Jahir M. Gutierrez

This paper introduces REPRESS, a deep learning model that predicts cell-type-specific microRNA binding and mRNA degradation from RNA sequences, outperforming existing methods in multiple tasks.

The paper develops deep learning models trained on synonymous variant datasets to predict and optimize protein expression in E. coli.

The paper develops a hyperbolic graph neural network for drug repurposing in leishmaniasis, identifying two drugs that target proteins involved in parasite survival.

Deep generative models combined with high-throughput screening design de novo anti-HER2 antibodies without further optimization, yielding nanomolar binders functionally comparable or superior to trastuzumab.

Language models trained on high-throughput affinity data predict KD of unseen antibody variants across three orders of magnitude, and a "naturalness" score can be optimised alongside affinity.

The paper develops a deep learning pipeline for drug re-purposing in Leishmaniasis, combining it with molecular docking to select top candidates based on molecular descriptor similarity.

The paper introduces a framework to predict how changes in omics data affect metabolic functions in mammalian cells using curated metabolic tasks and genome-scale networks.

The paper analyzes the global spread and structural impact of the D614G mutation in the SARS-CoV-2 spike protein, finding it predominant in Europe and neutral in function regarding ACE2 receptor binding.

The paper maps and characterizes the human secretome by annotating 2,623 predicted secreted proteins and their spatial distribution, using a high-throughput cell factory for recombinant protein production and analysis.