Ancestral genome reconstructions get noisier the deeper in time you go. The usual response: distrust them and joke about reading entrails. Ours is to train on the noise! The result is calibrated phenotype prediction back to the LBCA deep in the Archaean. New preprint www.biorxiv.org/content/10.6...
Models trained with noisy genomes extend bacterial phenotype prediction into deep time
Predicting phenotype from genotype in extant organisms is increasingly tractable through the accumulation of genome sequences and the development of machine-learning algorithms. Here we show that mach...
biorxiv.org
