Rheumatoid arthritis (RA) is an autoimmune disease causing progressive joint damage. Early diagnosis and treatment is critical, but remains challenging due to RA complexity and heterogeneity. Machine learning (ML) techniques may enhance RA management by identifying patterns within multidimensional biomedical data to improve classification, diagnosis, and treatment predictions. In this review, we summarize the applications of ML for RA management. Emerging studies or applications have developed diagnostic and predictive models for RA that utilize a variety of data modalities, including electronic health records, imaging, and multi-omics data. High-performance supervised learning models have demonstrated an Area Under the Curve (AUC) exceeding 0.85, which is used for identifying RA patients and predicting treatment responses. Unsupervised learning has revealed potential RA subtypes. Ongoing research is integrating multimodal data with deep learning to further improve performance. However, key challenges remain regarding model overfitting, generalizability, validation in clinical settings, and interpretability. Small sample sizes and lack of diverse population testing risks overestimating model performance. Prospective studies evaluating real-world clinical utility are lacking. Enhancing model interpretability is critical for clinician acceptance. In summary, while ML shows promise for transforming RA management through earlier diagnosis and optimized treatment, larger scale multisite data, prospective clinical validation of interpretable models, and testing across diverse populations is still needed. As these gaps are addressed, ML may pave the way towards precision medicine in RA.

Lysine (K)-specific demethylase 6B (KDM6B), a stress-inducible H3K27me3 demethylase, plays oncogenic or antitumoral roles in malignant tumors depending on the type of tumor cell. However, how this histone modifier affects the progression of prostate cancer (PCa) is still unknown. Here we analyzed sequenced gene expression data and tissue microarray to explore the expression features and prognostic value of KDM6B in PCa. Further, we performed in vitro cell biological experiments and in vivo nude mouse models to reveal the biological function, upstream and downstream regulation mechanism of KDM6B. In addition, we investigated the effects of a KDM6B inhibitor, GSK-J4, on PCa cells. We showed that KDM6B overexpression was observed in PCa, and elevated KDM6B expression was associated with high Gleason Score, low serum prostate-specific antigen level and shorted recurrence-free survival. Moreover, KDM6B prompted proliferation, migration, invasion and cell cycle progression and suppressed apoptosis in PCa cells. GSK-J4 administration could significantly suppress the biological function of KDM6B in PCa cells. KDM6B is involved in the development of castration-resistant prostate cancer (CRPC), and combination of MDV3100 plus GSK-J4 is effective for CRPC and MDV3100-resistant CRPC. Mechanism exploration revealed that androgen receptor can decrease the transcription of KDM6B and that KDM6B demethylates H3K27me3 at the cyclin D1 promoter and cooperates with smad2/3 to prompt the expression of cyclin D1. In conclusion, our study demonstrates that KDM6B is an androgen receptor regulated gene and plays oncogenic roles by promoting cyclin D1 transcription in PCa and GSK-J4 has the potential to be a promising agent for the treatment of PCa.

The landscape and characteristics of circulating exosomal messenger RNAs (emRNAs) are poorly understood, which hampered the accurate detection of circulating emRNAs. Through comparing RNA sequencing data of circulating exosomes with the corresponding data in tissues, we illustrated the different characteristics of emRNAs compared to tissue mRNAs. We then developed an improved strategy for emRNA detection based on the features of circulating emRNAs. Using the optimized detection strategy, we further validated prostate cancer (PCa) associated emRNAs discovered by emRNA-seq in a large cohort of patients and identified emRNA signatures for PCa screening and diagnosis using logistic regression analysis. The receiver operating characteristic curve (ROC) analysis showed that the circulating emRNA-based screening signature yielded an area under the ROC curve (AUC) of 0.948 in distinguishing PCa patients from healthy controls. The circulating emRNA-based diagnostic signature also showed a great performance in predicting prostate biopsy results (AUC: 0.851). In conclusion, our study developed an optimized emRNA detection strategy and identified novel emRNA signatures for the detection of PCa.

Background: There are no proven tumor biomarkers for the early diagnosis of clear cell renal cell carcinoma (ccRCC) thus far. This study aimed to identify novel biomarkers of ccRCC based on exosomal mRNA (emRNA) profiling and develop emRNA-based signatures for the early detection of ccRCC. Methods: Four hundred eighty-eight participants, including 226 localized ccRCCs, 73 patients with benign renal masses, and 189 healthy controls, were recruited. Circulating emRNA sequencing was performed in 12 ccRCCs and 22 healthy controls in the discovery phase. The candidate emRNAs were evaluated with 108 ccRCCs and 70 healthy controls in the test and training phases. The emRNA-based signatures were developed by logistic regression analysis and validated with additional cohorts of 106 ccRCCs, 97 healthy controls, and 73 benign individuals. Results: Five emRNAs, CUL9, KMT2D, PBRM1, PREX2, and SETD2, were identified as novel potential biomarkers of ccRCC. We further developed an early diagnostic signature that comprised KMT2D and PREX2 and a differential diagnostic signature that comprised CUL9, KMT2D, and PREX2 for RCC detection. The early diagnostic signature displayed high accuracy in distinguishing ccRCCs from healthy controls, with areas under the receiver operating characteristic curve (AUCs) of 0.836 and 0.830 in the training and validation cohorts, respectively. The differential diagnostic signature also showed great performance in distinguishing ccRCCs from benign renal masses (AUC = 0.816), including solid masses (AUC = 0.810) and cystic masses (AUC = 0.832). Conclusions: We established and validated novel emRNA-based signatures for the early detection of ccRCC and differential diagnosis of uncertain renal masses. These signatures could be promising and noninvasive biomarkers for ccRCC detection and thus improve the prognosis of ccRCC patients.

Cancer remains a leading global cause of mortality, making early detection crucial for improving survival outcomes. The study aims to develop a machine learning-enabled blood-derived exosomal RNA profiling platform for multi-cancer detection and localization. In this multi-phase, multi-center study, we analyzed RNA from exosomes derived from peripheral blood plasma in 818 participants across eight cancer types during the discovery phase. Machine learning techniques were applied to identify potential pan-cancer biomarkers. During the screening and model validation phases, the sample size was progressively expanded to 1,385 participants in two steps, while the candidate biomarkers were refined into a set of 12 exosomal tumor RNA signatures (ETR.sig). In the subsequent model construction phase, diagnostic models were developed using the expanded cohort and ETR.sig. Statistical analyses included the calculation of receiver operating characteristic (ROC) curves and AUC values to assess the models' ability to distinguish cancer cases from controls and determine tumor origins. To further validate and explore the biological relevance of the identified biomarkers, we integrated tissue RNA-seq, single-cell data, and clinical information. Machine learning analysis initially identified 33 candidate biomarkers, which were narrowed down to 20 ETR.sig in the screening phase and 12 ETR.sig in the validation phase. In the model construction phase, a diagnostic model based on ETR.sig, built using the Random Forest (RF) algorithm, showed excellent performance with an AUC of 0.915 for distinguishing pan-cancer from controls. The multi-class classification model also demonstrated strong classification power, with macro-average and micro-average AUCs of 0.983 and 0.985, respectively, for differentiating between eight cancer types. Additionally, tumor origin classification using the RF-based diagnostic models achieved high AUC values: BRCA 0.976, COAD 0.98, KIRC 0.947, LIHC 0.967, LUAD 0.853, OV 0.972, PAAD 0.977, and PRAD 0.898. Integration of tissue RNA-seq, single-cell data, and clinical information revealed key associations between ETR.sig-related genes and tumor development. The study demonstrates the robust potential of exosomal RNA as a minimally invasive biomarker resource for cancer detection. The developed ETR.sig platform offers a promising tool for precision oncology and broad-spectrum cancer screening, integrating advanced computational models with nanoscale vesicle biology for accurate and rapid diagnosis.