Carlos Óscar S. Sorzano

Astex-Faro improves cryo-EM hit identification by detecting structural deviations and enhancing weak features across diverse datasets.

This paper presents a pipeline for multi-epitope vaccine design that integrates multiple tools to predict B-cell epitopes and validates them against structural data.

ReconSIREN is a deep learning framework that improves CryoEM map accuracy by addressing preferred orientation errors in heterogeneous samples.

The paper introduces FlexConsensus, an algorithm that merges conformational landscapes from different CryoEM heterogeneity methods into a shared consensus space to improve reliability and reproducibility.

The paper investigates using p-values to estimate the number of distinguishable classes in cryoEM data by testing if classifications differ from random partitions.

The paper presents a cryo-EM conformational heterogeneity challenge to evaluate and improve methods for analyzing molecular motions in heterogeneous samples.

HetSIREN is a deep learning method for CryoEM conformational state reconstruction and refinement, improving structural accuracy by decoupling pose and CTF information from conformational landscapes.

This paper introduces HaPi, a method to automatically determine the handedness of CryoEM maps, achieving 89% accuracy on simulated data and identifying 11 incorrectly handed structures in a database.

The paper investigates the structural and functional impact of the S:A222V mutation in SARS-CoV-2, showing increased RBD opening and ACE2 binding without reducing neutralization capacity.

This study identifies DIDO3 binding at active chromatin and topological boundaries in mouse stem cells, linking it to chromatin organization and transcriptional regulation.

DeepEMhancer improves cryo-EM map quality using deep learning, achieving cleaner and more detailed maps on test cases like SARS-CoV-2 RNA polymerase.

NAP-CNB is a web server tool that predicts MHC-I-restricted T cell epitopes in mice using recurrent neural networks, achieving an AUC of 0.95 for H-2 peptide ligands.

MicrographCleaner uses deep learning to improve cryo-EM micrograph preprocessing by identifying suitable regions for particle picking.

The paper improves a marker-free image alignment method for electron tomography to enhance 3D reconstruction quality by addressing deformations during acquisition.

This work introduces a soft-alignment validation method to assess alignment precision, accuracy, and data homogeneity in cryo-EM single particle analysis, improving map resolution through data quality enhancement.