Dr Phil Romero, Ph.D.

Research Interests

Protein engineering, computational biology, technology development

Education

• Ph.D. California Institute of Technology, 2012

Positions

• Associate Professor of Biomedical Engineering

Courses Taught

• BME 590: Special Topics in Biomedical Engineering
• BME 493: Projects in Biomedical Engineering (GE)

Publications

• Blalock N, Seshadri S, Babbar A, Fahlberg SA, Kulkarni A, Romero PA. Functional alignment of protein language models via reinforcement learning. Cold Spring Harbor Laboratory. 2025.
• Freschlin CR, Yang KK, Romero PA. Scalable and cost-efficient custom gene library assembly from oligopools. Cold Spring Harbor Laboratory. 2025.
• Okal EF, Romero PA, Heinzelman P. Droplet microfluidic screening to engineer angiotensin-converting enzyme 2 (ACE2) catalytic activity. Journal of biological engineering. 2025 Feb;19(1):12.
• Okal EF, Romero PA, Heinzelman P. Droplet microfluidic screening to engineer angiotensin-converting enzyme 2 (ACE2) catalytic activity. Cold Spring Harbor Laboratory. 2024.
• Freschlin CR, Fahlberg SA, Heinzelman P, Romero PA. Neural network extrapolation to distant regions of the protein fitness landscape. Nature communications. 2024 Jul;15(1):6405.
• Gelman S, Johnson B, Freschlin C, Sharma A, Du2019Costa S, Peters J, et al. Biophysics-based protein language models for protein engineering. bioRxiv. 2024.
• Rodriguez JD, Lu W, Papadopoulos J, Venturelli O, Romero P. Engineered lysins to modulate human gut microbiome communities. bioRxiv. 2024.
• Rapp JT, Bremer BJ, Romero PA. Self-driving laboratories to autonomously navigate the protein fitness landscape. Nature chemical engineering. 2024 Jan;1(1):97u2013107.
• Du2019Costa S, Hinds EC, Freschlin CR, Song H, Romero PA. Inferring protein fitness landscapes from laboratory evolution experiments. PLoS computational biology. 2023 Mar;19(3):e1010956.
• Fahlberg S, Freschlin C, Heinzelman P, Romero P. Neural network extrapolation to distant regions of the protein fitness landscape. bioRxiv. 2023.
• Rapp J, Bremer B, Romero P. Self-driving laboratories to autonomously navigate the protein fitness landscape. bioRxiv. 2023.
• Hyman LB, Christopher CR, Romero PA. Competitive SNP-LAMP probes for rapid and robust single-nucleotide polymorphism detection. Cell reports methods. 2022 Jul;2(7):100242.
• Heinzelman P, Greenhalgh JC, Romero PA. Yeast surface display-based identification of ACE2 mutations that modulate SARS-CoV-2 spike binding across multiple mammalian species. Protein engineering, design & selectionu202f: PEDS. 2022 Feb;35:gzab035.
• Heinzelman P, Romero P. Directed evolution of angiotensin-converting enzyme 2 (ACE2) peptidase activity profiles for therapeutic applications. bioRxiv. 2022.
• Du2019Costa S, Hinds E, Freschlin C, Song H, Romero P. Inferring protein fitness landscapes from laboratory evolution experiments. bioRxiv. 2022.
• Roychowdhury H, Romero PA. Microfluidic deep mutational scanning of the human executioner caspases reveals differences in structure and regulation. Cell death discovery. 2022 Jan;8(1):7.
• Gelman S, Fahlberg SA, Heinzelman P, Romero PA, Gitter A. Neural networks to learn protein sequence-function relationships from deep mutational scanning data. Proceedings of the National Academy of Sciences of the United States of America. 2021 Nov;118(48):e2104878118.
• Greenhalgh JC, Fahlberg SA, Pfleger BF, Romero PA. Machine learning-guided acyl-ACP reductase engineering for improved in vivo fatty alcohol production. Nature communications. 2021 Oct;12(1):5825.
• Hyman LB, Christopher CR, Romero PA. Single-cell nucleic acid profiling in droplets (SNAPD) enables high-throughput analysis of heterogeneous cell populations. Nucleic acids research. 2021 Oct;49(18):e103.
• Kumar P, Adamczyk PA, Zhang X, Andrade RB, Romero PA, Ramanathan P, et al. Active and machine learning-based approaches to rapidly enhance microbial chemical production. Metabolic engineering. 2021 Sep;67:216u201326.
• Heinzelman P, Greenhalgh JC, Romero PA. Yeast surface display-based identification of ACE2 mutations that modulate SARS-CoV-2 spike binding across multiple mammalian species. Cold Spring Harbor Laboratory. 2021.
• Hyman L, Christopher C, Romero P. Competitive SNP-LAMP probes for rapid and robust single-nucleotide polymorphism detection. bioRxiv. 2021.
• Roychowdury H, Romero P. Microfluidic deep mutational scanning of the human executioner caspases reveals differences in structure and regulation. bioRxiv. 2021.
• Heinzelman P, Romero PA. Discovery of human ACE2 variants with altered recognition by the SARS-CoV-2 spike protein. PloS one. 2021 Jan;16(5):e0251585.
• Greenhalgh J, Fahlberg S, Pfleger B, Romero P. Machine learning-guided acyl-ACP reductase engineering for improved in vivo fatty alcohol production. bioRxiv. 2021.
• Heinzelman P, Romero PA. Discovery of human ACE2 variants with altered recognition by the SARS-CoV-2 spike protein. Cold Spring Harbor Laboratory. 2020.
• Song H, Bremer B, Hinds E, Raskutti G, Romero P. Inferring protein sequence-function relationships with large-scale positive-unlabeled learning. bioRxiv. 2020.
• Kumar P, Adamczyk P, Zhang X, Andrade RB, Romero P, Ramanathan P, et al. Active and machine learning-based approaches to rapidly enhance microbial chemical production. bioRxiv. 2020.
• Gelman S, Fahlberg S, Heinzelman P, Romero P, Gitter A. Neural networks to learn protein sequence-function relationships from deep mutational scanning data. bioRxiv. 2020.
• Gupta S, Ross T, Gomez M, Grant J, Romero P, Venturelli O. Investigating the dynamics of microbial consortia in spatially structured environments. bioRxiv. 2020.