Philip A Romero

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

AlphaFast: High-throughput AlphaFold 3 via GPU-accelerated MSA construction.

Preprint · February 18, 2026 Full text Link to item 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

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

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

Preprint · March 17, 2021 Full text Cite

Philip A Romero

Scholarly Works - Preprints

Benchmarking and behavioral characterization of LLM agents for protein design.

AlphaFast: High-throughput AlphaFold 3 via GPU-accelerated MSA construction.

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

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

Scalable and cost-efficient custom gene library assembly from oligopools

Functional alignment of protein language models via reinforcement learning

Engineered lysins to modulate human gut microbiome communities

Biophysics-based protein language models for protein engineering

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

Self-driving laboratories to autonomously navigate the protein fitness landscape

Neural network extrapolation to distant regions of the protein fitness landscape

Directed evolution of angiotensin-converting enzyme 2 (ACE2) peptidase activity profiles for therapeutic applications

Inferring protein fitness landscapes from laboratory evolution experiments

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

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

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

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

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

Investigating the dynamics of microbial consortia in spatially structured environments

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

Inferring protein sequence-function relationships with large-scale positive-unlabeled learning

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