small fixes

zUMIs will try to automatically do this, otherwise convert zUMIs output to loom by simply running `Rscript rds2loom.R myRun.yaml`.

## Changelog

18 Sept 2020: zUMIs.2.9.4b/c: Fix Smart-seq3 UMI read counting. Prevent crash when a chunk of cell BCs does not match any downsampling. Speed up barcode detection steps for some cases.

18 Sept 2020: zUMIs.2.9.4b/c/d: Fix & speed up Smart-seq3 UMI read counting. Prevent crash when a chunk of cell BCs does not match any downsampling. Speed up barcode detection steps for some cases. Prevent too much CPU usage in UMI error correction.

12 Sept 2020: [zUMIs2.9.4](https://github.com/sdparekh/zUMIs/releases/tag/2.9.4): Speed writing of error-corrected UMI tags to bam file up significantly. Prevent potential crash when no cells meet any user-defined downsampling criteria.

}

ham_helper_fun <- function(x){

    setDTthreads(1)

    x[, gbcid := paste(RG,GE,sep="_")]

    x_list <- split(x = x, drop = T, by = c("gbcid"), sorted = T, keep.by = T)

    out_list <- lapply(x_list, function(x) hammingFilter(x[!is.na(UB)]$UB, edit=opt$counting_opts$Ham_Dist, gbcid=unique(x$gbcid)) )

    #first check if a partial barcode matches the length of the whitelist

    bc_definition <- sapply(opt$sequence_files, function(x) grep("BC", x$base_definition, value = T))

    bc_definition <- bc_definition[which(sapply(bc_definition, length)>0)]

    if(length(bc_definition)>1){ #this only makes sense if there are at least 2 BC pieces defined

      bc_definition <- sapply(bc_definition, function(x) substr(x = x, start = 4, stop = nchar(x)-1))

      bc_len_mat <- t(matrix(as.numeric(unlist(strsplit(bc_definition, "-"))), ncol = length(bc_definition)))

#!/usr/bin/env python3

import pysam

import argparse

import multiprocessing as mp

def load_bcs(bcpath):

    with open(bcpath) as f:

            bc.append(l[0])

    return(bc)

def count_UMItags(inpath, bcs, threads, outpath):

def count_UMItags(inpath, bcs, chr):

    bccounts = {}

    for b in bcs:

        bccounts[b] = {}

        bccounts[b]['umi'] = 0

        bccounts[b]['int'] = 0

    inp = pysam.AlignmentFile(inpath, 'rb', threads = threads)

    for read in inp:

    inp = pysam.AlignmentFile(inpath, 'rb')

    for read in inp.fetch(chr):

        bc = read.get_tag('BC')

        if bc in bcs:

            ub = read.get_tag('UB')

                bccounts[bc]['int'] += 1

            else:

                 bccounts[bc]['umi'] += 1

    inp.close()

    return(bccounts)

def collect_write_stats(chrcounts, outpath):

    bccounts = chrcounts.pop(0) #get first dict

    for b in bccounts: #for every cell collect counts

        bccounts[b]['umi'] += sum( [chrcounts[i][b]['umi'] for i in range(len(chrcounts))] )

        bccounts[b]['int'] += sum( [chrcounts[i][b]['int'] for i in range(len(chrcounts))] )

    with open(outpath, 'w') as out:

        out.write('XC\tnNontagged\tnUMItag\n')

        for bc in bccounts:

    bcs = load_bcs(args.bcs)

    count_UMItags(inpath = args.bam, bcs = bcs, threads = args.p, outpath = args.bcs+".BCUMIstats.txt")

    inp = pysam.AlignmentFile(args.bam, 'rb')

    chrs = list(inp.references)

    chrs.append('*') #don't forget unmapped reads

    inp.close()

    if(args.p > len(chrs)):

        num_threads = len(chrs)

    else:

        num_threads = args.p

    pool = mp.Pool(num_threads)

    results = [pool.apply_async(count_UMItags, (args.bam, bcs, chr, )) for chr in chrs]

    x = [r.get() for r in results]

    collect_write_stats(x, args.bcs+".BCUMIstats.txt")

if __name__ == "__main__":

    main()

# Pipeline to run UMI-seq analysis from fastq to read count tables.

# Authors: Swati Parekh, Christoph Ziegenhain, Beate Vieth & Ines Hellmann

# Contact: sparekh@age.mpg.de or christoph.ziegenhain@ki.se

vers=2.9.4c

vers=2.9.4d

currentv=$(curl -s https://raw.githubusercontent.com/sdparekh/zUMIs/main/zUMIs.sh | grep '^vers=' | cut -f2 -d "=")

if [ "$currentv" != "$vers" ] ; then

    echo -e "------------- \n\n Good news! A newer version of zUMIs is available at https://github.com/sdparekh/zUMIs \n\n-------------";