←
Arjun Krishnan1,121 posts
Arjun Krishnan avatar

Arjun Krishnan

@compbiologist

ML & data-driven discovery; Complex traits & diseases; Data reuse & open science. Associate Professor | Group leader @KrishnanLab | @compbiologist everywhere

◷ Joined May 2008▧ 98 Photos and videos
Arjun Krishnan avatar
Arjun Krishnan@compbiologist·Nov 16

4/ Full tuition, health and dental insurance, and a $44,290/year stipend. About five years to degree, in person in the Denver area. Questions: BIMA@cuanschutz.edu

Arjun Krishnan avatar
Arjun Krishnan@compbiologist·Nov 16

3/ Your dissertation can be a discovery, a new method, a deployed clinical system, a venture, or open-source infrastructure. Each pathway produces a different evidence of impact, all evaluated under one standard of rigor.

Arjun Krishnan avatar
Arjun Krishnan@compbiologist·Nov 16

2/ Four specializations: Bioinformatics & Computational Biology, Computational Neuroscience, Imaging Informatics, and Clinical Informatics. Molecules to neural circuits to imaging to clinical care.

Arjun Krishnan avatar
Arjun Krishnan@compbiologist·Nov 16

1/ A new six-course core built around the lifecycle of computational science, from scientific question to translation. Students build skills by hand first, then learn to direct and verify AI and to defend every analytical choice.

Arjun Raj avatar
⟳ Arjun Krishnan retweeted
Arjun Raj@arjunrajlab·Aug 12

I am beyond humbled to take on the role of CSO at Cellular Intelligence while on leave from Penn! Thrilled to have the opportunity to work with an incredible team tackling hugely exciting and challenging problems!

We're excited to announce that Arjun Raj, Ph.D. @arjunrajlab has been appointed Chief Scientific Officer and named Scientific Co-Founder of Cellular Intelligence. Arjun joined us full time in 2025 while on leave from @Penn, where he is the Richard K. Lubin Professor of Bioengineering and Professor of Genetics. A mathematician turned experimental systems biologist, he co-developed the method that made it possible to count individual RNA molecules inside single cells. In his first year here he architected our data engine and scientific program. "What has always limited the field is the data," Arjun said. "For the first time, I can see a path from observing cellular decisions to predicting and eventually controlling them." Congratulations Arjun! 🔗 Official announcement: prnewswire.com/news-releases…

David Manheim avatar
⟳ Arjun Krishnan retweeted
David Manheim@davidmanheim·Jun 3

Thanks for the link, interesting post by @blekhman, lots of good points! @compbiologist: "the best model is usually the one that is consistently number 2 in benchmarks across the literature." - Yes, it's Goodhart's curse, overoptimization for narrow targets will fail. (Though in more general GenAI domains, the problem is even harder because all the benchmarks are getting saturated as well!) On the importance of evaluations, the newer work on improving eval practices and reporting - @EvalConsensusAI / @evaluatingevals - seems likely to be relevant, though it needs to be adapted to bio models. Seems like a good place to continue exploring; both Noga Aharony and Reut Danino are separately interested in related issues; we should put something together on this! There are also a number of points in our RAND report that I think are touched upon, especially about prediction vs. validation, and about metadata (i.e. our discussion of the problem of multimodal data and integrating data;) rand.org/pubs/research_repor… And one last point - "a recurring theme... was that ignoring theory and history is a mistake" - that sounds like the bitter lesson isn't supposed to apply here; I remain skeptical. But as the Delphi explored, there may be fundamentally too little data in this domain to brute force answers; @alexijielu's approaches with self-supervision seem to be trying to address this. (And given that he's working to characterize limitations of current AI methods, I really wish we had gotten him into the Delphi Panel for our study!)

Stephen Turner avatar
⟳ Arjun Krishnan retweeted
Stephen Turner@strnr·Mar 9

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: papers.ssrn.com/sol3/papers.… 🧵 1/

Post attachment
Kelly Sullivan avatar
⟳ Arjun Krishnan retweeted
Kelly Sullivan@kellydsullivan·Jan 16

Excited to share this work. A huge effort from many team members, led by former @CUHMGGP PhD student and current @CrnicInstitute Post-doc, Dr. Lauren Dunn! Altered hepatic metabolism in Down syndrome: Cell Reports cell.com/cell-reports/fullte…

Arjun Krishnan avatar
Arjun Krishnan@compbiologist·Jan 5

Our perspective is now out in @naturemethods! Congratulations again to @yhbioinfo & the rest of the team! nature.com/articles/s41592-0…

Preprint 🚨 A review state-of-the-art computational strategies for cross-species knowledge transfer in biomedicine 💻👩‍🦰🐭🐟🪰🪱🧬🫁⚕️ Led by an excellent team at @KrishnanLab: @yhbioinfo, @ChrisAMancuso, & @kaylainbio in collab w/ @FishEvoDevoGeno 🧵 arxiv.org/abs/2408.08503

Arjun Krishnan avatar
Arjun Krishnan@compbiologist·7 Nov 2024

#ASHG24 Interested in comparing & transferring data & knowledge across species for translational biomedicine? This review is for you! We take a deep dive into methods & highlight gaps/challenges. Details on implementation, data, & benchmarks: github.com/krishnanlab/cross…

Preprint 🚨 A review state-of-the-art computational strategies for cross-species knowledge transfer in biomedicine 💻👩‍🦰🐭🐟🪰🪱🧬🫁⚕️ Led by an excellent team at @KrishnanLab: @yhbioinfo, @ChrisAMancuso, & @kaylainbio in collab w/ @FishEvoDevoGeno 🧵 arxiv.org/abs/2408.08503

Arjun Krishnan avatar
Arjun Krishnan@compbiologist·5 Nov 2024

#ASHG2024 #ASHG24 If you’re interested in effectively reusing public omics data and/or passionate about data discovery, data reuse, metadata, etc., do ping me!

Annotating Publicly-Available Samples and Studies Using Interpretable Modeling of Unstructured Metadata 1. This study introduces txt2onto 2.0, an improved NLP and ML-based tool that automates the annotation of unstructured biomedical metadata, linking samples and studies to controlled disease and tissue vocabularies without manual intervention . 2. By using a TF-IDF-based feature extraction approach instead of averaging word embeddings, txt2onto 2.0 offers more interpretable results, allowing it to accurately identify key predictive terms within sample and study metadata . 3. The model outperforms its predecessor in both tissue and disease annotation tasks, excelling particularly in scenarios with limited training data, thus making it ideal for infrequent or rare biomedical terms . 4. A notable strength of txt2onto 2.0 is its ability to work across different biomedical text sources (e.g., GEO, PRIDE, ClinicalTrials), providing consistent annotations by capturing meaningful semantic relationships even with unseen terms . 5. The interpretability of txt2onto 2.0 is highlighted through word clouds of predictive terms, where it captures domain-specific keywords without requiring explicit mentions of target terms, showcasing its robustness and potential to adapt to new datasets . 6. This tool’s transparent prediction process and scalability support its application across various data repositories, advancing the FAIR data principles (Findable, Accessible, Interoperable, Reusable) in biomedical research . @compbiologist 💻Code: github.com/krishnanlab/txt2o… 📜Paper: doi.org/10.1101/2024.06.03.5… #BiomedicalNLP #DataAnnotation #MachineLearning #FAIRdata #ComputationalBiology

Post attachment