bims-fragic 2025-06-01 papers

Issue of 2025–06–01
two papers selected by
Laura Mannarino, Humanitas Research

Nat Med. 2025 May 27.

Early detection of multiple cancer types using multidimensional cell-free DNA fragmentomics.

The multicancer early detection (MCED) test has the potential to enhance current cancer-screening methods. We evaluated a new MCED test that analyzes plasma cell-free DNA using genetic- and fragmentomics-based features from whole-genome sequencing. The present study included an internal validation cohort of 3,021 patients with cancer and 3,370 noncancer controls, and an independent cohort of 677 patients with cancer and 687 noncancer individuals. The results demonstrated an overall sensitivity of 87.4%, specificity of 97.8% and tissue-of-origin prediction accuracy of 82.4% in the independent validation cohort. Preliminary results from a prospective study of 3,724 asymptomatic participants showed a sensitivity of 53.5% (predominantly early stage cancers) and specificity of 98.1%. These findings indicate that the MCED test has strong potential to improve early cancer detection and support clinical decision-making.

DOI: https://doi.org/10.1038/s41591-025-03735-2

AMIA Annu Symp Proc. 2024 ;2024 684-692

Unlocking Early Cancer Detection: Leveraging Machine Learning in Cell-Free DNA Analysis for Precision Oncology.

Hui Li, Jinlian Wang, Hongfang Liu.

This study introduces a groundbreaking approach to early cancer detection through the analysis of cell-free DNA (cfDNA), utilizing machine learning algorithms to navigate the complexities of low circulating tumor DNA (ctDNA) fractions and genetic heterogeneity. CfDNA, found in bodily fluids and comprising fragments from apoptotic or necrotic cells, offers a non-invasive means to identify cancer signals. With ctDNA-a subset of cfDNA from cancer cells-serving as a biomarker, the potential for detecting cancer at its earliest stages is vastly improved, enhancing treatment effectiveness and patient prognosis. However, the challenges of distinguishing cancer-specific signatures within cfDNA due to low ctDNA levels and the noise of genetic heterogeneity necessitate advanced methods beyond traditional mutation analysis. Leveraging high-throughput sequencing technologies and the precision of machine learning, our research aims to surmount these obstacles by identifying nuanced cancer signatures within cfDNA sequencing data. Machine learning's capability to model complex data relationships allows for the differentiation of subtle oncogenic patterns from background noise, thereby increasing the diagnostic accuracy of liquid biopsies. This paper outlines our exploration into employing machine learning for early cancer detection via cfDNA, detailing our method of transforming sequencing data into analyzable formats, enhancing signal detection through a sliding window technique, and predicting true tumor-origin fragments. By advancing cfDNA-based cancer diagnostics, this research not only signifies a leap towards more sensitive and specific early-stage cancer detection but also opens avenues for personalized oncology, where treatment strategies are informed by the unique genetic profile unveiled through cfDNA analysis. Our findings underscore the potential of integrating artificial intelligence with liquid biopsy technologies to revolutionize cancer diagnostics, offering new hope for early detection and personalized treatment pathways.