Sebastian M. Castillo-Hair

Programming human cell type-specific gene expression via an atlas of AI-designed enhancers

The paper designs cell type-specific enhancers using deep learning models trained on chromatin accessibility data and validates their function across human and mouse cell types.

Iterative deep learning-design of human enhancers exploits condensed sequence grammar to achieve cell type-specificity

This study uses iterative deep learning to design human enhancers with cell type-specific activity, validated through experimental testing and perturbation experiments.

The regulatory landscape of 5' UTRs in translational control during zebrafish embryogenesis

This study uses MPRA and polysome profiling to analyze 5' UTR regulatory features in zebrafish embryos, identifying motifs and factors influencing ribosome recruitment and translation dynamics.

MicroRNA-directed control of complex mRNA stability patterns across cell types

The paper develops a model to predict mRNA stability based on microRNA expression data and applies it to design microRNA-responsive constructs with specific activity patterns across cell types.

Dissecting the regulatory logic of specification and differentiation during vertebrate embryogenesis

This study creates a single-cell multi-omics atlas of zebrafish embryogenesis and identifies transcription factors that drive cell-type-specific chromatin landscapes and instant differentiation.

Optimizing 5'UTRs for mRNA-delivered gene editing using deep learning

The paper uses deep learning to design optimized 5'UTRs for mRNA-delivered gene editing, showing improved editing efficiency across cell types and targets.

BatCRISPRi: Bacillus titratable CRISPRi for dynamic control in Bacillus subtilis

This paper introduces BatCRISPRi, a CRISPRi system in Bacillus subtilis that uses a rapamycin-dependent degron to eliminate leakiness and enable reversible gene knockdown.

Meeting Measurement Precision Requirements for Effective Engineering of Genetic Regulatory Networks

The paper derives an Engineering Error Inequality to estimate measurement precision requirements for genetic regulatory network engineering and validates these requirements using flow cytometry data.