Machine learning on syngeneic mouse tumor profiles to model clinical immunotherapy response

Abstract

Most patients with cancer are refractory to immune checkpoint blockade (ICB) therapy, and proper patient stratification remains an open question. Primary patient data suffer from high heterogeneity, low accessibility, and lack of proper controls. In contrast, syngeneic mouse tumor models enable controlled experiments with ICB treatments. Using transcriptomic and experimental variables from >700 ICB-treated/control syngeneic mouse tumors, we developed a machine learning framework to model tumor immunity and identify factors influencing ICB response. Projected on human immunotherapy trial data, we found that the model can predict clinical ICB response. We further applied the model to predicting ICB-responsive/resistant cancer types in The Cancer Genome Atlas, which agreed well with existing clinical reports. Last, feature analysis implicated factors associated with ICB response. In summary, our computational framework based on mouse tumor data reliably stratified patients regarding ICB response, informed resistance mechanisms, and has the potential for wide applications in disease treatment studies.

Multi-omics and artificial intelligence predict clinical outcomes of immunotherapy in non-small cell lung cancer patients

“…They demonstrated that their method could distinguish tumor samples with high and low ITH levels and identify transcriptomic markers associated with ITH [ 77 ]. To facilitate the investigation of heterogeneity in the ICI response, Zeng et al developed a non-negative matrix factorization (NMF)-based ML framework to identify factors affecting the immunotherapy response using data from TCGA samples [ 78 ]. With the advent of the era of precision medicine, AI-assisted transcriptomic technology will continue to develop and become more common in immunotherapy research, providing valuable information for the formulation of new strategies to improve the efficacy of cancer immunotherapy.…”

Artificial Intelligence-Assisted Transcriptomic Analysis to Advance Cancer Immunotherapy

“…To better investigate the heterogeneity of the ICI response, Zeng et al developed an ML framework based on nonnegative matrix factorization (NMF) to identify factors influencing the ICI response in TCGA samples. They found that ubiquitin E3 ligases may be potential regulators of ICI response [ 35 ]. Another group applied the NMF algorithm to transcriptome profiles from ovarian cancer (OV) cell lines.…”

Engineering Heterogeneous Tumor Models for Biomedical Applications

“…[528] AI algorithms are being utilized to identify predictive markers and extract novel insights from the data, such as elucidating the immunological signatures and assisting in determining the most effective treatment strategy for a patient. [529,530] Moreover, AI models can help researchers predict how tumors may evolve over time and evaluate the success of var-ious treatments in clinical trials. For instance, a machine learning algorithm was employed to classify the immunological status based on features from transcriptome profiling, T cell repertoire analysis, and whole exome sequencing of patient tumor tissues (Figure 39b).…”