Vaitea Opuu

This paper introduces Leff, a spectral measure to quantify effective information in multiple sequence alignments, showing evolutionary constraints reduce sequence diversity in RNA and proteins.

DORA predicts dose-dependent changes in transcriptomes and cell viability using a deep learning autoencoder, outperforming existing methods in viability prediction.

The paper uses probabilistic generative models to estimate the number of self-reproducing RNAs and finds that at least 10^39 such ribozymes may exist.

This paper explores active learning strategies for synergistic drug discovery, finding that environmental features improve predictions and that small batch sizes with dynamic strategies can identify 60% of synergistic pairs from 10% of the combinatorial space.

The paper introduces a hybrid generative model for RNA design that combines coevolutionary likelihood with secondary structure priors to expand functional sequence diversity.

This paper introduces D-LIM, an interpretable neural network for genotype-to-fitness mapping, achieving state-of-the-art accuracy in predicting gene and gene-environment interactions in mutational scanning data.

The paper shows global regulators enable adaptation to a growth-motility trade-off in E. coli by modulating both phenotypes, while local regulators mainly affect motility.

This paper introduces CARNAGE, a graph neural network that embeds RNA structure into sequence-like representations, enabling structural-aware sequence analysis without explicit alignment.

RAFFT predicts RNA folding pathways using a heuristic combining a folding algorithm and kinetic ansatz, efficiently generating near-native structures for RNA sequences up to 200 nucleotides.