Deep-learning-enabled multi-omics analyses for prediction of future metastasis in cancer
dc.contributor.author | Wang, Xiaoying | |
dc.contributor.author | Duan, Maoteng | |
dc.contributor.author | Su, Po-Lan | |
dc.contributor.author | Li, Jianying | |
dc.contributor.author | Krull, Jordan | |
dc.contributor.author | Jin, Jiacheng | |
dc.contributor.author | Chen, Hu | |
dc.contributor.author | Sun, Yuhan | |
dc.contributor.author | Wu, Weidong | |
dc.contributor.author | He, Kai | |
dc.contributor.author | Carpenter, Richard L. | |
dc.contributor.author | Zhang, Chi | |
dc.contributor.author | Cao, Sha | |
dc.contributor.author | Xu, Dong | |
dc.contributor.author | Wang, Guangyu | |
dc.contributor.author | Li, Lang | |
dc.contributor.author | Xin, Gang | |
dc.contributor.author | Carbone, David P. | |
dc.contributor.author | Li, Ziha | |
dc.contributor.author | Ma, Qin | |
dc.contributor.department | Biochemistry and Molecular Biology, School of Medicine | |
dc.date.accessioned | 2025-07-14T11:02:45Z | |
dc.date.available | 2025-07-14T11:02:45Z | |
dc.date.issued | 2025-05-22 | |
dc.description.abstract | Metastasis 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.version | Preprint | |
dc.identifier.citation | Wang 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.uri | https://hdl.handle.net/1805/49399 | |
dc.language.iso | en_US | |
dc.publisher | bioRxiv | |
dc.relation.isversionof | 10.1101/2025.05.16.654579 | |
dc.rights | Attribution-NonCommercial 4.0 International | en |
dc.rights.uri | http://creativecommons.org/licenses/by-nc/4.0/ | |
dc.source | PMC | |
dc.subject | Cancer-related mortality | |
dc.subject | Metastasis | |
dc.subject | EmitGCL | |
dc.title | Deep-learning-enabled multi-omics analyses for prediction of future metastasis in cancer | |
dc.type | Article |