PFP-WGAN: Protein function prediction by discovering Gene Ontology term correlations with generative adversarial networks

Seyyedsalehi, Seyyede Fatemeh; Soleymani, Mahdieh; Rabiee, Hamid R.; Mofrad, Mohammad R. K.

doi:10.1371/journal.pone.0244430

Cited by 10 publications

(8 citation statements)

References 37 publications

(68 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Specifically, a GO annotation is an association between a specific gene product and a GO concept. GO was well established and has often been used to evaluate the quality of newly constructed or reconstructed protein-protein interaction networks (Xu et al, 2018;Seyyedsalehi et al, 2021). We focused on BP ontology enrichment analysis since we are interested in what biological processes are involved in COPD.…”

Section: Gene Ontology Enrichment Analysis On Hub Proteins In Copd Associated Networkmentioning

confidence: 99%

An Augmented High-Dimensional Graphical Lasso Method to Incorporate Prior Biological Knowledge for Global Network Learning

et al. 2022

View full text Add to dashboard Cite

Biological networks are often inferred through Gaussian graphical models (GGMs) using gene or protein expression data only. GGMs identify conditional dependence by estimating a precision matrix between genes or proteins. However, conventional GGM approaches often ignore prior knowledge about protein-protein interactions (PPI). Recently, several groups have extended GGM to weighted graphical Lasso (wGlasso) and network-based gene set analysis (Netgsa) and have demonstrated the advantages of incorporating PPI information. However, these methods are either computationally intractable for large-scale data, or disregard weights in the PPI networks. To address these shortcomings, we extended the Netgsa approach and developed an augmented high-dimensional graphical Lasso (AhGlasso) method to incorporate edge weights in known PPI with omics data for global network learning. This new method outperforms weighted graphical Lasso-based algorithms with respect to computational time in simulated large-scale data settings while achieving better or comparable prediction accuracy of node connections. The total runtime of AhGlasso is approximately five times faster than weighted Glasso methods when the graph size ranges from 1,000 to 3,000 with a fixed sample size (n = 300). The runtime difference between AhGlasso and weighted Glasso increases when the graph size increases. Using proteomic data from a study on chronic obstructive pulmonary disease, we demonstrate that AhGlasso improves protein network inference compared to the Netgsa approach by incorporating PPI information.

show abstract

Section: Gene Ontology Enrichment Analysis On Hub Proteins In Copd Associated Networkmentioning

confidence: 99%

An Augmented High-Dimensional Graphical Lasso Method to Incorporate Prior Biological Knowledge for Global Network Learning

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The goal of the Critical Assessment of Protein Function Annotation (CAFA) programme is to evaluate protein function prediction methods on a large scale. The results of the first two CAFA challenges showed that protein function prediction is still a difficult area to study [11], [12]. Artificial neural networks (ANNs) and other machine learning methods have been used to predict protein function [13].…”

Section: Functional Classification Schemesmentioning

confidence: 99%

Fusion protein functionality prediction using genetic algorithm

Subhashini

Bhargavi

Jyothi

2022

ijhs

View full text Add to dashboard Cite

A fusion gene, which is composed by fusing pieces of two distinct genes, gives rise to a protein. The body may naturally produce fusion genes by transferring DNA between chromosomes. For instance, the BCR-ABL gene, which is a fusion gene that creates the BCR-ABL fusion protein, is found in a few different types of leukemia. By combining genes or segments of genes from related or unrelated animals, fusion genes and proteins can be produced further. Real-time lab tests, however, are expensive and time-consuming for automated fusion protein functionality prediction. In order to address this issue, this research suggests a brand-new Fusion Protein Functionality Prediction (FPFP) approach based on the Genetic Algorithm (GA) technique. The results of the experiments showed that the FPFP method accurately predicts the functionality of fusion proteins.

show abstract

“…Over the past decade, several GO term-based protein activity prediction methods has been proposed to automate protein sequencing using machine learning and statistical analysis methods [12], [13], [14]. Considering the forecast performance of the current methods, it can be said that there is still room for significant improvement in this area.…”

Section: )mentioning

confidence: 99%

A Hybrid Genetic Particle Swarm Optimization Algorithm Based Fusion Protein Functionality Prediction

Subhashini¹,

Bhargavi²,

Jyothi³

2022

Journal of Pharmaceutical Negative Results

View full text Add to dashboard Cite

A fusion protein is a protein with at least two domains that are each encoded by a different gene and are combined into a single polypeptide by transcription and translation. For example, chromosomal rearrangement could result in the in vivo production of fusion proteins. One such fusion protein is the one responsible for chronic myelogenous leukaemia, the BCR-ABL protein. Recombinant DNA techniques could be used to create fusion proteins in vitro. By combining genes or portion of genes from similar or dissimilar organisms, fusion genes and proteins may be produced. But, real-time lab experiments for automated fusion protein functionality prediction are expensive and time-consuming. This paper proposes a novel Fusion Protein Functionality Prediction based on a Hybrid Genetic Particle Swarm Optimization (HybGPSO) algorithm to deal with this problem. The cellular component, biological process, and molecular function of an unannotated fusion protein by the GO consortium are the three functionalities predicted by this algorithm. The results of the experiments demonstrate that the proposed HybGPSO algorithm accurately predicts the function of fusion proteins.

show abstract

PFP-WGAN: Protein function prediction by discovering Gene Ontology term correlations with generative adversarial networks

Cited by 10 publications

References 37 publications

An Augmented High-Dimensional Graphical Lasso Method to Incorporate Prior Biological Knowledge for Global Network Learning

An Augmented High-Dimensional Graphical Lasso Method to Incorporate Prior Biological Knowledge for Global Network Learning

Fusion protein functionality prediction using genetic algorithm

A Hybrid Genetic Particle Swarm Optimization Algorithm Based Fusion Protein Functionality Prediction

Contact Info

Product

Resources

About