AJS-5 Forefront challenge in the SCRUM-Japan utilizing Artificial Intelligence (AI) – Virtual Sequencing (VSQ) and QA Commons (QAC) projects and beyond

Abstract

Recent progress in artificial intelligence (AI) technologies make big data analyses possible, which may offer more precise, rapid, valuable information in terms of clinical implementation of precision oncology. Numerous genetic and epigenetic abnormalities may lead to various morphologies of cancer. However, exactly which gene abnormality causes which morphology is unknown. The SCRUM-Japan Genesis Virtual Sequencing (VSQ) Project aims to investigate a novel algorithm by synergistically fusing deep learning (DL) technology and pathological diagnostics for the prediction of cancer genome abnormalities. This was achieved by elucidating the association between the morphological findings and genetic abnormalities, including BRAF V600E mutations and MSI status directly linked to the therapeutic strategies for advanced colorectal cancer (CRC) patients, indicating that VSQ can appropriately predict these alterations in advanced CRC, potentially without performing NGS tests and may also enable a prompt initiation of systemic treatments in CRC patients. Clinical sequencing of tumor tissue or circulating tumor DNA (ctDNA) enables the identification of genomic alterations that can be targeted therapeutically, and the importance of knowledge-based curation systems is on the rise. We assessed the utility of the AI-based curation system, QA Commons (QAC) for clinical sequencing. It demonstrated the utility of QAC in treatment decision making by tissue or ctDNA sequencing, especially in information of clinical trials. We will initiate the 4th stage SCRUM-Japan MONSTAR-SCREEN project as -from genomics to multi-omics with AI- since April 2021, to assess clinical utility for analyzing tissue-based WES, WTS, and Protein analyses as well as circulating tumor NA (nucleic acid) analyses in all solid tumors, utilizing the DL technology. In this ASCO-JSMO joint symposium, I would like to present the current status and perspective in the SCRUM-Japan Project.