Deep Learning-Based Protein Features Predict Overall Survival and Chemotherapy Benefit in Gastric Cancer

Zhao, Xuefei; Xia, Xia; Wang, Xinyue; Bai, Mingze; Zhan, Dongdong; Shu, Kunxian

doi:10.3389/fonc.2022.847706

Cited by 5 publications

(5 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This new feature subset could be used to build a new machine learning model and its performance could be analyzed. Autoencoder neural network has been recently used extensively in medical image processing [60][61][62]. We plan to apply these networks to our dataset to see if we can come up with a better performance.…”

Section: Discussionmentioning

confidence: 99%

A Neoteric Feature Extraction Technique to Predict the Survival of Gastric Cancer Patients

Islam,

Abdoli,

Alam

et al. 2024

Diagnostics

View full text Add to dashboard Cite

Background: At the time of cancer diagnosis, it is crucial to accurately classify malignant gastric tumors and the possibility that patients will survive. Objective: This study aims to investigate the feasibility of identifying and applying a new feature extraction technique to predict the survival of gastric cancer patients. Methods: A retrospective dataset including the computed tomography (CT) images of 135 patients was assembled. Among them, 68 patients survived longer than three years. Several sets of radiomics features were extracted and were incorporated into a machine learning model, and their classification performance was characterized. To improve the classification performance, we further extracted another 27 texture and roughness parameters with 2484 superficial and spatial features to propose a new feature pool. This new feature set was added into the machine learning model and its performance was analyzed. To determine the best model for our experiment, Random Forest (RF) classifier, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Naïve Bayes (NB) (four of the most popular machine learning models) were utilized. The models were trained and tested using the five-fold cross-validation method. Results: Using the area under ROC curve (AUC) as an evaluation index, the model that was generated using the new feature pool yields AUC = 0.98 ± 0.01, which was significantly higher than the models created using the traditional radiomics feature set (p < 0.04). RF classifier performed better than the other machine learning models. Conclusions: This study demonstrated that although radiomics features produced good classification performance, creating new feature sets significantly improved the model performance.

show abstract

Section: Discussionmentioning

confidence: 99%

A Neoteric Feature Extraction Technique to Predict the Survival of Gastric Cancer Patients

Islam,

Abdoli,

Alam

et al. 2024

Diagnostics

View full text Add to dashboard Cite

show abstract

“…Enrichment analysis showed patients with good revealed outcomes of the pathways that were related to DNA replication, cell cycle, and programmed cell death. Meanwhile, patients with poor outcomes are enriched in ECM-related pathways [52]. ECM constituents that characterize the matrisome of GC contexts were identified.…”

Section: Proteomics-based Validation Of Predictive and Prognostic Mar...mentioning

confidence: 99%

Bioinformatics Analysis and Validation of Potential Markers Associated with Prediction and Prognosis of Gastric Cancer

Matsuoka,

Yashiro

2024

IJMS

View full text Add to dashboard Cite

Gastric cancer (GC) is one of the most common cancers worldwide. Most patients are diagnosed at the progressive stage of the disease, and current anticancer drug advancements are still lacking. Therefore, it is crucial to find relevant biomarkers with the accurate prediction of prognoses and good predictive accuracy to select appropriate patients with GC. Recent advances in molecular profiling technologies, including genomics, epigenomics, transcriptomics, proteomics, and metabolomics, have enabled the approach of GC biology at multiple levels of omics interaction networks. Systemic biological analyses, such as computational inference of “big data” and advanced bioinformatic approaches, are emerging to identify the key molecular biomarkers of GC, which would benefit targeted therapies. This review summarizes the current status of how bioinformatics analysis contributes to biomarker discovery for prognosis and prediction of therapeutic efficacy in GC based on a search of the medical literature. We highlight emerging individual multi-omics datasets, such as genomics, epigenomics, transcriptomics, proteomics, and metabolomics, for validating putative markers. Finally, we discuss the current challenges and future perspectives to integrate multi-omics analysis for improving biomarker implementation. The practical integration of bioinformatics analysis and multi-omics datasets under complementary computational analysis is having a great impact on the search for predictive and prognostic biomarkers and may lead to an important revolution in treatment.

show abstract

“…[ 1 , 2 ] According to GLOBOCAN statistics, in 2020, there were an estimated 19.3 million new cases and 10 million cancer deaths worldwide, with gastrointestinal cancers being one of the leading causes of death. [ 3 ] Currently, GC is mainly treated by surgical resection, radiotherapy, chemotherapy and targeted therapy, [ 4 , 5 ] but for metastatic gastric cancer patients, surgery is difficult to eradicate, and chemotherapeutic drugs not only have strong toxicity and side effects, but also lead to drug resistance in long-term use, [ 6 , 7 ] therefore, the development of new drugs with low side effects and anticancer effects is of great clinical significance. Studies have shown that some natural Chinese medicinal ingredients show unique advantages in anticancer, which can not only alleviate the clinical problems of strong side effects of chemotherapeutic drugs and drug resistance, but also enhance the patient own immune system, play an anti-tumor activity, thus improving the patient quality of life.…”

Section: Introductionmentioning

confidence: 99%

Banxia-Shengjiang drug pair inhibits gastric cancer development and progression by improving body immunity

Yang,

Yuan,

Liu

et al. 2024

Medicine

View full text Add to dashboard Cite

To investigate the mechanism of action of Banxia-Shengjiang drug pair on the inhibition of gastric cancer (GC) using network pharmacology and bioinformatics techniques. The action targets of the Banxia (Pinellia ternata (Thunb.) Makino) -Shengjiang (Zingiber officinale Roscoe) drug pair obtained from the TCMSP database were intersected with differentially expressed genes (DEGs) and GC-related genes, and the intersected genes were analyzed for pathway enrichment to identify the signaling pathways and core target genes. Subsequently, the core target genes were analyzed for clinical relevance gene mutation analysis, methylation analysis, immune infiltration analysis and immune cell analysis. Finally, by constructing the PPI network of hub genes and corresponding active ingredients, the key active ingredients of the Banxia-Shengjiang drug pair were screened for molecular docking with the hub genes. In this study, a total of 557 target genes of Banxia-Shengjiang pairs, 7754 GC-related genes and 1799 DEGs in GC were screened. Five hub genes were screened, which were PTGS2, MMP9, PPARG, MMP2, and CXCR4. The pathway enrichment analyses showed that the intersecting genes were associated with RAS/MAPK signaling pathway. In addition, the clinical correlation analysis showed that hub genes were differentially expressed in GC and was closely associated with immune infiltration and immunotherapy. The results of single nucleotide variation (SNV) and copy number variation (CNV) indicated that mutations in the hub genes were associated with the survival of gastric cancer patients. Finally, the PPI network and molecular docking results showed that PTGS2 and MMP9 were potentially important targets for the inhibition of GC by Banxia-Shengjiang drug pair, while cavidine was an important active ingredient for the inhibition of GC by Banxia-Shengjiang drug pair. Banxia-Shengjiang drug pair may regulate the immune function and inhibit GC by modulating the expression of core target genes such as RAS/MAPK signaling pathway, PTGS2 and MMP9.

show abstract

Deep Learning-Based Protein Features Predict Overall Survival and Chemotherapy Benefit in Gastric Cancer

Cited by 5 publications

References 58 publications

A Neoteric Feature Extraction Technique to Predict the Survival of Gastric Cancer Patients

A Neoteric Feature Extraction Technique to Predict the Survival of Gastric Cancer Patients

Bioinformatics Analysis and Validation of Potential Markers Associated with Prediction and Prognosis of Gastric Cancer

Banxia-Shengjiang drug pair inhibits gastric cancer development and progression by improving body immunity

Contact Info

Product

Resources

About