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.

SOSTDC1 Nuclear Translocation Facilitates BTIC Maintenance and CHD1-Mediated HR Repair to Promote Tumor Progression and Olaparib Resistance in TNBC.

Breast tumor-initiating cells (BTICs) of triple-negative breast cancer (TNBC) tissues actively repair DNA and are resistant to treatments including chemotherapy, radiotherapy, and targeted therapy. Herein, it is found that a previously reported secreted protein, sclerostin domain containing 1 (SOSTDC1), is abundantly expressed in BTICs of TNBC cells and positively correlated with a poor patient prognosis. SOSTDC1 knockdown impairs homologous recombination (HR) repair, BTIC maintenance, and sensitized bulk cells and BTICs to Olaparib. Mechanistically, following Olaparib treatment, SOSTDC1 translocates to the nucleus in an importin-α dependent manner. Nuclear SOSTDC1 interacts with the N-terminus of the nucleoprotein, chromatin helicase DNA-binding factor (CHD1), to promote HR repair and BTIC maintenance. Furthermore, nuclear SOSTDC1 bound to ß-transducin repeat-containing protein (ß-TrCP) binding motifs of CHD1 is found, thereby blocking the ß-TrCP-CHD1 interaction and inhibiting ß-TrCP-mediated CHD1 ubiquitination and degradation. Collectively, these findings identify a novel nuclear SOSTDC1 pathway in regulating HR repair and BTIC maintenance, providing insight into the TNBC therapeutic strategies.

IL1R2 Blockade Alleviates Immunosuppression and Potentiates Anti-PD-1 Efficacy in Triple-Negative Breast Cancer.

Triple-negative breast cancer (TNBC) is an aggressive subtype of breast cancer with limited therapeutic options. IL1 receptor type 2 (IL1R2) promotes breast tumor-initiating cell (BTIC) self-renewal and tumor growth in TNBC, indicating that targeting it could improve patient treatment. In this study, we observed that IL1R2 blockade strongly attenuated macrophage recruitment and the polarization of tumor-associated macrophages (TAM) to inhibit BTIC self-renewal and CD8+ T-cell exhaustion, which resulted in reduced tumor burden and prolonged survival in TNBC mouse models. IL1R2 activation by TAM-derived IL1ß increased PD-L1 expression by interacting with the transcription factor Yin Yang 1 (YY1) and inducing YY1 ubiquitination and proteasomal degradation in both TAMs and TNBC cells. Loss of YY1 alleviated the transcriptional repression of c-Fos, which is a transcriptional activator of PDL-1. Combined treatment with an IL1R2-neutralizing antibodies and anti-PD-1 led to enhanced antitumor efficacy and reduced TAMs, BTICs, and exhausted CD8+ T cells. These results suggest that IL1R2 blockade might be a strategy to potentiate immune checkpoint blockade efficacy in TNBC to improve patient outcomes. Significance: IL1R2 in both macrophages and breast cancer cells orchestrates an immunosuppressive tumor microenvironment by upregulating PD-L1 expression and can be targeted to enhance the efficacy of anti-PD-1 in triple-negative breast cancer.