Deep-learning-enabled multi-omics analyses for prediction of future metastasis in cancer

dc.contributor.authorWang, Xiaoying
dc.contributor.authorDuan, Maoteng
dc.contributor.authorSu, Po-Lan
dc.contributor.authorLi, Jianying
dc.contributor.authorKrull, Jordan
dc.contributor.authorJin, Jiacheng
dc.contributor.authorChen, Hu
dc.contributor.authorSun, Yuhan
dc.contributor.authorWu, Weidong
dc.contributor.authorHe, Kai
dc.contributor.authorCarpenter, Richard L.
dc.contributor.authorZhang, Chi
dc.contributor.authorCao, Sha
dc.contributor.authorXu, Dong
dc.contributor.authorWang, Guangyu
dc.contributor.authorLi, Lang
dc.contributor.authorXin, Gang
dc.contributor.authorCarbone, David P.
dc.contributor.authorLi, Ziha
dc.contributor.authorMa, Qin
dc.contributor.departmentBiochemistry and Molecular Biology, School of Medicine
dc.date.accessioned2025-07-14T11:02:45Z
dc.date.available2025-07-14T11:02:45Z
dc.date.issued2025-05-22
dc.description.abstractMetastasis remains the leading cause of cancer-related mortality, yet predicting future metastasis is a major clinical challenge due to the lack of validated biomarkers and effective assessment methods. Here, we present EmitGCL, a deep-learning framework that accurately predicts future metastasis and its corresponding biomarkers. Based on a comprehensive benchmarking comparison, EmitGCL outperformed other computational tools across six cancer types from seven cohorts of patients with superior sensitivity and specificity. It captured occult metastatic cells in a patient with a lymph node-negative breast cancer, who was declared to have no evidence of disease by conventional imaging methods but was later confirmed to have a metastatic disease. Notably, EmitGCL identified HSP90AA1 and HSP90AB1 as predictable biomarkers for future breast cancer metastasis, which was validated across five independent cohorts of patients (n=420). Furthermore, we demonstrated YY1 transcription factor as a key driver of breast cancer metastasis which was validated through in-silico and CRISPR-based migration assays, suggesting that YY1 is a potential therapeutic target for deterring metastasis.
dc.eprint.versionPreprint
dc.identifier.citationWang X, Duan M, Su PL, et al. Deep-learning-enabled multi-omics analyses for prediction of future metastasis in cancer. Preprint. bioRxiv. 2025;2025.05.16.654579. Published 2025 May 22. doi:10.1101/2025.05.16.654579
dc.identifier.urihttps://hdl.handle.net/1805/49399
dc.language.isoen_US
dc.publisherbioRxiv
dc.relation.isversionof10.1101/2025.05.16.654579
dc.rightsAttribution-NonCommercial 4.0 Internationalen
dc.rights.urihttp://creativecommons.org/licenses/by-nc/4.0/
dc.sourcePMC
dc.subjectCancer-related mortality
dc.subjectMetastasis
dc.subjectEmitGCL
dc.titleDeep-learning-enabled multi-omics analyses for prediction of future metastasis in cancer
dc.typeArticle
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Wang2025Deep-CCBYNC.pdf
Size:
1.25 MB
Format:
Adobe Portable Document Format
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
2.04 KB
Format:
Item-specific license agreed upon to submission
Description: