BAMORF: A Novel Computational Method for Predicting the Extracellular Matrix Proteins

Guan, Lianzhong; Zhang, Shouwei; Xu, Hong-qi

doi:10.1109/access.2017.2751499

“…Feature selection involves the selection of a subset of features that are relevant for predicting target variables (Navot et al, 2006). For instance, a new binary feature selection method has been proposed by Guan et al (2017) for predicting extracellular matrix proteins. We implement the global iterative approach, a multilabel learning method that maximizes dependence between functional similarities.…”

Section: Cnpfp Algorithmmentioning

confidence: 99%

Predicting Protein Functions Based on Differential Co-expression and Neighborhood Analysis

Wekesa

¹

,

Luan

²

,

Meng

³

2021

Journal of Computational Biology

View full text Add to dashboard Cite

Proteins are polypeptides essential in biological processes. Protein physical interactions are complemented by other types of functional relationship data including genetic interactions, knowledge about co-expression, and evolutionary pathways. Existing algorithms integrate protein interaction and gene expression data to retrieve context-specific subnetworks composed of genes/proteins with known and unknown functions. However, most protein function prediction algorithms fail to exploit diverse intrinsic information in feature and label spaces. We develop a novel integrative method based on differential Co-expression analysis and Neighbor-voting algorithm for Protein Function Prediction, namely CNPFP. The method integrates heterogeneous data and exploits intrinsic and latent linkages via global iterative approach and genomic features. CNPFP performs three tasks: clustering, differential co-expression analysis, and predicts protein functions. Our aim is to identify yeast cell cycle-specific proteins linked to differentially expressed proteins in the protein-protein interaction network. To capture intrinsic information, CNPFP selects the most relevant feature subset based on global iterative neighbor-voting algorithm. We identify eight condition-specific modules. The most relevant subnetwork has 87 genes highly enriched with cyclin-dependent kinases, a protein kinase relevant for cell cycle regulation. We present comprehensive annotations for 3538 Saccharomyces cerevisiae proteins. Our method achieves an AUROC of 0.9862, accuracy of 0.9710, and F-score of 0.9691. From the results, we can summarize that exploiting intrinsic nature of protein relationships improves the quality of function prediction. Thus, the proposed method is useful in functional genomics studies.

show abstract

“…In this context, ECMPride is established based on the top 151 features. A series of tools had been developed by researchers to predict ECM proteins (Ali & Hayat, 2016;Guan, Zhang & Xu, 2017;Jung et al, 2010;Kabir et al, 2018;Kandaswamy et al, 2013;Yang et al, 2015;Zhang et al, 2014), so it's necessary to compare ECMPride with these tools. As the datasets used by ECMPride differ from the datasets used for previous tools, it is meaningless to compare their performance directly.…”

Section: Ecmpride Achieves Good Performancementioning

confidence: 99%

“…By utilizing the domain-based structure of ECM proteins, Naba et al used an in silico approach to define ECM components and, based on this, constructed the Matrisome database in 2012 (Naba et al, 2012). The Matrisome has become a general reference database for proteomics-based ECM research in recent years (Åhrman et al, 2018;Gopal et al, 2017;Lennon et al, 2014;Mayorca-Guiliani et al, 2017). Further, Naba et al (2016) presented the first draft of the ECM atlas, which was established by integrating publicly available mass spectrometry data from studies explicitly designed to characterize the global composition of ECM proteins.…”

Section: Introductionmentioning

confidence: 99%

ECMPride: prediction of human extracellular matrix proteins based on the ideal dataset using hybrid features with domain evidence

Liu

¹

,

Leng

²

,

Sun³

et al. 2020

PeerJ

View full text Add to dashboard Cite

Extracellular matrix (ECM) proteins play an essential role in various biological processes in multicellular organisms, and their abnormal regulation can lead to many diseases. For large-scale ECM protein identification, especially through proteomic-based techniques, a theoretical reference database of ECM proteins is required. In this study, based on the experimentally verified ECM datasets and by the integration of protein domain features and a machine learning model, we developed ECMPride, a flexible and scalable tool for predicting ECM proteins. ECMPride achieved excellent performance in predicting ECM proteins, with appropriate balanced accuracy and sensitivity, and the performance of ECMPride was shown to be superior to the previously developed tool. A new theoretical dataset of human ECM components was also established by applying ECMPride to all human entries in the SwissProt database, containing a significant number of putative ECM proteins as well as the abundant biological annotations. This dataset might serve as a valuable reference resource for ECM protein identification.

show abstract

“…A series of tools had been developed by researchers to predict ECM proteins (Ali & Hayat 2016;Guan et al 2017;Jung et al 2010;Kabir et al 2018;Kandaswamy et al 2013;Yang et al 2015;Zhang et al 2014), so it's necessary to compare ECMPride with these tools. As the datasets used by ECMPride differ from the datasets used for previous tools, it is meaningless to compare their performance directly.…”

Section: Ecmpride Achieves Good Performancementioning

confidence: 99%

Peer Review #2 of "ECMPride: prediction of human extracellular matrix proteins based on the ideal dataset using hybrid features with domain evidence (v0.1)"

2020

0

View full text Add to dashboard Cite

Extracellular matrix (ECM) proteins play an essential role in various biological processes in multicellular organisms, and their abnormal regulation can lead to many diseases. For large-scale ECM protein identification, especially through proteomic-based techniques, a theoretical reference database of ECM proteins is required. In this study, based on the experimentally verified ECM datasets and by the integration of protein domain features and a machine learning model, we developed ECMPride, a flexible and scalable tool for predicting ECM proteins. ECMPride achieved excellent performance in predicting ECM proteins, with appropriate balanced accuracy and sensitivity, and the performance of ECMPride was shown to be superior to the previously developed tool. A new theoretical dataset of human ECM components was also established by applying ECMPride to all human entries in the SwissProt database, containing a significant number of putative ECM proteins as well as the abundant biological annotations. This dataset might serve as a valuable reference resource for ECM protein identification.

show abstract

BAMORF: A Novel Computational Method for Predicting the Extracellular Matrix Proteins

Cited by 9 publications

References 30 publications

Predicting Protein Functions Based on Differential Co-expression and Neighborhood Analysis

Predicting Protein Functions Based on Differential Co-expression and Neighborhood Analysis

ECMPride: prediction of human extracellular matrix proteins based on the ideal dataset using hybrid features with domain evidence

Peer Review #2 of "ECMPride: prediction of human extracellular matrix proteins based on the ideal dataset using hybrid features with domain evidence (v0.1)"

Contact Info

Product

Resources

About