Browsing by Author "Krull, Jordan"

Now showing 1 - 1 of 1
  • Thumbnail Image
    Item
    Deep-learning-enabled multi-omics analyses for prediction of future metastasis in cancer
    (bioRxiv, 2025-05-22) Wang, Xiaoying; Duan, Maoteng; Su, Po-Lan; Li, Jianying; Krull, Jordan; Jin, Jiacheng; Chen, Hu; Sun, Yuhan; Wu, Weidong; He, Kai; Carpenter, Richard L.; Zhang, Chi; Cao, Sha; Xu, Dong; Wang, Guangyu; Li, Lang; Xin, Gang; Carbone, David P.; Li, Ziha; Ma, Qin; Biochemistry and Molecular Biology, School of Medicine
    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.