Hello Bioinformatics lovers,

Tommy here. AI is taking over the world. It is the same with Bioinformatics.

I watched Claude Code parse my VCF files, run comparisons, generate plots, and spit out insights — all faster than I could type the commands myself.

Commands I learned through years of hard experience. Typed in seconds.

It was exciting. And honestly? A little unsettling.

After two months of using Claude Code for bioinformatics work, here's what I've learned:

AI is remarkably good at the mechanical parts of our job. Writing pipelines.

Optimizing tools. Generating boilerplate analysis code.

Most of the time, it gets it right.

But "most of the time" is exactly the problem.

Edge cases — that's where your years of training earn their keep.

When Claude Code produces an analysis, it looks polished. The code runs. The plots render.

The "insights" sound reasonable. But catching when something is subtly wrong — a filtering threshold that doesn't make biological sense, a normalization choice that's inappropriate for your experimental design, a variant call that ignores the context of your specific assay — that requires domain knowledge no AI currently has.

Here's what my workflow actually looks like now: AI generates the first pass. I review it with the skepticism of someone who's been burned by bad defaults before.

When I spot a problem, I describe the fix in plain English. AI implements it instantly.

It's fast. It's powerful. And it absolutely requires a human bioinformatician in the loop.

So are bioinformaticians losing their jobs to AI?

Not for the foreseeable future. But AI is fundamentally changing how we work.

The value we bring isn't typing commands into a terminal — it never was.

It's knowing which commands to run, why those parameters matter, and when the output doesn't pass the smell test. AI amplifies that expertise. It doesn't replace it.

The bioinformaticians who thrive will be the ones who embrace AI as a force multiplier while continuing to sharpen the one thing it can't replicate: deep biological intuition built from years of working with real data.

The commands are the easy part. The judgment is everything.

Start experimenting with AI tools in your daily workflows now. Not because you'll be replaced if you don't — but because the productivity gains are real, and the researchers who learn to work with AI will have a significant edge.

Happy Learning!

Tommy aka crazyhottommy

PS:

If you want to learn Bioinformatics, there are other ways that I can help:

1. My free YouTube Chatomics channel, make sure you subscribe to it.
2. I have many resources collected on my github here.
3. I have been writing blog posts for over 10 years https://divingintogeneticsandgenomics.com/​
4. My daily Linkedin post ​https://www.linkedin.com/in/%F0%9F%8E%AF-ming-tommy-tang-40650014/recent-activity/all/​

You will find tips like this in my Linkedin posts:

​

Stay awesome!