Spotlight
New platform enables ultrafast, reference-free sequence searches across millions of single cells
·Pepkio Team·3 min read
Scientists report today in Nature the launch of Malva, a computational platform that allows researchers to search for any RNA sequence – from viral genomes to cancer mutations – across millions of single cells in…
Read summary →
New AI model predicts how cells respond to drugs and genetic perturbations across diverse contexts
·Pepkio Team·2 min read
Scientists at the Arc Institute have developed State, a machine learning model that predicts how individual cells will respond to drugs, genetic edits, and other perturbations—even in cell types or tissues where no such…
Read summary →
FuncVEP: functional training yields best-performing missense variant predictor, uncovers new disease links
·Pepkio Team·2 min read
A new family of variant effect predictors, FuncVEP, trained exclusively on experimental functional data rather than clinical labels, outperforms 48 existing tools across multiple benchmarks, scientists report today in…
Read summary →
Deep learning unlocks de novo design of complex RNA pseudoknots
·Pepkio Team·2 min read
Complex RNA structures govern fundamental processes like translation and viral replication, but designing entirely new RNA folds from scratch has remained out of reach—until now. Scientists report today in Science that…
Read summary →AI-designed cell-surface tags boost antigen display for vaccines and CAR-T therapies
·Pepkio Team·2 min read
Scientists report today in Nature Biotechnology that a deep learning suite called DeepSCan can discover and design potent cell-surface display (CSD) elements — short protein modules that anchor antigens or receptors to…
Read summary →
AI that learns the mechanics of prime editing picks better guides—and fixes a mutation in mouse brains
·Pepkio Team·3 min read
Prime editing can rewrite DNA with great precision, but finding the right guide RNA often means testing hundreds of candidates. A new machine-learning tool, OptiPrime, cuts that search down dramatically—and, in a mouse…
Read summary →
Aligning protein AI with experimental fitness stabilizes influenza vaccines
·Pepkio Team·2 min read
Scientists report today in Nature Methods a new way to make protein-generating AI models follow experimental fitness data. The work, led by Brian L. Hie at Stanford University, with first author Talal Widatalla,…
Read summary →
AI model PRISM2 matches clinical-grade pathology tests without additional training
·Pepkio Team·2 min read
Scientists report today in Nature Medicine that a new AI model, PRISM2, trained on millions of pathology images and clinical reports, can detect cancer in prostate, breast, and lymph node samples with accuracy matching…
Read summary →AI tool 'Raygun' shrinks and expands proteins while preserving function, opening new avenues for protein engineering
·Pepkio Team·3 min read
Scientists report recently in Nature a new AI framework called Raygun that can miniaturize, expand, and modify natural proteins while preserving their function. The work, led by senior author Rohit Singh at Duke…
Read summary →
A Smaller AI Model Learns How Proteins Interact, Challenging the Need for Massive Protein Language Models
·Pepkio Team·2 min read
Understanding how proteins interact is crucial for decoding cellular functions and developing targeted therapeutics. However, current AI models struggle to predict these complex interactions without relying on massive,…
Read summary →AI Model Creates a Universal Map of Cell Biology, Works Across Species Without Retraining
·Pepkio Team·3 min read
A new artificial intelligence model can instantly place any cell—from human, mouse, chicken, or even fruit fly—into a shared biological map, without needing to be retrained on new data. The advance, reported this week…
Read summary →Generalist AI Agent Matches Experts on Biomedical Research Tasks While Slashing Analysis Time
·Pepkio Team·3 min read
Biomedical research is often bogged down by fragmented, time-consuming workflows that require stitching together specialized tools, vast datasets, and deep domain knowledge. A study published today in Science describes…
Read summary →
An interpretable AI model predicts immunotherapy outcomes across multiple cancer types
·Pepkio Team·3 min read
While immune checkpoint inhibitors—cancer treatments designed to help the immune system recognize and attack tumors—have transformed oncology, the majority of patients still do not experience durable responses.…
Read summary →
A Roadmap to Build an AI-Powered Virtual Yeast That Simulates a Eukaryotic Cell
·Pepkio Team·3 min read
A team of scientists has laid out an ambitious blueprint to construct a virtual yeast cell—an AI-driven simulation that captures how a living eukaryotic cell responds to genetic changes, drugs, and environmental shifts.…
Read summary →AlphaFold3 Learns from Lab Experiments to Map Proteins’ Shape-Shifting Behavior
·Pepkio Team·3 min read
Proteins are not the rigid sculptures often depicted in textbook diagrams—they flex, twist, and sample a range of shapes to carry out their functions. Yet the most celebrated protein-structure prediction tools,…
Read summary →
How Single Neurons Encode the Grammar and Meaning of Our Words
·Pepkio Team·4 min read
Language allows us to combine words into an endless variety of phrases and sentences, yet how individual brain cells support this unique human ability has remained a mystery. Now, by recording the activity of hundreds…
Read summary →Blood Proteomics Maps Cellular Aging and Links It to Disease Risk Years Before Diagnosis
·Pepkio Team·2 min read
A large study in Nature Medicine shows that a simple blood draw may capture how different cell types in the body are aging—and that these signals can predict future disease risk years in advance. The work was led by…
Read summary →
AI models reveal how noncoding DNA mutations shape human development and disease risk
·Pepkio Team·3 min read
Unlocking the mysteries of the genome’s noncoding regions—the vast stretches of DNA that regulate gene activity rather than building proteins—has long frustrated geneticists trying to pinpoint the causes of inherited…
Read summary →Paralyzed Man Uses Brain-Computer Interface at Home to Speak, Work, and Browse the Web for Nearly Two Years
·Pepkio Team·3 min read
A 45-year-old man with severe paralysis and severe speech impairment from amyotrophic lateral sclerosis (ALS) has used an implanted brain–computer interface (BCI) in his own home to communicate, control a computer, and…
Read summary →General-Purpose AI Models Beat Specialized Clinical Tools in Real-World Physician Test, Study Finds
·Pepkio Team·4 min read
Specialized clinical AI tools are increasingly marketed to hospitals, but a new study suggests they may not outperform widely available general-purpose AI models. Scientists report today in Nature Medicine that leading…
Read summary →