Future Pharmacology

Background/Objective: Predicting pharmacological response in cancer remains a key challenge in precision oncology due to intertumoral heterogeneity and the complexity of drug–gene interactions. While machine learning models using multi-omics data have shown promise in predicting pharmacological response, selecting the features with the highest predictive power critically affects model performance and biological interpretability. This study aims to compare computational and biologically informed gene selection strategies for predicting drug response in cancer cell lines and to propose a feature selection strategy that optimizes performance. Methods: Using gene expression and drug response data, we trained models on both data-driven and biologically informed gene sets based on the drug target pathways to predict IC₅₀ values for seven anticancer drugs. Several feature selection methods were tested on gene expression profiles of cancer cell lines, including Recursive Feature Elimination (RFE) with Support Vector Regression (SVR) against gene sets derived from drug-specific pathways in KEGG and CTD databases. The predictability was comparatively analyzed using both AUC and IC₅₀ values and further assessed on proteomics data. Results: RFE with SVR outperformed other computational methods, while pathway-based gene sets showed lower performance compared to data-driven methods. The integration of computational and biologically informed gene sets consistently improved prediction accuracy across several anticancer drugs, while the predictive value of the corresponding proteomic features was significantly lower compared with the mRNA profiles. Conclusions: Integrating biological knowledge into feature selection enhances both the accuracy and interpretability of drug response prediction models. Integrative approaches offer a more robust and generalizable framework with potential applications in biomarker discovery, drug repurposing, and personalized treatment strategies.

Background/Objectives: Colorectal carcinoma (CRC) is among the most commonly diagnosed cancers in both men and women. Although CRC mortality is generally decreasing, new therapeutic options are needed for unresponsive subgroups of CRC patients. Methods: A series of known and new tyrphostin derivatives was tested for their efficacy against three CRC cell lines with varying KRAS, p53, and/or BRAF statuses. Growth inhibition, apoptosis induction, and inhibition of EGFR and VEGFR-2 were investigated. Results: Tyrphostin A9, the known RG13022-related tyrphostin 1a and its dichlorido(p-cymene)ruthenium(II) complex 1b, and the new SF₅-substituted compounds 2a and 2b showed selective antiproliferative activity against KRAS-mutant HCT-116 CRC cells expressing wildtype p53, while p53-knockout HCT-116 and KRAS-wildtype BRAF/p53-mutant HT-29 CRC cells were distinctly less sensitive. In HCT-116 cells, only tyrphostin A9 increased mRNA expression of caspases 3 and 8, as well as the kinases MEK1 and MEK2, whereas 2a reduced caspase 8 mRNA levels. Tyrphostin A9 increased caspase 3 activity and induced apoptosis in HCT-116 p53-wildtype cells while simultaneously inhibiting the receptor tyrosine kinases EGFR and VEGFR-2 at low nanomolar concentrations. Conclusions: Tyrphostin A9 could be a promising therapeutic option for the treatment of KRAS-mutant CRC that expresses wildtype p53.

In the original publication [1], during the revisions and restructuring of the manuscript, the following references were inadvertently removed by the authors and were not cited:103 [...]