BreastCAR: A Machine Learning Framework for Breast Cancer Drug Activity Prediction

Breast cancer is a highly prevalent and molecularly heterogeneous malignancy, where therapeutic resistance and off-target toxicity remain major challenges. Here, we introduce BreastCAR, a multi-target quantitative structure-activity relationship framework trained on ChEMBL bioactivity data covering 53 cancer-relevant targets and 233975 compounds. The model integrates 2048-bit Morgan fingerprints with physicochemical descriptors and applies random forest, XGBoost, LightGBM (LGB), support vector machine with RBF kernel (SVM-RBF) and multilayer perceptron (MLP) for both regression (pIC₅₀) and three-class activity classification. The framework achieves a mean R² of 0.723 and root mean squared error of 0.661, with a peak R² of 0.894 for NOTC1. Classification performance shows a mean F1 score of 0.826, area under the curve-receiver operating characteristic of 0.919, Matthews correlation coefficient of 0.679 and balanced accuracy of 0.759. Y-randomisation confirmed non-trivial model learning (permuted R² = -0.167 vs. real 0.723; permuted F1 = 0.467 vs. real 0.826). Applicability domain analysis (Tanimoto k-NN, 95th-percentile threshold) demonstrated that 94.8% of test compounds fall within the training AD. To experimentally validate the top-ranked BreastCAR predictions, a panel of 13 benzylidene-scaffold compounds (R26-01 to R26-13) was evaluated in vitro against MCF-7 human breast cancer cells using the MTT antiproliferative assay (n = 3, IC₅₀ determined by non-linear regression). Two compounds-R26-06 (4-bromobenzylidene, IC₅₀ = 5.84 ± 0.24 μM, SI = 9.2) and R26-07 (3-chlorobenzylidene, IC₅₀ = 6.72 ± 0.28 μM, SI = 8.4)-surpassed tamoxifen (IC₅₀ = 14.23 ± 0.58 μM) with statistical significance (p < 0.001), demonstrating that BreastCAR-guided prioritisation translates computational predictions into experimentally confirmed antiproliferative activity. A FastAPI-based web interface enables real-time SMILES input, structural visualisation and activity prediction. The complete code and models are provided to ensure reproducibility.