Main
John Zobolas
Researcher in Clinical AI and Computational Statistics with a background in computer science, software engineering and computational biology. My research focuses on machine learning for cancer research, particularly survival analysis and high-dimensional biomarker discovery. I am a core contributor to the open-source mlr3 R ecosystem for machine learning and maintainer of mlr3proba and several CRAN packages, including CoxBoost and fastVoteR.
Research Experience
Researcher in Clinical AI
Oslo University Hospital
Oslo
Present - Oct 2025
- Machine learning for survival analysis and cancer research
- High-dimensional, multi-omics feature selection
- Adverse-event modeling
- Development of open-source statistical/ML software
Postdoc Researcher in Clinical AI for Pancreatic Cancer
Oslo University Hospital
Oslo
Sept 2025 - Jan 2022
Internship in Molecular AI group
AstraZeneca
Gothenburg
April 2021 - Jan 2021
Predicting bioactivity data using Matrix Factorization for target-based clustering and validation
Research stay in Molecular Interactions Team
European Bioinformatics Institute
Hinxton, England
July 2018
Extending the PSICQUIC Java-based Web service platform to include causality information of molecular interactions
Industry
Linux Systems Engineer
Commsquare
Athens
2015 - 2013
Education
PhD in Computational Biology
Norwegian University of Science and Technology (NTNU)
Trondheim
2021 - 2017
Software implementations allowing new approaches toward data analysis, modeling and curation of biological knowledge for Systems Medicine [link ] [Defence video ] [Results] [Diploma]
MSc in Computer Science
Athens University of Economics and Business (AUEB)
Athens
2015 - 2013
Publications
Prognostic biomarker discovery in pancreatic cancer through hybrid ensemble feature selection and multi-omics data, BioData Mining
N/A
N/A
2026
A Large-Scale Neutral Comparison Study of Survival Models on Low-Dimensional Data, Bioinformatics
N/A
N/A
2026
mlr3extralearners: Expanding the mlr3 Ecosystem with Community-Driven Learner Integration, Journal of Open Source Software
N/A
N/A
2025
Boolean function metrics can assist modelers to check and choose logical rules, Journal of Theoretical Biology
N/A
N/A
2022
Funding
Olav Raagholt and Gerd Meidel Raagholt Grant
30,000 NOK, Advancing Machine Learning Methods for Survival Analysis in Cancer Research.
N/A
2025
Astri and Birger Torsteds Grant to Fight Cancer
50,000 NOK, IT equipment for cancer research within PANCAIM.
N/A
2024
Supervision
Alberto López
PhD student
N/A
2026 - 2023
Incomplete Multi-View Clustering Algorithms
Philip Studener & Markus Goeswein
Student Assistants (LMU)
N/A
2025 - 2024
Implementation of Reduction Techniques for Survival Analysis in mlr3proba [Lifetime Data Analysis ]
Laura Szekeres
Master student
N/A
2025 - 2024
Cancer Treatment gets Logical: An Ensemble Boolean Modeling Pipeline in Python [PyDrugLogics ] [JOSS ]
Tanguy Dumontier
Apprentice Data Engineer
N/A
2024
Optimizing Incomplete Multi-View Clustering: From MATLAB to Python [iMML ]
Hedda Fjell Scheel
Veterinary Research Student (Forskerlinjestudent)
N/A
2024 - 2023
Genetic Heterogeneity of Canine Mammary Tumors [Veterinary Oncology ]
Invited Talks, Tutorials & Conferences
Examining Properness in the External Validation of Survival Models with Squared and Logarithmic Losses
NORA Annual Conference 2024 [slides ]
Kristiansand
2024
Teaching
ML Course for Cancer Researchers
Institute for Cancer Research in Oslo [Trees&Ensembles, SVMs, NNs , Benchmarking ]
N/A
2022