Jonathan L. Golob, MD, PhD

I lead applied AI/ML and data engineering within the Biomedical AI group in R&D at GSK, turning consequential vaccine and infectious-disease questions into technically sound, human-centered decision systems.

• Operational decision systems — leads the transition of biomedical-AI models into maintained tools for clinical-development decision-makers, spanning user discovery, workflow and interface/API design, uncertainty communication, leadership engagement, and adoption planning.
• Strategic model impact — built deep-learning models predicting viral evolution, infection incidence and case-accrual timing, and host–immune interactions, used to guide development and lifecycle decisions for a $1B vaccine program; related approaches supported additional programs in the $100M–$500M range.
• Technical research judgment — regularly advises senior scientific and R&D leaders alongside engineering teams on biomedical problem framing, AI method selection, data strategy, and evaluation; personally develops and directs work using protein and RNA language models, diffusion approaches, and uncertainty-aware biological-sequence modeling.
• AI/ML and data accountability — leads and is accountable for GSK’s AI/ML and data-engineering strategy and delivery across all six Fleming Initiative Grand Challenges.
• Scientific leadership — GSK scientific co-lead for the Antibiotics and Antifungals Grand Challenges; co-developed their scopes of work and scientific plans.
• Focused-team leadership — built and directly manages a specialist ML engineering team while repeatedly forming and directing cross-disciplinary teams of 20–30; establishes maintainable systems and durable ownership so embedded teams can continue independently.
• Build–buy–partner leadership — influences technical investment and resource allocation; personally presents technical and business cases; works with business development and procurement on external partners and vendors; defines scopes, success criteria, evaluation, and delivery accountability.
• Responsible AI — piloted a project for GSK’s Responsible AI programme and authored a perspective on the work.
• Clinical and scientific depth — maintains a limited active clinical practice and brings expertise in clinical-trial design and implementation, global vaccine-safety oversight, EHR data, vaccines, antimicrobials, and antimicrobial resistance.

I led a research group focused on the practical clinical translation of microbiome science to patients within precision medicine — pairing novel computational techniques with cutting-edge in vitro and in vivo models — and responded to the COVID-19 pandemic, caring for hundreds of critically ill patients while developing and running human observational and interventional trials.

• Computational biologist — multi-omics integration, massive multi-study datasets, and novel approaches and workflows; technical team leader with hands-on software depth.
• Human clinical trialist — observational trial development, novel therapeutic and target development, protocol writing, safety monitoring, and implementation.
• Clinical care — transplant infectious disease; cancer, solid-organ and hematopoietic stem cell transplant.
• Translational research — inflammatory bowel disease, stem cell transplant, immunotherapy, and prematurity / birth outcomes.
• Basic research — microbe–microbe and host–microbe interaction modeling; stem-cell biology and organoids.

Postdoctoral fellow studying how the gut microbiome relates to and mechanistically contributes to outcomes in patients undergoing hematopoietic stem cell transplant. Mentor: David Fredricks.

• Combined human observational study data with novel analytic and computational techniques.
• Attending physician specializing in cancer-related infections.

My doctoral work used the (then-new) pluripotent stem-cell model to establish the basic epigenetic mechanisms behind the earliest stages of human development. I employed some of the earliest “next-generation” high-throughput sequencing and built a novel computational pipeline integrating transcriptional micro-array and tiling-array data. Mentor: Charles “Chuck” Murry.

Conceived, designed, and built an independent AI evaluation research and engineering project using realistic tasks, hidden tests, anti-gaming constraints, structured failure analysis, cost-aware comparison, and API-driven recommendations.

Develops deep learning models to support biodefense and detect anomalous or potentially concerning uses of AI in health and biological contexts.

Applies responsible AI practice to clinical AI safety, model evaluation, and governance for tools deployed in high-stakes scientific and healthcare settings.

Independent AI evaluation research and engineering project. Conceived, designed, and built ChoreCode end to end: a cost-aware evaluation platform that benchmarks AI coding models on realistic maintenance work using hidden tests, anti-gaming constraints, structured failure analysis, downloadable data, and API-driven recommendations.

Building on MaLiAmPi, an atlas of the human microbiome in health and disease — harmonizing new raw data into existing feature sets, a key step toward clinical translation of microbiome-based predictive models like those from the preterm-birth DREAM challenge.

Led a crowdsourced machine-learning challenge to identify pregnancies at high risk of early preterm birth from vaginal-microbiome data, validated on independent datasets harmonized post-hoc. With Marina Sirota and Tomiko Oskotsky.

Identified the clinical relevance of microbiome butyrate production inhibiting gut recovery after injury during hematopoietic stem cell transplant — combining human observational data with organoid-based in vitro modeling — and latent HHV-7 infection of epithelium as a modulator of host–microbiome interactions.

Decoding the meaning of genetic variation — especially “variants of unknown significance” — for a general audience, with Ranjani Ramamurthy.

Core method behind MaLiAmPi — generalizable, taxonomy-independent microbiome features via phylogenetic placement.

Answered readers' science questions; extensive coverage of the 2008 financial crisis and the 2011 Fukushima disaster.

Long-form science & technology features for a general audience.

Public-facing analysis from a physician-scientist.

Decoding the genetic jigsaw: interpreting variants of unknown significance and cancer screening.

Leads and is accountable for GSK's AI/ML and data-engineering strategy and delivery across all six Grand Challenges. GSK scientific co-lead for Antibiotics and Antifungals; co-developed their scopes of work and scientific plans; established cross-organizational data coordination across industry and academic partners.

Provided medical expert testimony on protecting incarcerated people from COVID-19.

Protocol and biomarker development, global unblinded vaccine-safety oversight, trial implementation, and organizing-committee leadership.