Spatially Aware GCNs for efficient, high-accuracy cancer grading: Mitigating oversmoothing via frequency analysis.

Learning graph structure via graph convolutional networks

The major Objective of the Study is to augment the predictive analytics of Non-Small Cell Lung Cancer (NSCLC) datasets with Feature Pre-Processing (FPP) technique in three stages viz. Remove base errors with common analytics on emptiness or non-numerical or missing values in the dataset, remove repeated features through regression analysis and eliminate irrelevant features through clustering methods. The FPP Model is validated using classifiers like simple and complex Tree, Linear and Gaussian SVM, Weighted KNN and Boosted Trees in terms of accuracy, sensitivity, specificity, kappa, positive and negative likelihood. The result showed that the NSCLC dataset formed after FPP outperformed the raw NSCLC dataset in all performance levels and showed good augmentation in predictive analytics of NSCLC datasets. The research proved that preprocessing is essential for better prediction of complex medical datasets.

Previous studies have shown that asthma is a risk factor for lung cancer, while the mechanisms involved remain unclear. We attempted to further explore the association between asthma and non-small cell lung cancer (NSCLC) via bioinformatics analysis. We obtained GSE143303 and GSE18842 from the GEO database. Lung adenocarcinoma (LUAD) and lung squamous cell carcinoma (LUSC) groups were downloaded from the TCGA database. Based on the results of differentially expressed genes (DEGs) between asthma and NSCLC, we determined common DEGs by constructing a Venn diagram. Enrichment analysis was used to explore the common pathways of asthma and NSCLC. A protein-protein interaction (PPI) network was constructed to screen hub genes. KM survival analysis was performed to screen prognostic genes in the LUAD and LUSC groups. A Cox model was constructed based on hub genes and validated internally and externally. Tumor Immune Estimation Resource (TIMER) was used to evaluate the association of prognostic gene models with the tumor microenvironment (TME) and immune cell infiltration. Nomogram model was constructed by combining prognostic genes and clinical features. 114 common DEGs were obtained based on asthma and NSCLC data, and enrichment analysis showed that significant enrichment pathways mainly focused on inflammatory pathways. Screening of 5 hub genes as a key prognostic gene model for asthma progression to LUAD, and internal and external validation led to consistent conclusions. In addition, the risk score of the 5 hub genes could be used as a tool to assess the TME and immune cell infiltration. The nomogram model constructed by combining the 5 hub genes with clinical features was accurate for LUAD. Five-hub genes enrich our understanding of the potential mechanisms by which asthma contributes to the increased risk of lung cancer.

Survival prediction of a patient is a critical task in clinical medicine for physicians and patients to make an informed decision. Several survival and risk scoring methods have been developed to estimate the survival score of patients using clinical information. For instance, the Global Registry of Acute Coronary Events (GRACE) and Thrombolysis in Myocardial Infarction (TIMI) risk scores are developed for the survival prediction of heart patients. Recently, state-of-the-art medical imaging and analysis techniques have paved the way for survival prediction of cancer patients by understanding key features extracted from Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) scanned images with the help of image processing and machine learning techniques. However, survival prediction is a challenging task due to the complexity in benchmarking of image features, feature selection methods, and machine learning models. In this article, we evaluate the performance of 156 visual features from radiomic and hand-crafted feature classes, six feature selection methods, and 10 machine learning models to benchmark their performance. In addition, MRI scanned Brain Tumor Segmentation (BraTS) and CT scanned non-small cell lung cancer (NSCLC) datasets are used to train classification and regression models. Our results highlight that logistic regression outperforms for the classification with 66 and 54% accuracy for BraTS and NSCLC datasets, respectively. Moreover, our analysis of best-performing features shows that age is a common and significant feature for survival prediction. Also, gray level and shape-based features play a vital role in regression. We believe that the study can be helpful for oncologists, radiologists, and medical imaging researchers to understand and automate the procedure of decision-making and prognosis of cancer patients.

In this study, we propose a novel method for identifying lithology using an attention mechanism-enhanced graph convolutional neural network (AGCN). The aim of this method is to address the limitations of traditional approaches that evaluate unbalanced lithology by improving the identification of thin layers and small samples, while providing reliable data support for reservoir evaluation. To achieve this goal, we begin by using Principal Component Analysis (PCA) with maximum and minimum distance clustering (Max-min-distance) to correct the logging curves, which compensates for the low resolution of thin layers and enhances the accuracy of stratigraphic representation. Subsequently, we transform the logging data into graph-structured data by connecting distance similarity points and feature similarity points of the logging samples. We then use the graph convolutional network (GCN) to identify lithology, leveraging both labeled and unlabeled data to enhance the ability to identify lithology in small sample datasets. Additionally, our model incorporates a channel and spatial attention mechanism that assigns weights to the graph structure during lithology identification, improving the model’s capability to discern differences across samples. To evaluate the performance of our model, we constructed a lithology dataset comprising five wells and conducted experiments. The results indicate that our approach achieves a maximum accuracy of 97.67%, surpassing the performance of a singlestructure model in lithology identification. In conclusion, our proposed method provides a promising and effective approach for unbalanced lithology identification, significantly improving accuracy levels.

Colorectal cancer (CRC) and non-small cell lung cancer (NSCLC) are among the deadliest cancers worldwide, especially in advanced stages with limited treatment options. While immune checkpoint inhibitors (ICIs) targeting PD-1/PD-L1 have shown significant potential, their efficacy is limited to a small subset of CRC patients with microsatellite instability-high (MSI-H) tumors, and their use in NSCLC is often limited by severe side effects, further restricting their applicability. This underscores the urgent need for alternative immunotherapeutic approaches employing novel targets to expand clinical benefit. Here, we present a novel strategy exploiting natural killer (NK) cell mediated antibody-dependent cellular cytotoxicity (ADCC) using a monoclonal antibody (mAb) targeting B7-H3 (CD276). B7-H3, a B7 family immune checkpoint protein, is overexpressed in several tumor types, including CRC and NSCLC, but minimally expressed in normal tissues, making it an ideal target for cancer immunotherapy. Our engineered B7-H3 mAb, 8H8, was modified by introducing amino acid substitutions (S239D/I332E) in the Fc region to create the Fc-optimized variant 8H8-SDIE. This variant shows increased affinity for CD16 on NK cells, thereby enhancing ADCC potential. Preclinical characterization demonstrated robust B7-H3 expression and specific binding of 8H8-SDIE to CRC (n=5) and NSCLC (n=3) cell lines, with saturation at approximately 1 µg/mL. Co-culture of allogeneic peripheral blood mononuclear cells (PBMCs) with B7-H3-positive CRC and NSCLC cells confirmed that 8H8-SDIE significantly activated NK cells, as evidenced by increased expression of CD69 and CD25. Upregulation of CD107a further indicated NK cell degranulation. Additional analyses showed that 8H8-SDIE treatment promoted the secretion of IFNγ, TNF, and effector molecules such as granzyme A, granzyme B, granulysin, and perforin, thereby enhancing NK cell-mediated cytotoxicity. In short-term, mid-term and long-term cytotoxicity assays, 8H8-SDIE induced potent target cell-restricted lysis of CRC and NSCLC cell lines, while the iso-SDIE control showed no effect. In conclusion, 8H8-SDIE is a potent immunotherapeutic candidate that effectively induces NK cell anti-cancer reactivity and represents a promising treatment option for CRC and NSCLC. Citation Format: Sylwia Anna Stefanczyk, Xenija Kaiser, Samuel J. Holzmayer, Ilona Hagelstein, Latifa Zekri, Susanne Jung, Melanie Märklin. Enhanced NK cell reactivity with Fc-optimized B7-H3 antibody for colorectal and non-small cell lung cancer [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2025; Part 1 (Regular Abstracts); 2025 Apr 25-30; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2025;85(8_Suppl_1):Abstract nr 6082.

e20517 Background: Downregulation of C-type lectin domain family 3 member B (CLEC3B) is observed in non-small cell lung cancer (NSCLC), but its role remains largely unclear. Thus, we conducted this large scale genomic and transcriptomic analysis to gain novel insights into molecular and immunological functions of CLEC3B mRNA expression in NSCLC. Methods: Five publicly available WTS/WES NSCLC datasets (TCGA LUAD/LUSC, GSE41271, GSE66863, GSE81089, BATTLE) and the lung cancer single-cell atlas (Salcher, Cancer Cell 2022) were re-analyzed to decipher various molecular and biological aspects of CLEC3B in NSCLC. Findings were validated in a cohort of 19,982 NSCLC samples, which were centrally profiled (Caris Life Sciences, Phoenix, AZ) using WES/WTS. The cohort was stratified in quartiles according to CLEC3B mRNA expression status, with CLEC3Bhigh ( CLEC3BH) and CLEC3Blow ( CLEC3BL) expression defined as top and bottom quartile of transcripts per million (TPM) for further comparison. Immune cell fractions were calculated using QuantiSeq. Real-world overall survival (OS) was calculated using data from insurance claims. Results: CLEC3B mRNA expression was diminished in NSCLC compared to matched normal tissue (p < 0.001). Adenomatous histology was associated with higher CLEC3B expression compared to squamous/large-cell carcinomas (p < 0.005). In CLEC3B H tumors we observed lower rates of somatic mutations in TP53 (44.1 vs 81.7%), TTN (54.1 vs 79%), CDKN2A (5.2 vs 15%), but higher rates in KRAS (24 vs 7.8%) and STK11 (15.8 vs 2.69%) (all, q < 0.01), which we corroborated in our validation cohort (TP53 (52.4 vs 74.7%), CDKN2A (8.3 vs 13%), RB1 (9.2 vs 13.5%), KMT2D (3.8 vs 7.3%), KRAS (31.8 vs 25.6%), EGFR (17.2 vs 8.1%) and STK11 (15.9 vs 11.3%, all q < 0.05)). Further, CLEC3BH tumors were characterized by an immunosuppressive phenotype reflected by lower TMB and lower rates of MSI-H/dMMR, lower PD-L1 IHC expression and abundance of M2 macrophages and regulatory T-cells. Analysis of bulk and single cell transcriptomic datasets revealed that CLEC3BH was linked to endothelium-specific signaling and higher expression levels in endothelial cells. Finally, increased CLEC3B expression was associated with improved OS in the exploratory and validation cohorts. Conclusions: We herein described the molecular landscape of NSCLCs according to CLEC3B mRNA expression. We speculate that CLEC3B is mainly expressed by endothelial cells, and observed that CLEC3BH was associated with a distinct genetic profile and an immunosuppressive tumor-microenvironment. Thus, CLEC3B expression warrants further investigation as a stratification marker for NSCLC patients undergoing immune checkpoint therapy.

Simple SummaryAltered DNA damage response (DDR) contributes to numerous processes during the progression of tumors, such as genomic instability, the emergence of neoantigens, aberrations in cell-cell signaling, and acquired tumor resistance to DNA damaging agents, such as platinating agents and irradiation. This study describes a novel role for the scaffolding protein NEDD9 in regulating DDR signaling and characterizes its effects on sensitivity to DNA damaging therapies in a non-small cell lung cancer (NSCLC) setting. Our data demonstrate that NEDD9 depletion is capable of upregulating ATM-CHK2 signaling, shifting NEDD9 depleted cells towards a more mesenchymal phenotype and elevated sensitivity to UV irradiation. Immunohistochemical analysis of the cohort of human NSCLC samples revealed an association between reduced NEDD9 protein expression and a decrease in overall (OS) survival of NSCLC patients.DNA damaging modalities are the backbone of treatments for non-small cell lung cancer (NSCLC). Alterations in DNA damage response (DDR) in tumor cells commonly contribute to emerging resistance to platinating agents, other targeted therapies, and radiation. The goal of this study is to identify the previously unreported role of NEDD9 scaffolding protein in controlling DDR processes and sensitivity to DNA damaging therapies. Using a siRNA-mediated approach to deplete NEDD9 in a group of human and murine KRAS/TP53-mutant NSCLC cell lines, coupled with a set of cell viability and clonogenic assays, flow cytometry analysis, and Western blotting, we evaluated the effects of NEDD9 silencing on cellular proliferation, DDR and epithelial-to-mesenchymal transition (EMT) signaling, cell cycle, and sensitivity to cisplatin and UV irradiation. Using publicly available NSCLC datasets (TCGA) and an independent cohort of primary NSCLC tumors, subsequent in silico and immunohistochemical (IHC) analyses were performed to assess relevant changes in NEDD9 RNA and protein expression across different stages of NSCLC. The results of our study demonstrate that NEDD9 depletion is associated with the increased tumorigenic capacity of NSCLC cells. These phenotypes were accompanied by significantly upregulated ATM-CHK2 signaling, shifting towards a more mesenchymal phenotype in NEDD9 depleted cells and elevated sensitivity to UV-irradiation. IHC analyses revealed an association between reduced NEDD9 protein expression and a decrease in overall (OS) and progression-free survival (PFS) of the NSCLC patients. These data, for the first time, identified NEDD9 as a negative regulator of ATM kinase activity and related DDR signaling in numerous KRAS/TP53 mutated NSCLC, with its effects on the regulation of DDR-dependent EMT signaling, sensitivity to DNA damaging modalities in tumor cells, and the survival of the patients.

Microsatellite instability (MSI) is caused mainly by dysfunction of hMLH1, where aberrant hypermethylation (HM) of its promoter region is involved. Previously, we suggested that HM in the proximal region of the hMLH1 promoter plays a critical role in progression of gastric cancer with MSI and this specific region should be analyzed for diagnostic use of hMLH1 HM. We expanded the analyses of hMLH1 HM and MSI phenotype to sporadic colorectal cancer (CRC) and non-small cell lung cancer (NSCLC) to further evaluate the diagnostic value of hMLH1 HM. A total of 174 CRC and 94 NSCLC samples were used for hMLH1 methylation analysis by real-time methylation-specific PCR. Methylation levels were measured in three distinct regions of the promoter, designated as hMLH1-A, hMLH1-B, and hMLH1-C from distal to proximal. MSI phenotype was determined using five microsatellite markers, BAT25, BAT26, D2S123, D5S346, and D17S250. Methylation profile of the hMLH1 promoter varies between CRC and NSCLC. High methylation levels were observed in a group of CRC samples. Consequently, three patterns of methylation in the hMLH1 promoter regions were found: 1) low methylation level in all regions, 2) high methylation level in hMLH1-A with low methylation level in hMLH1-C, 3) high methylation level in all regions. In contrast, only one NSCLC showed high methylation level in hMLH1-A. Of the 134 CRCs examined, 14 (10.4%) showed MSI phenotype. No MSI phenotype was found in the initial 80 NSCLCs analyzed. Eight (57.1%) of 14 CRC with MSI showed HM in hMLH1-C, which was linked exclusively with MSI phenotype. However, the HM in hMLH1-A or -B was not sufficient for MSI. CRC with MSI phenotype was significantly more frequent in older patients and in the proximal colon, and was more evident in cases with hMLH1-C HM. The results suggested that hMLH1 HM cannot be used as an alternative diagnostic marker of MSI phenotype in sporadic CRC and NSCLC. CRC with MSI might have clinicopathologically distinct subgroups according to hMLH1-C HM status. The observed profiles of hMLH1 methylation and MSI in gastric cancer, CRC, and NSCLC were quite different from each other, facilitating the better understanding of the pathogenesis of these cancers.

BackgroundNumerous studies have reported that long non-coding RNAs (lncRNAs) play important roles in immune-related pathways in cancer. However, immune-related lncRNAs and their roles in predicting immunotherapeutic response and prognosis of non-small cell lung cancer (NSCLC) patients treated with immunotherapy remain largely unexplored.MethodsTranscriptomic data from NSCLC patients were used to identify novel lncRNAs by a custom pipeline. ImmuCellAI was utilized to calculate the infiltration score of immune cells. The marker genes of immunotherapeutic response-related (ITR)-immune cells were used to identify immune-related (IR)-lncRNAs. A co-expression network was constructed to determine their functions. LASSO and multivariate Cox analyses were performed on the training set to construct an immunotherapeutic response and immune-related (ITIR)-lncRNA signature for predicting the immunotherapeutic response and prognosis of NSCLC. Four independent datasets involving NSCLC and melanoma patients were used to validate the ITIR-lncRNA signature.ResultsIn total, 7,693 novel lncRNAs were identified for NSCLC. By comparing responders with non-responders, 154 ITR-lncRNAs were identified. Based on the correlation between the marker genes of ITR-immune cells and lncRNAs, 39 ITIR-lncRNAs were identified. A co-expression network was constructed and the potential functions of 38 ITIR-lncRNAs were annotated, most of which were related to immune/inflammatory-related pathways. Single-cell RNA-seq analysis was performed to confirm the functional prediction results of an ITIR-lncRNA, LINC01272. Four-ITIR-lncRNA signature was identified and verified for predicting the immunotherapeutic response and prognosis of NSCLC. Compared with non-responders, responders had a lower risk score in both NSCLC datasets (P<0.05). NSCLC patients in the high-risk group had significantly shorter PFS/OS time than those in the low-risk group in the training and testing sets (P<0.05). The AUC value was 1 of responsiveness in the training set. In melanoma validation datasets, patients in the high-risk group also had significantly shorter OS/PFS time than those in the low-risk group (P<0.05). The ITIR-lncRNA signature was an independent prognostic factor (P<0.001).ConclusionThousands of novel lncRNAs in NSCLC were identified and characterized. In total, 39 ITIR-lncRNAs were identified, 38 of which were functionally annotated. Four ITIR-lncRNAs were identified as a novel ITIR-lncRNA signature for predicting the immunotherapeutic response and prognosis in NSCLC patients treated with immunotherapy.

MA09.07 Genomic Landscape and Clinical Outcomes With Immune Checkpoint Inhibitors in NF1-Mutant NSCLC

The dysregulation of receptor tyrosine kinases (RTK) has garnered plenty of interest within the cancer field, and attention has begun to turn to phosphatases regulating RTK behavior. Under normal cellular conditions, protein tyrosine phosphatases remove phosphate groups from tyrosine residues, thus maintaining signaling homeostasis. In whole genome sequencing primary mouse mammary tumors from the polyoma virus middle T antigen (PyMT) mouse model, we found a mutation in the protein tyrosine phosphatase receptor type H (Ptprh) gene. Targeted resequencing of 45 mouse tumors showed a conserved heterozygous or homozygous mutation present in 80% of tumors. This C&gt;T mutation results in a valine to methionine shift within one of the fibronectin domains of PTPRH. Previous literature has shown interactions between PTPRH and epidermal growth factor receptor (EGFR). To determine the relevancy of PTPRH mutations in human cancer, data from The Cancer Genome Atlas (TCGA) was analyzed and revealed PTPRH mutations in five percent of non‐small cell lung cancer (NSCLC) patients. Moreover, patients with a mutation in PTPRH were mutually exclusive from those with mutation or amplification of EGFR. We hypothesize a mutation in PTPRH results in a failure of PTPRH to dephosphorylate EGFR, resulting in inappropriate maintenance of downstream signaling pathways important for proliferation and evading apoptosis. Since NCSLC patients with EGFR mutations are successfully treated with tyrosine kinase inhibitors (TKI), we also hypothesize tumors with a mutation in PTPRH will be sensitive to TKIs. In support of this, we demonstrated mouse tumors with a mutation in Ptprh had increased phosphorylated EGFR (pEGFR). Furthermore, CRISPR mediated knockout of PTPRH in H23 NSCLC cells leads to increased pEGFR. Pathway signature analysis applied to microarray gene expression data from the Breast TCGA dataset (due to low sample size in the NSCLC dataset), and single sample gene set enrichment analysis applied to RNA sequencing data from the NSCLC TCGA dataset both predicted an increase in PI3K and AKT activity. This suggested the EGFR residue targeted by PTPRH was tyrosine 1197. Western blots on Ptprh mutant mouse tumors confirmed increased levels of pAKT. Additionally, immunohistochemistry for pEGFR 1197 revealed increased staining in mouse tumors with a mutation in Ptprh, with sub‐cellular location in the nucleus rather than the membrane. To determine whether TKIs may be an effective treatment for NSCLC patients who harbor a PTPRH mutation, H1155 and H2228 NSCLC cell lines with PTPRH mutations in the fibronectin and phosphatase domains respectively, were subjected to a dose response curve with the TKI osimertinib. These lines show significant growth differences as compared to the negative control cell line A427. While more work is needed to elucidate the role of mutant PTPRH in NSCLC, preliminary data suggests mutant PTPRH fails to dephosphorylate EGFR, and patients with a mutation in PTPRH may benefit from TKI therapy.

Non-small cell lung cancer (NSCLC) represents the vast majority of lung cancer cases, comprising 80-85% of all diagnoses, and continues to be a primary contributor to cancer-related deaths. Early detection is essential for improving patient outcomes, yet current diagnostic markers lack both sensitivity and specificity. This study aims to identify novel biomarkers that could enhance early diagnosis. We conducted a comprehensive gene expression analysis of three NSCLC datasets (GSE33479, GSE18842, and GSE32863) and identified seven genes with relevance to the extracellular region and space: MMP11, SPP1, ERO1L, CTHRC1, SPINK1, LAD1, and SFN. We further assessed these markers through serum protein analysis involving 200 NSCLC patients and 200 healthy controls, employing receiver operating characteristic (ROC) curve analysis to evaluate their diagnostic efficacy. Among the identified genes, MMP11 and SPP1 exhibited significant upregulation and strong discriminatory power in NSCLC tissues, achieving area under the curve (AUC) values exceeding 0.9. Serum protein levels of MMP11 and SPP1 were significantly higher in NSCLC patients compared to healthy controls. ROC curve analysis confirmed the diagnostic potential of MMP11 (AUC: 0.9896) and SPP1 (AUC: 0.9053), both outperforming the existing marker carcinoembryonic antigen (CEA) (AUC: 0.7109). MMP11 demonstrated sensitivity of 94.53% and specificity of 94.97%, while SPP1 showed sensitivity of 83.17% and specificity of 83.84%. In contrast, CEA exhibited a sensitivity of 66.83% and specificity of 67.69%. The results indicate that MMP11 and SPP1, detectable in serum, may serve as valuable non-invasive biomarkers for the early diagnosis of NSCLC, particularly within health screening contexts. However, further research within larger and more diverse cohorts is imperative to validate these biomarkers and investigate the mechanisms underlying MMP11 and SPP1 expression in NSCLC. This study highlights the potential of these biomarkers to enhance diagnostic accuracy and improve patient outcomes in NSCLC.

BackgroundResearch interest into regulation of gene expression by physical activity and its effect on cancer prognosis has intensified. This study investigated the role of an exercise-related gene, NUP155, in the progression of non-small cell lung cancer (NSCLC) and its potential as therapy target.MethodsUsing the GSE41914 dataset, which includes data related to exercise, and the Cancer Genome Atlas (TCGA)-NSCLC dataset, we identified differentially expressed genes (DEGs) and selected NUP155 as a hub gene for further analysis. NUP155 expression levels were measured in NSCLC cell lines and normal lung cells using in vitro assays. The functional roles of NUP155 were investigated through small interfering RNA (siRNA) knockdown experiments, assessing effects on migration, cell proliferation, invasion, and apoptosis. The involvement of the PTEN/AKT signaling pathway was examined using the PTEN inhibitor SF1670.ResultsNUP155 was downregulated in postexercise samples and upregulated in NSCLC samples, indicating its association with poor prognosis in NSCLC. Knockdown of NUP155 in NSCLC cell lines resulted in reduced cell viability, migration, and invasion, alongside increased apoptosis. Western blotting revealed that NUP155 knockdown upregulated PTEN levels and downregulated phosphorylated AKT (p-AKT), without altering total AKT levels. The addition of SF1670 partially reversed the effects of NUP155 knockdown, indicating the involvement of the signaling pathway PTEN/AKT in NUP155-mediated tumorigenesis.ConclusionsNUP155 is upregulated in NSCLC, which promotes cell invasion and migration via the PTEN/AKT signaling pathway. Targeting NUP155, potentially influenced by exercise, could be a promising therapy. Combining exercise with targeted treatments may enhance patient outcomes.

Background: Non–small cell lung cancer (NSCLC) is highly malignant with driver somatic mutations and genomic instability. Long non-coding RNAs (lncRNAs) play a vital role in regulating these two aspects. However, the identification of somatic mutation-derived, genomic instability-related lncRNAs (GIRlncRNAs) and their clinical significance in NSCLC remains largely unexplored. Methods: Clinical information, gene mutation, and lncRNA expression data were extracted from TCGA database. GIRlncRNAs were screened by a mutator hypothesis-derived computational frame. Co-expression, GO, and KEGG enrichment analyses were performed to investigate the biological functions. Cox and LASSO regression analyses were performed to create a prognostic risk model based on the GIRlncRNA signature (GIRlncSig). The prediction efficiency of the model was evaluated by using correlation analyses with mutation, driver gene, immune microenvironment contexture, and therapeutic response. The prognostic performance of the model was evaluated by external datasets. A nomogram was established and validated in the testing set and TCGA dataset. Results: A total of 1446 GIRlncRNAs were selected from the screen, and the established GIRlncSig was used to classify patients into high- and low-risk groups. Enrichment analyses showed that GIRlncRNAs were mainly associated with nucleic acid metabolism and DNA damage repair pathways. Cox analyses further identified 19 GIRlncRNAs to construct a GIRlncSig-based risk score model. According to Cox regression and stratification analyses, 14 risk lncRNAs (AC023824.3, AC013287.1, AP000829.1, LINC01611, AC097451.1, AC025419.1, AC079949.2, LINC01600, AC004862.1, AC021594.1, MYRF-AS1, LINC02434, LINC02412, and LINC00337) and five protective lncRNAs (LINC01067, AC012645.1, AL512604.3, AC008278.2, and AC089998.1) were considered powerful predictors. Analyses of the model showed that these GIRlncRNAs were correlated with somatic mutation pattern, immune microenvironment infiltration, immunotherapeutic response, drug sensitivity, and survival of NSCLC patients. The GIRlncSig risk score model demonstrated good predictive performance (AUCs of ROC for 10-year survival was 0.69) and prognostic value in different NSCLC datasets. The nomogram comprising GIRlncSig and tumor stage exhibited improved robustness and feasibility for predicting NSCLC prognosis. Conclusion: The newly identified GIRlncRNAs are powerful biomarkers for clinical outcome and prognosis of NSCLC. Our study highlights that the GIRlncSig-based score model may be a useful tool for risk stratification and management of NSCLC patients, which deserves further evaluation in future prospective studies.