Background: Skeletal muscle loss during treatment is associated with poor survival outcomes in patients with ovarian cancer. Although changes in muscle mass can be assessed on computed tomography (CT) scans, this labour‐intensive process can impair its utility in clinical practice. This study aimed to develop a machine learning (ML) model to predict muscle loss based on clinical data and to interpret the ML model by applying SHapley Additive exPlanations (SHAP) method.Methods: This study included the data of 617 patients with ovarian cancer who underwent primary debulking surgery and platinum‐based chemotherapy at a tertiary centre between 2010 and 2019. The cohort data were split into training and test sets based on the treatment time. External validation was performed using 140 patients from a different tertiary centre. The skeletal muscle index (SMI) was measured from pre‐ and post‐treatment CT scans, and a decrease in SMI ≥ 5% was defined as muscle loss. We evaluated five ML models to predict muscle loss, and their performance was determined using the area under the receiver operating characteristic curve (AUC) and F1 score. The features for analysis included demographic and disease‐specific characteristics and relative changes in body mass index (BMI), albumin, neutrophil‐to‐lymphocyte ratio (NLR), and platelet‐to‐lymphocyte ratio (PLR). The SHAP method was applied to determine the importance of the features and interpret the ML models.Results: The median (inter‐quartile range) age of the cohort was 52 (46–59) years. After treatment, 204 patients (33.1%) experienced muscle loss in the training and test datasets, while 44 (31.4%) patients experienced muscle loss in the external validation dataset. Among the five evaluated ML models, the random forest model achieved the highest AUC (0.856, 95% confidence interval: 0.854–0.859) and F1 score (0.726, 95% confidence interval: 0.722–0.730). In the external validation, the random forest model outperformed all ML models with an AUC of 0.874 and an F1 score of 0.741. The results of the SHAP method showed that the albumin change, BMI change, malignant ascites, NLR change, and PLR change were the most important factors in muscle loss. At the patient level, SHAP force plots demonstrated insightful interpretation of our random forest model to predict muscle loss.Conclusions: Explainable ML model was developed using clinical data to identify patients experiencing muscle loss after treatment and provide information of feature contribution. Using the SHAP method, clinicians may better understand the contributors to muscle loss and target interventions to counteract muscle loss.

Metabolite marker discovery for the detection of bladder cancer by comparative metabolomics

A number of membrane-anchored proteins are known to be released from cell surface via ectodomain shedding. The cleavage and release of membrane proteins has been shown to modulate various cellular processes and disease pathologies. Numerous studies revealed that cell membrane molecules of diverse functional groups are subjected to proteolytic cleavage, and the released soluble form of proteins may modulate various signaling processes. Therefore, in addition to the secreted protein markers that undergo secretion through the secretory pathway, the shed membrane proteins may comprise an additional resource of noninvasive and accessible biomarkers. In this context, identifying the membrane-bound proteins that will be shed has become important in the discovery of clinically noninvasive biomarkers. Nevertheless, a data repository for biological and clinical researchers to review the shedding information, which is experimentally validated, for membrane-bound protein shed markers is still lacking. In this study, the database SheddomeDB was developed to integrate publicly available data of the shed membrane proteins. A comprehensive literature survey was performed to collect the membrane proteins that were verified to be cleaved or released in the supernatant by immunological-based validation experiments. From 436 studies on shedding, 401 validated shed membrane proteins were included, among which 199 shed membrane proteins have not been annotated or validated yet by existing cleavage databases. SheddomeDB attempted to provide a comprehensive shedding report, including the regulation of shedding machinery and the related function or diseases involved in the shedding events. In addition, our published tool ShedP was embedded into SheddomeDB to support researchers for predicting the shedding event on unknown or unrecorded membrane proteins. To the best of our knowledge, SheddomeDB is the first database for the identification of experimentally validated shed membrane proteins and currently may provide the most number of membrane proteins for reviewing the shedding information. The database included membrane-bound shed markers associated with numerous cellular processes and diseases, and some of these markers are potential novel markers because they are not annotated or validated yet in other databases. SheddomeDB may provide a useful resource for discovering membrane-bound shed markers. The interactive web of SheddomeDB is publicly available at http://bal.ym.edu.tw/SheddomeDB/ .

Background Early detection of bladder cancer remains challenging because patients with early-stage bladder cancer usually have no incentive to take cytology or cystoscopy tests if they are asymptomatic. Our goal is to find non-invasive marker candidates that may help us gain insight into the metabolism of early-stage bladder cancer and be examined in routine health checks. Results We acquired urine samples from 124 patients diagnosed with early-stage bladder cancer or hernia (63 cancer patients and 61 controls). In which 100 samples were included in our marker discovery cohort, and the remaining 24 samples were included in our independent test cohort. We obtained metabolic profiles of 922 compounds of the samples by gas chromatography-mass spectrometry. Based on the metabolic profiles of the marker discovery cohort, we selected marker candidates using Wilcoxon rank-sum test with Bonferroni correction and leave-one-out cross-validation; we further excluded compounds detected in less than 60% of the bladder cancer samples. We finally selected eight putative markers. The abundance of all the eight markers in bladder cancer samples was high but extremely low in hernia samples. Moreover, the up-regulation of these markers might be in association with sugars and polyols metabolism. Conclusions In the present study, comparative urine metabolomics selected putative metabolite markers for the detection of early-stage bladder cancer. The suggested relations between early-stage bladder cancer and sugars and polyols metabolism may create opportunities for improving the detection of bladder cancer.

Ectodomain shedding of membrane proteins is a proteolytic event involved in several biological phenomena, including inflammation, development, diseases, and cancer progression. Though ectodomain shedding is a post-translational modification that plays an important role in cellular regulation, this biological phenomenon is seriously underannotated in public protein databases. Given the importance of the shedding events, we conducted a comprehensive literature review for membrane protein shedding and constructed the database, SheddomeDB in 2017. In response to user feedback, novel shedding findings, more associated biomedical events, and the advance in web technology, we revised SheddomeDB to a new version, SheddomeDB 2023. The revised SheddomeDB 2023 includes 481 protein entries across seven species; all the content was manually verified and curated. The content of SheddomeDB 2023 mainly came from a comprehensive literature survey by our newly developed semiautomated screening tool. We also integrated verified and updated cleavage and secretome information from other databases into the revision. In addition, SheddomeDB 2023 features a graphical presentation of cleavage information and a user-friendly interface for searching and browsing entries in the database. This revised comprehensive database of ectodomain shedding is expected to benefit biomedical researchers across different disciplines.

Background: Androgen deprivation therapy (ADT) increases the risk of adverse cardiovascular events in patients with prostate cancer. ADT can induce body composition change; however, the association between body composition change and cardiovascular outcomes remains unclear. This study aimed to determine the association between ADT‐induced body composition change and cardiovascular outcomes in patients with prostate cancer.Methods: This retrospective study included 681 patients with prostate cancer (410 in the derivation cohort and 271 in the external validation cohort) who underwent radiotherapy and ADT between 2008 and 2021. Computed tomography (CT) scans at baseline and 6 months post‐ADT were used to assess the changes in skeletal muscle index (ΔSMI), subcutaneous adipose tissue index (ΔSATI) and visceral adipose tissue index (ΔVATI) at the L3 vertebral level. The primary outcome was major adverse cardiovascular events (MACEs), defined as a composite of myocardial infarction, stroke, heart failure, arterial revascularization and cardiovascular death. The association between body composition changes and MACE was analysed using the SHapley Additive ExPlanations (SHAP) method and validated using the Cox proportional hazards model.Results: The median age was 72 years (interquartile range: 66–77). With a median follow‐up of 6.0 years (derivation cohort) and 6.6 years (validation cohort), 62 (15.1%) and 39 (14.4%) patients experienced MACE, respectively. Six months post‐ADT, there was a reduction in SMI, whereas SATI and VATI had increased (p < 0.001). The ΔSMI and ΔSATI were the most important features for predicting MACE in both cohorts, whereas ΔVATI and baseline body composition parameters were less influential. SMI loss was inversely correlated with MACE risk, whereas increases in SATI and VATI were positively correlated. The identified thresholds for MACE prediction were SMI loss ≥ 4.7% and SATI gain ≥ 8.2%. On multivariable Cox regression analysis, ΔSMI (hazard ratio: 1.27 per 1% decrease, p < 0.001) and ΔSATI (hazard ratio: 1.07 per 1% increase, p < 0.001) were independently associated with MACE risk; however, ΔVATI was not (hazard ratio: 0.99, p = 0.23). Stratification based on thresholds confirmed that SMI loss ≥ 4.7% (hazard ratio: 10.58, p < 0.001) and SATI gain ≥ 8.2% (hazard ratio: 3.03, p < 0.001) were independently associated with increased MACE risk.Conclusions: ADT‐induced muscle loss and increased subcutaneous adipose tissue were associated with an increased MACE risk in patients with prostate cancer. These findings highlight the need to monitor and address body composition changes in patients undergoing ADT to reduce cardiovascular risk. Future research should explore interventions to mitigate these metabolic effects and improve patient outcomes.