WALTHAM, MASSACHUSETTS / ACCESS Newswire / April 28, 2025 / Data4Cure, Inc., a leading biomedical data-to-knowledge company, today announced the presentation of two new research abstracts at the 2025 American Association for Cancer Research (AACR) Annual Meeting. The presentations highlight Data4Cure's advances in AI-based approaches for drug target discovery and large-scale cancer subtyping using foundation models applied to large collections of sequencing data.
In the first study, titled "Knowledge graph AI-based prioritization of drug target candidates" (Abstract LB112/13), Data4Cure researchers leveraged the company's large-scale biomedical knowledge graph encompassing over 4 billion relations across more than 1 million entities including genes, diseases, drugs, pathways, cell types and tissues. To prioritize candidate cancer drug targets, they trained and optimized 17 state-of-the-art knowledge graph embedding (KGE) and graph neural network (GNN) models. The best such models significantly outperformed standard machine learning approaches, uncovered clusters of predicted targets enriched for specific biological functions and identified novel target candidates, including within previously underexplored functional classes.
The second study, titled "Foundation model integration of >180,000 bulk RNA-seq samples identifies cancer subtypes with prognostic and treatment response associations" (Abstract LB343/6), describes the development of RNA1, a novel transformer-based foundation model trained on over 180,000 bulk RNA-seq profiles. RNA1 enables systematic assignment of cancer samples to molecular subtypes and the discovery of new subtypes across more than 36,000 tumor samples. RNA1-based subtyping shows significant associations with survival outcomes as well as with drug response outcomes on published clinical trial datasets, outperforming previously published subtyping approaches across a majority of evaluated benchmarks.
"Our knowledge graph and foundation model approaches are aimed at a more comprehensive, data-driven understanding of cancer biology," said Janusz Dutkowski, Ph.D., CEO and Co-Founder of Data4Cure. "By integrating massive, diverse datasets using advanced AI, we can help uncover new therapeutic opportunities and inform patient stratification strategies."
"Our work illustrates the power of integrated data and AI to systematically map complex biological relationships and reveal actionable insights at scale," said Roy Ronen, Ph.D., CTO of Data4Cure. "It is deeply motivating to develop tools that support our pharmaceutical and biotech partners and the broader research community in advancing new discoveries and improving patient outcomes."
Both projects build upon Data4Cure's Biomedical Intelligence Cloud platform and its mission to help turn complex multi-modal data into knowledge that drives biomedical research and therapeutic innovation.
About Data4Cure
Data4Cure is a leading biomedical AI company specializing in biology-informed AI tools for semantic data integration, analytics, and knowledge synthesis. The company's flagship product, the Biomedical Intelligence® Cloud, helps pharmaceutical and biotech organizations turn multimodal data into knowledge and insights to drive drug discovery and development. By connecting diverse data sources through its extensive continuously updated knowledge graph - spanning over 4 billion relations from public and proprietary datasets - the platform enables the discovery of new insights into complex biological mechanisms. Data4Cure's latest AI capabilities include automated data curation, data and literature-evidence synthesis, multi-task foundation models, and Knowledge Graph AI-based target intelligence. To learn more about Data4Cure visit www.data4cure.com.
Contact Information
Anna Iwinska-Nowak
Media and Marketing, Data4Cure, Inc.
media@data4cure.com
SOURCE: Data4Cure, Inc.
