o Rŀg:$@sfdZdZGdddZGdddZddZdd Zd d Zd d Zedkr1ddl m Z e dSdS)z:Tools to manipulate data from nmrview .xpk peaklist files.c@seZdZdZddZdS)XpkEntryaProvide dictionary access to single entry from nmrview .xpk file. This class is suited for handling single lines of non-header data from an nmrview .xpk file. This class provides methods for extracting data by the field name which is listed in the last line of the peaklist header. Parameters ---------- xpkentry : str The line from an nmrview .xpk file. xpkheadline : str The line from the header file that gives the names of the entries. This is typically the sixth line of the header, 1-origin. Attributes ---------- fields : dict Dictionary of fields where key is in header line, value is an entry. Variables are accessed by either their name in the header line as in self.field["H1.P"] will return the H1.P entry for example. self.field["entrynum"] returns the line number (1st field of line) cCsR|}|}tt||dd|_z |d|jd<WdSty(YdSw)Initialize the class.Nentrynum)splitdictzipfields IndexError)selfentryheadlinedatlistheadlistrD/var/www/html/myenv/lib/python3.10/site-packages/Bio/NMR/xpktools.py__init__$s zXpkEntry.__init__N)__name__ __module__ __qualname____doc__rrrrrr s rc@s(eZdZdZddZddZddZdS) Peaklista;Provide access to header lines and data from a nmrview xpk file. Header file lines and file data are available as attributes. Parameters ---------- infn : str The input nmrview filename. Attributes ---------- firstline : str The first line in the header. axislabels : str The axis labels. dataset : str The label of the dataset. sw : str The sw coordinates. sf : str The sf coordinates. datalabels : str The labels of the entries. data : list File data after header lines. Examples -------- >>> from Bio.NMR.xpktools import Peaklist >>> peaklist = Peaklist('../Doc/examples/nmr/noed.xpk') >>> peaklist.firstline 'label dataset sw sf ' >>> peaklist.dataset 'test.nv' >>> peaklist.sf '{599.8230 } { 60.7860 } { 60.7860 }' >>> peaklist.datalabels ' H1.L H1.P H1.W H1.B H1.E H1.J 15N2.L 15N2.P 15N2.W 15N2.B 15N2.E 15N2.J N15.L N15.P N15.W N15.B N15.E N15.J vol int stat ' cCst|M}|dd|_|dd|_|dd|_|dd|_|dd|_|dd|_dd|D|_ WddS1sTwYdS)r rcSsg|] }|ddqS)rr)r).0linerrr jsz%Peaklist.__init__..N) openreadliner firstline axislabelsdatasetswsf datalabelsdata)r infninfilerrrr^s "zPeaklist.__init__c Csd}d}i|_|jD]M}t||jj|d}|dd}t|}|dkr(|}|dkr.|}t||g}t||g}t |}z |j| |Wq t yW|g|j|<Yq w||jd<||jd<|jS)aReturn a dict of lines in 'data' indexed by residue number or a nucleus. The nucleus should be given as the input argument in the same form as it appears in the xpk label line (H1, 15N for example) Parameters ---------- index : str The nucleus to index data by. Returns ------- resdict : dict Mappings of index nucleus to data line. Examples -------- >>> from Bio.NMR.xpktools import Peaklist >>> peaklist = Peaklist('../Doc/examples/nmr/noed.xpk') >>> residue_d = peaklist.residue_dict('H1') >>> sorted(residue_d.keys()) ['10', '3', '4', '5', '6', '7', '8', '9', 'maxres', 'minres'] >>> residue_d['10'] ['8 10.hn 7.663 0.021 0.010 ++ 0.000 10.n 118.341 0.324 0.010 +E 0.000 10.n 118.476 0.324 0.010 +E 0.000 0.49840 0.49840 0'] z.L.rmaxresminres) rr%rr$r rintmaxminstrappendKeyError)r indexr*r+rindkeyresrrr residue_dictls,      zPeaklist.residue_dictcCst|dK}||j|d||j|d||j|d||j|d||j|d||j|dWddS1sSwYdS)z7Write header lines from input file to handle ``outfn``.wrN)rwriterr r!r"r#r$)r outfnoutfilerrr write_headers             "zPeaklist.write_headerN)rrrrrr6r;rrrrr3s * ;rcCsJt||}t||dd}|d|t||||d}|S)zReplace an entry in a string by the field number. No padding is implemented currently. Spacing will change if the original field entry and the new field entry are of different lengths. Nr)_find_start_entrylenrr/)rfieldnnewentrystartlengnewlinerrr replace_entrys $rCcCs|dkrdSd}t|}|ddkrd}d}nd}d}||krN||krN|rB||dkr6||ddkr6d}n ||dkrBd}|d7}|d7}||krN||ks#|dS)a"Find the starting character for entry ``n`` in a space delimited ``line`` (PRIVATE). n is counted starting with 1. The n=1 field by definition begins at the first character. Returns ------- starting character : str The starting character for entry ``n``. rr FT)r=)rncrAinfieldfieldrrrr<s&   r<cCsg}t||\}}|dd}|dd}|D]}||dkr#|d}||dkr-|d}q|} | |krsd} t| } | } |D]#}|| } | |vrY| dt|| d| j|} n| d7} | d7} q>| d7} || | d7} | |ks4|S)azGenerate a data table from a list of input xpk files. Parameters ---------- fn_list : list List of .xpk file names. datalabel : str The data element reported. keyatom : str The name of the nucleus used as an index for the data table. Returns ------- outlist : list List of table rows indexed by ``keyatom``. rr+r* z *rr) _read_dictsr/rr r0)fn_list datalabelkeyatomoutlist dict_listlabel_line_listminrmaxr dictionaryr5countr4rlabelrrr data_tables6      rVcCsBg}g}|D]}t|}||}||||jq||gS)zBRead multiple files into a list of residue dictionaries (PRIVATE).)rr6r0r$)rKrMrOdatalabel_listfnpeaklistrSrrrrJ)s  rJ__main__r) run_doctestN) r HEADERLENrrrCr<rVrJr Bio._utilsr[rrrrs),6