dbotu.py 文件源码

def __init__(self, seq_table, records, max_dist, min_fold, threshold_pval, log=None):
        '''
        seq_table: pandas.DataFrame
          Samples on the columns; sequences on the rows
        records: index of Bio.Seq
          Indexed, unaligned input sequences. This could come from BioPython's
          SeqIO.to_dict or SeqIO.index.
        max_dist: float
          genetic distance cutoff above which a sequence will not be merged into an OTU
        min_fold: float
          Multiply the sequence's abundance by this fold to get the minimum abundance
          of an OTU for merging
        threshold_pval: float
          P-value below which a sequence will not be merged into an OTU
        log: filehandle
          Log file reporting the abundance, genetic, and distribution checks.
        '''
        self.seq_table = seq_table
        self.records = records
        self.max_dist = max_dist
        self.min_fold = min_fold
        self.threshold_pval = threshold_pval
        self.log = log

        # get a list of the names of the sequences in order of their (decreasing) abundance
        self.seq_abunds = self.seq_table.sum(axis=1).sort_values(ascending=False)

        # check that all sequence IDs in the table are in the fasta
        missing_ids = [seq_id for seq_id in self.seq_abunds.index if seq_id not in self.records]
        if len(missing_ids) > 0:
            raise RuntimeError("{} sequence IDs found in the sequence table but not in the fasta: {}".format(len(missing_ids), missing_ids))

        # initialize OTU information
        self.membership = {}
        self.otus = []