Biostatistician building trustworthy machine learning for biomedical research

I develop open-source R software for reproducible biomedical data science. My work focuses on trustworthy machine learning, leakage-aware model evaluation, and transparent statistical workflows. Through methodological studies and software tools, I aim to improve the reliability and reproducibility of computational analyses in clinical and biological datasets.

Leakage-aware evaluation Reproducible workflows Bioinformatics Cheminformatics R package development

Software

Six R packages on CRAN, three open-source web tools, and a biostatistics teaching app.

BiostatQuest

Biostatistics learning app: 50+ case-based challenges and 1,000+ board-style questions.

Open app

splitGraph

Dataset dependency graphs for leakage-aware evaluation.

CRAN Source

bioLeak

Leakage-safe modeling and auditing for genomic and clinical data.

CRAN Source Paper

fastml

Guarded resampling workflows for leakage-aware machine learning in R.

CRAN Source Paper

MVN

Multivariate normality testing with six statistical tests, diagnostics, and outlier detection.

CRAN Source Paper

rPDBapi

A comprehensive interface for accessing the Protein Data Bank.

CRAN Source Paper

PubChemR

Access PubChem programmatically for cheminformatics analysis.

CRAN Source Paper

BioVar

Online biological variation analysis for clinical laboratory data.

Source Paper

geneSurv

Interactive web tool for survival analysis in genomics research.

Source Paper

MLViS

Machine learning-based virtual screening for early-phase drug discovery.

Source Paper

Selected publications

/

Showing all 17 publications

2026
The Strong Get Stronger: The Matthew Effect in Academic Publishing
Korkmaz S. Balkan Medical Journal, 43(6), 294–296.
2026
2026
fastml: Guarded Resampling Workflows for Safer Automated Machine Learning in R
Korkmaz S, Goksuluk D, Karaismailoglu E. arXiv preprint arXiv:2604.05225.
2025
rPDBapi: A Comprehensive R Package Interface for Accessing the Protein Data Bank
Korkmaz S, Yamasan B. E. The R Journal, 17(2), 109–145.
2025
2025
Statistical Rigor and Reproducibility in the AI Era
Korkmaz S. Balkan Medical Journal, 42(5), 386–387.
2024
PubChemR: An R Package for Accessing Chemical Data from PubChem
Korkmaz S, Yamasan B. E., Goksuluk D. The R Journal, 16(3), 150–185.
2024
Binding Activity Classification of Anti-SARS-CoV-2 Molecules using Deep Learning Across Multiple Assays
Yamasan B. E, Korkmaz S. Balkan Medical Journal, 41(3), 186–192.
2024
2020
BioVar: an online biological variation analysis tool
Korkmaz S, Zarasız G, Göksülük D, Senes M, Sönmez C, Yucel D. Turkish Journal of Biochemistry, 45(5), 479–489.
2020
Deep learning-based imbalanced data classification for drug discovery
Korkmaz S. Journal of Chemical Information and Modeling, 60(9), 4180–4190.
2019
Small Drug Molecule Classification Using Deep Neural Networks
Korkmaz S. Turkiye Klinikleri Journal of Biostatistics, 11(2), 93–101.
2018
Investigation of Protein Quaternary Structure via Stoichiometry and Symmetry Information
Korkmaz S, Duarte JM, Prlic A, Goksuluk D, Zararsiz G, Saracbasi O, Burley SK, Rose PW. PLOS ONE, 13(6): e0197176.
2017
geneSurv: An interactive web-based tool for survival analysis in genomics research
Korkmaz S, Goksuluk D, Zararsiz G, Karahan S. Computers in Biology and Medicine, 89, 487–496.
2015
2014
MVN: An R Package for Assessing Multivariate Normality
Korkmaz S, Goksuluk D, Zararsiz G. The R Journal, 6(2), 151–162.
2014
Drug/Nondrug Classification Using Support Vector Machines with Various Feature Selection Strategies
Korkmaz S, Zararsiz G, Goksuluk D. Computer Methods and Programs in Biomedicine, 117(2), 51–60.

Full list on Google Scholar and ORCID.

Contact

Email

selcukkorkmaz@trakya.edu.tr

Address

Department of Biostatistics
Trakya University Faculty of Medicine
22030 Edirne, Türkiye