endrebak

SEP 1 -- Improved and automated logging

Abstract

This Snakemake Enhancement Proposal (SEP) suggests several enhancements of Snakemake's logging and report generating capabilities.

Introduction

Bioinformaticians often have an enormous library of homemade scripts

endrebak

import pandas as pd

mir_miR_correspondence = "/local/home/annata/mirna.mature.offset0.txt"

mirna_example_file = "/local/home/annata/SHORTREADS/OFFCONTROL/offcontrol-start/Demux.SRhi10002.Adipocyte%20-%20omental%2c%20donor3.SRhi10002_hg19.11475-119C8.GTGAAA.fastq.gz.filter.shortreads"

### READ FILES

mirna_df = pd.read_table(mirna_example_file, sep="\s+", header=None,
                         names="id1 id2 nb1 mirna_seq score nb2 short_read_seq type end offset".split(), index_col=0)

endrebak

grouping <- c("A","A","B","B")
design<-model.matrix(~factor(grouping))


#############################################################
### csaw, with its combined window methodology.
############################################################

xparam <- readParam(dedup=FALSE)

endrebak

switchTab(n) -> {{ RUNTIME('goToTab', {index: n - 1}); }}
map 1 :call switchTab(1)<CR>
map 2 :call switchTab(2)<CR>
map 3 :call switchTab(3)<CR>
map 4 :call switchTab(4)<CR>
map 5 :call switchTab(5)<CR>
map 6 :call switchTab(6)<CR>
map 7 :call switchTab(7)<CR>
map 8 :call switchTab(8)<CR>
map 9 :call switchTab(9)<CR>

endrebak

import pandas as pd

# A combined P-value was computed for each peak cluster using Simes’ method
# (19). For a cluster containing n windows, the combined P-value is defined as
# p{s}=min{np{r}/r;r=1,2…,n} where the p{r} are the individual window P-values sorted
# in increasing order. This provides weak control of the family-wise error rate
# across the set of null hypotheses for all windows in the cluster. In other
# words, p{s} represents evidence against the global null hypothesis, i.e. that
# no windows in the cluster are DB.

endrebak

{
    "global": {
        "check_for_updates_on_startup": true,
        "show_in_menu_bar": true,
        "show_profile_name_in_menu_bar": false
    },
    "profiles": [
        {

endrebak

# Works on very large datasets.

import pandas as pd

try:
    import mkl
    mkl.set_num_threads(1)
except:
    pass

endrebak

# wget http://big.databio.org/example_data/AIList/AIListTestData.tgz

nrows = 1.5e6

from ncls import NCLS
from ailist import AIList

import numpy as np
import pandas as pd

endrebak

# ctypedef struct ailist_t:
#     int64_t nr, mr  					# Number of regions
#     interval_t *interval_list			# Regions data
#     uint32_t first, last				# Record range of intervals
#     int nc, lenC[10], idxC[10]
#     uint32_t *maxE
# ...
#     uint32_t binary_search(interval_t* As, uint32_t idxS, uint32_t idxE, uint32_t qe) nogil

endrebak

# Author: denis.engemann@gmail.com
# License: simplified BSD (3 clause)
# Note: code is based on scipy.stats.pearsonr

def ss(a, axis):
    return np.sum(a * a, axis=axis)

def compute_corr(x, y):
    x = np.asarray(x)
    y = np.asarray(y)