A new study revealed molecular features linked to more aggressive prostate cancer in a subset of patients who had been classified as low risk, highlighting biological differences that may not be apparent from clinical measures alone. The results could lead to new therapeutic strategies.
The results were published in npj Digital Medicine by researchers at KTH Royal Institute of Technology, who combined multi-omics analysis of different molecular layers with machine learning, modelling and network analysis. This new approach reveals molecular features of aggressive prostate cancer that are not captured by conventional clinical risk classification.
“The study is a good example of the type of data-driven precision medicine research we are building at KTH, combining large-scale molecular data with machine learning to address clinically relevant questions in cancer,” says assistant professor Arian Lundberg, whose A.Lundberg Lab has launched one of the largest national and international efforts to study the tumor microbiome, using extensive Swedish and global clinical cohorts.
The multi-omics approach means that the researchers look at different molecular measurements to tell the complete story of a tumor.
“For example, genomics tells us about DNA alterations, transcriptomics tells us which genes are active, and epigenomics tells us about regulatory changes that can influence gene activity,” Lundberg says.
“Instead of looking at these layers separately, we integrate them to build a more complete, patient-specific picture of tumor biology.”
Machine-learning and network-analysis were central to the study and its findings.The study's machine-learning model was developed by a team led by Assistant Professor Golnaz Taheri at the Department of Computational Science and Technology at KTH.
At the moment, the new method is at the research stage and not yet ready for clinical use. The next step is to test some of the potential therapeutic vulnerabilities suggested by the analysis, through laboratory experiments. This will help Lundberg’s team understand whether the molecular changes they identified are useful for risk prediction alone or may also point towards new therapeutic strategies.
“In the longer term, the goal is to translate these findings into more precise risk stratification, and to potentially identify patients who could benefit from earlier or more targeted treatment,” Lundberg says.
The work was supported by SciLifeLab-Knut and Alice Wallenberg Data-Driven Life Science (DDLS) program, Vetenskapsrådet (Swedish Research Council), Prostatacancerförbundet and Digital Futures.
npj Digital Medicine
A novel multiomics machine learning signature identifies rapid progression in clinically low risk prostate cancer
14-Sep-2026
A.L. is an editorial board member of Scientific Reports (Sci Rep) as part of Springer Nature’s publication. A.L. was not involved in, and had no influence over, the review of, or decision related to, this manuscript.