160
views
0
recommends
+1 Recommend
1 collections
    0
    shares
      scite_
       
      • Record: found
      • Abstract: found
      • Conference Proceedings: found
      Is Open Access

      Drug Response Prediction with Machine Learning: A Critical Assessment of Current Approaches

      Published
      conference-abstract
        1 , 1 , 1 , 1
      REPO4EU
      RExPO23
      25-26 October 2023
      Drug response prediction, pipeline, reproducibility, generalization, robustness, machine learning, baselines, proteomics
      Bookmark

            Abstract

            Drug response prediction is pivotal in personalized medicine as it allows healthcare providers to tailor treatments to individual patients for improved therapeutic outcomes. Machine learning has emerged as a promising tool for predicting drug responses; however, this burgeoning field faces three substantial challenges that remain inadequately addressed. State-of-the-art methods, including deep learning approaches, do not systematically compare themselves against simple baseline models. We found that published methods lack reproducible implementations, suffer from overfitting, and do not pass fundamental consistency and robustness tests. This leads to over-optimism about prediction results, which can often be matched by a simple mean predictor. In addition, frequently used measures to quantify and summarize drug response, such as IC50, EC50, and AUC values, do not capture the dynamic of drug response adequately, leading to poor generalization of findings across data sets. Finally, drug response prediction methods typically rely exclusively on transcriptomics measurements, neglecting proteomics and phospho-proteomics data, which offer unique insights into the response of the drug targets themselves. To address these research gaps, we propose the development of a new pipeline for systematically benchmarking drug response prediction methods against baseline and state-of-the-art predictors on curated multiomics data in ProteomicsDB. Through these concerted efforts, we pave the way for more accurate and clinically relevant drug response predictions, ultimately enhancing patient care and treatment outcomes.

            Content

            Author and article information

            Conference
            REPO4EU
            4 October 2023
            Affiliations
            [1 ] Technical University of Munich, Freising (Germany) ( https://ror.org/02kkvpp62)
            Author information
            https://orcid.org/0000-0001-5812-8013
            https://orcid.org/0000-0003-0428-1703
            https://orcid.org/0000-0002-0941-4168
            https://orcid.org/0000-0002-9224-3258
            Article
            10.58647/REXPO.23015
            8862d58c-b1d1-402a-b186-063928df8db5
            Authors

            Published under Creative Commons Attribution 4.0 International ( CC BY 4.0). Users are allowed to share (copy and redistribute the material in any medium or format) and adapt (remix, transform, and build upon the material for any purpose, even commercially), as long as the authors and the publisher are explicitly identified and properly acknowledged as the original source.

            RExPO23
            2
            Stockholm, Sweden
            25-26 October 2023
            History
            Product

            REPO4EU

            Categories

            Data sharing not applicable to this article as no datasets were generated or analysed during the current study.
            Pharmacology & Pharmaceutical medicine
            Drug response prediction,pipeline,reproducibility,generalization,robustness,machine learning,baselines,proteomics

            References

            1. Lautenbacher Ludwig, Samaras Patroklos, Muller Julian, Grafberger Andreas, Shraideh Marwin, Rank Johannes, Fuchs Simon T, Schmidt Tobias K, The Matthew, Dallago Christian, Wittges Holger, Rost Burkhard, Krcmar Helmut, Kuster Bernhard, Wilhelm Mathias. ProteomicsDB: toward a FAIR open-source resource for life-science research. Nucleic Acids Research. Vol. 50(D1)2022. Oxford University Press (OUP). [Cross Ref]

            Comments

            Comment on this article