Improving protein function prediction using protein sequence and GO-term similarities

Makrodimitris, Stavros; Ham, Roeland C. H. J. van; Reinders, Marcel J. T.

doi:10.1093/bioinformatics/bty751

Cited by 23 publications

(16 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, representing terms as high-dimensional vectors makes us lose the intuition, which implies that we would like this representation to be invertible, i.e., also provide us with a rule to convert a given vector in this "functional space" back to a term or a set of terms, ideally in a unique way. This is possible for linear mappings and we and others have worked on such approaches [90,91]. Linear approaches can capture simple relationships between terms such as co-occurrence or mutual exclusivity of a pair of terms [90], but might struggle to find more complicated relationships "hidden" either in the graph or in the semantics of terms.…”

Section: Function Representationmentioning

confidence: 99%

“…This is possible for linear mappings and we and others have worked on such approaches [90,91]. Linear approaches can capture simple relationships between terms such as co-occurrence or mutual exclusivity of a pair of terms [90], but might struggle to find more complicated relationships "hidden" either in the graph or in the semantics of terms. We therefore suspect that non-linear (e.g., neural) term embeddings are required to capture the whole structure.…”

Section: Function Representationmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Gene Function Prediction in the 2020’s

Makrodimitris

Ham

Reinders

2020

Genes

Self Cite

View full text Add to dashboard Cite

The current rate at which new DNA and protein sequences are being generated is too fast to experimentally discover the functions of those sequences, emphasizing the need for accurate Automatic Function Prediction (AFP) methods. AFP has been an active and growing research field for decades and has made considerable progress in that time. However, it is certainly not solved. In this paper, we describe challenges that the AFP field still has to overcome in the future to increase its applicability. The challenges we consider are how to: (1) include condition-specific functional annotation, (2) predict functions for non-model species, (3) include new informative data sources, (4) deal with the biases of Gene Ontology (GO) annotations, and (5) maximally exploit the GO to obtain performance gains. We also provide recommendations for addressing those challenges, by adapting (1) the way we represent proteins and genes, (2) the way we represent gene functions, and (3) the algorithms that perform the prediction from gene to function. Together, we show that AFP is still a vibrant research area that can benefit from continuing advances in machine learning with which AFP in the 2020s can again take a large step forward reinforcing the power of computational biology.

show abstract

Section: Function Representationmentioning

confidence: 99%

Section: Function Representationmentioning

confidence: 99%

Automatic Gene Function Prediction in the 2020’s

Makrodimitris

Ham

Reinders

2020

Genes

Self Cite

View full text Add to dashboard Cite

show abstract

“…Statistical analysis of the interacting residues of the Cystatin C protein responsible for the inhibition of cysteine protease activity revealed seven closely situated amino acids. These residues were identified as 2 Phe, 3 Leu, 9 Phe, 124 Glu, 125 Asn, 126 Ser and 127 Cyx. The seven residues displayed their activity in the inhibition of the Cathepsin proteins.…”

Section: Prediction Of Cystatin C Active Binding Sitementioning

confidence: 99%

“…On identification of a novel protein followed by characterization of its polypeptide chain, the next step is functional analysis [9]. In bioinformatics this process is twofold.…”

Section: Introductionmentioning

confidence: 99%

A benchmarked in-silico driven pipeline capable of complete trifecta protein analysis

Perera¹,

Peiris²

2020

Preprint

View full text Add to dashboard Cite

Background Current in-silico based proteomics requires the prediction, validation and functional analysis of a modelled protein. The main drawback in this protocol is the lack of a singular protocol that utilizes a proper set of benchmarked open science tools to accurately predict a protein’s structure and function. Results The present study aims to utilize a series of openly available computational tools to formulate a complete pipeline capable of analyzing a novel protein’s amino acid sequence, reveal its phylogenetic relationships and conserved residues. The resultant data would then be utilized in the formulation of the protein’s tertiary structure followed by functional analysis through virtual screening. This novel protocol was benchmarked utilizing the Cystatin C protein obtained from Danio rerio and the AChE proteins of Homo sapiens and Rattus norvegicus. Conclusion The resultant pipeline utilizes freely available in-silico tools capable of complete protein analysis including a novel protein’s functional analysis. The methodology has been proven and the tools have been benchmarked as the most suited for complete trifecta protein analysis.

show abstract

“…This dynamic network is enriched with PPIN, time course gene expression data, protein’s domain information and protein complex information which ultimately predict function of a protein using majority ranking. While most of the predictive models highlights on the most highly related similar proteins in the neighborhood of the test protein, Reinders, Van Ham & Makrodimitris (2018) focuses on the less similar proteins. It is shown by the application of label-space dimensionality reduction techniques that though these proteins are less similar but they are quite informative and plays an important role in protein function prediction.…”

Section: Introductionmentioning

confidence: 99%

FunPred 3.0: improved protein function prediction using protein interaction network

Saha¹,

Chatterjee²,

Basu

et al. 2019

PeerJ

View full text Add to dashboard Cite

Proteins are the most versatile macromolecules in living systems and perform crucial biological functions. In the advent of the post-genomic era, the next generation sequencing is done routinely at the population scale for a variety of species. The challenging problem is to massively determine the functions of proteins that are yet not characterized by detailed experimental studies. Identification of protein functions experimentally is a laborious and time-consuming task involving many resources. We therefore propose the automated protein function prediction methodology using in silico algorithms trained on carefully curated experimental datasets. We present the improved protein function prediction tool FunPred 3.0, an extended version of our previous methodology FunPred 2, which exploits neighborhood properties in protein–protein interaction network (PPIN) and physicochemical properties of amino acids. Our method is validated using the available functional annotations in the PPIN network of Saccharomyces cerevisiae in the latest Munich information center for protein (MIPS) dataset. The PPIN data of S. cerevisiae in MIPS dataset includes 4,554 unique proteins in 13,528 protein–protein interactions after the elimination of the self-replicating and the self-interacting protein pairs. Using the developed FunPred 3.0 tool, we are able to achieve the mean precision, the recall and the F-score values of 0.55, 0.82 and 0.66, respectively. FunPred 3.0 is then used to predict the functions of unpredicted protein pairs (incomplete and missing functional annotations) in MIPS dataset of S. cerevisiae. The method is also capable of predicting the subcellular localization of proteins along with its corresponding functions. The code and the complete prediction results are available freely at: https://github.com/SovanSaha/FunPred-3.0.git.

show abstract

Improving protein function prediction using protein sequence and GO-term similarities

Abstract: Supplementary data are available at Bioinformatics online.

Cited by 23 publications

References 40 publications

Automatic Gene Function Prediction in the 2020’s

Automatic Gene Function Prediction in the 2020’s

A benchmarked in-silico driven pipeline capable of complete trifecta protein analysis

FunPred 3.0: improved protein function prediction using protein interaction network

Contact Info

Product

Resources

About