Machine learning modeling and prognostic value analysis of invasion-related genes in cutaneous melanoma

Yang, Enyu; Ding, Qianyun; Fan, Xin; Ye, Haihan; Xuan, Cheng; Zhao, Shuo; Ji, Qing; Yu, Wei; Liu, Yongfu; Cao, Jun; Fang, Man; Ding, Xiaohu

doi:10.1016/j.compbiomed.2023.107089

Cited by 7 publications

(3 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It also plays an important role in immunotherapy with anti‐PD‐1 and anti‐CTLA‐4 antibodies in the treatment of breast cancer patients 46,47 . We found THEMIS was an independent prognosis factor of PFS, and it has previously been reported that the absence of THEMIS results in defective TCR signaling in CD4+ T cells, leading to a reduction in their effector functions 48 . To the best of our knowledge, at present, there is no specific research that explores the relationship between TRBV12‐5 and the TME.…”

Section: Discussionmentioning

confidence: 56%

“… 46 , 47 We found THEMIS was an independent prognosis factor of PFS, and it has previously been reported that the absence of THEMIS results in defective TCR signaling in CD4+ T cells, leading to a reduction in their effector functions. 48 To the best of our knowledge, at present, there is no specific research that explores the relationship between TRBV12‐5 and the TME. In our study, the gene risk score was an independent factor of PFS and the model could predict PFS more accurately than PD‐L1 expression.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Identification of a risk score model based on tertiary lymphoid structure‐related genes for predicting immunotherapy efficacy in non‐small cell lung cancer

Mei,

Liu,

Huang

et al. 2024

Thoracic Cancer

View full text Add to dashboard Cite

BackgroundTertiary lymphoid structures (TLSs) affect the prognosis and efficacy of immunotherapy in patients with non‐small cell lung cancer (NSCLC), but the underlying mechanisms are not well understood.MethodsTLSs were identified and categorized online from the Cancer Digital Slide Archive (CDSA). Overall survival (OS) and disease‐free survival (DFS) were analyzed. GSE111414 and GSE136961 datasets were downloaded from the GEO database. GSVA, GO and KEGG were used to explore the signaling pathways. Immune cell infiltration was analyzed by xCell, ssGSEA and MCP‐counter. The analysis of WGCNA, Lasso and multivariate cox regression were conducted to develop a gene risk score model based on the SU2C‐MARK cohort.ResultsTLS‐positive was a protective factor for OS according to multivariate cox regression analysis (p = 0.029). Both the TLS‐positive and TLS‐mature groups exhibited genes enrichment in immune activation pathways. The TLS‐mature group showed more activated dendritic cell infiltration than the TLS‐immature group. We screened TLS‐related genes using WGCNA. Lasso and multivariate cox regression analysis were used to construct a five‐genes (RGS8, RUF4, HLA‐DQB2, THEMIS, and TRBV12‐5) risk score model, the progression free survival (PFS) and OS of patients in the low‐risk group were markedly superior to those in the high‐risk group (p < 0.0001; p = 0.0015, respectively). Calibration and ROC curves indicated that the combined model with gene risk score and clinical features could predict the PFS of patients who have received immunotherapy more accurately than a single clinical factor.ConclusionsOur data suggested a pivotal role of TLSs formation in survival outcome and immunotherapy response of NSCLC patients. Tumors with mature TLS formation showed more activated immune microenvironment. In addition, the model constructed by TLS‐related genes could predict the response to immunotherapy and is meaningful for clinical decision‐making.

show abstract

Section: Discussionmentioning

confidence: 56%

Section: Discussionmentioning

confidence: 99%

Identification of a risk score model based on tertiary lymphoid structure‐related genes for predicting immunotherapy efficacy in non‐small cell lung cancer

Mei,

Liu,

Huang

et al. 2024

Thoracic Cancer

View full text Add to dashboard Cite

show abstract

“…In the early 2000s, most automated melanoma classification solutions primarily relied on the utilization of manually crafted, lowlevel features such as shape, color, and texture [19]. However, recent studies, exemplified by [20], have signaled a shift in melanoma identification and recognition methodologies. This transition signifies a departure from the heavy reliance on manual feature engineering, marking a substantial evolution in the field.…”

Section: Literature Reviewmentioning

confidence: 99%

Optimizing Hyperparameters for Improved Melanoma Classification using Metaheuristic Algorithm

Adamu,

Alhussian,

Aziz

et al. 2023

IJACSA

View full text Add to dashboard Cite

Melanoma, a prevalent and formidable skin cancer, necessitates early detection for improved survival rates. The rising incidence of melanoma poses significant challenges to healthcare systems worldwide. While deep neural networks offer the potential for precise melanoma classification, the optimization of hyperparameters remains a major obstacle. This paper introduces a groundbreaking approach that harnesses the Manta Rays Foraging Optimizer (MRFO) to empower melanoma classification. MRFO efficiently fine-tunes hyperparameters for a Convolutional Neural Network (CNN) using the ISIC 2019 dataset, which comprises 776 images (438 melanoma, 338 nonmelanoma). The proposed cost-effective DenseNet121 model surpasses other optimization methods in various metrics during training, testing, and validation. It achieves an impressive accuracy of 99.26%, an AUC of 99.56%, an F1 score of 0.9091, a precision of 94.06%, and a recall of 87.96%. Comparative analysis with EfficientB1, EfficientB7, EfficientNetV2B0, NesNetLarge, ResNet50, VGG16, and VGG19 models demonstrates its superiority. These findings underscore the potential of the novel MRFO-based approach in achieving superior accuracy for melanoma classification. The proposed method has the potential to be a valuable tool for early detection and improved patient outcomes.

show abstract

Lycorine suppresses the malignancy of breast carcinoma by modulating epithelial mesenchymal transition and β-catenin signaling

Sun¹,

Gu²,

Gao³

et al. 2023

Pharmacological Research

View full text Add to dashboard Cite

Machine learning modeling and prognostic value analysis of invasion-related genes in cutaneous melanoma

Cited by 7 publications

References 47 publications

Identification of a risk score model based on tertiary lymphoid structure‐related genes for predicting immunotherapy efficacy in non‐small cell lung cancer

Identification of a risk score model based on tertiary lymphoid structure‐related genes for predicting immunotherapy efficacy in non‐small cell lung cancer

Optimizing Hyperparameters for Improved Melanoma Classification using Metaheuristic Algorithm

Lycorine suppresses the malignancy of breast carcinoma by modulating epithelial mesenchymal transition and β-catenin signaling

Contact Info

Product

Resources

About