lpantano

#!/bin/bash
#SBATCH -N 1
#SBATCH -c 1
#SBATCH --mem=200
#SBATCH -J "init"
#SBATCH -e run.e
#SBATCH -o run.o
## SBATCH --mail-type=END,FAIL # this line is commented
## SBATCH --mail-user=tobias.jakobi@med.uni-heidelberg.de  # this line is commented

lpantano

# Read first X lines of R3 of inDrop fastq files and map to
# sequence barcodes to check if the top N match or not.
import argparse
import os                                                                                                                                                                                          [44/1831]
import gzip
from collections import Counter, defaultdict
from Bio.Seq import Seq

def open_fastq(in_file):
    """ open a fastq file, using gzip if it is gzipped

lpantano

seqcluster collapse -f example.fastq -o test

lpantano

mir = "CCCGGGGGGGGGGGGGGGGGGGGGCCC"
# generate different length +/-3 at both size
lapply(c(1,2,3,4,5,6,7), function(x){
    lapply(c(0,1,2,3,4,5,6,7), function(y){
        substr(mir, x, nchar(mir)-y)
    }) %>% unlist()
}) %>% unlist() -> trim

# add non-tempaltes 3' A or U up to 3
trim_add = expand.grid(trim, c("A","AA", "AAA", "U", "UU", "UUU", "")) %>% 

lpantano

Many sequences are not being capture in the current test_lossRand_3p.mirna. I don't know the reason, but following the instructions in how the authors generated this file I get different results.

```
wget https://github.com/lpantano/seqbuster/raw/miraligner/modules/miraligner/miraligner.jar 
wget https://github.com/lpantano/java_seqbuster/raw/master/miraligner/DB/hairpin.fa 
wget https://github.com/lpantano/java_seqbuster/raw/master/miraligner/DB/miRNA.str

java -jar miraligner.jar -sub 1 -trim 3 -add 3 -s hsa  -i test_lossRand_3p.fastq -db . -o miraligner_lossRand_3p

# this sequences is not detected in the published data, but it is when you run this code.

lpantano

require(TxDb.Hsapiens.UCSC.hg19.knownGene)
txdb <- TxDb.Hsapiens.UCSC.hg19.knownGene
library(ChIPseeker)
library(GenomicRanges)
# Hack chipseeker function to add annotaiton
getGenomicAnnoStat <- function(peakAnno) {
    if ( class(peakAnno) == "GRanges" )
        peakAnno <- as.data.frame(peakAnno)
    anno <- peakAnno$annotation
    ## anno <- sub(" \\(.+", "", anno)

lpantano

@NS500227_6_H160HBGXX:1:11108:2429:1048 1:N:0:1
AAAACNAAAAATGAGNTTAAATAACTANTNATATGNNTGTTATTTNCTGTNACTANNANANCTG
+
AA7AA#FF.FFF7FF#FFFF7FF<FAA#F#AFAFF##FF<<FA.F#7FF.#.F)<##<#.#FAF
@NS500227_6_H160HBGXX:1:11108:1920:1048 1:N:0:1
GAAGANGGTTCTGAGNATGCTTCTGATNTNGATCTNNGCGGTTTANCCCGNTAACNNCN
+

lpantano

#https://gist.github.com/jcheng5/4050398
library(ggplot2)
options(shiny.maxRequestSize = -1)
shinyServer(function(input, output,session) {
  
  observe({
    if (is.null(input$files)) {
      # User has not uploaded a file yet
      return(NULL)
    }