iiinova — where your digital self keeps evolving

Arjun Krishnan

@compbiologist.bsky.social

1.1K followers 172 following 48 posts

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.

Posts Replies Media

Arjun Krishnan @compbiologist.bsky.social · 20/03/2026

We have a new platform for employees to give and receive kudos, and it's weekly digests are brutal!

Recognition Digest: February 27, 2026 - March 6, 2026

Summary:
0
Recognitions Received by Your Team

Recognitions
Looks like no one in this group has been recognized recently. Start the momentum and send a recognition!

021

Arjun Krishnan @compbiologist.bsky.social · 08/01/2026

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

HMGP 7622
Rethinking Data Analysis — A researcher’s guide to avoiding missteps and misuse
Feb 3 – May 5, 2026 | Tue 2–3:30p

OVERVIEW
This is a short (1-credit) course designed to:
1) Discuss common misunderstandings & typical errors in the practice of statistical data analysis.
2) Provide a mental toolkit for critically thinking about statistical methods and results.

TOPICS
Estimating error, uncertainty • Underpowered statistics • Multiple testing • P-hacking • Pseudoreplication • Regression to the mean • Double dipping • Spurious associations • Visualization challenges • Reproducibility, replicability

PREREQUISITES
1) Introductory knowledge of statistics & probability
2) Introductory experience with data wrangling, analysis, & visualization using R/Python.

INSTRUCTOR
Arjun Krishnan
Associate Professor, Department of Biomedical Informatics
University of Colorado Anschutz Medical Campus
arjun.krishnan@cuanschutz.edu | @compbiologist | thekrishnanlab.org

120

Arjun Krishnan @compbiologist.bsky.social · 06/01/2026

4/10 Traditional approaches rely heavily on homology. But shared ancestry ≠ shared function & vice-versa. Here, we introduce the concept of Agnology, which embraces this complexity: "agno-" = unknown/not known, reflecting data-driven functional equivalence regardless of evolutionary origin.

Figure depicting how traditional methods rely on homology to determine functional equivalence and, by contrast, modern data-driven approaches use what we call 'agnology', identifying fully or partially functionally equivalent genes regardless of evolutionary origin, allowing for ambiguity in homology or analogy.

110

Arjun Krishnan @compbiologist.bsky.social · 06/01/2026

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...

Figure depicting the four classes of important questions that frequently arise when using research organisms to study biomedical questions and translating findings to humans. a, How to predict disease–gene or function–gene relationships across species? Diagram depicts genes in each species associating with specific functions, diseases and phenotypes. b, How to identify functionally equivalent molecular components across species? Diagram depicts finding the most equivalent gene, pathway or expression module or phenotype between species. c, How to infer perturbed molecular profiles across species? Diagram depicts gene expression in each species as a result of taking a particular perturbation like a drug. d, How to map equivalent cell types and cell states across species? Diagram depicts alignment of cell types across species. This Perspective comprehensively lays out the landscape of recent and state-of-the-art data-driven strategies, including those that leverage artificial intelligence and machine learning (ML), for answering these questions.

1164

Arjun Krishnan @compbiologist.bsky.social · 21/09/2023

[1st post!] Checkout this comprehensive review & perspective on the "Current and future directions in network biology" arxiv.org/abs/2309.08478. A bunch of us got to lead the section on "Machine learning on networks". Kudos to the whole community and to Dr. Tijana Milenković for the leadership!

Graphical abstract of the review article that pictorially summarizes the five major themes: 1) Network inference and comparison, 2) Multimodal data integration and heterogeneous networks, 3) Higher-order network analysis, 4) Machine learning on networks, and 5) Network-based personalized medicine.

Graphical abstract of the section on "Machine learning on networks". The box on the top left shows the overall workflow of approaches in this area, beginning from the biological network that using a machine learning model, is able to generate learned representations of various elements in the network. The box on the top right describes three additional idea: building generative models, transfer learning, and application to downstream tasks. The final box at the bottom shows two important foci of work in this area: i) benchmarking and ii) explainability and uncertainty quantification.

0138