Comparative analysis of molecular representations in prediction of drug combination effects
Preprint
Abstract
A bstract: Application of machine and deep learning methods in drug discovery and cancer research has gained a considerable amount of attention in the past years. As the field grows, it becomes crucial to systematically evaluate the performance of novel computational solutions in relation to established techniques. To this end we compare rule-based and data-driven molecular representations in prediction of drug combination sensitivity and drug synergy scores using standardized results of 14 throughput screening studies, comprising 64 200 unique combinations of 4 153 molecules tested in 112 cancer cell lines. We evaluate the clustering performance of molecular representations and quantify their similarity by adapting the Centered Kernel Alignment metric. Our work demonstrates that to identify an optimal molecular representation type it is necessary to supplement quantitative benchmark results with qualitative considerations, such as model interpretability and robustness, which may vary between and throughout preclinical drug development projects. Abstract Figure:Keywords
This publication has 85 references indexed in Scilit:
- Open-source platform to benchmark fingerprints for ligand-based virtual screeningJournal of Cheminformatics, 2013
- Similarity Coefficients for Binary Chemoinformatics Data: Overview and Extended Comparison Using Simulated and Real Data SetsJournal of Chemical Information and Modeling, 2012
- Towards a Universal SMILES representation - A standard method to generate canonical SMILES based on the InChIJournal of Cheminformatics, 2012
- Quantitative Methods for Assessing Drug SynergismGenes & Cancer, 2011
- ChEMBL: a large-scale bioactivity database for drug discoveryNucleic Acids Research, 2011
- Measuring performance and missing the point?BMJ, 2007
- Averaging Correlations: Expected Values and Bias in Combined Pearsonrs and Fisher'szTransformationsThe Journal of General Psychology, 1998
- Editorial boardCommunications in Statistics - Theory and Methods, 1974
- The Generation of a Unique Machine Description for Chemical Structures-A Technique Developed at Chemical Abstracts Service.Journal of Chemical Documentation, 1965
- FREQUENCY DISTRIBUTION OF THE VALUES OF THE CORRELATION COEFFIENTS IN SAMPLES FROM AN INDEFINITELY LARGE POPU;ATIONBiometrika, 1915