Subtypes Of Lung Adenocarcinoma Research Articles

A Bi-LSTM and multihead attention-based model incorporating radiomics signatures and radiological features for differentiating the main subtypes of lung adenocarcinoma.

The radiological features of computed tomography (CT) images and the sequence of radiomics signatures in continuous slices of lung CT lesions are helpful in identifying subtypes of lung adenocarcinoma. A model based on bidirectional long short-term memory (Bi-LSTM) and multihead attention can learn the rules of this sequence well. In this study, 421 patients with 427 lesions confirmed as adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA) or invasive adenocarcinoma (IAC) were recruited from three hospitals. The radiomics signatures of the identified lesion regions in each CT image were extracted using 'PyRadiomics' software, and the corresponding radiological features were subsequently documented and collected. Then, the top 100 features were extracted by the minimum redundancy maximum relevance (mRMR) feature ranking method. A model based on the radiological and imaging features was established to classify the lesions using Bi-LSTM and multihead attention. The diagnostic performance of the model was measured by the area under the curve (AUC) of the receiver operating characteristic (ROC). The model combined radiological features and radiomics signatures. The AUCs of the model in the training, testing, and validation groups were 0.985, 0.94 and 0.981, respectively, and the accuracy was 0.92, 0.976 and 0.91, respectively. In addition, we trained two other models [convolutional neural network (CNN) + multihead attention, long short-term memory (LSTM) + multihead attention] and compared them using the testing dataset. The precision of the two models was 0.89 and 0.88, respectively, and the accuracy was 0.88 and 0.87, respectively. Bi-LSTM and multihead attention based on radiomics signatures and radiological features provide a way to distinguish AIS, MIA, and IAC.

Molecular subtypes of lung adenocarcinoma patients for prognosis and therapeutic response prediction with machine learning on 13 programmed cell death patterns.

Lung adenocarcinoma (LUAD) seriously threatens people's health worldwide. Programmed cell death (PCD) plays a critical role in regulating LUAD growth and metastasis as well as in therapeutic response. However, currently, there is a lack of integrative analysis of PCD-related signatures of LUAD for accurate prediction of prognosis and therapeutic response. The bulk transcriptome and clinical information of LUAD were obtained from TCGA and GEO databases. A total of 1382 genes involved in regulating 13 various PCD patterns (apoptosis, necroptosis, pyroptosis, ferroptosis, cuproptosis, netotic cell death, entotic cell death, lysosome-dependent cell death, parthanatos, autophagy-dependent cell death, oxeiptosis, alkaliptosis and disulfidptosis) were included in the study. Weighted gene co-expression network analysis (WGCNA) and differential expression analysis were performed to identify PCD-associated differential expression genes (DEGs). An unsupervised consensus clustering algorithm was used to explore the potential subtypes of LUAD based on the expression profiles of PCD-associated DEGs. Univariate Cox regression analysis, Least Absolute Shrinkage and Selection Operator (LASSO) regression, Random Forest (RF) analysis and stepwise multivariate Cox analysis were performed to construct a prognostic gene signature. The "oncoPredict" algorithm was utilized for drug-sensitive analysis. GSVA and GSEA were utilized to perform function enrichment analysis. MCPcounter, quanTIseq, Xcell and ssGSEA algorithms were used for tumor immune microenvironment analysis. A nomogram incorporating PCDI and clinicopathological characteristics was established to predict the prognosis of LUAD patients. Forty PCD-associated DEGs related to LUAD were obtained by WGCNA analysis and differential expression analysis, followed by unsupervised clustering to identify two LUAD molecular subtypes. A programmed cell death index (PCDI) with a five-gene signature was established by machine learning algorithms. LUAD patients were then divided into a high PCDI group and a low PCDI group using the median PCDI as a cutoff. Survival and therapeutic analysis revealed that the high PCDI group had a poor prognosis and was more sensitive to targeted drugs but less sensitive to immunotherapy compared to the low PCDI group. Further enrichment analysis showed that B cell-related pathways were significantly downregulated in the high PCDI group. Accordingly, the decreased tumor immune cell infiltration and the lower tumor tertiary lymphoid structure (TLS) scores were also found in the high PCDI group. Finally, a nomogram with reliable predictive performance PCDI was constructed by incorporating PCDI and clinicopathological characteristics, and a user-friendly online website was established for clinical reference ( https://nomogramiv.shinyapps.io/NomogramPCDI/ ). We performed the first comprehensive analysis of the clinical relevance of genes regulating 13 PCD patterns in LUAD and identified two LUAD molecular subtypes with distinct PCD-related gene signature which indicated differential prognosis and treatment sensitivity. Our study provided a new index to predict the efficacy of therapeutic interventions and the prognosis of LUAD patients for guiding personalized treatments.

Association of Molecular Profiles and Mutational Status With Distinct Histological Lung Adenocarcinoma Subtypes. An Analysis of the LACE-Bio Data

BackgroundAdjuvant chemotherapy (AC) is indicated for stage II and stage III lung adenocarcinomas (ADC). Using the LACE Bio II database, we analyzed the distribution of various mutations across the subtypes of ADCs and studied the prognostic and predictive roles of PD-L1, TMB, and Tumor Infiltrating Lymphocytes (TILs). Materials and MethodsClinical and genomic data from the LACE Bio II data were extracted. Patients were divided into ADC subtypes, in which the grouping was done based on their known clinical behavior (Lepidic [LEP], Acinar/Papillary [ACI or PAP], Micropapillary/Solid [MIP or SOL], Mucinous [MUC] and Others). Kaplan-Meier (KM) and log-rank test were used to compare survival based on PD-L1, TMB, TILs and combinations of TMB with PD-L1 and TILs. Adjusted Hazard Ratios (HR) were analyzed with Overall Survival (OS), Disease-Free Survival (DFS) and Lung Cancer-Specific Survival (LCSS) as endpoints. ResultsA total of 375 ADC patients were identified. MIP/SOL was the subtype most commonly positive for various biomarkers. PD-L1 Negative/high TMB was associated with better outcomes in terms of OS (HR = 0.46 [0.23-0.89], P = .021) and DFS (HR = 0.52 [0.30-0.90], P = .02), relative to PD-L1 Negative/low TMB. High TMB predicted worse outcome with AC use in terms of OS (ratio of hazard ratio rHR = 2.75 [1.07-7.04], P = .035). Marked TILs had better outcome with AC for DFS (rHR = 0.22 [0.06-0.87], P = .031 and LCSS (rHR = 0.08 [0.01-0.66], P = .019) respectively. There was also a beneficial effect of AC among patients with Marked TILs/low TMB in terms of DFS (rHR = 0.06 [0.01-0.53], P = .011). ConclusionHigh TMB has a prognostic role in resectable lung ADC. The high TMB group had a poor outcome with AC, suggesting that this group may be better served with immune checkpoint therapy.

B4GALT1 promotes immune escape by regulating the expression of PD-L1 at multiple levels in lung adenocarcinoma

BackgroundInvasive adenocarcinoma (IAC), which is typically preceded by minimally invasive adenocarcinoma (MIA), is the dominant pathological subtype of early-stage lung adenocarcinoma (LUAD). Identifying the molecular events underlying the progression from MIA to IAC may provide a crucial perspective and boost the exploration of novel strategies for early-stage LUAD diagnosis and treatment.MethodsTranscriptome sequencing of four pairs of MIA and IAC tumours obtained from four multiple primary lung cancer patients was performed to screen out beta-1,4-galactosyltransferase1 (B4GALT1). Function and mechanism experiments in vitro and in vivo were performed to explore the regulatory mechanism of B4GALT1-mediated immune evasion by regulating programmed cell death ligand 1 (PD-L1).ResultsB4GALT1, a key gene involved in N-glycan biosynthesis, was highly expressed in IAC samples. Further experiments revealed that B4GALT1 regulated LUAD cell proliferation and invasion both in vitro and in vivo and was related to the impaired antitumour capacity of CD8 + T cells. Mechanistically, B4GALT1 directly mediates the N-linked glycosylation of PD-L1 protein, thus preventing PD-L1 degradation at the posttranscriptional level. In addition, B4GALT1 stabilized the TAZ protein via glycosylation, which activated CD274 at the transcriptional level. These factors lead to lung cancer immune escape. Importantly, inhibition of B4GALT1 increased CD8 + T-cell abundance and activity and enhanced the antitumour immunity of anti-PD-1 therapy in vivo.ConclusionB4GALT1 is a critical molecule in the development of early-stage LUAD and may be a novel target for LUAD intervention and immunotherapy.

Establishment of a nomogram predictive model for survival and prognosis of 97 patients with different subtypes of lung adenocarcinoma after radical resection.

e20596 Background: Postoperative recurrence and metastasis of lung adenocarcinoma (LUAD) is a major obstacle to long-term survival, and how to identify patients at high risk of recurrence / death after surgery and those likely to benefit from adjuvant therapy is currently a clinically relevant question. In this study, we investigated the survival characteristics of patients with different subtypes of LUAD after radical resection and established predictive prognostic models to inform postoperative management, recurrence prediction and risk management in lung cancer patients. Methods: A retrospective analysis of 97 patients who underwent concurrent genetic testing for LUAD radical resection at The Affiliated Tumor Hospital of Xinjiang Medical University between December 01, 2014 and December 30, 2017 was performed. A COX proportional risk regression model was used to construct a prognosis model for patients with LUAD after surgery and visualization of the model was performed using column diagrams. The performance of the model was evaluated using C index, calibration curve, and ROC curve. Results: (1)46 patients (47.42%) were included and 51 patients died (52.58%), with a median survival of 78 months (95% CI: 63-93). Twenty of these patients had a good prognosis (20.62%) and 77 had a poor prognosis (79.38%), with a median survival time of 88 months (95% CI: 81-95). The overall survival rate was 98.9%, 78.3% and 59.7%, respectively, and the cumulative disease-free survival rate was 77.3%, 37.1% and 20.6%, respectively, for 1, 3 and 5 years. Pathologic types were lepidic, acina/papillaryand solid/micropapillary with 87.50%, 56.90% and 58.80% OS and DFS, respectively. 37.50%、80%、11.80%. (2)26 patients (26.8%)had recurrent metastasis,the main site of metastasis was extrapulmonary, and multiple metastases were more common. (3)Univariateand multivariate analysis showed that TNM stage III, pathological classification as solid/micropapillary, tumor diameter ≥ 3cm, and gene mutation positivity were independent risk factors for prognosis in patients with lung adenocarcinoma after surgery. Based on the above risk factors, the Nomogram prognostic model was established with a C index of 0.687 (95% CI: 0.622-0.752) and calibration curves and ROCs for the 1, 3, and 5 year models, respectively, with AUC values of 0.742, 0.752, and 0.820 > 0.7, suggesting that the model is within the acceptable range of partitioning and accuracy, with the highest AUC for the 5-year DFS prediction. Conclusions: High TNM staging, pathotyping of micronipples or entities, ≥ 3cm tumor diameter, and mutant positivity were independent risk factors for recurrence and metastasis in patients with LUAD. The Nomogram predictive model based on patient risk factors after LUAD radical resection is effective in predicting long-term survival and guiding personalized treatment.

Tumor immune microenvironment (TIME) analysis of stage I lung adenocarcinoma with micropapillary pattern.

e20510 Background: Micropapillary is one of the most aggressive histologic subtypes of lung adenocarcinoma, which is considered a poor prognostic marker. Comprehensive analysis of tumor immune microenvironment (TIME) features of micropapillary of early invasive lung adenocarcinoma may provide better insight and facilitate the development of novel strategies for early detection and intervention. Methods: A total of 15 patients who underwent anatomical resection and were pathologically diagnosed with stage I micropapillary adenocarcinomas were included in this study. Gene expression profiles (GEPs) of tumor immune-related 289 genes were analyzed using NanoString nCounter. Differentially expressed genes(DEGs), estimation of TIME cell infiltration, and TIME signatures between micropapillary and non-micropapillary were assessed. Results: The number of micropapillary and non-micropapillary patients was 5 and 10. The comparison revealed CD69, IL6, CXCL8, CXCL2, POLR2A and so on were significantly upregulated in the micropapillary group compared with the non-micropapillary group, while HLA-DPA1, IFIT2, and other seven genes were down-regulated in the micropapillary group. These DEGs were mostly enriched in “positive regulation of cytokine production”， “T cell activation”， “receptor ligand activity，” and “signaling receptor activator activity” pathways according to GO enrichment analysis. The results of the KEGG analysis revealed that genes were significantly enriched in “IL-17 signaling pathway”, “TNF signaling pathway”, “cytokine-cytokine receptor interaction”, and so on. Meanwhile, different immune infiltration of the two groups was analyzed. Totally, there was a better TIME cell infiltration in the micropapillary group compared with the non-micropapillary group. Especially, the score of DCs and mast cells was significantly higher in micropapillary group. However, TIME signature scores were similar in both groups. Conclusions: Our study demonstrated that the TIME between micropapillary and non-micropapillary of stage I lung adenocarcinoma was different. Increased mast cells explained poor prognosis in lung adenocarcinoma with micropapillary pattern. A high level of DCs infiltration indicated that micropapillary adenocarcinoma might benefit from immunotherapy.

Correlation analysis of MRD positivity after non-small cell lung cancer surgery.

e20590 Background: To explore the relationship between postoperative molecular residual disease (MRD) status in patients with non-small cell lung cancer (NSCLC) and clinicopathological features, gene mutations, the tumour immune microenvironment and treatment effects. Methods: The clinical data of 90 patients with stage I-IIIA NSCLC who underwent radical resection of lung cancer from January 2021 to March 2022 in our hospital were retrospectively collected, and demographic data, clinicopathological characteristics, genetic test results, MRD status, and treatment effects were analysed. Results: Sex, age, smoking status, pathological type, and gene mutations were not associated with postoperative MRD status. T (tumour diameter > 3 cm) and N (lymph node metastasis) were statistically correlated with MRD positivity ( p values of 0.004 and 0.003, respectively). The higher the proportion of micropapillary and solid pathological subtypes of lung adenocarcinoma, the higher was the MRD-positivity rate after surgery ( p = 0.005). MRD positivity was correlated with vascular invasion ( p = 0.0002). For the expression of programmed cell death ligand 1 (PD-L1), tumour positive score (TPS) ≥ 1% and combined positive score (CPS) ≥ 5 were correlated with postoperative MRD status ( p value distribution was 0.0391 and 0.0153). For ctDNA clearance, among postoperative MRD-positive patients, postoperative adjuvant targeted therapy was superior to chemotherapy for patients without gene mutations. Conclusions: Postoperative ctDNA-MRD status in NSCLC patients is associated with primary tumour size, lymph node metastasis, lung adenocarcinoma pathological subtype, vascular invasion, TPS and CPS for PD-L1 expression; for postoperative MRD-positive patients, clearance of ctDNA by adjuvant EGFR-TKI target treatment is superior to chemotherapy.

A radiomic-based predictive model of lung adenocarcinoma brain metastases and molecular subtypes.

2014 Background: Non-small cell lung cancer (NSCLC) comprises the largest portion of brain metastases (BM) from solid cancer with 40% of patients developing BM during the course of their disease. There are currently no reliable prediction tools for identifying patients at risk for BM, especially in the early-stage setting where MRI screening is not performed. Furthermore, in the later stage setting, brain MRI are only performed annually. Therefore, there is a critical need to identify high-risk patients for BM that could benefit from MRI surveillance. Methods: We identified 162 lung adenocarcinoma (LUAD) patients with (N = 66) or without (N = 96) BM that had treatment-naïve CT scans with a segmentable lesion. The tumor, surrounding ground glass opacity and necrosis were segmented via 3D slicer to create a volume of interest for radiomic texture analysis and 400 features were extracted. The Least Absolute Shrinkage and Selection Operator (LASSO) logistic regression feature selection method was used to select the most relevant features and models were built using the machine learning method XGBoost classifier. Training and testing sets with random splitting was used for cross validation. We report the accuracy, sensitivity, specificity, and area under the curve (AUC) for each model. Results: Among the extracted features that LASSO deemed as most discriminative for development of BM, we identified the most relevant features using XGBoost that predicted BM with 79% accuracy, 83% sensitivity, 72% specificity, and 79% AUC ( p= 0.01) in the overall population. The addition of ground glass opacity and necrosis to the model did not significantly improve performance. Furthermore, the model distinguished those with metachronous vs synchronous BM with 84% accuracy, 83% sensitivity, 86% specificity, and 83% AUC ( p = 0.04). Our model held up across molecular subtypes ( EGFR and KRAS mutant). Importantly, the model was predictive in early-stage patients with 92% accuracy, 96% sensitivity, 83% specificity, and 95% AUC ( p= 0.0005). Moreover, our model predicted for high vs. low overall survival, and was BM-specific as it was not predictive of other sites of metastases. We further developed a model from the CT features that correctly classified KRAS mutant vs. KRAS wild type LUAD with 77% accuracy, 73% sensitivity, 80% specificity, and 80% AUC ( p= 0.002). Conclusions: Utilizing a radiomics approach, we were able to predict BM from primary lung CT features including in stage I and II disease, predict synchronous vs metachronous BM, and distinguish distinct molecular LUAD subtypes. We are currently validating our BM prediction model in a large independent cohort and developing models to classify targetable LUAD-BM molecular alterations utilizing brain MRI scans. These studies will identify patients that require MRI surveillance in the early-stage setting and more intensive surveillance in the late-stage setting for BM.

Implications of obstructive sleep apnea in lung adenocarcinoma: A valuable omission in cancer prognosis and immunotherapy

Lung adenocarcinoma (LUAD) is a highly invasive malignant tumor with poor prognosis, and there is growing evidence that obstructive sleep apnea (OSA) could significantly promotes the risk of LUAD. In order to improve the treatment outcomes of patients with LUAD and OSA, we aim to screen OSA-related genes that may potentially affect LUAD and to discover a high sensitivity prognostic signature that can stratify LUAD/OSA patients and to further accurately identify LUAD patients who might respond to immunotherapy. Molecular subtypes classified by the prognostic signature did not belong to any previously reported subtypes of LUAD. The tumor microenvironment (TME), mutation, and so on, were significantly distinct between patients within different risk groups or clusters. Combined with gene set variation analysis (GSVA) and drug susceptibility analysis, patients in the low-risk group (The vast majority of patients belonging to cluster2 by molecular subtyping) were not suitable for immunotherapy due to T-cell exhaustion caused by long-term inflammatory response; the question of how to reverse T-cell exhaustion may be a primary consideration. Cluster3 patients had the highest benefit from immunotherapy, and although cluster1 patients had the worst prognosis, they were more sensitive to traditional chemotherapeutic drugs. Animal experiments showed that chronic intermittent hypoxia (CIH) could not only significantly promote the tumor growth of LUAD, but also increase the expression levels of risk genes. This risk model may contribute greatly to the evaluation of prognosis, molecular characteristics, and treatment modalities of LUAD/OSA, and could be further translated into clinical applications to ameliorate the treatment dilemmas.

A multilayer perceptron-based model applied to histopathology image classification of lung adenocarcinoma subtypes.

Lung cancer is one of the most common malignant tumors in humans. Adenocarcinoma of the lung is another of the most common types of lung cancer. In clinical medicine, physicians rely on the information provided by pathology tests as an important reference for the fifinal diagnosis of many diseases. Thus, pathological diagnosis is known as the gold standard for disease diagnosis. However, the complexity of the information contained in pathology images and the increase in the number of patients far exceeds the number of pathologists, especially in the treatment of lung cancer in less-developed countries. This paper proposes a multilayer perceptron model for lung cancer histopathology image detection, which enables the automatic detection of the degree of lung adenocarcinoma infifiltration. For the large amount of local information present in lung cancer histopathology images, MLP IN MLP (MIM) uses a dual data stream input method to achieve a modeling approach that combines global and local information to improve the classifification performance of the model. In our experiments, we collected 780 lung cancer histopathological images and prepared a lung histopathology image dataset to verify the effectiveness of MIM. The MIM achieves a diagnostic accuracy of 95.31% and has a precision, sensitivity, specificity and F1-score of 95.31%, 93.09%, 93.10%, 96.43% and 93.10% respectively, outperforming the diagnostic results of the common network model. In addition, a number of series of extension experiments demonstrated the scalability and stability of the MIM. In summary, MIM has high classifification performance and substantial potential in lung cancer detection tasks.

Identification of lung adenocarcinoma subtypes and predictive signature for prognosis, immune features, and immunotherapy based on immune checkpoint genes.

Background: Lung adenocarcinoma (LUAD) is the most common variant of non-small cell lung cancer (NSCLC) across the world. Recently, the rapid development of immunotherapy has brought a new dawn for LUAD patients. Closely related to the tumor immune microenvironment and immune cell functions, more and more new immune checkpoints have been discovered, and various cancer treatment studies targeting these novel immune checkpoints are currently in full swing. However, studies on the phenotype and clinical significance of novel immune checkpoints in LUAD are still limited, and only a minority of patients with LUAD can benefit from immunotherapy. Methods: The LUAD datasets were downloaded from The Cancer Genome Atlas (TCGA) and the Gene Expression Omnibus (GEO) databases, and the immune checkpoints score of each sample were calculated based on the expression of the 82 immune checkpoints-related genes (ICGs). The weighted gene co-expression network analysis (WGCNA) was used to obtain the gene modules closely related to the score and two different LUAD clusters were identified based on these module genes by the Non-negative Matrix Factorization (NMF) Algorithm. The differentially expressed genes between the two clusters were further used to construct a predictive signature for prognosis, immune features, and the response to immunotherapy for LUAD patients through a series of regression analyses. Results: A new immune checkpoints-related signature was finally established according to the expression of 7 genes (FCER2, CD200R1, RHOV, TNNT2, WT1, AHSG, and KRTAP5-8). This signature can stratify patients into high-risk and low-risk groups with different survival outcomes and sensitivity to immunotherapy, and the signature has been well validated in different clinical subgroups and validation cohorts. Conclusion: We constructed a novel immune checkpoints-related LUAD risk assessment system, which has a good predictive ability and significance for guiding immunotherapy. We believe that these findings will not only aid in the clinical management of LUAD patients but also provide some insights into screening appropriate patients for immunotherapy.

Abstract A027: Defining the role of PER1 and circadian rhythm dysregulation in KRAS/LKB1-mutant lung adenocarcinoma

Abstract KRAS and LKB1 are frequently co-mutated in lung adenocarcinoma and characterize a particularly aggressive, metastatic, and treatment-resistant subtype of this disease. We recently published that the outputs of biological rhythm pathways downstream of the AMPK kinase are altered in KRAS/LKB1-mutant tumors. In a live-cell phenotyping screen we used RNAseq to identify the circadian clock genes PER1 and PER2 as uniquely upregulated in partially transformed and invasive KRAS/LKB1-mutant human bronchial epithelial cells. We have analyzed expression of individual circadian clock genes in KRAS-mutant and KRAS/LKB1-mutant patient tumors and found that expression of the PER genes, particularly PER1, is increased in the KRAS/LKB1 subtype of lung adenocarcinoma. At the protein level, PER1 expression is increased in KRAS/LKB1-mutant HBECs as compared to KRAS-mutant cells. Addback of wild-type LKB1 in A549 cells, which are KRAS/LKB1-mutant, results in a decrease in PER1 protein levels, confirming that LKB1 has a role in controlling PER1 levels. Multiple phosphorylation events lead to PER1 nuclear translocation to control its role as a transcriptional repressor in the core clock. In circadian-synced HBECs, PER1 enters the nucleus in KRAS-mutant cells, but remains cytosolic in KRAS/LKB1-mutant cells. In circadian-synced A549 cells, we also observed a lack of nuclear PER1 localization. Addback of wild-type LKB1 restored nuclear localization of PER1, as did expression of kinase-dead LKB1, suggesting that LKB1’s regulation of PER1 localization is kinase-independent. Our current and future experiments aim to determine how clock-controlled gene expression may be altered in KRAS/LKB1-mutant cells, what the functional impact of altered PER1 expression and localization is on growth of KRAS/LKB1-mutant tumors, and whether pharmacological manipulation of LKB1-related signaling pathways can restore nuclear localization of PER1. Citation Format: Rebecca E. Parker, Junghui Koo, Bhakti Dwivedi, Adam I. Marcus, Melissa Gilbert-Ross. Defining the role of PER1 and circadian rhythm dysregulation in KRAS/LKB1-mutant lung adenocarcinoma [abstract]. In: Proceedings of the AACR Special Conference: Targeting RAS; 2023 Mar 5-8; Philadelphia, PA. Philadelphia (PA): AACR; Mol Cancer Res 2023;21(5_Suppl):Abstract nr A027.

Characterization of molecular subtypes based on chromatin regulators and identification of the role of NPAS2 in lung adenocarcinoma

BackgroundChromatin regulators (CRs) are critical epigenetic modifiers and have been reported to play critical roles during the progression of various tumors, but their role in lung adenocarcinoma (LUAD) has not been comprehensively studied.MethodsDifferential expression and univariate Cox regression analyses were conducted to identify the prognostic CRs. Consensus clustering was applied to classify the subtypes of LUAD based on prognostic CRs. LASSO-multivariate Cox regression method was used for construction of a prognostic signature and development of chromatin regulator-related gene index (CRGI). The capacity of CRGI to distinguish survival was evaluated via Kaplan–Meier method in multiple datasets. Relationship between CRGI and tumor microenvironment (TME) was evaluated. Additionally, clinical variables and CRGI were incorporated to create a nomogram. The role of the prognostic gene NPAS2 in LUAD was elucidated via clinical samples validation and a series of in vitro and in vivo experiments.ResultsTwo subtypes of LUAD were classified based on 46 prognostic CRs via consensus clustering which had significantly different survival and TME. A prognostic signature consisting of six CRs (MOCS, PBK, CBX3, A1CF, NPAS2, and CTCFL) was developed and proved to be an effective survival predictor in multiple independent datasets. The prognostic signature was also demonstrated to be an indicator of TME and sensitivity to immunotherapy and chemotherapy. The nomogram was suggested to be a simple tool that can predict survival accurately. Clinical samples show that NPAS2 is highly expressed in LUAD tissues, and in vitro and in vivo experiments demonstrated that inhibition of NPAS2 impeded malignant progression of LUAD cells.ConclusionsOur study comprehensively unveiled the functions of CRs in LUAD, developed a classifier to predict survival and response to treatments, and suggested that NPAS2 promoted LUAD progression for the first time.

The Swin-Transformer network based on focal loss is used to identify images of pathological subtypes of lung adenocarcinoma with high similarity and class imbalance.

The classification of primary lung adenocarcinoma is complex and varied. Different subtypes of lung adenocarcinoma have different treatment methods and different prognosis. In this study, we collected 11 datasets comprising subtypes of lung cancer and proposed FL-STNet model to provide the assistance for improving clinical problems of pathologic classification in primary adenocarcinoma of lung. Samples were collected from 360 patients diagnosed with lung adenocarcinoma and other subtypes of lung diseases. In addition, an auxiliary diagnosis algorithm based on Swin-Transformer, which used Focal Loss for function in training, was developed. Meanwhile, the diagnostic accuracy of the Swin-Transformer was compared to pathologists. The Swin-Transformer captures not only information in the overall tissue structure but also the local tissue details in the images of lung cancer pathology. Furthermore, training FL-STNet with the Focal Loss function can further balance the difference in the amount of data between different subtypes, improving recognition accuracy. The average classification accuracy, F1, and AUC of the proposed FL-STNet reached 85.71%, 86.57%, and 0.9903. The average accuracy of the FL-STNet was higher by 17% and 34%, respectively, than in the senior pathologist and junior pathologist group. The first deep learning based on an 11-category classifier was developed for classifying lung adenocarcinoma subtypes based on WSI histopathology. Aiming at the deficiencies of the current CNN and Vit, FL-STNet model is proposed in this study by introducing Focal Loss and combining the advantages of Swin-Transformer model.

Association of frequent hypermethylation with high grade histological subtype in lung adenocarcinoma.

Lung adenocarcinoma is classified morphologically into five histological subtypes according to the WHO classification. While each histological subtype correlates with a distinct prognosis, the molecular basis has not been fully elucidated. Here we conducted DNA methylation analysis of 30 lung adenocarcinoma cases annotated with the predominant histological subtypes and three normal lung cases using the Infinium BeadChip. Unsupervised hierarchical clustering analysis revealed three subgroups with different methylation levels: high-, intermediate-, and low-methylation epigenotypes (HME, IME, and LME). Micropapillary pattern (MPP)-predominant cases and those with MPP components were significantly enriched in HME (p = 0.02 and p = 0.03, respectively). HME cases showed a significantly poor prognosis for recurrence-free survival (p < 0.001) and overall survival (p = 0.006). We identified 365 HME marker genes specifically hypermethylated in HME cases with enrichment of "cell morphogenesis" related genes; 305 IME marker genes hypermethylated in HME and IME, but not in LME, with enrichment "embryonic organ morphogenesis"-related genes; 257 Common marker genes hypermethylated commonly in all cancer cases, with enrichment of "regionalization"-related genes. We extracted surrogate markers for each epigenotype and designed pyrosequencing primers for five HME markers (TCERG1L, CXCL12, FAM181B, HOXA11, GAD2), three IME markers (TBX18, ZNF154, NWD2) and three Common markers (SCT, GJD2, BARHL2). DNA methylation profiling using Infinium data was validated by pyrosequencing, and HME cases defined by pyrosequencing results also showed the worse recurrence-free survival. In conclusion, lung adenocarcinomas are stratified into subtypes with distinct DNA methylation levels, and the high-methylation subtype correlated with MPP-predominant cases and those with MPP components and showed a poor prognosis.

Deep learning-based classification and spatial prognosis risk score on whole-slide images of lung adenocarcinoma.

Classification of histological patterns in lung adenocarcinoma (LUAD) is critical for clinical decision-making, especially in the early stage. However, the inter- and intraobserver subjectivity of pathologists make the quantification of histological patterns varied and inconsistent. Moreover, the spatial information of histological patterns is not evident to the naked eye of pathologists. We establish the LUAD-subtype deep learning model (LSDLM) with optimal ResNet34 followed by a four-layer Neural Network classifier, based on 40 000 well-annotated path-level tiles. The LSDLM shows robust performance for the identification of histopathological subtypes on the whole-slide level, with an area under the curve (AUC) value of 0.93, 0.96 and 0.85 across one internal and two external validation data sets. The LSDLM is capable of accurately distinguishing different LUAD subtypes through confusion matrices, albeit with a bias for high-risk subtypes. It possesses mixed histology pattern recognition on a par with senior pathologists. Combining the LSDLM-based risk score with the spatial K score (K-RS) shows great capacity for stratifying patients. Furthermore, we found the corresponding gene-level signature (AI-SRSS) to be an independent risk factor correlated with prognosis. Leveraging state-of-the-art deep learning models, the LSDLM shows capacity to assist pathologists in classifying histological patterns and prognosis stratification of LUAD patients.

Preoperative levels of folate receptor-positive circulating tumor cells in different subtypes of early-stage lung adenocarcinoma: Predictive value for determining extent of surgical resection.

The objective was to measure the correlations of preoperative levels of folate receptor-positive circulating tumor cells (FR+CTCs) with clinical characteristics and histologic subtype in early-stage lung adenocarcinoma, and to determine the predictive value of FR+CTC level in preoperative determination of the extent of surgical resection. In this retrospective, single-institution, observational study, preoperative FR+CTC levels were measured via ligand-targeted enzyme-linked polymerization in patients with early-stage lung adenocarcinoma. Receiver operating characteristic (ROC) analysis was used to identify the optimal cutoff value of FR+CTC level for prediction of various clinical characteristics and histologic subtypes. No significant difference in FR+CTC level was observed among patients with adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA), and invasive adenocarcinoma (IAC) (P = 0.813). Within the non-mucinous adenocarcinoma group, no difference was observed among patients with tumors whose predominant growth patterns were lepidic, acinar, papillary, micropapillary, solid, and complex gland (P = 0.053). However, significant differences in FR+CTC level were observed between patients with and without the micropapillary subtype [11.21 (8.22-13.61) vs. 9.85 (7.43-12.63), P = 0.017], between those with and without the solid subtype [12.16 (8.27-14.90) vs. 9.87 (7.50-12.49), P = 0.022], and between those with any of the advanced subtypes (micropapillary, solid, or complex glands) vs. none of these [10.48 (7.83-13.67) vs. 9.76 (7.42-12.42), P = 0.032]. FR+CTC level was also correlated with degree of differentiation of lung adenocarcinoma (P = 0.033), presence of visceral pleural invasion (VPI) of lung carcinoma (P = 0.003), and lymph node metastasis of lung carcinoma (P = 0.035). FR+CTC level is of potential predictive value in determining the presence of aggressive histologic patterns (micropapillary, solid, and advanced subtypes), degree of differentiation, and occurrence of VPI and lymph node metastasis in IAC. Measurement of FR+CTC level combined with intraoperative frozen sections may represent a more effective method of guiding resection strategy in cases of cT1N0M0 IAC with high-risk factors.

Mapping Mitochondrial Diversity in NSCLC.

A recent study shows that mitochondrial networks in the two main subtypes of non-small cell lung cancer, adenocarcinoma and squamous cell carcinoma, are structurally and functionally distinct. This difference could impact therapeutic targeting of cancer metabolism, a complex field that has been slow to bear fruit.

Identification of natural killer cell associated subtyping and gene signature to predict prognosis and drug sensitivity of lung adenocarcinoma.

Introduction: This research explored the immune characteristics of natural killer (NK) cells in lung adenocarcinoma (LUAD) and their predictive role on patient survival and immunotherapy response. Material and methods: Molecular subtyping of LUAD samples was performed by evaluating NK cell-associated pathways and genes in The Cancer Genome Atlas (TCGA) dataset using consistent clustering. 12 programmed cell death (PCD) patterns were acquired from previous study. Riskscore prognostic models were constructed using Least absolute shrinkage and selection operator (Lasso) and Cox regression. The model stability was validated in Gene Expression Omnibus database (GEO). Results: We classified LUAD into three different molecular subgroups based on NK cell-related genes, with the worst prognosis in C1 patients and the optimal in C3. Homologous Recombination Defects, purity and ploidy, TMB, LOH, Aneuploidy Score, were the most high-expressed in C1 and the least expressed in C3. ImmuneScore was the highest in C3 type, suggesting greater immune infiltration in C3 subtype. C1 subtypes had higher TIDE scores, indicating that C1 subtypes may benefit less from immunotherapy. Generally, C3 subtype presented highest PCD patterns scores. With four genes, ANLN, FAM83A, RHOV and PARP15, we constructed a LUAD risk prediction model with significant differences in immune cell composition, cell cycle related pathways between the two risk groups. Samples in C1 and high group were more sensitive to chemotherapy drug. The score of PCD were differences in high- and low-groups. Finally, we combined Riskscore and clinical features to improve the performance of the prediction model, and the calibration curve and decision curve verified that the great robustness of the model. Conclusion: We identified three stable molecular subtypes of LUAD and constructed a prognostic model based on NK cell-related genes, maybe have a greater potential for application in predicting immunotherapy response and patient prognosis.

Distribution and prognostic impact of EGFR and KRAS mutations according to histological subtype and tumor invasion status in pTis-3N0M0 lung adenocarcinoma

BackgroundThe prognostic impact of EGFR mutation as major targetable somatic gene variant on lung adenocarcinoma is controversial. KRAS is another major somatic variant in lung adenocarcinoma, and a therapeutic agent for KRAS G12C became available in clinical settings. These mutations represent clinicopathological features of lung adenocarcinoma and can guide the treatment choice after recurrence. We evaluated the prognostic impact of EGFR and KRAS mutations by considering other clinicopathological recurrence risks in resected pTis-3N0M0 lung adenocarcinoma.MethodsClinicopathological features related to recurrence and genetic status were estimated in consecutive 877 resected cases. Recurrence-free survival (RFS), cumulative recurrence rate (CRR), and overall survival (OS) were compared. Uni- and multivariate analyses for RFS were performed after excluding cases with little or no recurrence risks.ResultsEGFR mutation was more likely to be harbored in female, never-smoker, or patients accompanied by > 5% lepidic component. KRAS mutation was more likely to be harbored in patients with current/ex-smoking history, International Association for the Study of Lung Cancer (IASLC) grade 3, or accompanied lymphatic or vascular invasion. In IASLC grade 2 and 3 patients, EGFR or KRAS mutation cases had significantly worse 5-year RFS than wild type patients (76.9% vs. 85.0%, hazard ratio [HR] = 1.55, 95% confidence interval [CI] = 1.62–6.41, P < 0.001). EGFR or KRAS mutation cases had significantly higher 5-year CRR than wild type patients (17.7% vs. 9.8%, HR = 1.69, 95% CI = 1.44–6.59, P = 0.0038). KRAS mutation cases had higher 5-year CRR than EGFR mutation cases (16.7% vs. 21.4%, HR = 1.62, 95% CI = 0.96–7.19, P = 0.061). There was no significant difference in OS between cohorts. Multivariate analysis revealed that a positive EGFR/KRAS mutation status was risk factor for worse RFS (HR = 2.007, 95% CI = 1.265–3.183, P = 0.003).ConclusionPositive EGFR and KRAS mutation statuses were risk factors for recurrence in resected IASLC grade 2 and 3 patients. KRAS mutations were more likely to be confirmed in cases with an increased risk of recurrence. EGFR and KRAS mutation statuses should be evaluated simultaneously when assessing the risk of recurrence.