Luca Pinello

FlowMap jointly models cellular states and dynamics in a geometric framework, recovering interpretable trajectories and developmental patterns from single-cell RNA sequencing data.

This paper uses prime editing to classify LDLR variants by measuring their impact on LDL-C uptake, reclassifying many previously unclassified variants.

CRISPR-HAWK identifies genetic variants affecting CRISPR guide performance across diverse populations, revealing that 82.5% of therapeutic guides are impacted by variants.

The paper maps chemokine landscapes in solid tumors using spatial transcriptomics, identifying conserved and tumor-specific patterns and revealing perivascular CCR7 dendritic cells as key sources of lymphocyte-attracting chemokines.

The paper introduces UKBioBERT, a DNA language model pre-trained on UK BioBank variants, which improves gene expression prediction and enables eQTL identification when combined with sequence-to-function models.

CRISPRLungo is a computational pipeline for analyzing long-read CRISPR experiments, improving accuracy in detecting structural variants and small indels through UMI-based error correction and benchmarking.

Spacelink integrates spatial transcriptomics with genetics to identify spatially variable genes linked to disease, showing improved detection power and disease informativeness.

GAME provides a standardized framework for benchmarking genomics models across tasks, enabling consistent evaluation and community contributions.

This paper introduces a method for targeted genomic integration and rearrangement in human cells using CRISPR-targeted dual flap synthesis, enabling DNA sequence assembly without requiring double-stranded DNA donors or cell cycle progression.

The paper maps spatially-resolved transcriptomes in systemic sclerosis to identify a fibrotic niche and disease-specific cell states, linking them to clinical outcomes.

The paper introduces ACCESS-ATAC, a method that improves TF binding site prediction resolution and reveals allele-specific co-occupancy patterns in HepG2 and K562 cells.

This study shows that gene editing of HSCs without ex vivo culture reduces genotoxicity while maintaining therapeutic efficacy for beta-hemoglobinopathy treatment.

This paper introduces a statistical RNA velocity model that improves dynamical consistency and inference of cell cycle speed from scRNA-seq data.

CRISPR-CLEAR maps regulatory elements at nucleotide resolution by directly assessing genotype-phenotype effects through targeted sequencing of CRISPR-introduced alleles.

EPInformer predicts gene expression by integrating promoter-enhancer sequences, epigenomic signals, and chromatin contacts, outperforming existing models in cross-chromosome validation and CRISPR experiments.

The paper develops ABSOLVE-seq to assess genome editing off-targets linked to genetic variants using primary cells and sequencing, enabling evaluation of human genetic diversity's impact on gene editing specificity.

The paper introduces PERSIST-On, a CRISPR-based method for stable and tunable gene activation by recruiting endogenous transcription factors to target promoters.

MOSAIC enables high-throughput in situ saturation mutagenesis and CRISPR prime editing guide RNA optimization in human cells, identifying optimized pegRNAs and drug resistance variants.

This paper improves variant effect quantification in base editing screens by integrating genotypic and phenotypic data using a Bayesian network called BEAN.

DNA-Diffusion uses diffusion models to generate cell type-specific regulatory DNA sequences that modulate chromatin accessibility and gene expression.

scDiffEq models single-cell dynamics using neural stochastic differential equations, improving trajectory reconstruction and fate prediction in hematopoiesis.

This study benchmarks 14 computational methods for identifying spatially variable genes and peaks using simulated and real-world spatial transcriptomics and ATAC-seq data, finding spatialDE2 performs best and highlighting the need for specialized algorithms for peaks.

Dictys infers dynamic gene regulatory networks from single-cell multi-omics data, revealing context-specific and developmental GRNs in human blood and mouse skin.

SIMBA is a graph embedding method that jointly embeds single cells and their features into a common space, enabling diverse single-cell analysis tasks.

The paper identifies critical base-resolution regulatory elements in immune gene expression using base editing and deep learning.

The paper develops CRISPRme, a tool that integrates genetic diversity data to assess off-target risks of gene editing, finding allele-specific off-target effects in clinical gRNAs.

Pyro-Velocity improves RNA velocity inference by modeling raw sequencing counts with synchronized cell time across genes to better estimate cell fate and trajectory dynamics.

GRAFIMO scans transcription factor binding sites in pangenome variation graphs, identifying variant-specific binding events that are missed or altered in reference genomes.

ONE-seq identifies population-specific off-target effects of CRISPR gene editors using global human genome sequence diversity.

PrimeDesign is a tool for designing prime editing guide RNAs, enabling single and combination edits, and it supports the creation of a database for over 68,500 pathogenic variants.