David Nelson
Senior Research Scientist
Affiliation: NYU Abu Dhabi
Education: BA Colorado College; PhD University of Minnesota
Research Websites: Center for Genomics and Systems Biology
Research Areas: Biology, Computer Science, Genomics, Multi-omics, AI, Protein Language Models, World Models, Global Primary Productivity, Photosynthesis, Microalgae
David Nelson develops AI models for biological sequence analysis and generates large-scale genomic resources to address evolutionary and systems-level questions. Recent work includes interpretable deep learning for protein function prediction (Patterns, 2025), a telomere-to-telomere gorilla genome (Scientific Data, 2025), comparative macroalgal genomics (Molecular Plant, 2024), and viral drivers of microalgal evolution (Cell Host & Microbe, 2021).
Summary of Research
The Laboratory of Algal, Artificial Intelligence, Synthetic, and Systems Biology integrates multi-omics, computational genomics, and generative artificial intelligence to extract biological insight from large-scale sequence and functional data. The lab develops AI-based and foundation language models tailored for biological sequences, enabling scalable inference interpretation and design across genomic and functional landscapes (Patterns, 2025). Research includes the generation of foundational genomic resources supporting integrative analysis — from assembling telomere-to-telomere reference genomes (Scientific Data, 2025) to comparative datasets resolving evolutionary transitions such as the origins of photosynthetic multicellularity (Molecular Plant, 2024) and viral drivers of microalgal genome evolution (Cell Host & Microbe, 2021).
Current directions extend AI approaches to interactomics for predicting protein-protein interactions and regulatory networks, quantum computing applications for molecular simulation and combinatorial sequence design, and robotic automation platforms enabling closed-loop integration between computational prediction and experimental validation. Across systems — particularly algal and microbial — the lab emphasizes interpretability, data integration, and the linkage of large sequence repositories to evolutionary, ecological, and systems-level biological questions.