Explainable machine learning and hybrid transformer-based proteochemometric modelling for breast cancer molecular subtyping and multi-target natural product discovery

Breast cancer comprises five intrinsic molecular subtypes with distinct transcriptomic programs, prognoses, and therapeutic vulnerabilities. Yet, accurate subtype discrimination remains limited by boundary-overlap and poor cross-cohort generalisability, while single-target agents often fail against pathway redundancy and acquired resistance. We developed an integrated computational framework linking transcriptomic-classification, explainable target prioritisation, and multi-target natural-product discovery. Three transcriptomic cohorts (METABRIC-BRCA-2016, TCGA-BRCA-2012, and TCGA-BRCA-2018; n = 2512 after quality-control and ComBat-correction) were integrated. Differential-expression analysis and PCA-based feature selection yielded a 50-gene signature that retained more than 90% of the subtype-associated variance. Among the six evaluated classifiers, XGBoost achieved the best performance and generalised to an independent cohort of 3,409 samples (accuracy: 85.70%; ROC-AUC: 0.95–0.99). SHAP-analysis identified 30-candidate genes associated with Basal-like and HER2-enriched subtypes, which were cross-referenced against ChEMBL to retain 11 targets for proteochemometric (PCM) modelling. A hybrid PCM multilayer-perceptron integrating ProtBERT and ChemBERTa embeddings with molecular fingerprints and chemical descriptors achieved a balanced-accuracy of 0.9140 and mean ROC-AUC of 0.9696. Screening of 30,898 NPASS natural products identified 292 pan-active compounds. Independent binding- and safety-prioritisation strategies converged on three leads: NPC139056, NPC196231, and NPC471997. This reproducible pipeline provides computationally prioritised leads for experimental validation in clinically challenging breast cancer subtypes.