Using sequence-determined functional genomic features instead of original genotypes can partially overcome challenges in genetic association studies, such as rare variant exclusion and population structure.
Integration of language model and geometric deep learning enables accurate and efficient genome-scale annotation of comprehensive protein-ligand binding sites.
Thomas Grandits, Christoph M Augustin ... Alexander Jung
Neural networks can emulate normal and abnormal human ventricular action potentials accurately and potentially much faster than regular simulations paving the way for more efficient quantitative systems pharmacology studies.
Domingos Leite de Castro, Miguel Aroso ... Paulo Aguiar
Adaptive delayed feedback control is presented as a new real-time, closed-loop control algorithm for neurostimulation which can disrupt oscillations and reduce network synchrony in neuronal populations.
Acute myeloid leukemia-specific predictive logic models reveal new therapeutic targets involved in cancer resistance mechanisms paving the way for personalized precision medicine.
Integrating multiple protein language models using protein geometric graphs can dramatically improve the model performance for predicting the contacting residue pairs between interacting proteins.
Arthur L Schneider, Rita Martins-Silva ... Nuno L Barbosa-Morais
voyAGEr is an online platform that facilitates the exploration of age-related gene expression dynamics in human tissues, allowing users to analyse tissue- and sex-specific changes alongside donor medical histories.
Alain Pulfer, Diego Ulisse Pizzagalli ... Santiago Fernandez Gonzalez
ADeS, a novel deep learning approach for apoptosis detection, achieves 98% accuracy in vitro and in vivo while providing unprecedented insights into the spatial–temporal foundation of cell death.
