Heather H. Sestili

An Epigenetic Signature of Vulnerable Neurons is Under Selective Pressure Associated with Longevity Across Placental Mammals.

The paper identifies cell-type-specific epigenetic signatures linked to neuronal vulnerability and longevity across placental mammals using epigenomics and AI.

Challenges in predicting chromatin accessibility differences between species

This study trains CNNs to predict chromatin accessibility across species but finds poor performance in predicting quantitative differences between species.

Context-dependent regulatory variants in Alzheimer's disease

The paper identifies context-dependent regulatory variants in Alzheimer's disease by analyzing their effects across different cellular contexts using MPRAs and machine learning.

Combining Machine Learning and Multiplexed, In Situ Profiling to Engineer Cell Type and Behavioral Specificity

The paper develops a platform combining machine learning and multiplexed in situ screening to identify enhancers with cell-type and behavioral specificity for neural circuit engineering.

RERconverge Expansion: Using Relative Evolutionary Rates to Study Complex Categorical Trait Evolution

The paper expands RERconverge to analyze multi-categorical traits by introducing methods for ancestral state reconstruction, statistical tests, and phylogenetic permutations, showing improved performance in identifying diet-related genes and pathways.

Regression convolutional neural network models implicate peripheral immune regulatory variants in the predisposition to Alzheimer's disease

The paper uses CNN regression models to predict the impact of AD-associated variants on open chromatin in different cell types, finding greater effects in peripheral cells than in microglia or neurons.

Relating enhancer genetic variation across mammals to complex phenotypes using machine learning

A machine learning approach identifies enhancer-phenotype associations across mammals, revealing links to brain size and behavior evolution.