Marc S. Halfon

EnhancerDetector: Enhancer Discovery from Human to Fly via Interpretable Deep Learning

EnhancerDetector identifies enhancers across species using interpretable deep learning, showing strong performance and generalizability with experimental validation.

Regulatory genome annotation of 33 insect species

The paper develops a workflow for annotating regulatory sequences in insect genomes and provides a database with enhancer predictions for 33 species, validated through multiple lines of evidence.

Mechanisms of transcriptional regulation in Anopheles gambiae revealed by allele specific expression

The paper identifies cis-regulated genes and cis-regulatory modules in Anopheles gambiae associated with insecticide resistance using allele-specific expression and machine learning.

EnhancerTracker: Comparing cell-type-specific enhancer activity of DNA sequence triplets via an ensemble of deep convolutional neural networks

EnhancerTracker identifies cell-type-specific enhancers using an ensemble of deep convolutional neural networks trained on FANTOM5 data, achieving 64% accuracy with three-sequence input.

Reporter gene assays and chromatin-level assays define substantially non-overlapping sets of enhancer sequences

The paper compares enhancer definitions from reporter gene assays and chromatin-level assays, finding limited overlap between the two sets.

Distinct roles and requirements for Ras pathway signaling in visceral versus somatic muscle founder specification

The paper shows that Ras pathway signaling uses different mechanisms for specifying somatic versus visceral muscle founder cells in Drosophila, highlighting distinct roles and requirements.

Enhancer identification and activity evaluation in the red flour beetle, Tribolium castaneum

The paper identifies and evaluates enhancer activity in Tribolium castaneum using chromatin profiling and a cross-species reporter assay system.