Protein function prediction with gene ontology: from traditional to deep learning models

Vu, Thi Thuy Duong; Jung, Jaehee

doi:10.7717/peerj.12019

Cited by 13 publications

(10 citation statements)

References 79 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In brief, these methods can be classified into two categories, that is, amino acid residue sequence-based prediction and integrated data-based prediction. 18 The former extracts information only from protein sequences. For instance, DEEPred 19 acquired features from sequences and fed them into a stack of multitask feed-forward deep neural networks (DNNs).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Enhancing Protein Function Prediction Performance by Utilizing AlphaFold-Predicted Protein Structures

Zhang

et al. 2022

J. Chem. Inf. Model.

View full text Add to dashboard Cite

The structure of a protein is of great importance in determining its functionality, and this characteristic can be leveraged to train data-driven prediction models. However, the limited number of available protein structures severely limits the performance of these models. AlphaFold2 and its open-source data set of predicted protein structures have provided a promising solution to this problem, and these predicted structures are expected to benefit the model performance by increasing the number of training samples. In this work, we constructed a new data set that acted as a benchmark and implemented a state-of-the-art structure-based approach for determining whether the performance of the function prediction model can be improved by putting additional AlphaFold-predicted structures into the training set and further compared the performance differences between two models separately trained with real structures only and AlphaFold-predicted structures only. Experimental results indicated that structure-based protein function prediction models could benefit from virtual training data consisting of AlphaFold-predicted structures. First, model performances were improved in all three categories of Gene Ontology terms (GO terms) after adding predicted structures as training samples. Second, the model trained only on AlphaFold-predicted virtual samples achieved comparable performances to the model based on experimentally solved real structures, suggesting that predicted structures were almost equally effective in predicting protein functionality.

show abstract

Section: Introductionmentioning

confidence: 99%

“…A considerable number of methods have been proposed to predict protein function. In brief, these methods can be classified into two categories, that is, amino acid residue sequence-based prediction and integrated data-based prediction . The former extracts information only from protein sequences.…”

Section: Introductionmentioning

confidence: 99%

Enhancing Protein Function Prediction Performance by Utilizing AlphaFold-Predicted Protein Structures

Zhang

et al. 2022

J. Chem. Inf. Model.

View full text Add to dashboard Cite

show abstract

“…In particular, throughput technologies have greatly increased the number of protein sequences in public repositories, but only about 1% of the sequences in the UniProtKB database have been functionally characterized [ 10 ]. This gap motivates computational approaches [ 11 ], and the computational literature on protein function prediction is rich [ 12 ].…”

Section: Introductionmentioning

confidence: 99%

GOProFormer: A Multi-Modal Transformer Method for Gene Ontology Protein Function Prediction

Kabir

Shehu

2022

Biomolecules

View full text Add to dashboard Cite

Protein Language Models (PLMs) are shown to be capable of learning sequence representations useful for various prediction tasks, from subcellular localization, evolutionary relationships, family membership, and more. They have yet to be demonstrated useful for protein function prediction. In particular, the problem of automatic annotation of proteins under the Gene Ontology (GO) framework remains open. This paper makes two key contributions. It debuts a novel method that leverages the transformer architecture in two ways. A sequence transformer encodes protein sequences in a task-agnostic feature space. A graph transformer learns a representation of GO terms while respecting their hierarchical relationships. The learned sequence and GO terms representations are combined and utilized for multi-label classification, with the labels corresponding to GO terms. The method is shown superior over recent representative GO prediction methods. The second major contribution in this paper is a deep investigation of different ways of constructing training and testing datasets. The paper shows that existing approaches under- or over-estimate the generalization power of a model. A novel approach is proposed to address these issues, resulting in a new benchmark dataset to rigorously evaluate and compare methods and advance the state-of-the-art.

show abstract

“…The latter was evidently highly advantageous. For example, in cis -regulatory element (CRE) prediction, the CNN, in the absence of a priori knowledge on the target location, outperforms conventional k-mer enrichment, expectation maximization and Gibbs sampling methods with a lower false positive rate [ 13 , 14 , 15 ].…”

Section: Introductionmentioning

confidence: 99%

Multi-Omics Approaches and Resources for Systems-Level Gene Function Prediction in the Plant Kingdom

Abdullah‐Zawawi

Govender

Harun

et al. 2022

Plants

View full text Add to dashboard Cite

In higher plants, the complexity of a system and the components within and among species are rapidly dissected by omics technologies. Multi-omics datasets are integrated to infer and enable a comprehensive understanding of the life processes of organisms of interest. Further, growing open-source datasets coupled with the emergence of high-performance computing and development of computational tools for biological sciences have assisted in silico functional prediction of unknown genes, proteins and metabolites, otherwise known as uncharacterized. The systems biology approach includes data collection and filtration, system modelling, experimentation and the establishment of new hypotheses for experimental validation. Informatics technologies add meaningful sense to the output generated by complex bioinformatics algorithms, which are now freely available in a user-friendly graphical user interface. These resources accentuate gene function prediction at a relatively minimal cost and effort. Herein, we present a comprehensive view of relevant approaches available for system-level gene function prediction in the plant kingdom. Together, the most recent applications and sought-after principles for gene mining are discussed to benefit the plant research community. A realistic tabulation of plant genomic resources is included for a less laborious and accurate candidate gene discovery in basic plant research and improvement strategies.

show abstract

Protein function prediction with gene ontology: from traditional to deep learning models

Cited by 13 publications

References 79 publications

Enhancing Protein Function Prediction Performance by Utilizing AlphaFold-Predicted Protein Structures

Enhancing Protein Function Prediction Performance by Utilizing AlphaFold-Predicted Protein Structures

GOProFormer: A Multi-Modal Transformer Method for Gene Ontology Protein Function Prediction

Multi-Omics Approaches and Resources for Systems-Level Gene Function Prediction in the Plant Kingdom

Contact Info

Product

Resources

About