The Molecular Biosciences Department at Northwestern is excited to announce a faculty search for a Tenure-Track Assistant Professor position! Learn more and apply at: molbiosci.northwestern.edu/f… #BiologyJobs #AcademicJobs #FacultySearch #FacultyJobs

The piece revisits the early days, our lab's initial work alongside other groups pioneering complementary approaches, together showing that mass-spec-based single-cell proteomics was feasible & promising. The proof-of-concept set the field in motion. 2/ nature.com/articles/d41586-0…

Accurately quantifying over 700K precursors in a single 9-plexDIA set of 20ng proteomes is a new milestone. JMod achieves high quantitative accuracy over a 32-fold dynamic range of proteome spiked-in ratios across single-cell and bulk sample sizes. 1/ doi.org/10.1101/2025.05.22.6…

Many drugs work by binding to a specific target in the body and blocking or changing what it does. An important first step in the drug development process is designing a molecule that can bind tightly to its target. Traditionally, that's meant weeks or months of expert work per target, sifting through a large number of candidates to identify the few that work. We wanted to test if Claude could successfully design novel protein binders from scratch (also called de novo design). With a protein design prompt written by a human expert, Claude autonomously designed protein binders against 14 out of 15 targets. We then worked with Adaptyv Bio and Twist Bioscience, who independently built and tested the proteins Claude designed.

In this revision, we expanded our analysis across more tissue types & more model systems. The conclusions held. Proteomes are shaped by tissue type-specific protein degradation rates ▶️ This effect strongly depends on the cell growth rates. 🔗biorxiv.org/content/10.1101/…

The data we need to understand human biology is about 1000x the quantity we've collected Full piece from @insitro founder and CEO @DaphneKoller: a16z.news/p/drug-discovery-h…

The space of all possible hypotheses is still far greater than the space of all data collected. Moreover, the data has all been collected through the lens of our current paradigms for understanding biology (largely based on what we can measure easily). For these reasons, I think most verification is still hard, especially for interesting ideas. But maybe I’m wrong. Planning to explore that alternative possibility :).

We report many proteins not predicted by the genetic code. They are stable & abundant O( 10³ ) copies / cell. Generative mechanisms include codon-anticodon mismatches & RNA modifications. Their abundance depends on codon frequency & protein stability. biorxiv.org/content/10.1101/…

No scaling laws for single-cell foundation models: when bigger atlases stop teaching the model anything In language and vision, the recipe has been simple: more data, bigger models, better performance. Single-cell biology borrowed that playbook. Foundation models for transcriptomics jumped from 1 million cells to atlases of over 100 million, on the assumption that scale would unlock the same gains. Alan DenAdel and coauthors put that assumption to the test, and the result is sobering. Working from a 22.2-million-cell corpus, they pretrained 400 models across five architectures (from PCA and a variational autoencoder up to the Geneformer transformer) and ran 6,400 evaluation experiments. They varied not just dataset size (1% to 75%) but also diversity, using cell-type re-weighting and geometric sketching to deliberately enrich rare cell types and transcriptional states. The finding: performance saturates almost immediately. On cell-type classification, batch integration, and perturbation prediction, most models hit their ceiling at roughly 1% of the corpus, about 200,000 cells. Beyond that, adding millions more cells changed essentially nothing. More diversity didn't help. Even spiking in genome-scale Perturb-seq data, to give the models perturbed phenotypes rather than just healthy ones, failed to move the needle. Larger models did score better overall, but they too plateaued early on data. Two points stood out. Simple baselines (PCA, logistic regression) often matched or beat the transformers. And the strongest model, SCimilarity, won not because of size but because its contrastive training objective is aligned with the downstream task. For single-cell data, what you train on and how you frame the objective matters far more than how much you collect. This reframes a quiet but expensive habit. In drug discovery, biotech, and any pipeline leaning on cell atlases, the instinct to keep scaling pretraining corpora may be burning compute for no return. The real leverage sits elsewhere: curating high-quality, task-relevant data and matching the training objective to the actual question you're trying to answer. Paper: DenAdel et al., journal license | doi.org/10.1038/s41592-026-0…