A Fecal-Microbial-Extracellular-Vesicles-Based Metabolomics Machine Learning Framework and Biomarker Discovery for Predicting Colorectal Cancer Patients

Colorectal cancer (CRC) is one of the most common and lethal diseases among all types of cancer, and metabolites play a significant role in the development of this complex disease. This study aimed to identify potential biomarkers and targets in the diagnosis and treatment of CRC using high-throughp...

Full description

Bibliographic Details
Main Authors: Fatma Hilal Yagin, Abedalrhman Alkhateeb, Cemil Colak, Mohammad Azzeh, Burak Yagin, Luis Rueda
Format: Article
Language:English
Published: MDPI AG 2023-04-01
Series:Metabolites
Subjects:
Online Access:https://www.mdpi.com/2218-1989/13/5/589
_version_ 1797599113119793152
author Fatma Hilal Yagin
Abedalrhman Alkhateeb
Cemil Colak
Mohammad Azzeh
Burak Yagin
Luis Rueda
author_facet Fatma Hilal Yagin
Abedalrhman Alkhateeb
Cemil Colak
Mohammad Azzeh
Burak Yagin
Luis Rueda
author_sort Fatma Hilal Yagin
collection DOAJ
description Colorectal cancer (CRC) is one of the most common and lethal diseases among all types of cancer, and metabolites play a significant role in the development of this complex disease. This study aimed to identify potential biomarkers and targets in the diagnosis and treatment of CRC using high-throughput metabolomics. Metabolite data extracted from the feces of CRC patients and healthy volunteers were normalized with the median normalization and Pareto scale for multivariate analysis. Univariate ROC analysis, the <i>t</i>-test, and analysis of fold changes (FCs) were applied to identify biomarker candidate metabolites in CRC patients. Only metabolites that overlapped the two different statistical approaches (false-discovery-rate-corrected <i>p</i>-value < 0.05 and AUC > 0.70) were considered in the further analysis. Multivariate analysis was performed with biomarker candidate metabolites based on linear support vector machines (SVM), partial least squares discrimination analysis (PLS-DA), and random forests (RF). The model identified five biomarker candidate metabolites that were significantly and differently expressed (adjusted <i>p</i>-value < 0.05) in CRC patients compared to healthy controls. The metabolites were succinic acid, aminoisobutyric acid, butyric acid, isoleucine, and leucine. Aminoisobutyric acid was the metabolite with the highest discriminatory potential in CRC, with an AUC equal to 0.806 (95% CI = 0.700–0.897), and was down-regulated in CRC patients. The SVM model showed the most substantial discrimination capacity for the five metabolites selected in the CRC screening, with an AUC of 0.985 (95% CI: 0.94–1).
first_indexed 2024-03-11T03:30:08Z
format Article
id doaj.art-300a0010df58444badc7e762f6b68397
institution Directory Open Access Journal
issn 2218-1989
language English
last_indexed 2024-03-11T03:30:08Z
publishDate 2023-04-01
publisher MDPI AG
record_format Article
series Metabolites
spelling doaj.art-300a0010df58444badc7e762f6b683972023-11-18T02:25:00ZengMDPI AGMetabolites2218-19892023-04-0113558910.3390/metabo13050589A Fecal-Microbial-Extracellular-Vesicles-Based Metabolomics Machine Learning Framework and Biomarker Discovery for Predicting Colorectal Cancer PatientsFatma Hilal Yagin0Abedalrhman Alkhateeb1Cemil Colak2Mohammad Azzeh3Burak Yagin4Luis Rueda5Department of Biostatistics and Medical Informatics, Faculty of Medicine, Inonu University, 44280 Malatya, TurkeySoftware Engineering Department, King Hussein School of Computing Science, Princess Sumaya University for Technology, Amman P.O. Box 1438, JordanDepartment of Biostatistics and Medical Informatics, Faculty of Medicine, Inonu University, 44280 Malatya, TurkeyData Science Department, King Hussein School of Computing Science, Princess Sumaya University for Technology, Amman P.O. Box 1438, JordanDepartment of Biostatistics and Medical Informatics, Faculty of Medicine, Inonu University, 44280 Malatya, TurkeySchool of Computer Science, University of Windsor, Windsor, ON N9B 3P4, CanadaColorectal cancer (CRC) is one of the most common and lethal diseases among all types of cancer, and metabolites play a significant role in the development of this complex disease. This study aimed to identify potential biomarkers and targets in the diagnosis and treatment of CRC using high-throughput metabolomics. Metabolite data extracted from the feces of CRC patients and healthy volunteers were normalized with the median normalization and Pareto scale for multivariate analysis. Univariate ROC analysis, the <i>t</i>-test, and analysis of fold changes (FCs) were applied to identify biomarker candidate metabolites in CRC patients. Only metabolites that overlapped the two different statistical approaches (false-discovery-rate-corrected <i>p</i>-value < 0.05 and AUC > 0.70) were considered in the further analysis. Multivariate analysis was performed with biomarker candidate metabolites based on linear support vector machines (SVM), partial least squares discrimination analysis (PLS-DA), and random forests (RF). The model identified five biomarker candidate metabolites that were significantly and differently expressed (adjusted <i>p</i>-value < 0.05) in CRC patients compared to healthy controls. The metabolites were succinic acid, aminoisobutyric acid, butyric acid, isoleucine, and leucine. Aminoisobutyric acid was the metabolite with the highest discriminatory potential in CRC, with an AUC equal to 0.806 (95% CI = 0.700–0.897), and was down-regulated in CRC patients. The SVM model showed the most substantial discrimination capacity for the five metabolites selected in the CRC screening, with an AUC of 0.985 (95% CI: 0.94–1).https://www.mdpi.com/2218-1989/13/5/589colorectal cancermetabolomics profilingmachine learningbiomarker discovery
spellingShingle Fatma Hilal Yagin
Abedalrhman Alkhateeb
Cemil Colak
Mohammad Azzeh
Burak Yagin
Luis Rueda
A Fecal-Microbial-Extracellular-Vesicles-Based Metabolomics Machine Learning Framework and Biomarker Discovery for Predicting Colorectal Cancer Patients
Metabolites
colorectal cancer
metabolomics profiling
machine learning
biomarker discovery
title A Fecal-Microbial-Extracellular-Vesicles-Based Metabolomics Machine Learning Framework and Biomarker Discovery for Predicting Colorectal Cancer Patients
title_full A Fecal-Microbial-Extracellular-Vesicles-Based Metabolomics Machine Learning Framework and Biomarker Discovery for Predicting Colorectal Cancer Patients
title_fullStr A Fecal-Microbial-Extracellular-Vesicles-Based Metabolomics Machine Learning Framework and Biomarker Discovery for Predicting Colorectal Cancer Patients
title_full_unstemmed A Fecal-Microbial-Extracellular-Vesicles-Based Metabolomics Machine Learning Framework and Biomarker Discovery for Predicting Colorectal Cancer Patients
title_short A Fecal-Microbial-Extracellular-Vesicles-Based Metabolomics Machine Learning Framework and Biomarker Discovery for Predicting Colorectal Cancer Patients
title_sort fecal microbial extracellular vesicles based metabolomics machine learning framework and biomarker discovery for predicting colorectal cancer patients
topic colorectal cancer
metabolomics profiling
machine learning
biomarker discovery
url https://www.mdpi.com/2218-1989/13/5/589
work_keys_str_mv AT fatmahilalyagin afecalmicrobialextracellularvesiclesbasedmetabolomicsmachinelearningframeworkandbiomarkerdiscoveryforpredictingcolorectalcancerpatients
AT abedalrhmanalkhateeb afecalmicrobialextracellularvesiclesbasedmetabolomicsmachinelearningframeworkandbiomarkerdiscoveryforpredictingcolorectalcancerpatients
AT cemilcolak afecalmicrobialextracellularvesiclesbasedmetabolomicsmachinelearningframeworkandbiomarkerdiscoveryforpredictingcolorectalcancerpatients
AT mohammadazzeh afecalmicrobialextracellularvesiclesbasedmetabolomicsmachinelearningframeworkandbiomarkerdiscoveryforpredictingcolorectalcancerpatients
AT burakyagin afecalmicrobialextracellularvesiclesbasedmetabolomicsmachinelearningframeworkandbiomarkerdiscoveryforpredictingcolorectalcancerpatients
AT luisrueda afecalmicrobialextracellularvesiclesbasedmetabolomicsmachinelearningframeworkandbiomarkerdiscoveryforpredictingcolorectalcancerpatients
AT fatmahilalyagin fecalmicrobialextracellularvesiclesbasedmetabolomicsmachinelearningframeworkandbiomarkerdiscoveryforpredictingcolorectalcancerpatients
AT abedalrhmanalkhateeb fecalmicrobialextracellularvesiclesbasedmetabolomicsmachinelearningframeworkandbiomarkerdiscoveryforpredictingcolorectalcancerpatients
AT cemilcolak fecalmicrobialextracellularvesiclesbasedmetabolomicsmachinelearningframeworkandbiomarkerdiscoveryforpredictingcolorectalcancerpatients
AT mohammadazzeh fecalmicrobialextracellularvesiclesbasedmetabolomicsmachinelearningframeworkandbiomarkerdiscoveryforpredictingcolorectalcancerpatients
AT burakyagin fecalmicrobialextracellularvesiclesbasedmetabolomicsmachinelearningframeworkandbiomarkerdiscoveryforpredictingcolorectalcancerpatients
AT luisrueda fecalmicrobialextracellularvesiclesbasedmetabolomicsmachinelearningframeworkandbiomarkerdiscoveryforpredictingcolorectalcancerpatients