✳flâneur — a map of the web's best reading

Publications — Debbie Marks Lab

deboramarkslab.com · 23,736 words · saved by 1 readers

Applying machine learning to biological sequences---DNA, RNA and protein---has enormous potential to advance human health and environmental sustainability. To support such high-stakes applications, it is important to develop models and evaluations that not only capture underlying biology, but also have theoretical guarantees of reliability and performance. In this article, we analyze kernel methods for biological sequences, including both hand-crafted kernels and deep neural network-based kernels. We show that popular biological kernels can severely fail at learning functions or distinguishing distributions. We then develop modified kernels that (1) are universal, characteristic, and metrize the space of distributions, and (2) preserve the underlying biological inductive biases and domain knowledge embedded in the original kernel. Our results rest on novel proof techniques for kernels that handle the structure of biological sequence space--discrete, variable length sequences--and biolo

Publications - Debbie Marks Lab Top Back Debora S Marks Members Alumni Collaborators Debbie's Google Scholar Page 2026 Unified sampling framework and experimental benchmarking of sequence- and structure-based protein models Aviv Spinner, Pascal Notin, Samuel Berry, Dana Cortade, Zach Sisson, Svetlana Ikonomova, David Ross, Debora Marks biorxiv; 12 May 2026 Abstract Generative models are increasingly used for protein design, but the lack of standardized evaluation frameworks limits comparison across model classes and hinders translation to experimental success. Here, we introduce a unified samp

Explore this link on the map →

related reading