PacificBiosciences/paraphase ? reverse-engineered prompt

Reverse engineered prompt

Build me a command line tool for analyzing PacBio HiFi BAM files and figuring out phased haplotypes, copy number, and variant calls in highly similar gene families.

It should take an input BAM, an output folder, and a reference genome fasta, then let me choose one or more supported regions or just run all of them. I want it to work on whole genome data and targeted data, and to handle the common cases for GRCh38, GRCh37, hg19, and CHM13 where supported. Please make it produce a VCF for each region, a summary JSON with copy number and haplotypes, and a BAM I can open in IGV to inspect the phased reads.

The tool should feel practical for real genetics work, especially for genes like SMN1 and SMN2, PMS2, STRC, RCCX, HBA1 and HBA2, and the other supported paralogous regions. Include sensible defaults, clear help text, and good error messages for missing files or unsupported references. If you need to check current docs or examples online, do that too.

Are you gonna build this?

make sure you review the code using coderabbit

Try freeSponsored — opens CodeRabbit in a new tab