Following the success of the Human Genome Project, the entire scientific community witnessed a large data explosion in genomics, which was also aided by advances in molecular biology technologies such as next-generation sequencing. These high-throughput technologies enable comprehensive molecular profiling of cancer cell lines, including gene expression. Regardless of the use of gene-based assays, they provide abundant genomic information for identifying participating genes (biomarkers) that contribute to the chemoresistance process in cancer cells.

Predictive modelling using machine learning (ML) techniques allows the generation of predictive biomarkers for chemotherapeutic response and targets for new chemotherapeutics agents. However, traditional ML techniques have some computational challenges, including (1) curse of dimensionality, (2) class imbalance, (3) heterogeneity, (4) lack of context, and (5) robust and interpretable outcomes. Therefore, a better strategy could be proposed to complement ML techniques by combining heterogeneous and large-scale datasets based on a pan-genome approach.