soh-i

import unittest
import basic_questions

class TestBasicQuestions(unittest.TestCase):
    def setUp(self):
        self.gff_dict = basic_questions.read_GFF_file("hsa.gff3")

    def test_question1(self):
        # Expected value of question1
        expected = {"mature": 2711, "primary": 1749}

soh-i

#!/usr/bin/env bash

/Applications/Karabiner.app/Contents/Library/bin/karabiner select_by_name HHKB # to HHKB mode
sudo kextunload /System/Library/Extensions/AppleUSBTopCase.kext/Contents/PlugIns/AppleUSBTCKeyboard.kext

case $? in
    3) exit 0;;
    *) exit $?;;
esac

soh-i

import HTSeq

def MIMAT_to_MI(mimat):
    # Convert MIMAT (mature) to MI ID (pre) of mirbase.org
    mat_gtf = "path_to_mature.gtf"
    pre_gtf = "path_to_pre.gtf"
    for mgtf in HTSeq.GFF_Reader(mat_gtf):
        if mimat == mgtf.attr["transcript_id"]:
            pre_query = mgtf.attr["Derives_from"]
            return filter(lambda pre: pre.attr["transcript_id"] == pre_query,

soh-i

from pyfasta import Fasta

f = Fasta("db/Human/Homo_sapiens/UCSC/hg19/Sequence/WholeGenomeFasta/genome.fa")

mir_base = "GGCUGAGCCGCAGUAGUUCUUCAGUGGCAAGCUUUAUGUCCUGACCCAGCUAAAGCUGCCAGUUGAAGAACUGUUGCCCUCUGCC".replace("U", "T")
mir_22 = {"chr": "chr17", "start":1617197 , "stop":1617281, "strand": "-"}
seq = f.sequence(mir_22)

if mir_base == seq:
    print mir_22

soh-i

chr11,.,exon,122017276,122017297,.,-,.,transcript_id "MIMAT0000062"; Alias "MIMAT0000062"; Name "hsa-let-7a-5p"; Derives_from "MI0000061";
chr22,.,exon,46508632,46508653,.,+,.,transcript_id "MIMAT0000062_1"; Alias "MIMAT0000062"; Name "hsa-let-7a-5p"; Derives_from "MI0000062";
chr9,.,exon,96938244,96938265,.,+,.,transcript_id "MIMAT0000062_2"; Alias "MIMAT0000062"; Name "hsa-let-7a-5p"; Derives_from "MI0000060";

soh-i

plot.wrap <- function(df, x, y, filename, ...) {
  g <- ggplot(df, aes_string(x=x, y=y)) +
    geom_point(colour="limegreen", size=3) + theme_light() + ...
  ggsave(plot=g, filename=filename)
    
d <- data.frame(A=1:10, B=2:11, C=3:12)
plot.wrap(d, "A", "B", filename="AB.pdf") # A-B plot
plot.wrap(d, "A", "C", filename="AC.pdf") # A-C plot
plot.wrap(d, "B", "C", filename="BC.pdf") # B-C plot

soh-i

##fileformat=VCFv4.0
##fileDate=20141202
##source=ClinVar and dbSNP
##dbSNP_BUILD_ID=142
##reference=GRCh37.p13
##phasing=partial
##variationPropertyDocumentationUrl=ftp://ftp.ncbi.nlm.nih.gov/snp/specs/dbSNP_BitField_latest.pdf	
##INFO=<ID=RS,Number=1,Type=Integer,Description="dbSNP ID (i.e. rs number)">
##INFO=<ID=RSPOS,Number=1,Type=Integer,Description="Chr position reported in dbSNP">
##INFO=<ID=RV,Number=0,Type=Flag,Description="RS orientation is reversed">

soh-i

object Main {
  def complement(nuc: List[String]): List[String] = {
    nuc.map { nt =>
      nt match {
        case "A" => "T"
        case "T" => "A"
        case "G" => "C"
        case "C" => "G"
        case _ => throw new IllegalArgumentException("Invalid seq")
      }

soh-i

bowtie2 -x genome -p 12 -1 1.fq -2 2.fq | samtools view -bS -@4  - | samtools sort -@4 - bw_map.sorted

soh-i

pn() {
    terminal-notifier -subtitle "Finished job" -message "Status: $?"
}