Move fast and learn things
Latest publications
An automated workflow for kit-based ELISAs
We developed a workflow to run the Cayman His-tag detection ELISA kit on the Opentrons OT-2 liquid-handling robot. We encourage others to adapt these resources for other kits.
Read now
Interpretable neural networks reveal global epistasis in yeast
We applied a mechanistic interpretability approach to neural networks trained on a large yeast genotype–phenotype dataset. This allowed us to uncover novel evidence of environmentally mediated global epistasis in these data.
Read now
Agentic PyMOL: Structural analysis in PyMOL through natural language
Agentic PyMOL is an MCP server that gives language-model agents discoverable, two-way access to a user's live PyMOL session, letting agents both manipulate molecular visualizations and read structured analytical results back out.
Read now
Raman spectroscopy may assist natural therapeutic discovery
Mining biology for therapeutically active small molecules is a promising path in drug discovery, but practical challenges make it laborious. We think that Raman spectroscopy can mitigate some of the challenges and find bioactive compounds faster.
Read now
SpectraLoRA: A graph neural network to predict simulated and experimental Raman spectra
We post-trained a molecular graph neural network for predicting Raman spectra, extending its capabilities to short-chain peptides and drug-like molecules, and implemented a method to improve its predictions for experimental spectra with a small experimental dataset.
Read now
Multi-wavelength Raman mapping of unicellular algae
We mapped live _Chlamydomonas_ cells with spontaneous Raman at 473, 532, and 785 nm. We share the analysis notebook here.
Read now