionType. )r7rvr}rrr0r0r1is_restrictioncs  zRestrictionBatch.is_restrictioncs@fdd}tt||}t}tt|dgt||_|S)zExtract enzymes of a certain class and put in new RestrictionBatch. It works but it is slow, so it has really an interest when splitting over multiple conditions. cs<D]}|jd}t||r|rqdS|rdSqdS)NTF)rrnr1)elementrBbboolclassesr0r1 splittestss z)RestrictionBatch.split..splittestTr)rDrrrr%rZr0rr1r[ls zRestrictionBatch.splitcCstdd|DS)zList the enzymes of the RestrictionBatch as list of strings. Give all the names of the enzymes in B sorted alphabetically. cs|]}t|VqdSrrrdrr0r0r1rrz,RestrictionBatch.elements..)rrIr0r0r1rszRestrictionBatch.elementscCsdd|DS)zList the names of the enzymes of the RestrictionBatch. Return a list of the name of the elements of the batch. cSg|]}t|qSr0rrr0r0r1rfz.RestrictionBatch.as_string..r0rIr0r0r1 as_stringrKzRestrictionBatch.as_stringcCsddtD}|S)zYReturn a dictionary with supplier codes. Letter code for the suppliers. cSsi|] \}}||dqSrlr0rmr0r0r1 rgz0RestrictionBatch.suppl_codes..rqrr0r0r1 suppl_codesszRestrictionBatch.suppl_codescCs(dd|D}td|dS)zPrint a list of supplier codes.cSsg|]}d|qS)z = )rrcr0r0r1rfr|z/RestrictionBatch.show_codes.. N)rrrrrrr0r0r1 show_codesrzRestrictionBatch.show_codesTcst|dsd|_ttr2t|f|jkr|jSt|f|_t|fdd|D|_|jSttrYtjf|jkrD|jStjf|_fdd|D|_|jStdt d)z?Return a dic of cutting sites in the seq for the batch enzymes.rNci|]}||qSr0rr)fseqr0r1rrz+RestrictionBatch.search..crr0rr)rr0r1rrz)Expected Seq or MutableSeq instance, got r) hasattrrr7DNArrr3r@r>rC)rDrr@r0)rrr1rs    zRestrictionBatch.searchN)r0r0)Frm)rnrorprqrFrrNrrrrrrrrrrrrrrr{rr[rrrrrrr0r0r0r1rs:             rrwc@seZdZdZeedfddZddZddZd d Z d d Z d dZ d9ddZ d9ddZ ddZd:ddZd;ddZd;ddZd;ddZd;dd Zd;d!d"Zd;d#d$Zd;d%d&Zd;d'd(Zd;d)d*Zd;d+d,Zd;d-d.Zd;d/d0Zd;d1d2Zd;d3d4Zd;d5d6Zd;d7d8ZdS)<Analysisz:Provide methods for enhanced analysis and pretty printing.TcCs<t||||_||_||_|jr||j|jdSdS)aInitialize an Analysis with RestrictionBatch and sequence. For most of the methods of this class if a dictionary is given it will be used as the base to calculate the results. If no dictionary is given a new analysis using the RestrictionBatch which has been given when the Analysis class has been instantiated, will be carried out and used. N)rrFrbsequencer@r)rDrestrictionbatchrr@r0r0r1rFs zAnalysis.__init__cCsd|jd|jd|jdS)z)Represent ``Analysis`` class as a string.z Analysis(rirL)rrr@rIr0r0r1rNszAnalysis.__repr__csfdd|jDS)zFilter result for keys which are in wanted (PRIVATE). Internal use only. Returns a dict. Screen the results through wanted set. Keep only the results for which the enzymes is in wanted set. ci|] \}}|vr||qSr0r0rmwantedr0r1rz%Analysis._sub_set..rrr)rDrr0rr1_sub_sets zAnalysis._sub_setcCst|tstdt|dt|tstdt|d|dkr)|t|j7}|dkr4|t|j7}||kr9n||}}||krH|||jfSdS)zSet boundaries to correct values (PRIVATE). Format the boundaries for use with the methods that limit the search to only part of the sequence given to analyse. zexpected int, got rrGN)r7intr>rCrHr _test_normal)rDraendr0r0r1 _boundariess    zAnalysis._boundariescCs||ko |kSS)zTTest if site is between start and end (PRIVATE). Internal use only r0rDrarrr0r0r1r szAnalysis._test_normalcCs6||ko t|jknpd|ko|kSS)zmTest if site is between end and start, for circular sequences (PRIVATE). Internal use only. rG)rHrrr0r0r1 _test_reverse s6zAnalysis._test_reverseNrwcCs|s|j}t||||S)zhCollect data and pass to PrintFormat. If dct is not given the full dictionary is used. )rr format_outputrDrtitles1r0r0r1r szAnalysis.format_outputcCst||||dS)zPrint the output of the analysis. If dct is not given the full dictionary is used. s1: Title for non-cutting enzymes This method prints the output of A.format_output() and it is here for backwards compatibility. N)rrrr0r0r1 print_that szAnalysis.print_thatcKs|D]n\}}|dvr!t||||j|j|_|j|j|_q|dkr4t|d|||j|jq|dkrCt |||j|j}q|dkrUt|d|||j|q|dvr`t|||q|dvrlt d|dt d |d S) aChange parameters of print output. It is possible to change the width of the shell by setting self.ConsoleWidth to what you want. self.NameWidth refer to the maximal length of the enzyme name. Changing one of these parameters here might not give the results you expect. In which case, you can settle back to a 80 columns shell or try to change self.Cmodulo and self.PrefWidth in PrintFormat until you get it right. ) NameWidth ConsoleWidthrrr@)IndentMaxsize)Cmodulo PrefWidthz To change z&, change NameWidth and/or ConsoleWidthzAnalysis has no attribute N) rrsetattrrrrrrrr@rrFr|)rDwhatrnror0r0r1change' s*     zAnalysis.changecCr^)zPerform analysis with all enzymes of batch and return all results. Full Restriction Map of the sequence, as a dictionary. )r)rDr@r0r0r1fullI sz Analysis.fullcC|s|j}dd|DS)z&Return only cuts that have blunt ends.cSi|] \}}|r||qSr0r.rmr0r0r1rT rz"Analysis.blunt..rrDrr0r0r1r-P zAnalysis.bluntcCr)z(Return only cuts that have 5' overhangs.cSrr0r7rmr0r0r1rZ rz&Analysis.overhang5..rrr0r0r1 overhang5V rzAnalysis.overhang5cCr)z(Return only cuts that have 3' overhangs.cSrr0r>rmr0r0r1r` rz&Analysis.overhang3..rrr0r0r1 overhang3\ rzAnalysis.overhang3cCr)z@Return only results from enzymes that produce defined overhangs.cSrr0)rArmr0r0r1rf rz$Analysis.defined..rrr0r0r1definedb rzAnalysis.definedcCr)z6Return only results from enzyme with at least one cut.cSsi|] \}}|r||qSr0r0rmr0r0r1rl rgz'Analysis.with_sites..rrr0r0r1 with_sitesh rzAnalysis.with_sitescCr)z=Return only results from enzymes that don't cut the sequence.cSsi|] \}}|s||qSr0r0rmr0r0r1rr rgz)Analysis.without_site..rrr0r0r1 without_siten rzAnalysis.without_sitec |s|j}fdd|DS)z?Return only results from enzymes that cut the sequence N times.cs"i|] \}}t|kr||qSr0rHrmr&r0r1rx rpz)Analysis.with_N_sites..r)rDr&rr0rr1 with_N_sitest zAnalysis.with_N_sitescr)z.r)rDrrr0rr1with_number_listz rzAnalysis.with_number_listcs\t|D]\}}|tvrtd|t||=qs%t||j|jSfdd|DS)z8Return only results from enzymes which names are listed.zno data for the enzyme: csi|] }|vr||qSr0r0)rdr~rr0r1r rz&Analysis.with_name..) rrwarningswarnrrrrr@)rDnamesrrerr0rr1 with_name szAnalysis.with_namecs<fdd|D}|st||jSfdd|DS)z8Return only results form enzymes with a given site size.csg|] }|jkr|qSr0)rk)rdr site_sizer0r1rf rgz+Analysis.with_site_size..crr0r0rmrr0r1r rz+Analysis.with_site_size..)rrrrr)rDrrsitesr0rr1with_site_size szAnalysis.with_site_sizec Csd|||\}}}|s|j}t|}|D]\}}|s ||=q|D] }||||r+q"||=q|S)zAReturn only results from enzymes that only cut within start, end.rrrrr rDrarrtestr%keyrrr0r0r1 only_between s zAnalysis.only_betweenc CsX|||\}}}i}|s|j}|D]\}}|D]}||||r(|||<nqq|S)zReturn only results from enzymes that cut at least within borders. Enzymes that cut the sequence at least in between start and end. They may cut outside as well. rrrrrr0r0r1between s zAnalysis.betweencs`g}krfdd||D}t|Sfdd||D}t|S)zReturn only results from within start, end. Enzymes must cut inside start/end and may also cut outside. However, only the cutting positions within start/end will be returned. c(g|]\}}|fdd|DfqS)cs(g|]}|krkrnn|qSr0r0rdvvrrar0r1rf s(9Analysis.show_only_between...r0rmrr0r1rf z.Analysis.show_only_between..cr)cs g|] }|ks |kr|qSr0r0rrr0r1rf rrr0rmrr0r1rf r)rrrrrDrarrr%r0rr1show_only_between s  zAnalysis.show_only_betweenc Csf|||\}}}|s|j}t|}|D]\}}|s ||=q|D] }||||r/||=nq"q|S)zReturn only results from enzymes that only cut outside start, end. Enzymes that cut the sequence outside of the region in between start and end but do not cut inside. rrr0r0r1 only_outside s zAnalysis.only_outsidec CsV|||\}}}|s|j}i}|D]\}}|D] }||||r#q|||<q|S)zReturn only results from enzymes that at least cut outside borders. Enzymes that cut outside the region in between start and end. They may cut inside as well. rrr0r0r1outside s zAnalysis.outsidecCs*|s|j}|}||||||S)z@Return only results from enzymes that don't cut between borders.)rrupdaterrr0r0r1 do_not_cut s zAnalysis.do_not_cut)Nrwrwrmr) rnrorprq_restrictionbatch _empty_DNArFrNrrrrrrrrr-rrrrrrrrrrrrrrrr0r0r0r1rs:     "              rccrr)r}rr0r0r1r$ rrcCrr0rrr0r0r1rfB rrf)r3rrrCommOnlyNonComm)Drq itertoolsrhrrrBiorBio.Restriction.PrintFormatr&Bio.Restriction.Restriction_Dictionaryr enzymedictrrrBio.Seqrrr\rr,r2r3rCrvrrrrrrrrr r r4r=r?rTrcrgrzrrrrrrrrrTYPErenzymesr)bases2__new__rrnnewenzryrrrrlocalsrr__all__r0r0r0r1s J        v+YOQ *] wp&( E