Python MotifConfig.get_score_dir方法代码示例

# 需要导入模块: from gimmemotifs.config import MotifConfig [as 别名]
# 或者: from gimmemotifs.config.MotifConfig import get_score_dir [as 别名]
class MotifComparer(object):
    """Class for motif comparison.
    
    Compare two or more motifs using a variety of metrics. Probably the best
    metric to compare motifs is seqcor. The implementation of this metric 
    is similar to the one used in Grau (2015), where motifs are scored 
    according to the Pearson correlation of the scores along sequence. In this
    case a de Bruijn of k=7 is used.

    Valid metrics are:
    seqcor - Pearson correlation of motif scores along sequence.
    pcc - Pearson correlation coefficient of motif PFMs.
    ed - Euclidean distance-based similarity of motif PFMs.
    distance - Distance-based similarity of motif PFMs.
    wic - Weighted Information Content, see van Heeringen 2011.
    chisq - Chi-squared similarity of motif PFMs.
    akl - Similarity based on average Kullback-Leibler similarity, see Mahony, 2011.
    ssd - Sum of squared distances of motif PFMs.
    
    Examples
    --------
    mc = MotifComparer()
    
    # Compare two motifs
    score, pos, strand = mc.compare_motifs(m1, m2, metric="seqcor")

    # Compare a list of motifs to another list of motifs
    mc.get_all_scores(motifs, dbmotifs, match, metric, combine)

    # Get the best match for every motif in a list of reference motifs
    get_closest_match(motifs, dbmotifs=None)
    """  
    def __init__(self):
        self.config = MotifConfig()
        self.metrics = ["pcc", "ed", "distance", "wic"]
        self.combine = ["mean", "sum"]
        self._load_scores()
        # Create a parallel python job server, to use for fast motif comparison
        

    def _load_scores(self):
        self.scoredist = {}
        for metric in self.metrics:
            self.scoredist[metric] = {"total": {}, "subtotal": {}}
            for match in ["total", "subtotal"]:
                for combine in ["mean"]:
                    self.scoredist[metric]["%s_%s" % (match, combine)] = {}
                    score_file = os.path.join(self.config.get_score_dir(), "%s_%s_%s_score_dist.txt" % (match, metric, combine))
                    if os.path.exists(score_file):
                        with open(score_file) as f:
                            for line in f:
                                l1, l2, m, sd = line.strip().split("\t")[:4]
                                self.scoredist[metric]["%s_%s" % (match, combine)].setdefault(int(l1), {})[int(l2)] = [float(m), float(sd)]
    
    def compare_motifs(self, m1, m2, match="total", metric="wic", combine="mean", pval=False):
        """Compare two motifs.
        
        The similarity metric can be any of seqcor, pcc, ed, distance, wic, 
        chisq, akl or ssd. If match is 'total' the similarity score is 
        calculated for the whole match, including positions that are not 
        present in both motifs. If match is partial or subtotal, only the
        matching psotiions are used to calculate the score. The score of
        individual position is combined using either the mean or the sum.

        Note that the match and combine parameters have no effect on the seqcor
        similarity metric.      

        Parameters
        ----------
        m1 : Motif instance
            Motif instance 1.

        m2 : Motif instance
            Motif instance 2.

        match : str, optional
            Match can be "partial", "subtotal" or "total". Not all metrics use 
            this.

        metric : str, optional
            Distance metric.

        combine : str, optional
            Combine positional scores using "mean" or "sum". Not all metrics
            use this.

        pval : bool, optional
            Calculate p-vale of match.
        
        Returns
        -------
        score, position, strand 
        """
        if metric == "seqcor":
            return seqcor(m1, m2)
        elif match == "partial":
            if pval:
                return self.pvalue(m1, m2, "total", metric, combine, self.max_partial(m1.pwm, m2.pwm, metric, combine))
            elif metric in ["pcc", "ed", "distance", "wic", "chisq", "ssd"]:
                return self.max_partial(m1.pwm, m2.pwm, metric, combine)
#.........这里部分代码省略.........