Eric Kernfeld

Eric Kernfeld

@ekernf01.bsky.social

Statistician and computational biologist; uw alum; jhu student. He/him. http://ekernf01.github.io

1.3K followers422 following315 posts

Eric Kernfeld
@ekernf01.bsky.social

This is so friggin cool. You don't have to rewrite all that FORTRAN to do autodiff on it. "Enzyme"

Adrien Corenflos@adriencorenflos.bsky.social

Found the paper arxiv.org/abs/2010.01709

arxiv.orgInstead of Rewriting Foreign Code for Machine Learning, Automatically Synthesize Fast GradientsApplying differentiable programming techniques and machine learning algorithms to foreign programs requires developers to either rewrite their code in a machine learning framework, or otherwise provid...
Eric Kernfeld
@ekernf01.bsky.social

For people that have tried to hire someone recently, did you encounter this problem? www.linkedin.com/posts/olga-v...

linkedin.comFailed to weed out LLM-generated applications for bioinformatics role | Olga Sazonova, Ph.D. posted on the topic | LinkedInWell, that's it. Hiring is f*cked. I'm just opened a contract role for a bioinformatics project. I know it's a wild market at the moment - each open role gets flooded with resumes, making it hard to separate qualified candidates from the noise. I'm convinced LLMs are partially to blame. So I devised a process to select qualified, committed candidates and avoid generic applications. Instead of resumes and cover letters, I created an intake questionnaire requiring bespoke effort to reduce cookie-cutter applications. The questions focused on specific scenarios from past experience, and therefore shouldn't be directly outsourced to chatbots. I also accidentally made the application link hard to access, but decided not to fix it. After all, computational biology often requires hacking and clever work-arounds. Finally, I included an honor code asking people not to use LLMs. Initially, I felt good about my approach. I had 20 applications after two days, and the candidates were differentiating themselves: A few didn't answer all questions, a few didn't have the right background, and several candidates provided well-written, topical, plausible answers. It was only after I read a few of these "high signal" applications in a row that the alarm bells started ringing: - Multiple candidates highlighted the same methodological paper - Many cited required skills in the exact same order - A high percentage reported identical troubleshooting scenarios involving differential gene expression studies with lab-derived batch effects The nail in the coffin was repeated phrases like "my initial hypothesis was a bug in [popular tool]" and "the spurious result disappeared." Clearly, candidates were using LLMs. Instead of learning about fitness for the role, I was learning how LLMs answer my "clever" questions. So...I failed. My approach was naive, perhaps even hypocritical. After all, I use LLMs for technical documentation myself. Still, it's really disappointing. I'm no closer to a hiring process that identifies qualified, motivated, and trustworthy candidates for remote work. Now what, y'all? | 109 comments on LinkedIn
View full thread
View full thread
Eric Kernfeld
@ekernf01.bsky.social

In October 2024, I twote that "something is deeply wrong" with what we now call virtual cell models. A lot has happened since then. How am I updating? New blog post: ekernf01.github.io/virtual-cell...

ekernf01.github.ioA recap of virtual cell releases circa June 2025In October 2024, I twote that “something is deeply wrong” with what we now call virtual cell models. A lot has happened since then: modelers are advancing new architectures and mining new sources of i...

Eric Kernfeld reposted

Elizabeth Wood, PhD
@lizbwood.bsky.social

The biggest challenge for AI in biology isn't just models, it's the data used to train them. Standard biological data isn't built for AI. To unlock generative AI for drug discovery, we must rethink how we generate and capture data. 1/

Eric Kernfeld reposted

Sara Rouhanifard
@srouhanifard.bsky.social

1/🧵 🚨 New paper published in RNA! Scientists often say anecdotally that RNA modifications are disrupted in immortalized cells — but no one’s really tested it. So we did: ψ-mapping in primary T cells vs. Jurkat cells using direct RNA-seq. 📄 tinyurl.com/TCellPsiRNA #nanopore #RNA #pseudouridine

Eric Kernfeld
@ekernf01.bsky.social

BLOG ALERT! 🧬 If you do RNA-seq, ATAC-seq, ChIP-seq, or modeling thereof, you may be overlooking LD score regression methods. These should be standard tools to study genes, variants, and regions en masse, but they are hard to understand. I wrote intros:

Eric Kernfeld
@ekernf01.bsky.social

Terrific opportunity. If I were not committed to the east coast for personal reasons, I would apply to this immediately.

Anshul Kundaje@anshulkundaje.bsky.social

@saramostafavi.bsky.social (@Genentech) & I (@Stanford) r excited to announce co-advised postdoc positions for candidates with deep expertise in ML for bio (especially sequence to function models, causal perturbational models & single cell models). See details below. Pls RT 1/

Eric Kernfeld reposted

Eli Weinstein
@eliweinstein.bsky.social

Thrilled to announce that I am joining DTU in Copenhagen in the fall, as an assistant professor of chemistry. My research group will focus on fundamental methodology in machine learning for molecules.

Eric Kernfeld reposted

Han Yuan
@hy395.bsky.social

1/ DNA sequence models like Borzoi predict gene expression and variant effects across tissues — but how can someone adapt the model to a custom experiment? @drkbio.bsky.social, Johannes Linder and I propose a solution via parameter-efficient fine-tuning (PEFT). www.biorxiv.org/content/10.1...

biorxiv.orgParameter-Efficient Fine-Tuning of a Supervised Regulatory Sequence ModelDNA sequence deep learning models accurately predict epigenetic and transcriptional profiles, enabling analysis of gene regulation and genetic variant effects. While large-scale training models like E...
Eric Kernfeld
@ekernf01.bsky.social

new advance in classifying species-of-origin for long reads. Potentially very valuable for diagnostics!! But hot damn, look at that memory consumption.

Mohsen Zakeri@mohsenzakeri.bsky.social

1/5 We introduce Movi Color, led by Steven Tan (a brilliant undergrad member of Langmead lab) for taxonomic and multi-class classification. It uses a full-text index based on the move structure and does not rely on predefined values (like k-mer length) for index building. github.com/mohsenzakeri...

github.comRelease Movi Color · mohsenzakeri/MoviThis version introduces Movi Color. Movi rows are augmented with run colors, defined based on the origin of the suffixes within each run. The Movi Color index can be built by either an additional ...
Eric Kernfeld
@ekernf01.bsky.social

This is a really nice piece of work. biorxiv.org/content/10.1... - The sustainability and software quality is far superior to most one-off academic software projects. It is informed by deep experience with similar problems. - It is an especially clever data split. In causal ...

biorxiv.orggeneRNIB: a living benchmark for gene regulatory network inferenceGene regulatory networks (GRNs) underpin cellular identity and function, playing a key role in health and disease. Despite various benchmarking efforts, existing studies remain limited in the number o...
Eric Kernfeld
@ekernf01.bsky.social

... gene network modeling, it is possible to fool oneself by learning predictive models that are not causally correct. It is also possible to test on counterfactual scenarios that are so far out of distribution that the task is nearly impossible and all the methods look bad ...

Eric Kernfeld
@ekernf01.bsky.social

... I kinda did this with PEREGGRN, though txpert now claims some real progress. This study threads the needle nicely by finding a data split that will probably favor the more causally correct models, but also isn't so hard that the signal evaporates.

Eric Kernfeld
@ekernf01.bsky.social

Family is important: cells in culture share variations in density, autocrine signals, humidity/temp/O2, and importantly, their mommas. This renders them not statistically independent. Need full bio replicates. Related: www.nature.com/articles/s41...

nature.comCRISPR-StAR enables high-resolution genetic screening in complex in vivo models - Nature BiotechnologyPooled genetic CRISPR screening is improved in complex models through leveraging internal controls.
Silvia Domcke@sdomcke.bsky.social

Expanding Perturb-seq-like screens to multicellular systems also increases the complexity of confounding effects. We encountered this when we perturbed all TFs in mosaic embryoid bodies (EBs) and develop a scalable solution by barcoding monoclonal individuals. 🧵 www.biorxiv.org/content/10.1...

biorxiv.orgBarcoded monoclonal embryoids are a potential solution to confounding bottlenecks in mosaic organoid screensGenetic screens in organoids hold tremendous promise for accelerating discoveries at the intersection of genomics and developmental biology. Embryoid bodies (EBs) are self-organizing multicellular str...

Eric Kernfeld reposted

Jakob Trendel
@jtrend.bsky.social

Excited our paper is out in Cell @cp-cell.bsky.social! 🧬⚡ DNA photo-crosslinking proteomics in living cells 🎯 Pinpoints protein-DNA interactions to single amino acids 🌎 Globally quantifies DNA binding for >1800 proteins at a timescale of minutes 🔗 www.cell.com/cell/fulltex... 🧵

cell.comThe human proteome with direct physical access to DNAZero-distance photo-crosslinking reveals direct protein-DNA interactions in living cells, enabling quantitative analysis of the DNA-interacting proteome on a timescale of minutes with single-amino-aci...
Eric Kernfeld
@ekernf01.bsky.social

For me, it's roughly day 100 of being pleasantly surprised that a position-weight matrix can capture a complex-seeming distribution over zillions of possible antibodies... ... and then bust out of the screen and be manufactured in real life.

Elizabeth Wood, PhD@lizbwood.bsky.social

If there's such a thing as AI for drug design & development on easy mode, then it's probably in being able to build and test every design. Check out our journey to the 10 quadrillion AI-designed antibody library now; we're going to be sharing some big updates soon: ▶️ www.jura.bio/blog/variati...

Eric Kernfeld reposted

Sara Carioscia
@saracarioscia.bsky.social

I'm defending my PhD next Friday, May 23!(!!!!). I'll be highlighting our work looking at aneuploidy in early human development. If you're interested I'd love to have you join via Zoom (DM me for info) or on the Homewood campus!

Eric Kernfeld reposted

Arun Das
@arun-das.bsky.social

Easily the most important thing happening next week. Come and watch my friend Sara defend her PhD!

Sara Carioscia@saracarioscia.bsky.social

I'm defending my PhD next Friday, May 23!(!!!!). I'll be highlighting our work looking at aneuploidy in early human development. If you're interested I'd love to have you join via Zoom (DM me for info) or on the Homewood campus!