pb-jchin

from falcon_kit.FastaReader import FastaReader
import networkx as nx

RCMAP = dict(zip("ACGTacgt","TGCAtgca"))
def rc_seq(seq):
    return "".join([RCMAP[c] for c in seq[::-1]])

def main(*argv):
    ctg_g = nx.DiGraph()
    ctg_path = {}

pb-jchin

read_length = {}
edges = {}

print "H\tVN:Z:2.0"
with open("sg_edges_list") as f:
    for row in f:
        row = row.strip().split()
        """ 000264577:E 000291380:B 000291380  4496     0 23388 99.53 G """
        v, w, sid2, x2, y2, ovlp, idt, t = row
        ovlp = int(ovlp)

pb-jchin

import tornado.ioloop
import tornado.web

import urllib
import json

class ExamineReadAlignment(tornado.web.RequestHandler):

    def post(self):
        chr_ = self.get_argument("chr", "NA")

pb-jchin

For the dailgner for the raw reads, the user time is about 7156 cpu-hr from 1156 jobs

$ ls rj*raw*.o* | xargs grep user | tr "m" " " | awk '{s+=$2+1};END{print s/60}'
7156.47


Las file sort-merge ~ 10 cpu-hr from 596 jobs
$ ls rp*m*.o* | xargs grep user | tr "m" " " | awk '{s+=$2+1};END{print s/60}'
9.93333

pb-jchin

http://datasets.pacb.com.s3.amazonaws.com/2013/Yeast/0001/Analysis_Results/m130605_000141_42207_c100515142550000001823076608221372_s1_p0.1.bax.h5
http://datasets.pacb.com.s3.amazonaws.com/2013/Yeast/0001/Analysis_Results/m130605_000141_42207_c100515142550000001823076608221372_s1_p0.2.bax.h5
http://datasets.pacb.com.s3.amazonaws.com/2013/Yeast/0001/Analysis_Results/m130605_000141_42207_c100515142550000001823076608221372_s1_p0.3.bax.h5
http://datasets.pacb.com.s3.amazonaws.com/2013/Yeast/0001/Analysis_Results/m130605_000141_42207_c100515142550000001823076608221372_s1_p0.bas.h5
http://datasets.pacb.com.s3.amazonaws.com/2013/Yeast/0001/m130605_000141_42207_c100515142550000001823076608221372_s1_p0.metadata.xml
http://datasets.pacb.com.s3.amazonaws.com/2013/Yeast/0002/Analysis_Results/m130605_032054_42207_c100515142550000001823076608221373_s1_p0.1.bax.h5
http://datasets.pacb.com.s3.amazonaws.com/2013/Yeast/0002/Analysis_Results/m130605_032054_42207_c100515142550000001823076608221373_s1_p0.2.bax.h5
http://datasets.p