Hello Bioinformatics lovers,

Tommy here. It can be overwhelming with all the advancement of AI.

AI won't replace bioinformaticians. But a bioinformatician who uses AI will replace one who doesn't.

In 2013, when you hit a wall — a confusing error, a method you'd never used — you posted on Biostars and waited.

Or you searched for hours and hoped someone had blogged about it.

Now you ask Claude or ChatGPT and get a working answer in 30 seconds.

That's not magic. That's leverage.

I still use AI constantly, even after 14 years in this field. Not because it makes me lazier — because it helps me think faster.

Two examples from my own work this week:

Someone asked me why you calculate TSS enrichment scores in ATAC-seq. Ten years ago I'd have spent hours digging through papers to piece together the answer. I eventually did write it up — it took a long time.

Today I'd ask AI first, then go deeper myself.

Another question: why is only ~0.1% of input DNA used in a ChIP-seq experiment?

Short answer — input chromatin is abundant, but the immunoprecipitated fraction (DNA bound to your protein of interest) is not. You use a tiny fraction of input to match the much smaller ChIP yield. AI can explain that clearly in seconds.

These are exactly the kinds of questions where AI earns its keep — conceptual explanations, quick orientation, unblocking your thinking.

What to ask AI:

• Explain PCA vs UMAP for single-cell data
• Write a bash loop to process multiple samples
• Describe the difference between ChIP-seq and ATAC-seq
• Draft a function to filter low-quality cells in Seurat

What AI can't do: replace your judgment. Double-check its code. Validate its logic. When it gets something wrong — and it will — you need the expertise to catch it.

AI gives you speed. You bring the biology.

Use it often. Use it wisely. The window to build this habit is now.

Happy Learning!

Tommy aka crazyhottommy

PS:

If you want to learn Bioinformatics, there are four 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. I am learning Claude Code myself, and you will find many tips in my Linkedin posts https://www.linkedin.com/in/%F0%9F%8E%AF-ming-tommy-tang-40650014/recent-activity/all/​

Stay awesome!

PPS: