Author:
Pan Chenxi,He Yi,Wang He,Yu Yang,Li Lu,Huang Lingling,Lyu Mengge,Ge Weigang,Yang Bo,Sun Yaoting,Guo Tiannan,Liu Zhiyu
Abstract
AbstractBackgroundProstate cancer (PCa) is the second most prevalent malignancy and the fifth cause of cancer-related deaths in men. A crucial challenge is identifying the population at risk of rapid progression from hormone-sensitive PCa (HSPC) to the lethal castration-resistant PCa (CRPC).MethodsWe collected 78 HSPC biopsies and measured their proteomes using pressure cycling technology and a pulsed data-independent acquisition pipeline. The proteomics data and clinical metadata were used to generate models for classifying HSPC patients and predicting the development of each case.ResultsWe quantified 7,961 proteins using the HSPC biopsies. A total of 306 proteins were differentially expressed between patients with a long- or short-term progression to CRPC. Using a random forest model, we identified ten proteins that significantly discriminated long-from short-term cases, which were used to classify PCa patients with an 86% accuracy. Next, two clinical parameters (Gleason sum and total PSA) and five proteins (DPT, ARGEF1, UTP23, CMAS, and ANAPC4) were found to be significantly associated with rapid disease progression. A nomogram model using these seven features was generated for stratifying patients into groups with significant progression disparities (p-value = 5.2 × 10−9).ConclusionWe identified proteins associated with a fast progression to CRPC and an unfavorable prognosis. Based on these proteins, our machine learning and nomogram models stratified HSPC into high- and low-risk groups and predict their prognoses. These tools may aid clinicians in predicting the progression of patients, guiding individualized clinical management and decisions.
Publisher
Cold Spring Harbor Laboratory