f6v

from collections import defaultdict

def ordering(graph:dict):
    in_counts = defaultdict(int)
    for k, v in graph.items():
        if not k in in_counts:
            in_counts[k] = 0
        for in_node in v:
            in_counts[in_node] += 1

f6v

import itertools
from Bio import SeqIO

def overlap(read_a, read_b, min_length):
    start = 0
    while True:
        start = read_a.find(read_b[:min_length], start)
        if start == -1:
            return 0
        if read_b.startswith(read_a[start:]):

f6v

import itertools
from Bio import SeqIO

def overlap(read_a, read_b, min_length):
    start = 0
    while True:
        start = read_a.find(read_b[:min_length], start)
        if start == -1:
            return 0
        if read_b.startswith(read_a[start:]):

f6v

from collections import defaultdict
from Bio import SeqIO

def overlap(kmer_left, kmer_right, overlap_size):
    return kmer_left[-overlap_size:] == kmer_right[:overlap_size]

def maximal_overlap(kmer_left, kmer_right):
    overlap_sizes = []
    for overlap_size in range(1, len(kmer_right) + 1):
        has_overlap = overlap(kmer_left, kmer_right, overlap_size)

f6v

import sqlite3
import sys

def get_gene_ids(gene_symbol):
    try:
        # estabilish a SQLIte connection from Python
        sqlite_connection = sqlite3.connect('refGene_hg19.db')
        # Better formatting for results
        sqlite_connection.row_factory = lambda cursor, row: row[0]
        # create a cursor object using the connection object

f6v

#http://stackoverflow.com/a/8010133/468311
with open(...) as f:
    for line in f:
        <do something with line>