DUfddlmZddlZddlZddlZddlmZddlmZddlm Z ddl m Z m Z dd l mZejej ejejd d ed ejddeeedejdddejddddejddeddejdddde ejd!d"ed#dejd$d%eddejd&d'ed(dejd)d*ed+dejd,d-ed.dejd/d0ed1dejd2d3d4dd5ejd6d7d8ed9d:ZdS);)partialN)cli)api)make_cooler_view)read_viewframe_from_fileread_expected_from_file) validate_csv)level cool_path COOL_PATH)metavartypenargs expected_path EXPECTED_PATHz balanced.avg)default_column)rrcallbackz--viewz --regionsaPath to a BED file with the definition of viewframe (regions) used in the calculation of EXPECTED_PATH. Dot-calling will be performed for these regions independently e.g. chromosome arms. Note that '--regions' is the deprecated name of the option. Use '--view' instead. F)existsdir_okayT)helprdefault show_defaultz--clr-weight-namez+Use cooler balancing weight with this name.weightz-pz--nproczQNumber of processes to split the work between. [default: 1, i.e. no process pool])rrrz--max-loci-separationzLimit loci separation for dot-calling, i.e., do not call dots for loci that are further than max_loci_separation basepair apart. 2-20MB is reasonable and would capture most of CTCF-dots.iz--max-nans-tolerateda&Maximum number of NaNs tolerated in a footprint of every used filter. Must be controlled with caution, as large max-nans-tolerated, might lead to pixels scored in the padding area of the tiles to "penetrate" to the list of scored pixels for the statistical testing. [max-nans-tolerated <= 2*w ]z --tile-sizezlTile size for the Hi-C heatmap tiling. Typically on order of several mega-bases, and <= max_loci_separation.i[z--num-lambda-binsz}Number of log-spaced bins to divide your adjusted expected between. Same as HiCCUPS_W1_MAX_INDX (40) in the original HiCCUPS.-z--fdrzZFalse discovery rate (FDR) to control in the multiple hypothesis testing BH-FDR procedure.g{Gz?z--clustering-radiusz}Radius for clustering dots that have been called too close to each other.Typically on order of 40 kilo-bases, and >= binsize.iXz-vz --verbosezEnable verbose output)ris_flagrz-oz--outputzDSpecify output file name to store called dots in a BEDPE-like format)rrrequiredc tj|} |\}}|t| }nt|| d}t |d|g|| }t j| ||||d|||| | d||}| r|| dddd dSt|| dddd dS) a Call dots on a Hi-C heatmap that are not larger than max_loci_separation. COOL_PATH : The paths to a .cool file with a balanced Hi-C map. 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 EXPECTED_PATH, and therefore these chromosomes must be a subset of chromosomes referred to in COOL_PATH. Also chromosomes refered to in EXPECTED_PATH must be non-trivial, i.e., contain not-NaN signal. Thus, make sure to prune your EXPECTED_PATH before applying this script. COOL_PATH and EXPECTED_PATH must be binned at the same resolution. EXPECTED_PATH must contain at least the following columns for cis contacts: 'region1/2', 'dist', 'n_valid', value_name. value_name is controlled using options. Header must be present in a file. NT) check_sortingcis) contact_typeexpected_value_cols verify_view verify_cooler) expected_value_colclr_weight_nameview_dfkernelsmax_loci_separationmax_nans_tolerated n_lambda_binslambda_bin_fdrclustering_radiuscluster_filtering tile_sizenproc Fnan)sepheaderindexna_rep) coolerCoolerrr r r dotfinderdotsto_csvprint)r rviewr'r1r*r+r0num_lambda_binsfdrr.verboseoutputclrr&r(expected dot_calls_dfs O/var/www/html/software/conda/lib/python3.11/site-packages/cooltools/cli/dots.pyr;r;s'P - " "C(5%M% |"3''*4DIII&/0 H=%% -'/-%+&L$ FTuUUUUU    DU5        ) functoolsrr8loggingclickrr lib.commonrlib.ior r utilr basicConfigINFOcommandargumentstroptionPathintfloatr;rGrFrYs  ))))))FFFFFFFF',''''      W\. A A A    Z 55 1 1 1     6    *  A  R     M   J    ,    ;  +3T5 O  O O       HO O O rG