Prognostic model development for classification of colorectal adenocarcinoma by using machine learning model based on feature selection technique boruta

Maurya, Neha; Kushwah, Shikha; Kushwaha, Sandeep; Chawade, Aakash; Mani, Ashutosh

doi:10.1038/s41598-023-33327-4

Cited by 15 publications

(5 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[ 37,38 ] The genes included in their models were as follows: PTGER2, FGF2, IGFBP3, ANGPTL4, DKK1, WNT16, SPP1, ZNF532, COLEC12, DPP7/2, YWHAB, MCM4, FBXO46, GLP2R, VSTM2A, and so on. [ 37,39,40 ] In our model, we included directly nine key EIOGs, and finally got a mode with the highest AUC reached 0.788, which indicated that EIOS alone play an important role in the CRC progression. We also proposed that a better prognostic model could be established based on a comprehensive understanding all these genes.…”

Section: Discussionmentioning

confidence: 99%

Enterotoxin‐related genes PPFIA4 and SCN3B promote colorectal cancer development and progression

Zheng,

Yang,

Sun

et al. 2024

J Biochem & Molecular Tox

View full text Add to dashboard Cite

To identify the role of enterotoxin‐related genes in colorectal cancer (CRC) development and progression. Upregulated differentially expressed genes shared by three out of five Gene Expression Omnibus (GEO) data sets were included to screen the key enterotoxin‐induced oncogenes (EIOGs) according to criteria oncogene definition, enrichment, and protein–protein interaction (PPI) network analysis, followed by prognosis survival, immune infiltration, and protential drugs analyses was performed via integration of RNA‐sequencing data and The Cancer Genome Atlas‐derived clinical profiles. We screened nine common key EIOGs from at least three GEO data sets. A Cox proportional hazards regression models verified that more alive cases, decreased overall survival, and highest 4‐year survival prediction in CRC patients with high‐risk score. Protein tyrosine phosphatase receptor type F polypeptide‐interacting protein alpha‐4 (PPFIA4), STY11, SCN3B, and SPTBN5 were shared in the same PPI network. Immune infiltration results showed that SCN3B and synaptotagmin 11 expression were obviously associated with B cell, macrophage, myeloid dendritic cell, neutrophils, and T cell CD4+ and CD8+ in both colon adenocarcinoma and rectal adenocarcinoma. CHIR‐99021, MLN4924, and YK4‐279 were identified as the potential drugs for treatment. Finally, upregulated EIOGs genes PPFIA4 and SCN3B were found in colon adenocarcinoma and PPFIA4 and SCN3B were proved to promote cell proliferation and migration in vitro. We demonstrated here that EIOGs promoting a malignancy phenotype was related with poor survival and prognosis in CRC, which might be served as novel therapeutic targets in CRC management.

show abstract

Section: Discussionmentioning

confidence: 99%

Enterotoxin‐related genes PPFIA4 and SCN3B promote colorectal cancer development and progression

Zheng,

Yang,

Sun

et al. 2024

J Biochem & Molecular Tox

View full text Add to dashboard Cite

show abstract

“…Data was then transformed with the classical variance stabilizing transformation method. Finally, we retained protein coding genes and ncRNAs with a fold change of at least 2 and an adjusted P -value <0.001 or 0.05 for the HEFS standard mode or light mode, respectively ( 33–35 ).…”

Section: Methodsmentioning

confidence: 99%

Optimizing hybrid ensemble feature selection strategies for transcriptomic biomarker discovery in complex diseases

Claude,

Leclercq,

Thébault

et al. 2024

NAR Genomics and Bioinformatics

View full text Add to dashboard Cite

Biomedical research takes advantage of omic data, such as transcriptomics, to unravel the complexity of diseases. A conventional strategy identifies transcriptomic biomarkers characterized by expression patterns associated with a phenotype by relying on feature selection approaches. Hybrid ensemble feature selection (HEFS) has become increasingly popular as it ensures robustness of the selected features by performing data and functional perturbations. However, it remains difficult to make the best suited choices at each step when designing such approaches. We conducted an extensive analysis of four possible HEFS scenarios for the identification of Stage IV colorectal, Stage I kidney and lung and Stage III endometrial cancer biomarkers from transcriptomic data. These scenarios investigate the use of two types of feature reduction by filters (differentially expressed genes and variance) conjointly with two types of resampling strategies (repeated holdout by distribution-balanced stratified and random stratified) for downstream feature selection through an aggregation of thousands of wrapped machine learning models. Based on our results, we emphasize the advantages of using HEFS approaches to identify complex disease biomarkers, given their ability to produce generalizable and stable results to both data and functional perturbations. Finally, we highlight critical issues that need to be considered in the design of such strategies.

show abstract

“…The methods include none (all features in the space included), recursive feature elimination (RFE) until 5 features, and the boruta feature selection method [ 18 ]. The boruta method was evaluated due to the effectiveness of the approach in previous studies in the medical domain [ 19 – 23 ]. The boruta method utilised RF and XGBoost models respectively when they were being trained.…”

Section: Methodsmentioning

confidence: 99%

Machine learning pipeline for blood culture outcome prediction using Sysmex XN-2000 blood sample results in Western Australia

McFadden,

Inglis,

Reynolds

2023

BMC Infect Dis

View full text Add to dashboard Cite

Background Bloodstream infections (BSIs) are a significant burden on the global population and represent a key area of focus in the hospital environment. Blood culture (BC) testing is the standard diagnostic test utilised to confirm the presence of a BSI. However, current BC testing practices result in low positive yields and overuse of the diagnostic test. Diagnostic stewardship research regarding BC testing is increasing, and becoming more important to reduce unnecessary resource expenditure and antimicrobial use, especially as antimicrobial resistance continues to rise. This study aims to establish a machine learning (ML) pipeline for BC outcome prediction using data obtained from routinely analysed blood samples, including complete blood count (CBC), white blood cell differential (DIFF), and cell population data (CPD) produced by Sysmex XN-2000 analysers. Methods ML models were trained using retrospective data produced between 2018 and 2019, from patients at Sir Charles Gairdner hospital, Nedlands, Western Australia, and processed at Pathwest Laboratory Medicine, Nedlands. Trained ML models were evaluated using stratified 10-fold cross validation. Results Two ML models, an XGBoost model using CBC/DIFF/CPD features with boruta feature selection (BFS) , and a random forest model trained using CBC/DIFF features with BFS were selected for further validation after obtaining AUC scores of $$0.76 \pm 0.04$$ 0.76 ± 0.04 and $$0.75 \pm 0.04$$ 0.75 ± 0.04 respectively using stratified 10-fold cross validation. The XGBoost model obtained an AUC score of 0.76 on a internal validation set. The random forest model obtained AUC scores of 0.82 and 0.76 on internal and external validation datasets respectively. Conclusions We have demonstrated the utility of using an ML pipeline combined with CBC/DIFF, and CBC/DIFF/CPD feature spaces for BC outcome prediction. This builds on the growing body of research in the area of BC outcome prediction, and provides opportunity for further research.

show abstract

Prognostic model development for classification of colorectal adenocarcinoma by using machine learning model based on feature selection technique boruta

Cited by 15 publications

References 44 publications

Enterotoxin‐related genes PPFIA4 and SCN3B promote colorectal cancer development and progression

Enterotoxin‐related genes PPFIA4 and SCN3B promote colorectal cancer development and progression

Optimizing hybrid ensemble feature selection strategies for transcriptomic biomarker discovery in complex diseases

Machine learning pipeline for blood culture outcome prediction using Sysmex XN-2000 blood sample results in Western Australia

Contact Info

Product

Resources

About