ó ËdTc@sâddlZddlZddlmZddlmZddlmZmZddl m Z ddl m Z ddl m Z ddlZdfd „ƒYZed krÞd GHddlZejejjƒd d ƒe_ndS(iÿÿÿÿN(tdeepcopy(tWig(trt FloatVector(ttime(trandint(tlogtreadscBs+eZdddeddd„Zddd„Zd„Zddd „Zdddd „Zdddd „Zdddd „Z dddd „Z dddd„Z dddd„Z dddd„Z dddd„Zd„Zdd„Zd„Zd„Zd„Zddddd„Zdd„ZRS(tii g»½×Ùß|Û=tbedcCsi|_||_||_|dkr[|dkr[|r[|jd|d|jd|ƒn¨|dkr•|dkr•|jd|d|jd|ƒnn|dkrÕ|dkrÕ|rÕ|jd|d|jd|ƒn.|dkr|dkr|jd|d|jd|ƒnô|dkrO|dkrO|rO|jd|d|jd|ƒn´|dkr‰|dkr‰|jd|d|jd|ƒnz|dkrÉ|dkrÉ|rÉ|j d|d|jd|ƒn:|dkr|dkr|j d|d|jd|ƒnd S( s] Description: Initialize an instance of the class "reads". Parameters: rlen: read length step: each chrosome will present as an vector, each value in the vector represent a short region of the chrosome, the step value is the size of the short region paired: is the reads paired-end cut: the cutoff for removing clonal reads, could be P value larger than 0 and small than 1, or count as a positive integer. format: the file format of the reads data, can be 'bed','bam',or 'sam' Value: None RR tfiletsteptcuttbamtsamtbowtieN( tdatatrlenR t loadBedPairedtloadBedt loadBamPairedtloadBamt loadSamPairedtloadSamtloadBowtiePairedt loadBowtie(tselfR RR tpairedR tformat((sE/oak/stanford/groups/akundaje/marinovg/programs/danpos-2.2.2/reads.pyt__init__ s&   """""""i,c Cs¾|j}||:}||d}dGHi}x,t||ƒD]}d||||||||g} |d 7}|d dkr¤|GdGHnWndG| d GHqsnX| d d | d d krï| ddkr6| ddkr6| d| d | d d || d | d }}}nŠ| ddkr‘| ddkr‘| d| d | d d || d | d }}}n/dG| GdG| GdGH|d 7}gg} } qs|j|ƒsÜd ||H     3 "% " +"      cCsÜdG|GdGHd}i}d}tjd|ƒ}xò|D]ê}y“|jdƒ} d| dkrgw9n| d| d d t| d ƒt| d ƒf\} } } } }d | dkrÀd} n| |d}}Wn|jƒGHq9nX|d7}|ddkr|GdGHn| d kr)| |}n| dkrB||}n|jj| ƒs”itjdgƒd 6tjdgƒd6|j| sR  @      3 "% " +" cCs8dG|GdGHd}i}i}d}tjd|ƒ}xl|D]d} y?| jdƒ} d| dkrmw?nt| d ƒt| d ƒt| d ƒ| d <| d <| d <| d| d d d| d | d | d d |f\} } } }}d| dkr d} n| d | d kr=| d | d | d }n| d | d | d }|j|ƒssd||H     3 "% " +"      cCs|jƒd|jƒS(s± Description: calculate the average reads count per nucleotide Parameter: None Value: None gð?(R@R"(R((sE/oak/stanford/groups/akundaje/marinovg/programs/danpos-2.2.2/reads.pyR#­s cCs tƒ}t|ƒ}|dkr%dSdGH|jƒ|j}|dkrí|dkrítdƒ}dt|ƒtdƒ}t|dƒ}xGdtt|||ƒƒjƒdƒtdƒ|krÔ|d7}qŽW|dkríd}qínd G|Gd G|GH||j9}d}d}d}t j d gƒ} |j ƒ} d G| Gd GHx}|j D]r} xi|j | j ƒD]T} t|j | | ƒ} | |8} | dd| d} |j | | c| 8R#R RRR=R)R?R8RYR@RR%R(RR tssRFRGRHtcnumtrreadsttreadsttchrvtbeforeR0RJtafter((sE/oak/stanford/groups/akundaje/marinovg/programs/danpos-2.2.2/reads.pyRZ¹s@    <       cCsUd}xA|jD]6}x-|j|D]}||j||j7}q$WqW||jS(sÅ Description: Calculate the total genome size. Parameter: None value: Interger value representing genome size. i(RR"R (RRdR0RJ((sE/oak/stanford/groups/akundaje/marinovg/programs/danpos-2.2.2/reads.pyR"ãs  cCs¼i}x?t|ƒD]1}|jƒ}t|dƒ|j||d^=\/>0? *   "t__main__RR i(R8RvtcopyRR‘Rt rpy2.robjectsRRRtrandomRtmathRRVRR˜tsystfdopentstdouttfileno(((sE/oak/stanford/groups/akundaje/marinovg/programs/danpos-2.2.2/reads.pyts ÿÿÿT