Created
August 27, 2015 20:42
-
-
Save lomereiter/e4f4f2b0a6cf9cee4287 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
// compilation: rdmd --build-only -O -release -inline -IBioD sambamba_161.d | |
// to use LDC: rdmd --compiler=ldmd2 [--force] ... | |
import bio.bam.reader, bio.bam.writer, std.parallelism; | |
void main(string[] args) { | |
// boilerplate | |
defaultPoolThreads = 8; | |
auto input = new BamReader(args[1]); // use std.getopt for better args handling | |
auto output = new BamWriter(args[2]); | |
output.writeSamHeader(input.header); | |
output.writeReferenceSequenceInfo(input.reference_sequences); | |
scope(exit) output.finish(); | |
// filtering | |
immutable threshold = 90; | |
foreach (read; input.reads) { | |
// Warning: M corresponds to match/mismatch in BAM spec. | |
// If you are interested only in matches, use | |
// read.extended_cigar instead (requires ubiquitous MD tag) | |
// and '=' operation type. | |
uint total_len = 0; | |
foreach (op; read.cigar) | |
if (op.type == 'M') | |
total_len += op.length; | |
if (total_len > threshold) | |
output.writeRecord(read); | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment