Daniel J. Diaz

Folding scFv--Antigen Complexes at Scale

The paper benchmarks structure prediction models for scFv-Ag complexes using a large-scale dataset and evaluates confidence metrics for selecting high-quality predictions.

Promera: a unified model for biomolecular structure prediction, filtering, and design

Promera is a generative model for biomolecular structure prediction, filtering, and design that improves binder filtering and controllable design compared to existing methods.

Enzyme Classification via Semi-Supervised Functional ResidueLearning

This paper introduces SLEEC, a semi-supervised framework for enzyme classification that achieves state-of-the-art performance and provides residue-level annotations.

Efficient Search of Ultra-Large Synthesis On-Demand Libraries with Chemical Language Models

This paper introduces VVS, a machine learning framework for efficiently searching ultra-large chemical libraries by decomposing molecules into building blocks and improving retrieval precision.

Generating functional and multistate proteins with a multimodal diffusion transformer

This paper introduces ProDiT, a multimodal diffusion model for generating functional proteins with multiple states, demonstrating its ability to design proteins with specific molecular functions and allosteric regulation.

Ambient Proteins: Training Diffusion Models on Low Quality Structures

Treating low-confidence AlphaFold structures as noisy data at pLDDT-dependent diffusion times lets a 16.7M-parameter model generate long proteins with higher diversity, designability and novelty than Proteína.

A systematic evaluation of the language-of-viral-escape model using multiple machine learning frameworks

The paper evaluates a language-of-viral-escape model using multiple machine learning frameworks to identify immune escape mutations in viruses.

Distilling structural representations into protein sequence models

The paper introduces ISM, a sequence-only model that improves upon ESM2 by incorporating structural information, achieving better performance on mutation stability and structure prediction tasks.

Machine learning guided rational design of a non-heme iron-based lysine dioxygenase improves its total turnover number

This paper uses machine learning and molecular dynamics to design improved variants of a non-heme iron-dependent lysine dioxygenase, achieving higher turnover numbers.

Synthetic microbial sensing and biosynthesis of amaryllidaceae alkaloids

The paper develops a biosensor-AI system to engineer E. coli for efficient production of amaryllidaceae alkaloids, achieving improved titer and reduced byproducts.

GroovDB: A database of ligand-inducible transcription factors

GroovDB is a database of ligand-inducible transcription factors that provides curated data for building chemically-responsive genetic circuits.

Learning the local landscape of protein structures with convolutional neural networks

This study uses 3D CNNs to predict wild-type amino acids and consensus sequences from local structural context, finding high-confidence predictions correlate with correct outcomes.

A structure-based deep learning framework for protein engineering

This paper introduces a 3D convolutional neural network for protein engineering that identifies gain-of-function mutations, validated by experimental improvements in protein stability.