Oriol Fornés

The paper benchmarks methods for inferring transcription factor binding specificities using a large community challenge and finds deep learning models outperform traditional methods, though positional weight matrices are competitive.

This study identifies DNA binding motifs for 98 human transcription factors using meSMiLE-seq, revealing methylation-sensitive binding preferences for some TFs.

The paper uses GHT-SELEX to show many human TFs have high intrinsic sequence specificity and complex DNA binding, often matching in vivo ChIP-seq results.

The paper designs Müller glia-specific cis-regulatory elements using deep learning and validates their function in vivo.

ModCRElib is a package for modeling cis-regulatory elements, offering tools for TF-DNA interaction analysis, binding motif prediction, and regulatory complex modeling.

The paper evaluates cross-platform DNA motif discovery tools using 4,237 experiments to identify reliable transcription factor binding motifs and highlights challenges in motif detection.

The paper systematically determines the sequence specificity of 332 poorly characterized human transcription factors, identifying over 4,000 experiments and revealing tens of thousands of new TF binding sites.

ExplaiNN provides interpretable deep learning models for genomics tasks, achieving comparable performance to state-of-the-art methods while offering transparent predictions.

The paper identifies small molecules that enhance stem cell differentiation into definitive endoderm, reducing costs by 90% through a drug repurposing approach.

This study identifies heterozygous gain-of-function STAT6 variants in two patients with severe allergic disease and shows JAK inhibitors reduce the enhanced STAT6 responses.

The paper introduces a structure-based learning approach to predict TF binding preferences and model TF regulatory complexes, demonstrating its effectiveness over existing methods in cases of remote homology.

The paper curates a comprehensive catalogue of human DNA-binding transcription factors using Gene Ontology definitions and provides access to it via an online resource.

This study shows that transfer learning improves transcription factor binding prediction by pre-training with biologically relevant TFs and fine-tuning single-task models.

RADI improves the computational efficiency of direct-coupling analysis by reducing the alphabet size, achieving faster execution with comparable or better accuracy than traditional methods.

The paper examines X-chromosome inactivation across 12 species, finding mouse as an outlier with fewer escape genes and highlighting domain-level control and gene-based influences on inactivation.

GeneBreaker simulates rare genetic disease cases to benchmark variant calling and prioritization tools, aiding in the diagnosis of Mendelian disorders.

This study identifies a 4bp non-coding deletion in the FOXG1 locus at 14q12 as a candidate for isolated strabismus, showing its potential role in regulating FOXG1 expression.

The paper develops a computational method to predict DNA-binding preferences of C2H2-ZF domains using structural models and applies it to predict CTCF's binding sites.

The paper introduces TF2Exp, a framework predicting gene expression impact from cis-regulatory variants by modeling altered transcription factor binding, showing comparable performance to SNP-based models.