Charlotte Merzbacher
ARTIFICIAL INTELLIGENCE x BIOENGINEERING
Hi, I'm Charlotte Merzbacher, a scientist and researcher based in Amsterdam. I hold a PhD in Biomedical Artificial Intelligence from the University of Edinburgh, where my thesis work integrated machine learning and mechanistic mathematical models to study metabolism. I have published papers in various peer-reviewed scientific journals, including Nature Communications, Metabolic Engineering, and ACS Synthetic Biology. I graduated from Brown University with Honors in Biomedical Engineering.
I now work as the Founding Data Scientist at Differential Bio, a Munich-based startup focused on transforming the bioeconomy by making novel fermentation predictable and scalable. I previously worked as a Data Scientist at Natera, a genetic testing company based near San Francisco.
I also write fiction and nonfiction under the name C. J. Marten. I have a newsletter, Speculation Lab. I was a 2025 resident artist at Arteles Creative Center.
Creative Work
Academic Research
Industry Experience
Work Experience
Academia
2021 to 2025
Ph.D., Biomedical Artificial Intelligence
M.Res. with Distinction, 2022
University of Edinburgh
Edinburgh, Scotland
Advisors: Diego Oyarzún and Oisin Mac Aodha
Supervised students: Samuel Cain (BSc Honours), Nicholas Goguen-Copagnoni (BSc Honours), Nicola Hallman (MSc)
Machine Learning Practical & Theory, Mathematical Biology, Bioinformatics Algorithms
2015 to 2019
Sc.B., Biomedical Engineering (Honors)
Brown University
Providence, Rhode Island, USA
Sigma Xi Honors Society
Voss Fellowship, Karen Romer Research Award
Amgen Scholar, Washington University in St. Louis
Computational Biology, Reactor Kinetics, Statistics, Differential Equations, Algorithms, Biochemistry
Industry
October 2025 to present
Founding Data Scientist
Differential Bio
Munich, Germany
- Developing novel machine learning algorithms to transfer models between species, strains, and scales
- Productionizing and scaling customer delivery pipelines, including genomic and GEM-based analysis tools and model-informed DOE
- Managing growing team of data scientists; interfacing with wet lab biologists and C-suite customers
October 2019 to September 2021
Production Engineer & Data Scientist
Natera
San Carlos, California
- Managed operations on a team of 3 engineers for product algorithms with a total volume of >1M samples/year; completed over 500 investigations with an avg time to resolution less than 48 hours
- Designed product QC metrics and alerts dashboards to predict and detect neural network and Bayesian algorithm issues and separate failure modes in lab
Skills
Core Expertise
- Novel machine learning algorithm development
- Active learning and lab-in-the-loop optimization
- Hybrid mechanistic-ML modeling
Data & Software Engineering
- Scientific computing and statistical analysis (Julia, Python, R)
- Novel ML algorithm development and parallelization (PyTorch, Jax)
- Production ML & research pipelines (Docker, NextFlow, Prefect)
- Experiment tracking & model lifecycle management (MLFlow)
- Large-scale biological data processing (PostgresSQL, S3)
Machine Learning & Modeling
- Bayesian optimization & active learning
- Transfer learning across biological contexts
- Deep representation learning of high-dimensional spaces
- Constraint-based metabolic modeling (FBA, flux analysis)
- Nonlinear dynamic systems (ODEs)
Professional Skills
- Translating experimental goals into modeling strategies
- Collaborating across wet lab, software, and data teams
- Productionizing research models
- Customer-facing scientific communication
Publications
Multiobjective design of growth media with genome-scale metabolic models and Bayesian optimization.
bioRxiv. December 2025. In review at Computational and Structural Biology Journal.
Accurate prediction of gene deletion phenotypes with Flux Cone Learning.
Nature Communications. September 2025. doi: 10.1038/s41467-025-63436-9
Modeling host–pathway dynamics at the genome scale with machine learning
Metabolic Engineering. June 2025. doi: 10.1016/j.ymben.2025.05.008
Low-dimensional representations of genome-scale metabolism.
Foundations of Systems Biology in Engineering Conference Proceedings. September 2024. doi: 10.1016/j.ifacol.2024.10.011
Integration of DNA methylation datasets for individual prediction of DNA methylation-based biomarkers.
Genome Biology. December 2023. doi: 10.1186/s13059-023-03114-5
Applications of artificial intelligence and machine learning in dynamic pathway engineering.
Biochemical Society Transactions. October 2023. doi: 10.1042/BST20221542
Bayesian optimization for design of multiscale biological circuits.
ACS Synthetic Biology. June 2023. doi: 10.1021/acssynbio.3c00120
Identification of BvgA-dependent and BvgA-independent small RNAs (sRNAs) in Bordetella pertussis using the prokaryotic sRNA prediction toolkit ANNOgesic.
Microbiol Spectr. October 2021. doi: 10.1128/Spectrum.00044-21
Presentations
Talks
January 2026
AI, Engineering Biology and Beyond
Bristol, UK
Awarded best talk.
July 2025
Metabolic Pathway Analysis
Vienna, AT
October 2024
Low-dimensional representation of genome-scale metabolism
Edinburgh Centre for Engineering Biology Meeting, Edinburgh, UK
September 2024
Low-dimensional representations of genome-scale metabolism
Foundations of Systems Biology in Engineering, Corfu, GR
Awarded best talk.
September 2024
Learning representations and artificial intelligence: Is representation a byproduct of language? A philosophical grounding
Santa Fe Institute, Santa Fe, USA
April 2024
Machine learning meets mechanistic modelling for biology
CDT Biotech Industry Day, Edinburgh, UK
November 2023
Bridging the gap between genome-scale and kinetic models
SynBioUK Conference, Bristol, UK
September 2023
Bridging the gap between genome-scale and kinetic models
Edinburgh Centre for Engineering Biology Meeting, Edinburgh, UK
March 2023
Machine learning for complex biological circuit design
AI for Healthcare CDT Conference, York, UK
Awarded best talk.
March 2023
Machine learning for complex biological circuit design
Turing Workshop on AI, Engineering Biology, and Beyond, Edinburgh, UK
October 2022
Machine learning approaches for dynamic metabolic engineering
International Conference in Systems Biology, Berlin, DE
Workshops
March 2026
Centuriae invited scientific writing retreat
Hook, UK
February 2026
Emergence Art & Science workshop
Dumfriesshire, UK
October 2024
AI vulnerabilities and societal implications
Edinburgh Futures Institute, Edinburgh, UK
September 2024
Working Group: Assessing representation in minds and artificial systems
Santa Fe Institute, Santa Fe, USA
July 2024
Cambridge ELLIS Probabilistic Machine Learning Summer School
August 2023
SFI Complexity-GAINS on Representation
Isaac Newton Institute, Cambridge, UK
Awarded best group project and funding for working group conference.
October 2022
Synthetic biology in the age of machine learning
International Conference in Systems Biology
Organizer and host of full-day satellite session.
Posters
October 2024
Conference: Chief Data Officer Summit
London, UK
July 2024
Mechanistic modelling meets machine learning
Cambridge ELLIS Summer School, Cambridge, UK
May 2024
Host-pathway interactions in genome-scale metabolism
AI for Healthcare CDT Conference, Edinburgh, UK
November 2023
SynBioUK Conference
Bristol, UK
May 2023
Bayesian optimization for gene circuit design
AI for Healthcare CDT Conference, York, UK
April 2023
Conference: AI for Biology
TU Delft, Delft, NE
November 2022
Fast and scalable machine learning for dynamic metabolic engineering
SynBioUK Conference, Newcastle, UK
November 2022
CDT in Biomedical Artificial Intelligence Poster Session
Edinburgh, UK
October 2022
Machine learning approaches for dynamic metabolic engineering
International Conference in Systems Biology, Berlin, DE
November 2018
3D Scaffold-free lung microtissues for nanomaterial toxicity testing
Biomedical Engineering Society Conference, Atlanta, GA, USA
built by charlotte merzbacher