Comment by joshuamcginnis | Hacker News Reader

Comment by joshuamcginnis | Hacker News Reader

This is identical to what I've been building and using my own gpt (via ChatGPT) with API integration to automate full genome base-calling, assembly, annotation and prediction pipelines. Using this approach, me and my team can use it to debug pipeline failures, interpret the results, draw inferences and create context-dependent experiments. There's no leap in the tech beyond GPT facilitating the interaction with APIs, but it is a completely new way of working. This is what I can currently do:

User: Show me my genomes

ChatGPT: Here's a list of your genomes ... [API call to GET /genomes]

User: Annotate genome #nnnn

ChatGPT: Kicking off annotation [API call to POST /annotate]

User: Show me what genes are related to growth regulation for the genome

ChatGPT: The genome appears to have several genes related to growth regulation. Here's a list [API call to GET /genome/X/annotations] ...

User: Design an experiment to knock-out this gene using CRISPR in Aspergillus niger, include the guideRNA specific to this gene.

ChatGPT: Here you go...

Oh God this is going to be really bad, there are so so so many misannotated genes, even well known ones that have more or less "wrong names"[0], that a lot of lazy scientists are going to either be led astray or totally miss targets as a result from an uncritically science-believing LLM

[0] do you really really think ferritin is best described as an "iron carrier"?

Is this doing anything more than using ChatGPT as a frontend? I thought based on your comment ChatGPT would run all of that, not just call an API that does the actual work.

The parent article isn't doing anything more than using ChatGPT as a frontend either. The API does all the _work_ (pipeline running, robot control, etc) while ChatGPT uses it's vast knowledge to interpret, analyze and iterate on future commands sent to the API.

Really interesting, what would be your real-world use cases?

This is the real-world use-case! We're using to accelerate the discovery and elucidation of novel or unknown gene function in previously unstudied fungal strains.

I should have meant, have you already found customers? I am also working on a project on genomics, which is very orthogonal to yours, and finding customers in this field the difficult part

We're pursuing grant-funded research at the moment. We have some hunches on some specific fungal genetic functions but they need to be better characterized before we think about commercialization.

Why do you need ChatGPT for the API calls?

As an example, asking questions like "show me which genes from my genome are related to growth regulation" requires an API call to give ChatGPT a list of annotated genes from the genome we're studying so it can then filter them into growth regulation related genes. Leveraging ChatGPT's extensive knowledge of genes lets us find new insights into our newly assembled genomes much faster.

Reply on news.ycombinator.com