A number of supervised machine learning models have recently been introduced for the prediction of drug–target interactions based on chemical structure and genomic sequence information. Although these models could offer improved means for many network pharmacology applications, such as repositioning of drugs for new therapeutic uses, the prediction models are often being constructed and evaluated under overly simplified settings that do not reflect the real-life problem in practical applications. Using quantitative drug–target bioactivity assays for kinase inhibitors, as well as a popular benchmarking data set of binary drug–target interactions for enzyme, ion channel, nuclear receptor and G protein-coupled receptor targets, we illustrate here the effects of four factors that may lead to dramatic differences in the prediction results: (i) problem formulation (standard binary classification or more realistic regression formulation), (ii) evaluation data set (drug and target families in the application use case), (iii) evaluation procedure (simple or nested cross-validation) and (iv) experimental setting (whether training and test sets share common drugs and targets, only drugs or targets or neither). Each of these factors should be taken into consideration to avoid reporting overoptimistic drug–target interaction prediction results. We also suggest guidelines on how to make the supervised drug–target interaction prediction studies more realistic in terms of such model formulations and evaluation setups that better address the inherent complexity of the prediction task in the practical applications, as well as novel benchmarking data sets that capture the continuous nature of the drug–target interactions for kinase inhibitors.

We present an individualized systems medicine (ISM) approach to optimize cancer drug therapies one patient at a time. ISM is based on (i) molecular profi ling and ex vivo drug sensitivity and resistance testing (DSRT) of patients' cancer cells to 187 oncology drugs, (ii) clinical implementation of therapies predicted to be effective, and (iii) studying consecutive samples from the treated patients to understand the basis of resistance. Here, application of ISM to 28 samples from patients with acute myeloid leukemia (AML) uncovered fi ve major taxonomic drug-response subtypes based on DSRT profi les, some with distinct genomic features (e.g., MLL gene fusions in subgroup IV and FLT3 -ITD mutations in subgroup V). Therapy based on DSRT resulted in several clinical responses. After progression under DSRT-guided therapies, AML cells displayed signifi cant clonal evolution and novel genomic changes potentially explaining resistance, whereas ex vivo DSRT data showed resistance to the clinically applied drugs and new vulnerabilities to previously ineffective drugs. SIGNIFICANCE:Here, we demonstrate an ISM strategy to optimize safe and effective personalized cancer therapies for individual patients as well as to understand and predict disease evolution and the next line of therapy. This approach could facilitate systematic drug repositioning of approved targeted drugs as well as help to prioritize and de-risk emerging drugs for clinical testing.