DUfdZddlZddlZddlZddlmZddlZddlmZejdZ dZ dZ dZ d Z d d ZdS) z Interface between pybedtools and the R package VennDiagram. Rather than depend on the user to have rpy2 installed, this simply writes an R script that can be edited and tweaked by the user before being run in R. N)helpers) OrderedDictzb library(VennDiagram) venn.diagram( x=$x, filename=$filename, category.names = $names cg}|D]W}t|tjr#t|dd}|d|zXdd|zS)z Convert items in `x` to a string, and replace tabs with pipes in Interval string representations. Put everything into an R vector and return as one big string.  |"%s"zc(%s),) isinstance pybedtoolsIntervalstrreplaceappendjoin)xitemsis Z/var/www/html/software/conda/lib/python3.11/site-packages/pybedtools/contrib/venn_maker.py_list_to_R_syntaxrst E !! a, - - *AtS))A VaZ    SXXe__ $$c g}t|D]-\}}|d|dt|.dd|zS)zI Calls _list_to_R_syntax for each item. Returns one big string. "z" = zlist(%s), )listrrrr)drkeyvals r_dict_to_R_named_listr+so EOOBBS CCC):3)?)?)?@AAAA  %(( ((rctj|jt|jt|jgS)z= Convert a feature of any format into a BED3 format. )r create_interval_from_listchromr startstop)features r truncatorr%5s9  / GM**C ,=,=>  rcFt|dkr|dt}|dt}||z ||z}||fSt|dkr|dt}|dt}|dt}||z ||z}||z |z ||z||z |z}|||fSt|dkrv|dt}|dt}|dt}|dt}||z ||z}||z |z ||z||z |z}||z |z |z ||z||z |z||z |z |z}||||fSdS)at Perform interval intersections such that the end products have identical features for overlapping intervals. The VennDiagram package does *set* intersection, not *interval* intersection. So the goal here is to represent intersecting intervals as intersecting sets of strings. Doing a simple BEDTools intersectBed call doesn't do the trick (even with the -u argument). As a concrete example, what would the string be for an intersection of the feature "chr1:1-100" in file `x` and "chr1:50-200" in file `y`? The method used here is to substitute the intervals in `y` that overlap `x` with the corresponding elements in `x`. This means that in the resulting sets, the overlapping features are identical. To follow up with the example, both `x` and `y` would have an item "chr1:50-200" in their sets, simply indicating *that* one interval overlapped. Venn diagrams are not well suited for nested overlaps or multi-overlaps. To illustrate, try drawing the 2-way Venn diagram of the following two files. Specifically, what number goes in the middle -- the number of features in `x` that intersect `y` (1) or the number of features in `y` that intersect `x` (2)?:: x: chr1 1 100 chr1 500 6000 y: chr1 50 100 chr1 80 200 chr9 777 888 In this case, this function will return the following sets:: x: chr1:1-100 chr1:500-6000 y: chr1:1-100 chr9:777-888 This means that while `x` does not change in length, `y` can. For example, if there are 2 features in `x` that overlap one feature in `y`, then `y` will gain those two features in place of its single original feature. This strategy is extended for multiple intersections -- see the source for details. rN)leneachr%saveascat)rrynew_yznew_zqnew_qs rcleaned_intersectr5>sh 5zzQ !HMM) $ $ + + - - !HMM) $ $ + + - -Q AE""%x 5zzQ !HMM) $ $ + + - - !HMM) $ $ + + - - !HMM) $ $ + + - -Q AE"" QA&&**AEQ;77% 5zzQ !HMM) $ $ + + - - !HMM) $ $ + + - - !HMM) $ $ + + - - !HMM) $ $ + + - -Q AE""QA&&**AEQ;77QQ##AE**..A{;;??QaPP%%%'rFcN|d}nd|z}|ddt|}g}|D]E}t|tjstj|}||Ft |}t tt||} t t| |t|} |r| dd |zz } | dz } |stj} n|} t| d } | | | | d z} |rtjjst)jt,j tjjd d d | | g}t3j|t2jt2j}|\}}|s|r t;d|t;d||s| SdS)a Given a list of interval files, write an R script to create a Venn diagram of overlaps (and optionally run it). The R script calls the venn.diagram function of the R package VennDiagram for extremely flexible Venn and Euler diagram creation. Uses `cleaned_intersect()` to create string representations of shared intervals. `beds` is a list of up to 4 filenames or BedTools. `names` is a list of names to use for the Venn diagram, in the same order as `beds`. Default is "abcd"[:len(beds)]. `figure_filename` is the TIFF file to save the figure as. `script_filename` is the optional filename to write the R script to `additional_args` is list that will be inserted into the R script, verbatim. For example, to use scaled Euler diagrams with different colors, use:: additional_args = ['euler.d=TRUE', 'scaled=TRUE', 'cat.col=c("red","blue")'] If `run` is True, then assume R is installed, is on the path, and has VennDiagram installed . . . and run the script. The resulting filename will be saved as `figure_filename`. NNULLrabcd)rfilenamenamesr r)wz.RoutRCMDBATCH)stdoutstderrzstdout:zstderr:)r+r r BedToolrr5rrziptemplate substituterrr_tmpopenwriteclosesettings _R_installedr _check_for_Rospath_R_path subprocessPopenPIPE communicateprint)bedsr:figure_filenamescript_filenameadditional_argsrun_bedsbedcleanedresultssfnfoutoutcmdspr@rAs r venn_makerrdsL  ?2 }{T{# E#z122 *$S))C S&&G$s5'223344G  ( ( &&   A . S499_-- --HA    $ $ & &  C==DJJqMMMJJLLL w,C %"/ #  " " " Z08#>>wPRTWX  T*/*/ R R R  %V % )V $ $ $ )V $ $ $  4r)NNNNF)__doc__rMstringr rrP collectionsrTemplaterDrrr%r5rdrrrjs  ###### 6?   % % %)))`&`&`&J  [[[[[[r