2026-10-11T18:09:17Z https://api.figshare.com/v2/oai

oai:figshare.com:article/33957974 2026-09-21T17:50:49Z category_1 category_4 category_915 category_873 category_734 category_931 category_64 category_132 category_135 portal_5 item_type_3 month_year_09_2026

<p>Comparison of AlloPool and NRI performance in trajectory reconstruction.</p> Matthieu Marfoglia (25084871) Miguel A. Pedraza-Joya (25084874) Lucas Guirardel (25084877) Aisima Chatzi Souleiman (25084880) Patrick Barth (423061) Biophysics Biochemistry Physical Sciences not elsewhere classified Chemical Sciences not elsewhere classified Biological Sciences not elsewhere classified Information Systems not elsewhere classified Cancer Infectious Diseases Computational Biology resolution experimental data remains challenging due many biological processes integrating temporal attention energetic property prediction enabling accurate reconstruction including binding domains graph neural network interpreting protein dynamics resolved interaction networks outperforms existing machine dynamic trajectory reconstruction drive conformational transitions deep learning framework infers protein allostery interaction networks conformational dynamics protein function ligand binding graph aggregation general framework dynamic transitions learning models learning approaches uncover minimal synthetic biology structural responses static structures signaling receptors residue interactions mechanical perturbations mechanical forces dynamic trajectories drug discovery collectively known broad implications artificial intelligence allow proteins advance provides <p>Comparison of AlloPool and NRI performance in trajectory reconstruction.</p> 2026-09-21T17:50:12Z Dataset Dataset 10.1371/journal.pbio.3004002.t001 https://figshare.com/articles/dataset/_p_Comparison_of_AlloPool_and_NRI_performance_in_trajectory_reconstruction_p_/33957974 CC BY 4.0