Machine Learning Assistants Construct Oxidative Stress-Related Gene Signature and Discover Potential Therapy Targets for Acute Myeloid Leukemia

Machine learning in TCM with natural products and molecules: current status and future perspectives

Traditional Chinese medicine (TCM) has been practiced for thousands of years with clinical efficacy. Natural products and their effective agents such as artemisinin and paclitaxel have saved millions of lives worldwide. Artificial intelligence is being increasingly deployed in TCM. By summarizing the principles and processes of deep learning and traditional machine learning algorithms, analyzing the application of machine learning in TCM, reviewing the results of previous studies, this study proposed a promising future perspective based on the combination of machine learning, TCM theory, chemical compositions of natural products, and computational simulations based on molecules and chemical compositions. In the first place, machine learning will be utilized in the effective chemical components of natural products to target the pathological molecules of the disease which could achieve the purpose of screening the natural products on the basis of the pathological mechanisms they target. In this approach, computational simulations will be used for processing the data for effective chemical components, generating datasets for analyzing features. In the next step, machine learning will be used to analyze the datasets on the basis of TCM theories such as the superposition of syndrome elements. Finally, interdisciplinary natural product-syndrome research will be established by unifying the results of the two steps outlined above, potentially realizing an intelligent artificial intelligence diagnosis and treatment model based on the effective chemical components of natural products under the guidance of TCM theory. This perspective outlines an innovative application of machine learning in the clinical practice of TCM based on the investigation of chemical molecules under the guidance of TCM theory.

Comprehensive analysis of prognosis of cuproptosis-related oxidative stress genes in multiple myeloma

Introduction: Multiple myeloma (MM) is a highly heterogeneous hematologic malignancy. The patients’ survival outcomes vary widely. Establishing a more accurate prognostic model is necessary to improve prognostic precision and guide clinical therapy.

Methods: We developed an eight-gene model to assess the prognostic outcome of MM patients. Univariate Cox analysis, Least absolute shrinkage and selection operator (LASSO) regression, and multivariate Cox regression analyses were used to identify the significant genes and construct the model. Other independent databases were used to validate the model.

Results: The results showed that the overall survival of patients in the high-risk group was signifificantly shorter compared with that of those in the low-risk group. The eight-gene model demonstrated high accuracy and reliability in predicting the prognosis of MM patients.

Discussion: Our study provides a novel prognostic model for MM patients based on cuproptosis and oxidative stress. The eight-gene model can provide valid predictions for prognosis and guide personalized clinical treatment. Further studies are needed to validate the clinical utility of the model and explore potential therapeutic targets.

A novel oxidative stress- and ferroptosis-related gene prognostic signature for distinguishing cold and hot tumors in colorectal cancer

Oxidative stress and ferroptosis exhibit crosstalk in many types of human diseases, including malignant tumors. We aimed to develop an oxidative stress- and ferroptosis-related gene (OFRG) prognostic signature to predict the prognosis and therapeutic response in patients with colorectal cancer (CRC). Thirty-four insertion genes between oxidative stress-related genes and ferroptosis-related genes were identified as OFRGs. We then performed bioinformatics analysis of the expression profiles of 34 OFRGs and clinical information of patients obtained from multiple datasets. Patients with CRC were divided into three OFRG clusters, and differentially expressed genes (DEGs) between clusters were identified. OFRG clusters correlated with patient survival and immune cell infiltration. Prognosis-related DEGs in three clusters were used to calculate the risk score, and a prognostic signature was constructed according to the risk score. In this study, patients in the low-risk group had better prognosis, higher immune cell infiltration levels, and better responses to fluorouracil-based chemotherapy and immune checkpoint blockade therapy than high-risk patients; these results were successfully validated with multiple independent datasets. Thus, low-risk CRC could be defined as hot tumors and high-risk CRC could be defined as cold tumors. To further identify potential biomarkers for CRC, the expression levels of five signature genes in CRC and adjacent normal tissues were further verified via an in vitro experiment. In conclusion, we identified 34 OFRGs and constructed an OFRG-related prognostic signature, which showed excellent performance in predicting survival and therapeutic responses for patients with CRC. This could help to distinguish cold and hot tumors in CRC, and the results might be helpful for precise treatment protocols in clinical practice.