Marco Salvatore

The paper introduces nucCAGE and PRIME to identify active cis-regulatory elements with high sensitivity and applies them to create a cell-type-resolved CRE atlas.

This paper introduces an approach combining LLM and explainable ML to identify disease-related gene signatures across scRNA-seq datasets, showing improved generalization and interpretability.

RBPNet predicts CLIP crosslink count distributions from RNA sequences, outperforming existing methods and enabling variant impact scoring.

The paper examines how promoter sequence and transcription start site architecture influence expression variability and genetic variant effects in human genes.

This paper applies symbolic regression to clinical omics data to identify interpretable biomarker signatures that predict disease outcomes and reveal disease mechanisms.

This paper introduces ChromTransfer, a transfer learning method that improves cell-type specific chromatin accessibility prediction from DNA sequences using pre-trained models.

The paper characterizes transposon-derived regulatory elements in mouse embryonic stem cells, showing their role in gene regulation and pluripotency programs.

The paper evaluates 43 methods for predicting intrinsically disordered regions and binding regions in proteins, finding that deep learning methods outperform older physicochemical approaches but binding prediction remains challenging.

The paper introduces TargetP 2.0, a deep learning method to identify N-terminal sorting signals in proteins, revealing insights into the importance of the second residue in targeting peptides.

The paper investigates why eukaryotic proteins have more intrinsically disordered regions by comparing linker regions between eukaryotic and prokaryotic proteomes.

The paper improves orphan gene classification by combining proteome and genome searches, identifying fewer orphans in Drosophila species than previous studies.