DUf:ddlmZddlmZddlmZddlZddlmZddl m Z e j ej d d e eed  ej dde dejdddedddejdddejddgdddejdddedddejd d!d"edd#dejd$d%d&ejgd'd(dd)ejd*d+d,ejgd'd-dd)ejd.d/d0ed1d2ZdS)3)partial)expected)read_expected_from_fileN) validate_csv)cli expected_path EXPECTED_PATHz balanced.sum)default_column)metavartypecallback output_prefix OUTPUT_PREFIX)r rnargsz--bins-per-order-magnitudebins_per_order_magnitudezaHow many bins per order of magnitude. Default of 10 has a ratio of neighboring bins of about 1.25 T)r helprrdefault show_defaultz --bin-layout bin_layoutaZ'fixed' means that bins are exactly the same for different datasets, and only depend on bins_per_order_magnitude 'longest_regio' means that the last bin will end at size of the longest region. GOOD: the last bin will have as much data as possible. BAD: bin edges will end up different for different datasets, you can't divide them by each otherfixedlongest_regionz --min-nvalid min_nvalida For each region, throw out bins (log-spaced) that have less than min_nvalid valid pixels. This will ensure that each entree in Pc by region has at least n_valid valid pixels. Don't set it to zero, or it will introduce bugs. Setting it to 1 is OK, but not recommended.z --min-count min_countzIf counts are found in the data, then for each region, throw out bins (log-spaced) that have more than min_counts of counts.sum (raw Hi-C counts). This will ensure that each entree in P(s) by region has at least min_count raw Hi-C reads2z--spread-funcs spread_funcsa A way to estimate the spread of the P(s) curves between regions. * 'minmax' - the minimum/maximum of by-region P(s) * 'std' - weighted standard deviation of P(s) curves (may produce negative results) * 'logstd' (recommended) weighted standard deviation in logspace)minmaxstdlogstdr")r rrrrrz--spread-funcs-slopespread_funcs_slopezASame as spread-funcs, but for slope (derivative) ratehr than P(s)r!z --resolution resolutionzlData resolution in bp. If provided, additonal column of separation in bp (s_bp) will be added to the outputs)r rrrc |\}} | g} d| vr| dt|d| } | d^} } | d}tj| | ||||\}}}tj|||||\}}||d |z|d <|d |z|d <||d d d d||dd d ddS)a Logarithmically bin expected values generated using compute_expected for cis data. This smoothes the data, resulting in clearer plots and more robust analysis results. Also calculates derivative after gaussian smoothing. For a very detailed escription, see https://github.com/open2c/cooltools/blob/51b95c3bed8d00a5f1f91370fc5192d9a7face7c/cooltools/expected.py#L988 EXPECTED_PATH : The paths to a .tsv file with output of compute_expected. Must include a header. Use the '::' syntax to specify a summary column name. OUTPUT_PREFIX: Output file name prefix to store the logbinned expected (prefix.log.tsv) and derivative (prefix.der.tsv) in the tsv format." z count.sumcis) contact_typeexpected_value_cols.z.avg) summary_namerrrr)Pc_namebinned_exp_sloperr#Nzdist.avgs_bpz.log.tsv Fnan)sepindexna_repz.der.tsv)appendrsplitrlogbin_expectedcombine_binned_expectedto_csv)r rrrrrrr#r$exp_summary_nameexpected_summary_colscvdexp_summary_base_r+lb_cvd lb_slopes lb_distbins lb_cvd_agg lb_slopes_aggs Z/var/www/html/software/conda/lib/python3.11/site-packages/cooltools/cli/logbin_expected.pyr5r5 s|b'4#M#-.///$$[111 !1   C,11#66q!'''G%-%= %!9 &&&"FI{!) @"!- !!!J ' 3j@ 6 -j 9J F f """    """  ) functoolsrapirlib.iorclickutilrr commandargumentstroptionintChoicer5rCrBrQs,,,,,,    W\. A A A  s!LLL  & B      * w 01 2 2                  G 111 2 2      L 111 2 2    * LL          ML lLLLrC