Statistical and predictive treatment response modeling


Department of Mathematics and Statistics, University of Turku, FI-20014 Turku, Finland
Institute for Molecular Medicine Finland (FIMM), University of Helsinki, FI-00014 Helsinki, Finland

Research Group

Teemu Daniel Laajala, MSc (Tech), Doctoral student
Hannu-Pekka Schukov, MSc, Doctoral student
Vidal Fey, PhD, Postdoctoral researcher
Prem Adhikari, PhD, Postdoctoral researcher

The goal of the project

The research group has extensive expertise in statistical and predictive approaches to treatment response modeling in vitro, ex vivo and in vivo, as well as in large-scale omics data integration and mining for diagnostic and prognostic markers. Such systems pharmacology approach has the potential to suggest more effective and selective therapeutic targets.

  • Statistical modeling: we develop web-based tools for improved treatment effect testing in animal models, including patient-derived xenografts or genetically-modified mouse models; these tools are based on statistical modeling of tumor growth, optimal matching of animals at baseline, as well as power calculations for sufficient sample size estimation.
  • Predictive modeling: we implement computationally efficient and clinically applicable machine learning models through systematic mining of molecular features that are predictive of medical outcomes, including differences in disease risk or treatment response; such features may eventually provide predictive biomarkers for clinical translation.
  • Data integration: we apply advanced mathematical methods to make the most of the high-throughput omics datasets, including transcriptomics, proteomics and metabolomics, combined with clinical information; integrated analysis provides a systems-level view of the underlying disease model and mode of action of the therapeutic interventions.

Representative publications

Laajala TD, Corander J, Saarinen NM, Mäkelä K, Savolainen S, Suominen MI, Alhoniemi E, Mäkelä SI, Poutanen M, Aittokallio T. Improved statistical modeling of tumor growth and treatment effect in pre-clinical animal studies with highly heterogeneous responses in vivo. Clinical Cancer Research 2012; 18: 4385-4396.

Pahikkala T, Airola A, Pietilä S, Shakyawar S, Szwajda A, Tang J, Aittokallio T. Toward more realistic drug-target interaction predictions. Briefings in Bioinformatics 2015; 16:325-37.

Okser S, Pahikkala T, Airola A, Salakoski T, Ripatti S, Aittokallio T. Regularized machine learning in the genetic prediction of complex traits. PLoS Genetics 2014; 10: e1004754.

Cichonska A, Rousu J, Aittokallio T. Identification of drug candidates and repurposing opportunities through compound–target interaction networks. Expert Opin Drug Discov 2015:1–13.

Kibble M, Saarinen N, Tang J, Wennerberg K, Mäkelä S, Aittokallio T. Network pharmacology applications to map the unexplored target space and therapeutic potential of natural products. Natural Product Reports 2015; 32:1249-66

Laajala TD, Jumppanen M, Huhtaniemi R, Fey V, Kaur A, Knuuttila M, Aho E, Oksala R, Westermarck J, Mäkelä S, Poutanen M, Aittokallio T. Optimized design and analysis of preclinical intervention studies in vivo. Scientific Reports 2016, 6; 30723. doi:10.1038/srep30723

Aittokallio T, Scherer A, Poutanen M, Freedman LP. Matched preclinical designs for improved translatability. Sci Transl Med. 2017 May 10;9(389). pii: eaal4101. doi: 10.1126/scitranslmed.aal4101.



Principal Investigator

Tero Aittokallio, PhD
Professor of Statistics and Applied Mathematics

Phone: +358-2-333 5686