Move fast and learn things
Latest publications
Biology needs to become prospective
Since biological data are often non-independent, more data doesn't always mean more insight. We argue that a prospective approach is needed to uncover the deepest principles of life.
Read now
Strategizing the search for bio-utility: A framework for evolution-integrated _in silico_ bioprospecting
To accurately and efficiently identify instances of useful biological variation, we must establish an evolution-integrated bioprospecting framework. This will enable us to better interpret biological datasets and direct future sampling efforts to solve societal challenges.
Read now
Coherent Raman imaging of live, unfixed _Schizosaccharomyces pombe_ and mutants _dea2_ and _pdf1_
We acquired single-cell coherent Raman microscopy data (SRS and CARS) from wild-type fission yeast and two mutants. Our aim was to collect spatially resolved biochemical data on living yeast cells. We’re sharing the data and code for others to visualize and explore it!
Read now
MSA-based pLMs encode evolutionary distance but don’t reliably exploit it
We characterize how MSA Pairformer encodes phylogenetic relationships. Sequence weights correlate with evolutionary distance, with distinct layers specializing as phylogenetic filters. Yet uniform averaging often outperforms learned weights for contact prediction.
Read now
Equivalent linear mappings of deep networks are a promising path for biology
Deep networks make accurate predictions, but their nonlinearity makes them a black box, hiding what they have learned. Here, we look inside the black box and analyze the exact relationships they learn for UMAP embeddings and epistasis in a genotype–phenotype dataset.
Read now
A quantitative-genetic decomposition of a neural network
We tested equivalent linear mapping (ELM) on a neural network trained to predict phenotypes from genotypes in simulated data. We show that ELM successfully recapitulates additive and epistatic effects learned by the model, even in data with substantial environmental noise.
Read now