Simone G. Riva

This paper introduces ZEN, a normalization method for genomic data that reduces technical noise while preserving biological signals, improving alignment across different experimental platforms.

CREP predicts cis-regulatory element identity from DNA sequence using a fine-tuned Enformer model trained on cell-type-specific annotations.

The paper develops a machine learning framework to assess quality of chromatin accessibility bigWig tracks using biologically relevant features and internal controls.

This paper develops a supervised framework for annotating erythroid differentiation stages in scRNA-seq using expert-curated data, achieving high accuracy across cell states and transferability to bulk RNA-seq and external datasets.

The paper uses Enformer to reconstruct phylogenetic trees across multiple species by analyzing regulatory signals from orthologous genes, showing strong correlation with known evolutionary relationships.

REgulamentary is a tool for cell-type specific annotation of cis-regulatory elements, outperforming existing methods and applied to GWAS data to prioritize causal variants.

GENESIS converts Multiome GEX data into synthetic scRNA-Seq profiles using generative models, improving cell-type classification accuracy.

REnformer predicts chromatin accessibility from single-cell ATAC-seq data, outperforming Enformer in accuracy and error rates, and validates its utility with a known thalassemia variant.

CREST-GV prioritizes disease-relevant cell types by analyzing genetic variants intersecting open chromatin regions across hundreds of cell types.

The paper shows that active enhancers recruit cohesin to form cell-specific chromatin domains, using the alpha globin cluster as a model.

This study identifies PAF1 and FACT as essential for enhancer activity in MLL-AF4-driven leukemia by maintaining histone acetylation and enhancer-promoter interactions.

SMGen generates synthetic biochemical reaction network models for benchmarking, showing it can create models with 512 species and reactions in under 7 seconds.

SMaSH identifies marker genes from single-cell RNA sequencing data to improve spatial transcriptomics analysis.