Arjun Krishnan
@compbiologist.bsky.social
ML/AI methods & tools for using massive public data collections to gain insights into complex disease mechanisms. Associate Professor & Group leader thekrishnanlab.org at the Dept. of Biomedical Informatics at CU Anschutz.
New from the lab: cfDNA provides an unexpected window into telomere chromatin state and genome-wide chromatin changes that accompany telomere shortening, from a blood draw. We hope this opens a path toward monitoring telomere biology disorders with a blood test. www.biorxiv.org/content/10.6...
biorxiv.org
@nucatsinstitute.bsky.social and @kristiholmes.bsky.social were pleased to host @compbiologist.bsky.social for a seminar discussing his lab's work developing #ComputationalMethods that organize poorly labeled data. The goal is to make millions of publicly available datasets discoverable.
🧬 AI in Genomics Symposium next week! We're bringing together leading scientists from across academia and industry pushing the boundaries of AI in genomics research Join us May 8 at the University of Chicago - KCBD Auditorium, 9:30–5:00, reception to follow. No registration needed!
What is the PhD actually for, especially now that AI can do increasingly more of what we train scientists to do? compbiologist.substack.com/p/what-is-th... A response to @pracheeac.bsky.social's thought-provoking essay "Free the PhD".
What is the PhD actually for?
A response to Prachee’s “Free the PhD”, and a critique of my own work
compbiologist.substack.com
Sean Davis & I are hiring a postdoc to work on turning massive public biological data collections into reusable engines for discovery. #ML / #AI + large-scale omics + open software Details + apply: cu.taleo.net/careersectio... seandavi.github.io | thekrishnanlab.org @cubiomedinfo.bsky.social
Post-Doctoral Fellow
Click the link provided to see the complete job description.
cu.taleo.net
A lab using my recent articles on AI use during PhD training doi.org/10.5281/zeno... & doi.org/10.5281/zeno... to kickstart a discussion and draft guidelines for their group is exactly the kind of use I hoped these articles would inspire! Highly recommend reading Ran's post.
Build expertise first: why PhD training must sequence AI use after foundational skill development
Generative AI tools have arrived in PhD training environments faster than principled frameworks for their use. The debate has polarized between enthusiasts who argue trainees must adopt AI immediately...
doi.org
Ran Blekhman@blekhman.bsky.social · 4mo agoI wrote about why every lab should have AI use guidelines, and how to do it. open.substack.com/pub/blekhman...
I wrote about why every lab should have AI use guidelines, and how to do it. open.substack.com/pub/blekhman...
You need to make AI guidelines for your lab
Here's why you should, and how to start
open.substack.com
@compbiologist.bsky.social and @fishevodevogeno.bsky.social present newly minted Dr. Hao Yuan @yhbioinfo.bsky.social! @michiganstateu.bsky.social Amazing work @ the intersection of computational, biomedical, and evolutionary biology! Hao starts a postdoc in the @edwardmarcotte.bsky.social Lab soon.
We have a new platform for employees to give and receive kudos, and it's weekly digests are brutal!
Enjoyed working w/ Stephen & Agnes on this! Gave me a chance to think systematically about where AI 🤖 can backstop human 🧑🏼🔬 fallibilities in peer review (fatigue, ordering effects, bias) vs. where human judgment remains essential (novelty, feasibility, creative leaps) while grappling w/ the risks.
Stephen Turner@stephenturner.us · 5mo agoPeer review reliability is shockingly low. Meta-analyses show reviewer agreement barely above chance, and grant outcomes often depend more on who reviews than what's proposed. Our new preprint with Agnes Urban and Arjun Krishnan @compbiologist.bsky.social : papers.ssrn.com/sol3/papers.... 🧵 1/
Peer review reliability is shockingly low. Meta-analyses show reviewer agreement barely above chance, and grant outcomes often depend more on who reviews than what's proposed. Our new preprint with Agnes Urban and Arjun Krishnan @compbiologist.bsky.social : papers.ssrn.com/sol3/papers.... 🧵 1/
PhD programs worldwide face an urgent question: How should trainees use ChatGPT, Claude & similar tools? Now online: two resources on thoughtfully integrating generative AI into research training. 📄 Conceptual framework: zenodo.org/records/18649847 📋 Practical guide: zenodo.org/records/18452319 🧵
Build expertise first: why PhD training must sequence AI use after foundational skill development
Generative AI tools have arrived in PhD training environments faster than principled frameworks for their use. The debate has polarized between enthusiasts who argue trainees must adopt AI immediately...
zenodo.org
From Arjun Krishnan @compbiologist.bsky.social Expertise before augmentation: a practical guide to using generative AI during research training: zenodo.org/records/1845... Build expertise first: why PhD training must sequence AI use after foundational skill development: zenodo.org/records/1864...
Happy to share this new, very intentional chapter. I have left UCLA after 14 years to join the University of Colorado Anschutz as Professor of Biomedical Informatics and Neurosurgery and the inaugural Marsico Chair in Excellence in Functional Precision Medicine/n news.cuanschutz.edu/dbmi/cu-ansc...
CU Anschutz Recruits National Leader to Launch Functional Personalized Medicine Initiative
CU Anschutz welcomes Alice Soragni to launch a Functional Personalized Medicine Initiative using rapid tumor organoid testing to guide treatment decisions.
news.cuanschutz.edu
Our Fish EvoDevoGeno Lab @michiganstateu.bsky.social has its 10th anniversary today! 🐠🐟🧪🧬🔬 Thanks to all lab members - present & past, pictured or not - for making the last decade a success! & thanks to our partners in crime of the @brainyfishguts.bsky.social Lab, too! #EndlessFishMostBeautiful
I'm looking forward to re-teaching: Rethinking Data Analysis — A researcher’s guide to avoiding missteps and misuse This is an advanced short course on developing a mental toolkit for rigorous practice & critical consumption of statistical data analyses. 🧵 1/4
A Perspective reviews computational methods for cross-species knowledge transfer. www.nature.com/articles/s41...
Computational strategies for cross-species knowledge transfer - Nature Methods
This Perspective reviews computational methods for cross-species knowledge transfer and introduces ‘agnology’, a data-driven concept of functional equivalence independent of evolutionary origin.
nature.com
Our Perspective article on Computational Strategies for Cross-Species Knowledge Transfer is now published in @natmethods.nature.com! This was a collab b/w @krishnanlab.bsky.social & @fishevodevogeno.bsky.social, led by the amazing Hao Yuan @yhbioinfo.bsky.social. 🧵 www.nature.com/articles/s41...
Known for decades: DNA sequence drives nucleosome "rotational positioning" (which face of DNA contacts histones) But: How does this persist when remodelers & transcription constantly mobilize nucleosomes? Our new preprint 1/ : www.biorxiv.org/content/10.6...
biorxiv.org
This preprint is now out after peer review! Check it out: www.cell.com/cell-genomic.... Huge congrats (and thanks!) to the whole team that contributed!
Systematic analysis of nonsense variants uncovers peptide release rate as a novel modifier of nonsense-mediated mRNA decay
Kolakada et al. discover that the amino acid preceding a premature termination codon influences nonsense-mediated mRNA decay efficiency. They identify peptide release rate during translation terminati...
cell.com
Suja Jagannathan@rnabiologist.bsky.social · 3y agoExcited to share the latest work from the lab, led by Divya Kolakada, the first PhD from our group 🎓🤓🎉 Peptidyl-tRNA hydrolysis rate influences the efficiency of nonsense-mediated mRNA decay www.biorxiv.org/content/10.1...
Very proud to be a member of this team. A huge group effort to improve the lives of those with Down syndrome. Thank you to everyone that has helped us along the way.
CU Anschutz Linda Crnic Institute for Down Syndrome@crnicinstitute.bsky.social · last yr.The Linda Crnic Institute for Down Syndrome is proud to announce that we have been awarded the 2025 Research Collaboration Award at the 2025 @cuanschutz.bsky.social Research Awards! This award recognizes a team for outstanding contributions in research collaborations.
Congratulations! Kudos to @richabdill.com & @samanthagraham.bsky.social for leading this huge project! Thanks for bring us onboard! Mansooreh Ahmadian & Parker Hicks lead the part of the work on inferring study annotations from unstructured metadata and text from the linked publications.
Ran Blekhman@blekhman.bsky.social · 2y agoToday we report a new compendium of human gut microbiomes with >168,000 samples By analyzing this massive dataset, we discovered distinct microbiome patterns across the globe, and show we can predict where a person lives just from their gut bacteria Now out in Cell: www.cell.com/cell/fulltex...
A favorite! Interestingly, Goodhart stated (in 1975): “Any observed statistical regularity will tend to collapse once pressure is placed upon it for control purposes.” Marilyn Strathern generalized it in 1997 to its famous version👇🏽 pmc.ncbi.nlm.nih.gov/articles/PMC...
“When a Measure Becomes a Target, It Ceases to be a Good Measure”
pmc.ncbi.nlm.nih.gov
Atul Butte@atulbutte.bsky.social · 2y ago“When a measure becomes a target, it ceases to be a good measure." - Goodhart’s Law en.m.wikipedia.org/wiki/Goodhar...
Regularly tempted to write in my NIH grants innovation section: "Funding software that already exists and works well would be highly innovative for the NIH." (I bet half the panel would break down ROFL, but I'm also highly skeptical that I'd get a good score, or that the PO would be amused.)
Last update of our databases for the year. Download them here: 493 early-career funding opportunities: research.jhu.edu/rdt/funding-... 313 postdoc fellowships: research.jhu.edu/rdt/funding-... 189 PhD fellowships: research.jhu.edu/rdt/funding-...
Monday motivation from the wonderful @pracheeac.bsky.social: “[I hate the term] incentive structure… if you ask people to do a thing that they perceive to be against those processes and principles, well, you can't ask that — that it's somehow unacceptable…
I participated in a faculty panel a few weeks ago in which senior (ahem) faculty gave advice on careers in academia by pretending luck had very little to do with our success. One piece of advice riled me up, in which it was argued that a reason for their success was their ability to say no. 1/
Same reason that nanopore work with direct clinical application gets published in Annals of Obscurities while the tumor poopome and AlphaFold3 (which wasn’t even competitive in CASP16!) get published in Nature over the objections of highly qualified reviewers
Because it makes for a better $$$ barrier to entry. Broke: we fit a linear model and predicted results of a CRISPR screen Woke: we burned down the Amazon to train a 96-head transformer on 500 million cells and did ALMOST AS WELL as the linear model that runs on my phone
