Scientists at the University of Texas MD Anderson Cancer Center reported the development of a novel bioinformatics platform that predicts optimal treatment combinations for a given group of patients based on co-occurring tumor alterations. In retrospective validation studies, the tool selected combinations that resulted in improved patient outcomes across both pre-clinical and clinical studies.
The study “Precision combination therapies based on recurrent oncogenic co-alterations” is published in Cancer Discovery and its findings presented at the current AACR Annual Meeting in New Orleans.
The platform, called (REcurrent Features LEveraged for Combination Therapy (REFLECT), integrates machine learning and cancer informatics algorithms to analyze biological tumor features, including genetic mutations, copy number changes, gene expression and protein expression aberrations, and identify frequent co-occurring alterations that could be targeted by multiple drugs, according to the researchers.
“Cancer cells depend on multiple driver alterations whose oncogenic effects can be suppressed by drug combinations. Here, we provide a comprehensive resource of precision combination therapies tailored to oncogenic co-alterations that are recurrent across patient cohorts,” write the investigators.
“To generate the resource, we developed…REFLECT, which integrates machine learning and cancer informatics algorithms. Using multi-omic data, the method maps recurrent co-alteration signatures in patient cohorts to combination therapies. We validated the REFLECT pipeline using data from patient-derived xenografts, in vitro drug screens, and a combination therapy clinical trial. These validations demonstrate that REFLECT-selected combination therapies have significantly improved efficacy, synergy, and survival outcomes.
“In patient cohorts with immunotherapy response markers, DNA repair aberrations, and HER2 activation, we have identified therapeutically actionable and recurrent co-alteration signatures. REFLECT provides a resource and framework to design combination therapies tailored to tumor cohorts in data-driven clinical trials and pre-clinical studies.”
“Our ultimate goal is to make precision oncology more effective and create meaningful patient benefit,” said Anil Korkut, PhD, assistant professor of bioinformatics and computational biology. “We believe REFLECT may be one of the tools that can help overcome some of the current challenges in the field by facilitating both the discovery and the selection of combination therapies matched to the molecular composition of tumors.
“While REFLECT is still a concept that requires additional validation, we anticipate a great opportunity to translate this work into real clinical benefits. In the future, multi-omic profiles from pre-treatment patient samples could be loaded to the REFLECT pipeline to generate co-alteration signatures, allowing physicians to consider precision combination therapies tailored to molecular profiles of those patients.”
In the future, this approach will benefit from improved informatics resources to better match therapies to alterations at the RNA and protein level, according to Korkut. Additionally, the researchers plan to expand their study to better address and predict toxicity from matched drug combinations. Finally, future studies also will seek to address the significant heterogeneity within tumors, which can affect response to targeted therapies.
