pmenzel

/* lca.cpp, 2018, Peter Menzel

1. Download https://github.com/bioinformatics-centre/kaiju/ and compile
2. Copy lca.cpp to kaiju/src
3. Compile lca.cpp with:
g++ -O3 -std=c++11 -I./include/ncbi-blast+ -o lca lca.cpp Config.o util.o bwt/bwt.o bwt/compactfmi.o bwt/sequence.o bwt/suffixArray.o include/ncbi-blast+/algo/blast/core/blast_seg.o include/ncbi-blast+/algo/blast/core/blast_util.o include/ncbi-blast+/algo/blast/core/blast_filter.o include/ncbi-blast+/algo/blast/core/ncbi_std.o include/ncbi-blast+/algo/blast/core/blast_program.o include/ncbi-blast+/algo/blast/core/blast_encoding.o include/ncbi-blast+/algo/blast/core/blast_query_info.o include/ncbi-blast+/algo/blast/core/blast_stat.o include/ncbi-blast+/algo/blast/core/blast_options.o include/ncbi-blast+/algo/blast/core/blast_message.o include/ncbi-blast+/algo/blast/core/ncbi_math.o include/ncbi-blast+/algo/blast/core/pattern.o include/ncbi-blast+/algo/blast/core/blast_psi_priv.o include/ncbi-blast+/algo/blast/core/blast_dynarray.o include/ncbi-blast+/algo

pmenzel

my $cigar = "30M40D50M";
my $n_soft = 71;

my $out_cigar = "";

# there are already at least $n_soft soft-clipped bases at the end of the CIGAR
# then do nothing
if($cigar =~ m/(\d+)S$/ and $1 >= $n_soft) {
        $out_cigar = $cigar;
}

pmenzel

#!/usr/bin/env perl
#
# rotates and (if necessary reverse complements) an assembly of a circular genome
# so that it starts with the sequence having the best blast hit to a gene database,
# e.g. dnaA
#
# depends on blastn being installed
#
# Example usage:
# rotate_assembly.pl assembly.fasta  dnaA.fa > rotated_assembly.fa

pmenzel

===========================
Days 10 ...
===========================

see https://github.com/pmenzel/advent-of-code/tree/master/2022

===========================
Day 9
===========================
Part 1:

pmenzel

#!/usr/bin/env perl
# make-igv-genome-json.pl
# Peter Menzel
#
# This script creates an IGV genome json file (https://github.com/igvteam/igv/wiki/JSON-Genome-Format)
# The arguments are the paths to fasta, fai and gff files.
#
# Example usage:
# datasets download genome accession GCF_002101575.1
# unzip ncbi_dataset.zip

pmenzel

#!/usr/bin/env perl
#
# 2019, Peter Menzel, Labor Berlin
# This script converts the Kraken output format into
# a 3-column output format with columns:
# 1: read name
# 2: taxon id
# 3: score, which is defined as the fraction of k-mers having that taxon id and its ancestors over all k-mers
#
# use as input for ktImportTaxonomy