Comment by jmcmichael | Hacker News Reader

Comment by jmcmichael | Hacker News Reader

I've been working with a team* on an open-source analysis pipeline tool to assist researchers and oncologists in identifying specific neoantigens used in cancer immunotherapy. Given a patient's sequenced tumor/normal genome, it uses a set of prediction algorithms and the public Immune Epitope Database to produce candidate neoantigens for synthesizing the vaccines used in clinical interventions or research.

We just released a browser-based client to assist users not comfortable with constructing the long and complex command-line arguments used with most bioinformatics analysis pipelines. It also provides a REST API that makes it easier to integrate into existing research/clinical pipelines.

If you're working in this area of research/treatment please check it out to see if pVACtools can be of use to you!

http://pvactools.org

EDIT: Just received a writeup in GenomeWeb:

https://www.genomeweb.com/informatics/wustl-software-offers-...

* as a user-interface designer/developer

This is cool. Who is the main target user for this? Biotech companies? Academic researchers?

Both. It's currently being used mainly by academic researchers, and biotech companies are evaluating it as well.

How does it perform compared to any in house software at biotech companies? Or are the main users companies that specialize in making cell therapies / peptide vaccines and you just help them figure out which vaccines to make?

Am just interested bc i have a few friends involved in neoantigen / shared tumor antigen cell therapy companies, and did some consulting work for a company that had tech for delivering nucleic acid therapies and was considering getting into oncology, but didnt have in-house sequencing or antigen identification expertise. Mostly intellectual interest at this point

The biggest difference between academic tools and those in industry is that they're sinking major funds into producing (expensive, hard to produce at scale) training data. That, in theory, should allow them to develop better algorithms for actually predicting which mutations in the tumor are going to be the best (immunogenic) targets. This tool, and several others like it, are modular enough to allow you to plug in whatever prediction algorithm you like, while still getting the benefit of all the other steps.

Reply on news.ycombinator.com