Sihua Wang

Background and Objective: Lung transplantation (LTx) serves as the only definitive therapy for end-stage lung disease, yet, its clinical success is chronically constrained by the severe shortage of donor organs and the high incidence of postoperative complications such as primary graft dysfunction (PGD) and chronic rejection. As a transformative technology, artificial intelligence (AI) demonstrates substantial potential to address these systemic challenges and reshape the entire transplantation clinical pathway. The primary purpose of this article is to consolidate existing research findings to comprehensively assess the current status, technical mechanisms, and future ecosystem of AI applications in various stages of LTx, with a focus on its profound implications for organ allocation optimization, surgical assistance, complication prediction, and personalized medication management. Methods: A systematic search was performed in PubMed from inception to September 30, 2025, using a combination of Medical Subject Headings (MeSH) terms and keywords related to “artificial intelligence” (e.g., machine learning, deep learning) and “lung transplantation”. Inclusion criteria focused on English-language original research, reviews, and landmark case reports. Key Content and Findings: In the pre-transplant phase, AI optimizes organ allocation by shifting focus from “urgency” to “utility” and enhances donor assessment and matching via computer vision. Intraoperatively, AI integrates with robotic platforms to enable augmented reality navigation and real-time risk warnings. Post-transplant applications, currently the most mature area, utilize machine learning to accurately predict complications like PGD and chronic lung allograft dysfunction (CLAD), enabling non-invasive monitoring (e.g., electronic nose) and personalized immunosuppressant dosing through deep learning analysis of time-series data. Conclusions: AI has demonstrated distinct advantages in improving decision-making precision, optimizing resource allocation, and improving patient prognosis. However, the heterogeneity of data quality, model interpretability, and the complexity of clinical integration remain major barriers to its widespread adoption. Future efforts need to construct a data ecosystem based on FAIR (Findable, Accessible, Interoperable, and Reusable) principles and strengthen human-machine collaboration mechanisms to ensure that algorithmic precision translates into substantive improvements in patient survival and quality of life.

Background: Our previous findings have underscored the role of innate immunity in obliterative bronchiolitis (OB). However, despite the central importance of the cyclic GMP‒AMP synthase (cGAS)/stimulator of interferon genes (STING) signalling pathway in innate immune responses, its specific contribution to OB progression remains largely unexplored.Methods: A murine orthotopic tracheal transplantation model was established to replicate OB pathogenesis. RNA sequencing and single‐cell RNA sequencing data were analysed to investigate mechanisms underlying OB. Key molecules of the cGAS/STING pathway were assessed using immunofluorescence staining. Macrophage‐specific Sting1 knockout mice were generated to investigate the role of the cGAS/STING pathway in OB. Haematoxylin and eosin staining and Masson's trichrome staining were utilised to evaluate allograft stenosis and fibrosis. Immune cell infiltration and cytokine expression were analysed using immunofluorescence staining and qRT‐PCR. Flow cytometry was used to characterise splenic T‐cell subsets and assess co‐stimulatory molecule expression in macrophages.Results: The cGAS/STING pathway was upregulated in macrophages infiltrating allografts. Macrophage‐specific Sting1 knockout significantly attenuated alloreactive T‐cell responses and alleviated OB. Furthermore, Sting1 deletion reduced the expression of inflammatory marker NOS2, antigen‐presenting molecule MHC class II and co‐stimulatory molecules (CD80 and CD86) in macrophages. Mechanistically, Sting1 knockout inhibited the production of interferon‐α2 (IFN‐α2), while the protective effect of macrophage‐specific Sting knockout was reversed by IFN‐α2 administration. Importantly, STING inhibition enhanced the allograft tolerance‐promoting effects of cytotoxic T‐lymphocyte‐associated antigen 4‐Ig (CTLA4‐Ig), leading to the preservation of the airway epithelium.Conclusions: Our study demonstrated that cGAS/STING signalling pathway exacerbated allograft rejection in an IFN‐α2‐dependent manner. These findings provide insights into potential novel strategies for prolonging allograft survival.Key points: cGAS/STING signalling pathway was activated in macrophages infiltrating allografts. cGAS/STING signalling pathway in macrophages exacerbated allograft rejection, promoted antigen‐presenting ability of macrophages and enhanced alloreactive T‐cell responses in an IFN‐α2‐dependent manner. STING inhibition potentiated the therapeutic efficacy of CTLA4‐Ig in OB.

Neoadjuvant chemoimmunotherapy has demonstrated significant benefit for resectable non-small-cell lung cancer (NSCLC) excluding known EGFR/ALK genetic alterations. Recent evidence has shown that neoadjuvant chemoimmunotherapy could be clinically valuable in resectable localized driver gene-mutant NSCLC, though the data still lack robust support, especially for rare oncogenic mutations. Here, we report a patient with stage IIIA lung adenocarcinoma with a RET fusion gene and high expression of PD-L1 who underwent neoadjuvant chemoimmunotherapy and successfully attained a pathologic complete response. The patient has survived for 12 months with no recurrence or metastases after surgery. Our case suggests that this treatment strategy may be an alternative therapeutic option for resectable RET fusion-positive NSCLC patients.

Immunotherapy can improve the survival of patients with advanced lung squamous cell carcinoma (LUSC). T cytotoxic cells are one of the main members of the immune microenvironment. Herein, we aimed to identify the roles of T-cell cytotoxic markers interleukin 18 (IL18) receptor 1 (IL18R1) in the LUSC progression using bioinformatics, clinical tissue specimen, and cell experiment. We assessed the association between the IL18R1 expression and immune infiltration and IL18R1-related competing RNA network. The IL18R1 expression was downregulated in the LUSC tissues. The IL18R1 expression downregulation was associated with diagnosis and short overall survival and disease-specific survival, and it was also an independent risk factor for dismal survival time in LUSC. IL18R1-related nomograms predicted the survival time of patients with LUSC. IL18R1 overexpression inhibited the proliferation, migration, and invasion of LUSC cells. The IL18R1 expression was significantly associated with the microenvironment (stromal, immune, and estimate scores), immune cells (such as the T cells, cytotoxic cells, CD8 T cells), and immune cell markers (such as the CD8A, PD-1, and CTLA4) in LUSC. AC091563.1 and RBPMS-AS1 downregulation was positively associated with the IL18R1 expression, negatively associated with the miR-128-3p expression, and associated with short disease-specific survival and progression in LUSC. In conclusion, IL18R1 was significantly downregulated and associated with the prognosis and immune microenvironment. IL18R1 overexpression inhibits the growth and migration of cancer cells in LUSC. Furthermore, AC091563.1 and RBPMS-AS1 might compete with IL18R1 to bind miR-128-3p for participating in LUSC progression. These results showed that IL18R1 is a biomarker for evaluating the prognosis of patients with LUSC.

The roles and mechanisms of T-cell receptor (TCR)-associated transmembrane adaptor 1 (TRAT1) in lung adenocarcinoma (LAC) have not yet been reported in the relevant literature. Therefore, this study aimed to understand the roles and mechanisms of TRAT1 in LAC using bioinformatics and in vitro experiments. TRAT1 expression levels in LAC samples were analysed using various databases. TRAT1 co-expressed genes were acquired by the correlation analysis of LAC tissues. The functional mechanisms and protein network of TRAT1 co-expressed genes were analysed using bioinformatics analysis. The expression of TRAT1 was activated in LAC cells, and the roles of TRAT1 overexpression in the growth and migration of cancer cells was investigated using flow cytometry, Cell Counting Kit-8 (CCK-8), and migration and invasion assays. The relationship between TRAT1 overexpression, the immune microenvironment, and RNA modification was evaluated using correlation analysis. TRAT1 expression levels were significantly abnormal at multiple mutation sites and were related to the prognosis of LAC. TRAT1 co-expressed genes were involved in cell proliferation, adhesion, and differentiation, and TRAT1 overexpression significantly inhibited cell viability, migration, and invasion and promoted apoptosis of A549 and H1299 cells, which might be related to the TCR, B cell receptor (BCR), MAPK, and other pathways. TRAT1 expression levels were significantly correlated with the ESTIMATE, immune, and stromal scores in the LAC microenvironment. Additionally, TRAT1 expression levels were significantly correlated with the populations of B cells, CD8 T cells, cytotoxic cells, and other immune cells. TRAT1 overexpression was significantly correlated with the expression of immune cell markers (such as PDCD1, CD2, CD3E) and genes involved in RNA modification (such as ALKBH1, ALKBH3, ALKBH5). In conclusions, TRAT1 overexpression inhibited the growth and migration of LAC cells, thereby delaying cancer progression, and was correlated with the LAC microenvironment and RNA modifications.

Objective T cell receptor-associated transmembrane adaptor 1 (TRAT1) is one of the hub genes regulating T cell receptors (TCRs). Herein, the roles of TRAT1 in the prognosis and immune microenvironment of non-small cell lung cancer (NSCLC) were investigated. Methods The expression and prognosis values of TRAT1 in NSCLC, and the relationship between TRAT1 expression levels and cancer immune cell infiltration was identified via the TIMER, UALCAN, TISIDB, and other databases. The mechanism of TRAT1 in NSCLC was analyzed using gene set enrichment analysis (GSEA). Results The expression level of TRAT1 was decreased in NSCLC tissues. Low TRAT1 expression was associated with shorter overall survival of patients with NSCLC and was related to gender, smoking, and tumor grade. TRAT1 was involved in regulating immune response, TCR signaling pathway, PI3K/AKT, and other processes. TRAT1 expression levels were positively correlated with immune cell infiltration in NSCLC. Conclusion Down-regulation of TRAT1 expression was associated with an unfavorable prognosis and immune infiltration of NSCLC.

The tumor microenvironment (TME) plays an important regulatory role in the progression of non-small cell lung cancer (NSCLC). Mesenchymal stem cells (MSCs) in the TME might contribute to the occurrence and development of cancer. This study evaluates the role of differentially expressed genes (DEGs) of MSCs and the development of NSCLC and develops a prognostic risk model to assess the therapeutic responses. The DEGs in MSCs from lung tissues and from normal tissues were analyzed using GEO2R. The functions and mechanisms of the DEGs were analyzed using the Gene ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG). Additionally, the Cancer Genome Atlas (TCGA) database was used to determine the expression levels of the DEGs of MSCs in the NSCLC tissues. The prognostic factors of NSCLC related to MSCs were screened by survival analysis, meta-analysis, Cox regression analysis, and a prognostic risk model and nomogram was developed. The signaling mechanisms and immune roles that risk model participate in NSCLC development were determined via Gene Set Enrichment Analysis and CIBERSORT analysis. Compared to the normal tissues, 161 DEGs were identified in the MSCs of the lung tissues. These DEGs were associated with mechanisms, such as DNA replication, nuclear division, and homologous recombination. The overexpression of DDIT4, IL6, ITGA11, MME, MSX2, POSTN, and TRPA1 were associated with dismal prognosis of NSCLC patients. A high-risk score based on the prognostic risk model indicated the dismal prognosis of NSCLC patients. The nomogram showed that the age, clinical stage, and risk score affected the prognosis of NSCLC patients. Further, the high-risk model was associated with signaling mechanisms, such as the ECM-receptor interaction pathways, cytokine-cytokine receptor interaction, and MAPK pathways, involved in the progression of NSCLC and was also related to the components of the immune system, such as macrophages M0, T follicular helper cells, regulatory T cells. Therefore, the risk model and nomogram that was constructed on the basis of MSC-related factors such as POSTN, TRPA1, and DDIT4 could facilitate the discovery of target molecules that participate in the progression of NSCLC, which might also serve as new candidate markers for evaluating the prognosis of NSCLC patients.