Integration of machine learning for developing a prognostic signature related to programmed cell death in colorectal cancer.

BACKGROUND: Colorectal cancer (CRC) presents a significant global health burden, characterized by a heterogeneous molecular landscape and various genetic and epigenetic alterations. Programmed cell death (PCD) plays a critical role in CRC, offering potential targets for therapy by regulating cell elimination processes that can suppress tumor growth or trigger cancer cell resistance. Understanding the complex interplay between PCD mechanisms and CRC pathogenesis is crucial. This study aims to construct a PCD-related prognostic signature in CRC using machine learning integration, enhancing the precision of CRC prognosis prediction. METHOD: We retrieved expression data and clinical information from the Cancer Genome Atlas and Gene Expression Omnibus (GEO) datasets. Fifteen forms of PCD were identified, and corresponding gene sets were compiled. Machine learning algorithms, including Lasso, Ridge, Enet, StepCox, survivalSVM, CoxBoost, SuperPC, plsRcox, random survival forest (RSF), and gradient boosting machine, were integrated for model construction. The models were validated using six GEO datasets, and the programmed cell death score (PCDS) was established. Further, the model's effectiveness was compared with 109 transcriptome-based CRC prognostic models. RESULT: Our integrated model successfully identified differentially expressed PCD-related genes and stratified CRC samples into four subtypes with distinct prognostic implications. The optimal combination of machine learning models, RSF + Ridge, showed superior performance compared with traditional methods. The PCDS effectively stratified patients into high-risk and low-risk groups, with significant survival differences. Further analysis revealed the prognostic relevance of immune cell types and pathways associated with CRC subtypes. The model also identified hub genes and drug sensitivities relevant to CRC prognosis. CONCLUSION: The current study highlights the potential of integrating machine learning models to enhance the prediction of CRC prognosis. The developed prognostic signature, which is related to PCD, holds promise for personalized and effective therapeutic interventions in CRC.

[Effects of NaHS on MBP and learning and memory in hippocampus of mice with spinocerebellar ataxia].

Objective: To investigate the effects of exogenous NaHS on myelin basic protein (MBP) and learning and memory of hippocampal neurons in mice with spinocerebellar ataxia type 3 (SCA3) and its therapeutic significance.Methods: Twelve male normal mice were randomly selected as normal control group (NC Group), and 48 SCA3 mice were randomly selected as SCA3 model group (M Group), low dose group (NL Group, 10 µmol/kg), medium dose group (NM Group, 50µmol/kg) and high dose group (NH Group, 100 µmol/kg), 12 rats in each group. The drug treated groups were injected with NaHS intraperitoneally once a day for 4 weeks. The changes of learning and memory ability of SCA3 mice before and after the intervention of different doses of NaHS were determined by Morris water maze, the content of hydrogen sulfide (H2S) in hippocampus was measured by spectrophotometry, the expression of MBP was detected by immunohistochemistry, and the morphological changes of neuron myelin sheath were observed by electron microscope. Results: Compared with the control group, the learning and memory ability of SCA3 mice was decreased significantly (P＜0.05), and the content of H2S in hippocampus was decreased (P＜0.05). After different doses of exogenous NaHS treatment, the learning and memory ability was improved in different degrees (P＜0.05), and the contents of H2S and MBP in hippocampus of SCA3 mice were also improved in different degrees (P＜0.05). Conclusion: Exogenous NaHS may increase the contents of H2S and MBP in the hippocampus of SCA3 mice, which may have a protective effect on the neurons, and then improve the learning and memory ability of SCA3 mice, and provide a new idea for the treatment of SCA3.