Real-world performance analysis of a novel computational method in the precision oncology of pediatric tumors.

BACKGROUND: The utility of routine extensive molecular profiling of pediatric tumors is a matter of debate due to the high number of genetic alterations of unknown significance or low evidence and the lack of standardized and personalized decision support methods. Digital drug assignment (DDA) is a novel computational method to prioritize treatment options by aggregating numerous evidence-based associations between multiple drivers, targets, and targeted agents. DDA has been validated to improve personalized treatment decisions based on the outcome data of adult patients treated in the SHIVA01 clinical trial. The aim of this study was to evaluate the utility of DDA in pediatric oncology. METHODS: Between 2017 and 2020, 103 high-risk pediatric cancer patients (< 21 years) were involved in our precision oncology program, and samples from 100 patients were eligible for further analysis. Tissue or blood samples were analyzed by whole-exome (WES) or targeted panel sequencing and other molecular diagnostic modalities and processed by a software system using the DDA algorithm for therapeutic decision support. Finally, a molecular tumor board (MTB) evaluated the results to provide therapy recommendations. RESULTS: Of the 100 cases with comprehensive molecular diagnostic data, 88 yielded WES and 12 panel sequencing results. DDA identified matching off-label targeted treatment options (actionability) in 72/100 cases (72%), while 57/100 (57%) showed potential drug resistance. Actionability reached 88% (29/33) by 2020 due to the continuous updates of the evidence database. MTB approved the clinical use of a DDA-top-listed treatment in 56 of 72 actionable cases (78%). The approved therapies had significantly higher aggregated evidence levels (AELs) than dismissed therapies. Filtering of WES results for targeted panels missed important mutations affecting therapy selection. CONCLUSIONS: DDA is a promising approach to overcome challenges associated with the interpretation of extensive molecular profiling in the routine care of high-risk pediatric cancers. Knowledgebase updates enable automatic interpretation of a continuously expanding gene set, a "virtual" panel, filtered out from genome-wide analysis to always maximize the performance of precision treatment planning.

A computational method for prioritizing targeted therapies in precision oncology: performance analysis in the SHIVA01 trial.

Precision oncology is currently based on pairing molecularly targeted agents (MTA) to predefined single driver genes or biomarkers. Each tumor harbors a combination of a large number of potential genetic alterations of multiple driver genes in a complex system that limits the potential of this approach. We have developed an artificial intelligence (AI)-assisted computational method, the digital drug-assignment (DDA) system, to prioritize potential MTAs for each cancer patient based on the complex individual molecular profile of their tumor. We analyzed the clinical benefit of the DDA system on the molecular and clinical outcome data of patients treated in the SHIVA01 precision oncology clinical trial with MTAs matched to individual genetic alterations or biomarkers of their tumor. We found that the DDA score assigned to MTAs was significantly higher in patients experiencing disease control than in patients with progressive disease (1523 versus 580, P = 0.037). The median PFS was also significantly longer in patients receiving MTAs with high (1000+ <) than with low (<0) DDA scores (3.95 versus 1.95 months, P = 0.044). Our results indicate that AI-based systems, like DDA, are promising new tools for oncologists to improve the clinical benefit of precision oncology.