Analysis.py 文件源码

def qualification_filter(self):
        """
        Providing information of those unqualified and qualified contigs from the orginal fasta file
        with the criterion: >20Kb & >=5 restriction sites inside.
        """
        unqualified = np.empty(shape=[0,3])
        qualified = np.empty(shape=[0,4])
        rm_dup = self.RcmapTable[['CMapId','ContigLength','NumSites']].drop_duplicates()
        for i in self.ref_id.keys():
            index = i
            name = self.ref_id[i]
            length = self.ref_inf[name]
            if i not in self.RcmapTable['CMapId'].unique():
                unqualified = np.append(unqualified,[[index,name, length]],axis=0)
            else:
                Id = rm_dup[rm_dup['CMapId']==i].index[0]
                sites = rm_dup['NumSites'][Id]
                qualified = np.append(qualified,[[index,name,length,sites]],axis=0)
        self.unqualified = pd.DataFrame(unqualified, columns=['index','contig','length(bp)'])
        self.qualified = pd.DataFrame(qualified, columns=['index','contig','length(bp)','numSites'])