danielecook

{
    "cmd": ["/usr/local/var/pyenv/shims/python", "-u", "$file"],
    "file_regex": "^[ ]*File \"(...*?)\", line ([0-9]*)",
    "selector": "source.python"
}

danielecook

#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Author: Daniel E. Cook

This script summarizes variation for samples.

"""

import sys

danielecook

library(tidyverse)


# bcftools query -f "[%GT\t]\n" WI.20170531.impute.vcf.gz  | awk '{ gsub(":GT", "", $0); gsub("(# )?\[[0-9]+\]","",$0); print $0 }' | sed 's/0|0/0/g' | sed 's/1|1/1/g' | sed 's/0|1/NA/g' | sed 's/1|0/NA/g' | head -n 1000000 | gzip > ~/Desktop/impute_gts.test.tsv.gz


df_use <- tseries::read.matrix(gzfile("~/Desktop/impute_gts.tsv.gz"))
          
storage.mode(df_use) <- "logical"
# cols

danielecook

# OUT PUT FILES::::

# elegans_transcript_WS258.bed ( COMES FROM /elegans_genes_WS258.bb )
# elegans_gene_WS258.bed (remember; comes from GFF3)
# FASTA! c_elegans.PRJNA13758.WS245.genomic.fa (ftp://ftp.wormbase.org/pub/wormbase/releases/WS258/species/c_elegans/PRJNA13758/)

# Download gene file
wget ftp://ftp.wormbase.org/pub/wormbase/releases/WS258/MULTI_SPECIES/hub/elegans/elegans_genes_WS258.bb
# Bit of a misnomer --> These are transcripts
BigBedToBed elegans_genes_WS258.bb elegans_transcripts_WS258.bed

danielecook

import os
import shutil
import pickle
from subprocess import Popen, PIPE
from collections import defaultdict

out, err = Popen(['git','clone','https://github.com/leereilly/swot'],
                  stdout=PIPE,
                  stderr=PIPE).communicate()
school_directory = defaultdict()

danielecook

{
    "shell_cmd": "`pyenv which python` -u \"$file\"",
    "file_regex": "^[ ]*File \"(...*?)\", line ([0-9]*)",
    "selector": "source.python"
}

danielecook

license: gpl-3.0
height: 960

danielecook

license: gpl-3.0
height: 960

danielecook

git ls-files | xargs cat | wc -l

danielecook

test_df %>%
	dplyr::arrange(chromosome, isotype, start, stop) %>%
	dplyr::filter(
					(!(lead(start) == stop & lead(haplotype) == haplotype & lead(isotype) == isotype & lead(chromosome) == chromosome) | is.na(lag(start)) | is.na(lead(stop)))



					) %>%
	dplyr::mutate(stop = ifelse(lead(isotype) == isotype &
								lead(haplotype) == haplotype &