DUf+ddlmZddlmZddlZddlZddlZ ddl Z ddl Z ddl m Z ddlZddlmZddlmZmZmZddlmZmZdd l mZejejd d e ejd deeedejddeeedejdddejddgddejddeddejdd eddejd!d"d#ed$dejd%d&d'eefd(d)ejd*d+eefd(dejd,d-ed.dejd/d0dd12ejd3d4d5ej d6d17ejd8d9d:d;ejd<ejgd=dd>?ejd@dAejdBdCgdCdejdDdEdFdGejdHdIedJKejdLdMedKejdNdOPejdQdRdSdd12dTZ!dS)U)partialN)api) validate_csv)make_cooler_viewmask_cooler_bad_binsalign_track_with_cooler)read_viewframe_from_fileread_expected_from_file)cli cool_path COOL_PATH)metavartype track_path TRACK_PATHE1)default_column)rrcallback expected_path EXPECTED_PATHz balanced.avgz-tz--contact-typez!Type of the contacts to aggregatecistransT)helprdefault show_defaultz --min-distzMinimal distance between bins to consider, bp. If negative, removesthe first two diagonals of the data. Ignored with --contact-type trans.z --max-distzgMaximal distance between bins to consider, bp. Ignored, if negative. Ignored with --contact-type trans.z-nz--n-binsz+Number of bins for digitizing track values.2z--vrangevrangea7Low and high values used for binning genome-wide track values, e.g. if `range`=(-0.05, 0.05), `n-bins` equidistant bins would be generated. Use to prevent extreme track values from exploding the bin range and to ensure consistent bins across several runs of `compute_saddle` command using different track files.)NN)rrrnargsz--qrangea(Low and high values used for quantile bins of genome-wide track values,e.g. if `qrange`=(0.02, 0.98) the lower bin would start at the 2nd percentile and the upper bin would end at the 98th percentile of the genome-wide signal. Use to prevent the extreme track values from exploding the bin range.z--clr-weight-namez$Use balancing weight with this name.weightz--strength/--no-strengthz6Compute and save compartment 'saddle strength' profileF)ris_flagrz--viewz --regionsa Path to a BED file containing genomic regions for which saddleplot will be calculated. Region names can be provided in a 4th column and should match regions and their names in expected. Note that '--regions' is the deprecated name of the option. Use '--view' instead. )exists)rrrequiredz-oz --out-prefixzDump 'saddledata', 'binedges' and 'hist' arrays in a numpy-specific .npz container. Use numpy.load to load these arrays into a dict-like object. The digitized signal values are saved to a bedGraph-style TSV.)rr%z--fig)pngjpgsvgpdfpsepszGenerate a figure and save to a file of the specified format. If not specified - no image is generated. Repeat for multiple output formats.)rmultiplerz--scalezValue scale for the heatmaplinearlogz--cmapzName of matplotlib colormapcoolwarm)rrrz--vminzLow value of the saddleplot colorbar. Note: value in original units irrespective of used scale, and therefore should be positive for both vmin and vmax.g?)rrrz--vmaxz%High value of the saddleplot colorbarz --hist-colorz!Face color of histogram bar chart)rz-vz --verbosezEnable verbose outputc|tj|}|\}}|\}}ddd|g}dtjdtjdtj|tji}t j|||d|}t|}| |}nt| |d}tj d| dD}|g}t||||| }|d krd }n)ttj||jz }|d kr*ttj||jz } nd } | r.t'||f|dd| f}|d d}|d d}||t+d t-|||| dd}t.j|jddddf|||d\}!}"t.j|||!|ddd|| |d|| |\}#}$|#|$z }%t7|%|"|!|$}&| r/t.j|#|$}'|'dd }'|'|&d<tj| dzfi|&|!| dzddt?| r d dl }(|(!dd dl"m#})n?#tH$r2tKdtLj'tMj(dYnwxYw|d}*n|(j)j*+|}*tYj-|d .|z}+||d!z},n|},d"}-t.j/||%|||||||*|+|,|,|-|#| D]!}.|)0| d$z|.zd%& dSdS)'a Calculate saddle statistics and generate saddle plots for an arbitrary signal track on the genomic bins of a contact matrix. COOL_PATH : The paths to a .cool file with a balanced Hi-C map. Use the '::' syntax to specify a group path in a multicooler file. TRACK_PATH : The path to bedGraph-like file with a binned compartment track (eigenvector), including a header. Use the '::' syntax to specify a column name. EXPECTED_PATH : The paths to a tsv-like file with expected signal, including a header. Use the '::' syntax to specify a column name. Analysis will be performed for chromosomes referred to in TRACK_PATH, and therefore these chromosomes must be a subset of chromosomes referred to in COOL_PATH and EXPECTED_PATH. COOL_PATH, TRACK_PATH and EXPECTED_PATH must be binned at the same resolution (expect for EXPECTED_PATH in case of trans contact type). EXPECTED_PATH must contain at least the following columns for cis contacts: 'chrom', 'diag', 'n_valid', value_name and the following columns for trans contacts: 'chrom1', 'chrom2', 'n_valid', value_name value_name is controlled using options. Header must be present in a file. chromstartendN)usecolsdtypecommentverboseT) check_sortingcg|]H\}}|jjdtj|jtj|jfIS)r)r1ilocnpnanminr2nanmaxr3).0igroups Q/var/www/html/software/conda/lib/python3.11/site-packages/cooltools/cli/saddle.py zsaddle..sU   5[ a ")EK"8"8")EI:N:N O   ) contact_typeexpected_value_cols verify_view verify_coolerrrz,only one of vrange or qrange can be suppliedF)view_dfclr_weight_namemask_clr_bad_bins drop_track_naz.d)r qrangedigitized_suffixname) r rNrIrJexpected_value_col view_name_colmin_diagmax_diagr7) saddledatabinedges digitized saddlecountsrsaddle_strengthz .saddledumpz.digitized.tsv )sepindexAggzInstall matplotlib to use )file)g?g?g?z ({})z quantilesz(contact frequency / expected)) r rNscalevminvmaxcolortitlexlabelylabelclabelcmap.tight) bbox_inches)1coolerCoolerr;str_int64float64pd read_tablerr bioframemake_viewframe reset_indexgroupbyr intceilbinsizefloorr bins ValueErrorr rsaddledigitizer:dictrYsavezto_csvlen matplotlibusematplotlib.pyplotpyplot ImportErrorprintsysstderrexitcolorscolorConverterto_rgbopbasenameformat saddleplotsavefig)/rrrrDmin_distmax_distn_binsr rNrJstrengthview out_prefixfigr_rgr`ra hist_colorr7clrrQ track_name track_columns track_dtypetrackcooler_view_dfrI track_view_dfexpected_summary_colsexpectedrSrTdigitized_trackrVSCrUto_saveratiosmplpltrbrc track_labelrfexts/ rAr|r|sv - " "C(5%M%'J guj9M  rxBJ K M    E&c**N | *4DIII+  !--//77@@   M '!1 H!||rwx#+566771}}rx3; 67788 $ J #((**QQQ-!A  ay ay!3GHHH $  '    E!$ 3 3 111bqb5 !4!!OX :    '-   DAq QJ! G,++Aq11"%+!"HZ- '337333:(88d%PPP 3xx-E  $ $ $ $ GGENNN + + + + + + +    .SZ @ @ @ @ HQKKKKK   EE J-44Z@@E I&& )E)EE  $|3KK$K1        " E EC KK S(3.GK D D D D[-E-EX E Es2K9L L)" functoolsros.pathpathrrpandasrpnumpyr;rkrrrclickutilr lib.commonrr r lib.ior r r commandargumentstroptionChoicervfloatPathr|rCrArs5   XXXXXXXXXXFFFFFFFF 3  W\$ 7 7 7    W\. A A A   , ug& ' '   N   *   6    #       L      /   A      Z 4      ??? @ @    & x' ( (   0*SW  ?    :PQn#FGGG +3T5aEaEHG         RaEaEaErC