Integrated multiomics analysis and machine learning refine molecular subtypes and prognosis for muscle-invasive urothelial cancer

Chu, Guangdi; Ji, Xiaoyu; Wang, Yonghua; Niu, Haitao

doi:10.1016/j.omtn.2023.06.001

Cited by 16 publications

(10 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to prevent unsuitable model approaches owing to personal preferences, we combined 10 machine learning algorithms into 88 combinations and chose the best model. This combined ML model approach has been used to predict the prognosis of bladder cancer [ 41 ], muscle-invasive urothelial cancer [ 42 ], pancreatic cancer [ 29 ], and endometrial cancer [ 43 ], as well as validated in multiple datasets with good robust and AUC values. Importantly, the optimal model demonstrated strong and stable prediction performance by evaluating the C-index, IBS, and mean MSE.…”

Section: Discussionmentioning

confidence: 99%

Comprehensive machine learning-based preoperative blood features predict the prognosis for ovarian cancer

Wu,

Gu,

Yang

et al. 2024

BMC Cancer

View full text Add to dashboard Cite

Purpose Significant advancements in improving ovarian cancer (OC) outcomes have been limited over the past decade. To predict prognosis and improve outcomes of OC, we plan to develop and validate a robust prognosis signature based on blood features. Methods We screened age and 33 blood features from 331 OC patients. Using ten machine learning algorithms, 88 combinations were generated, from which one was selected to construct a blood risk score (BRS) according to the highest C-index in the test dataset. Results Stepcox (both) and Enet (alpha = 0.7) performed the best in the test dataset with a C-index of 0.711. Meanwhile, the low RBS group possessed observably prolonged survival in this model. Compared to traditional prognostic-related features such as age, stage, grade, and CA125, our combined model had the highest AUC values at 3, 5, and 7 years. According to the results of the model, BRS can provide accurate predictions of OC prognosis. BRS was also capable of identifying various prognostic stratifications in different stages and grades. Importantly, developing the nomogram may improve performance by combining BRS and stage. Conclusion This study provides a valuable combined machine-learning model that can be used for predicting the individualized prognosis of OC patients.

show abstract

Section: Discussionmentioning

confidence: 99%

Comprehensive machine learning-based preoperative blood features predict the prognosis for ovarian cancer

Wu,

Gu,

Yang

et al. 2024

BMC Cancer

View full text Add to dashboard Cite

show abstract

“…Enrichment scores for these gene sets were computed using the GSVA package, which allowed us to assess the level of activity of these genes in the context of chromatin remodelling. Additionally, we evaluated the GSVA scores for three gene sets related to treatment response, which were also gathered from the literature 29 . The ComplexHeatmap package was utilised to visualise these scores in a heatmap format, providing insights into the potential treatment responsiveness and malignancy of the subgroups.…”

Section: Methodsmentioning

confidence: 99%

“…Additionally, we evaluated the GSVA scores for three gene sets related to treatment response, which were also gathered from the literature. 29 The ComplexHeatmap package was utilised to visualise these scores in a heatmap format, providing insights into the potential treatment responsiveness and malignancy of the subgroups.…”

Section: Methodsmentioning

confidence: 99%

Inflammasome‐related gene signatures as prognostic biomarkers in osteosarcoma

Zhang,

Han,

Cao

et al. 2024

J Cellular Molecular Medi

View full text Add to dashboard Cite

Osteosarcoma, the primary bone cancer in adolescents and young adults, is notorious for its aggressive growth and metastatic potential. Our study delved into the prognostic impact of inflammasome‐related gene signatures in osteosarcoma patients, employing comprehensive genetic profiling to uncover signatures linked with patient outcomes. We identified three patient subgroups through consensus clustering, with one showing worse survival rates correlated with high FGFR3 and RARB expressions. Immune profiling revealed significant immune cell infiltration differences among these subgroups, affecting survival. Utilising advanced machine learning, including StepCox and gradient boosting machine algorithms, we developed a prognostic model with a notable c‐index of 0.706, highlighting CD36 and MYD88 as key genes. Higher inflammasome risk scores from our model were associated with poorer survival, corroborated across datasets. In vitro experiments validated CD36 and MYD88's roles in promoting osteosarcoma cell proliferation, invasion and migration, emphasising their therapeutic potential. This research offers new insights into inflammasomes' role in osteosarcoma, introducing novel biomarkers for risk assessment and potential therapeutic targets. Our findings suggest a pathway towards personalised treatment strategies, potentially improving patient outcomes in osteosarcoma.

show abstract

“…Furthermore, we collected complete information from four HCC cohorts as the validation set, including three from the Gene Expression Omnibus (http://www.ncbi.nlm.nih.gov/geo; GSE76427, GSE14520, GSE54236), and one from the International Cancer Genome Consortium (https://dcc.icgc.org/; ICGC_LIRI). Subsequently, we employed the limma package to perform background correction, log2 transformation, and quantile normalization on the data (21). To evaluate the homogeneity of the distribution of expression levels among samples, box plots were utilized as a visualization tool.…”

Section: Methodsmentioning

confidence: 99%

“…A lower IC50 value implies greater sample sensitivity to the drug under consideration. The drugs sensitivity prediction of CMOIC subtype were based on public databases CTRP2.0 and CTRP2.0, which include sensitivity data for 481 and 1448 compounds, respectively (21). The Area under the receiver operating characteristic curve (AUC) was calculated to assess drug sensitivity in these two datasets, and a lower AUC value indicates increased sensitivity to treatment.…”

Section: Screening For Sensitive Drugsmentioning

confidence: 99%

Integrated multi-omics analysis and machine learning based on O_linked_glycosylation genes refine molecular subtypes and prognosis for hepatocellular carcinoma

Li,

Gao,

et al. 2023

Preprint

View full text Add to dashboard Cite

O-glycosylation exerts significant influence on cellular physiological processes and disease regulation by modulating the structure, function, and stability of proteins. However, there is still a lack of research focusing on O-glycosylation in relation to the prognosis of HCC patients. Here we explored expression and function of O-glycosylation gene in HCC from both bulk and single-cell perspectives. The multi-omics data associated with O-glycosylation, identified through the Weighted Gene Co-expression Network Analysis (WGCNA), combined with ten distinct clustering algorithms to define the molecular subgroups of HCC. CS1 was characterized by significant genomic variation, moderate immune cell infiltration and immune function enrichment. CS2 performed a better prognosis, and was featured by stable genomic structure, an immune-hot phenotype with rich immune cell infiltration and sensitive to immunotherapy. CS3 was characterized by a poor prognosis, outstanding genomic instability, an immune-cold phenotype, but can benefit more from treatment with drugs such as sorafenib, cisplatin, paclitaxel, and gemcitabine. Ultimately, we re-emphasized O-glycosylation genes in individual HCC patients, deploying 59 types of machine learning to construct and evaluate the prognostic signature. The microarray results indicated a pronounced upregulation of Oglycosylation hub genes involved in HCC stratification and modeling within HCC tumorous tissues. In conclusion, we have highlighted the significant impacts of O-glycosylation on HCC by redefining the subtypes of HCC as well as constructing the CMLS. This research has established an optimized decision-making platform that enables precise stratification of HCC patients, refines tumor treatment plans, and predicts patient survivability holding broad clinical implications.

show abstract

Integrated multiomics analysis and machine learning refine molecular subtypes and prognosis for muscle-invasive urothelial cancer

Cited by 16 publications

References 64 publications

Comprehensive machine learning-based preoperative blood features predict the prognosis for ovarian cancer

Comprehensive machine learning-based preoperative blood features predict the prognosis for ovarian cancer

Inflammasome‐related gene signatures as prognostic biomarkers in osteosarcoma

Integrated multi-omics analysis and machine learning based on O_linked_glycosylation genes refine molecular subtypes and prognosis for hepatocellular carcinoma

Contact Info

Product

Resources

About