Publications
Work from 2019 onward. Earlier work is on Google Scholar.
2026
-
AlphaFold Database expands to proteome-scale quaternary structures
bioRxiv preprint, 2026 · under review · NVIDIA + Duke
31 million candidate complexes across 4,777 proteomes; 1.81 million high-confidence predictions released. Chris is corresponding author.
-
FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications
ICML 2026 · Oral · NVIDIA + Duke
Seven new datasets and splits that mirror real engineering campaigns. Simpler models often matched or beat fine-tuned protein language models.
-
Scaling Atomistic Protein Binder Design with Generative Pretraining and Test-Time Compute
ICLR 2026 · Oral · NVIDIA
Proteina-Complexa. One fully atomistic model that unifies conditional generation and hallucination, and keeps improving with test-time compute.
2025
-
GPU-accelerated homology search with MMseqs2
Nature Methods 22(10):2024–2027, 2025 · NVIDIA
Roughly 100 trillion cell updates per second, and it still runs on low-wattage GPUs.
-
Nucleotide Transformer: building and evaluating robust foundation models for human genomics
Nature Methods 22(2):287–297, 2025 · NVIDIA
-
Machine Learning for Protein Science and Engineering
Cold Spring Harbor Perspectives in Biology, a041877, 2025 · review
Chris co-edited the Cold Spring Harbor volume this appears in.
-
Consistent Synthetic Sequences Unlock Structural Diversity in Fully Atomistic De Novo Protein Design
arXiv preprint, 2025 · NVIDIA
Better training data, not a bigger model: +54% structural diversity and +27% co-designability for La-Proteina.
-
La-Proteina: Atomistic Protein Generation via Partially Latent Flow Matching
arXiv preprint, 2025 · NVIDIA
Co-designable proteins up to 800 residues, a length at which most baselines stop producing valid samples.
-
Proteina: Scaling Flow-based Protein Structure Generative Models
ICLR 2025 · Oral · NVIDIA
2023
-
GenSLMs: Genome-scale language models reveal SARS-CoV-2 evolutionary dynamics
International Journal of High Performance Computing Applications 37(6):683–705, 2023
ACM Gordon Bell Special Prize for COVID-19 Research, 2022.
-
Novel machine learning approaches revolutionize protein knowledge
Trends in Biochemical Sciences 48(4):345–359, 2023 · review
-
Illuminating enzyme design using deep learning
Nature Chemistry 15:749–750, 2023 · News & Views
-
From sequence to function through structure: Deep learning for protein design
Computational and Structural Biotechnology Journal 21:238–250, 2023 · senior author
2022
-
ProtTrans: Toward Understanding the Language of Life Through Self-Supervised Learning
IEEE Transactions on Pattern Analysis and Machine Intelligence 44(10):7112–7127, 2022
-
3D Infomax improves GNNs for molecular property prediction
ICML 2022, PMLR 162:20479–20502
-
ProteomicsDB: toward a FAIR open-source resource for life-science research
Nucleic Acids Research 50(D1):D1541–D1552, 2022
2021
-
FLIP: Benchmark tasks in fitness landscape inference for proteins
NeurIPS 2021 Datasets & Benchmarks · first author
-
Learned embeddings from deep learning to visualize and predict protein sets
Current Protocols 1(5):e113, 2021 · first author
bio_embeddings — the framework, still the lab's most-used open-source artifact.
-
PredictProtein — Predicting Protein Structure and Function for 29 Years
Nucleic Acids Research 49(W1):W535–W540, 2021
-
Light attention predicts protein location from the language of life
Bioinformatics Advances 1(1):vbab035, 2021
-
Embeddings from protein language models predict conservation and variant effects
Human Genetics 141(10):1629–1647, 2021
-
Protein embeddings and deep learning predict binding residues for various ligand classes
Scientific Reports 11:23916, 2021
-
Embeddings from deep learning transfer GO annotations beyond homology
Scientific Reports 11:1160, 2021
2019–2020
-
Pathway Commons 2019 Update: integration, analysis and exploration of pathway data
Nucleic Acids Research 48(D1):D489–D497, 2020
-
Modeling aspects of the language of life through transfer-learning protein sequences
BMC Bioinformatics 20:723, 2019
SeqVec — one of the first large-scale protein language models.
-
The EVcouplings Python framework for coevolutionary sequence analysis
Bioinformatics 35(9):1582–1584, 2019
Earlier work, and anything not listed here, is on Google Scholar.