Scholars@Duke
Philip A Romero

Philip A Romero

Associate Professor of Biomedical Engineering
Biomedical Engineering

Scholarly Works

Benchmarking and behavioral characterization of LLM agents for protein design.

Preprint · May 8, 2026 Large language models (LLMs) are increasingly deployed as agents for scientific discovery, but standardized frame-works for evaluating their performance and behaviour in scientific workflows are lacking. Protein design provides a demanding test case becaus ... Full text Link to item Cite

Scalable and cost-efficient custom gene library assembly from oligopools.

Journal article Science advances · May 2026 Advances in metagenomics, deep learning, and generative protein design have enabled broad in silico exploration of sequence space, but experimental characterization is still constrained by the cost and scalability of DNA synthesis. Here, we present OMEGA ( ... Full text Cite

Explicit representation of germline and non-germline residues improves antibody language modeling

Preprint · 2026 Antibodies originate from germline templates and are diversified by somatic hypermutation, producing sequences in which conserved germline residues scaffold structure while rare non-germline (NGL) substitutions refine antigen binding. Current antibody lang ... Full text Cite

Machine learning-guided olivetolic acid cyclase engineering enables tailored cannabinoid biosynthesis in yeast

Preprint · 2026 Cannabinoids comprise a diverse class of bioactive natural products with important therapeutic potential, but efficient microbial production remains limited by pathway bottlenecks and challenges in engineering key biosynthetic enzymes. Here, we develop a m ... Full text Cite

Biophysics-based protein language models for protein engineering.

Journal article Nature methods · September 2025 Protein language models trained on evolutionary data have emerged as powerful tools for predictive problems involving protein sequence, structure and function. However, these models overlook decades of research into biophysical factors governing protein fu ... Full text Cite

Droplet microfluidic screening to engineer angiotensin-converting enzyme 2 (ACE2) catalytic activity.

Journal article Journal of biological engineering · February 2025 BackgroundAngiotensin-Converting Enzyme 2 (ACE2) is a crucial peptidase in human peptide hormone signaling, catalyzing the conversion of Angiotensin-II to Angiotensin-(1-7), which activates the Mas receptor and elicits vasodilation, increased bloo ... Full text Cite

Scalable and cost-efficient custom gene library assembly from oligopools

Preprint · 2025 Advances in metagenomics, deep learning, and generative protein design have enabled broad in silico exploration of sequence space, but experimental characterization is still constrained by the cost and scalability of DNA synthesis. Here, we present OMEGA ( ... Full text Cite

Functional alignment of protein language models via reinforcement learning

Preprint · 2025 Protein language models (pLMs) enable generative design of novel protein sequences but remain fundamentally misaligned with protein engineering goals, as they lack explicit understanding of function and often fail to improve properties beyond those found i ... Full text Cite

Neural network extrapolation to distant regions of the protein fitness landscape.

Journal article Nature communications · July 2024 Machine learning (ML) has transformed protein engineering by constructing models of the underlying sequence-function landscape to accelerate the discovery of new biomolecules. ML-guided protein design requires models, trained on local sequence-function inf ... Full text Cite

Self-driving laboratories to autonomously navigate the protein fitness landscape.

Journal article Nature chemical engineering · January 2024 Protein engineering has nearly limitless applications across chemistry, energy and medicine, but creating new proteins with improved or novel functions remains slow, labor-intensive and inefficient. Here we present the Self-driving Autonomous Machines for ... Full text Cite

Inferring protein fitness landscapes from laboratory evolution experiments.

Journal article PLoS computational biology · March 2023 Directed laboratory evolution applies iterative rounds of mutation and selection to explore the protein fitness landscape and provides rich information regarding the underlying relationships between protein sequence, structure, and function. Laboratory evo ... Full text Cite

Competitive SNP-LAMP probes for rapid and robust single-nucleotide polymorphism detection.

Journal article Cell reports methods · July 2022 In this work, we developed a simple and robust assay to rapidly detect SNPs in nucleic acid samples. Our approach combines loop-mediated isothermal amplification (LAMP)-based target amplification with fluorescent probes to detect SNPs with high specificity ... Full text Cite

Yeast surface display-based identification of ACE2 mutations that modulate SARS-CoV-2 spike binding across multiple mammalian species.

Journal article Protein engineering, design & selection : PEDS · February 2022 Understanding how severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) interacts with different mammalian angiotensin-converting enzyme II (ACE2) cell entry receptors elucidates determinants of virus transmission and facilitates development of vacc ... Full text Cite

Microfluidic deep mutational scanning of the human executioner caspases reveals differences in structure and regulation.

Journal article Cell death discovery · January 2022 The human caspase family comprises 12 cysteine proteases that are centrally involved in cell death and inflammation responses. The members of this family have conserved sequences and structures, highly similar enzymatic activities and substrate preferences ... Full text Cite

Neural networks to learn protein sequence-function relationships from deep mutational scanning data.

Journal article Proceedings of the National Academy of Sciences of the United States of America · November 2021 The mapping from protein sequence to function is highly complex, making it challenging to predict how sequence changes will affect a protein's behavior and properties. We present a supervised deep learning framework to learn the sequence-function mapping f ... Full text Cite

Single-cell nucleic acid profiling in droplets (SNAPD) enables high-throughput analysis of heterogeneous cell populations.

Journal article Nucleic acids research · October 2021 Experimental methods that capture the individual properties of single cells are revealing the key role of cell-to-cell variability in countless biological processes. These single-cell methods are becoming increasingly important across the life sciences in ... Full text Cite

Machine learning-guided acyl-ACP reductase engineering for improved in vivo fatty alcohol production.

Journal article Nature communications · October 2021 Alcohol-forming fatty acyl reductases (FARs) catalyze the reduction of thioesters to alcohols and are key enzymes for microbial production of fatty alcohols. Many metabolic engineering strategies utilize FARs to produce fatty alcohols from intracellular ac ... Full text Cite

Active and machine learning-based approaches to rapidly enhance microbial chemical production.

Journal article Metabolic engineering · September 2021 In order to make renewable fuels and chemicals from microbes, new methods are required to engineer microbes more intelligently. Computational approaches, to engineer strains for enhanced chemical production typically rely on detailed mechanistic models (e. ... Full text Cite

Discovery of human ACE2 variants with altered recognition by the SARS-CoV-2 spike protein.

Journal article PloS one · January 2021 Understanding how human ACE2 genetic variants differ in their recognition by SARS-CoV-2 can facilitate the leveraging of ACE2 as an axis for treating and preventing COVID-19. In this work, we experimentally interrogate thousands of ACE2 mutants to identify ... Full text Cite