How to use the cooltools.lib.numutils.adaptive_coarsegrain function in cooltools

To help you get started, we’ve selected a few cooltools examples, based on popular ways it is used in public projects.

Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.

github calico / basenji / bin / akita_data_read.py View on Github external
# adjust for sequence indexes
          black_seq_start = (black_interval.begin - mseq.start)// options.pool_width
          black_seq_end =   int(  np.ceil( (black_interval.end - mseq.start)/ options.pool_width ) )
          seq_hic_raw[:,black_seq_start:black_seq_end] = np.nan
          seq_hic_raw[black_seq_start:black_seq_end,:] = np.nan
        seq_hic_nan = np.isnan(seq_hic_raw)

      # clip first diagonals and high values
      clipval = np.nanmedian(np.diag(seq_hic_raw,options.diagonal_offset))
      for i in range(-options.diagonal_offset+1,options.diagonal_offset):
        set_diag(seq_hic_raw, clipval, i)
      seq_hic_raw = np.clip(seq_hic_raw, 0, clipval)
      seq_hic_raw[seq_hic_nan] = np.nan

      # adaptively coarsegrain based on raw counts
      seq_hic_smoothed = adaptive_coarsegrain(
                              seq_hic_raw,
                              genome_hic_cool.matrix(balance=False).fetch(mseq_str),
                              cutoff=2, max_levels=8)
      seq_hic_nan = np.isnan(seq_hic_smoothed)
      #todo: pass an option to add a certain pseudocount value, or the minimum nonzero value

      if options.as_obsexp:
        # compute obs/exp        
        if options.global_obsexp: # compute global obs/exp
          exp_chr = genome_hic_expected.iloc[ genome_hic_expected['chrom'].values ==mseq.chr][0:seq_len_pool]
          if len(exp_chr) ==0: 
              raise ValueError('no expected values found for chr:'+mseq.chr)
          exp_map= np.zeros((seq_len_pool,seq_len_pool))
          for i in range(seq_len_pool):
            set_diag(exp_map,exp_chr['balanced.avg'].values[i],i)
            set_diag(exp_map,exp_chr['balanced.avg'].values[i],-i)
github calico / basenji / bin / basenji_data_hic_read.py View on Github external
for black_interval in black_chr_trees[mseq.chr][mseq.start:mseq.end]:
          # adjust for sequence indexes
          black_seq_start = (black_interval.begin - mseq.start)// options.pool_width
          black_seq_end =   int(  np.ceil( (black_interval.end - mseq.start)/ options.pool_width ) )
          seq_hic_raw[:,black_seq_start:black_seq_end] = np.nan
          seq_hic_raw[black_seq_start:black_seq_end,:] = np.nan
        seq_hic_nan = np.isnan(seq_hic_raw)

      # clip first diagonals and high values
      clipval = np.nanmedian(np.diag(seq_hic_raw,2))
      for i in [-1,0,1]: set_diag(seq_hic_raw,clipval,i)
      seq_hic_raw = np.clip(seq_hic_raw, 0, seq_hic_raw)
      seq_hic_raw[seq_hic_nan] = np.nan

      # adaptively coarsegrain based on raw counts
      seq_hic_smoothed =  adaptive_coarsegrain(
                              seq_hic_raw,  
                              genome_hic_cool.matrix(balance=False).fetch(mseq_str),  
                              cutoff= 2, max_levels=8)
      #todo: pass an option to add a certain pseudocount value, or the minimum nonzero value

      if options.as_obsexp == True:
        # interpolate single missing bins
        seq_hic_interpolated =  interpolate_bad_singletons(seq_hic_smoothed, mask=(~seq_hic_nan),
                                                 fillDiagonal=True, returnMask=False, secondPass=True,verbose=False)
        seq_hic_nan = np.isnan(seq_hic_interpolated)

        # compute observed/expected
        seq_hic_obsexp = observed_over_expected(seq_hic_interpolated, ~seq_hic_nan)[0]
        # todo: allow passing a global expected rather than computing locally

        # log