Gregory J. Fonseca

The paper improves sequence-to-expression models by incorporating chromatin accessibility, showing better performance in predicting gene expression and cell type-specific patterns.

AmalgaMo merges similar DNA motifs to improve regression-based motif enrichment analysis using human datasets.

The paper introduces a machine-learning pipeline, CellCartographer, to design TF pooled-screens for cell type conversion using chromatin accessibility data, achieving efficient differentiation of iPSCs into six cell types within 6 days.

DTractor improves cell-type deconvolution in spatial transcriptomics by integrating deep learning, transfer learning, and matrix factorization to better estimate cell-type proportions and gene expression with spatial coherence.

scSemiProfiler infers single-cell profiles from bulk data using deep generative models and active learning, validated across datasets to match true single-cell data.

The paper uses in vitro evolution in haploid human cells to identify drug resistance mechanisms and validates them through gene expression experiments.

This study shows that DOT1L regulates specific gene networks in cardiac development and cell cycle withdrawal through H3K79me2 modifications.

The paper systematically analyzes naturally occurring insertions and deletions (InDels) to assess their impact on transcription factor spacing and identifies tolerant and sensitive TF pairs.

The paper identifies non-redundant DNA binding activities of AP-1 family members in macrophages using ChIP-sequencing and machine learning, showing motif ensembles drive factor-specific binding.