def main(): kmers = ["TGTAT", "CGTAT", "TTAGT", "TCTAT", "TCTAC"] motif_clust = MotifCluster(kmers) #result = motif_clust.cluster_by_seq() #print "Result: ", result data = np.transpose(np.array(kmers)) print "DATA: " print data dist_func = lambda x, y: sw_align(x, y, return_score=True) linkage_method = "average" hclust = clustering.hierarchical_clust(np.array(kmers), dist_func, linkage_method)
def cluster_by_edit(self, kmers, linkage_method): """ Cluster sequences by edit distances. Parameters: ----------- kmers : flat list of kmers linkage_method : determines linkage function for hierarchical clustering ('average', 'single', ...). """ # Nest kmers to create matrix for clustering purposes. kmers = [kmers] data = np.array(kmers) hclust = clustering.hierarchical_clust(data, self.edit_dist_func, linkage_method) return hclust