PFP: Automated prediction of gene ontology functional annotations with confidence scores using protein sequence data

Exploring the nuclear proteins, viral capsid protein, and early antigen protein using immunoinformatic and molecular modeling approaches to design a vaccine candidate against Epstein Barr virus

The available Epstein Barr virus vaccine has tirelessly harnessed the gp350 glycoprotein as its target epitope, but the result has not been preventive. Right here, we designed a global multi-epitope vaccine for EBV; with special attention to making sure all strains and preventive antigens are covered. Using a robust computational vaccine design approach, our proposed vaccine is armed with 6-16 mers linear B-cell epitopes, 4-9 mer CTL epitopes, and 8-15 mer HTL epitopes which are verified to induce interleukin 4, 10 & IFN-gamma. We employed deep computational mining coupled with expert intelligence in designing the vaccine, using human Beta defensin-3-which has been reported to induce the same TLRs as EBV-as the adjuvant. The tendency of the vaccine to cause autoimmune disorder is quenched by the assurance that the construct contains no EBNA-1 homolog. The protein vaccine construct exhibited excellent physicochemical attributes such as Aliphatic index 59.55 and GRAVY - 0.710; and a ProsaWeb Z score of - 3.04. Further computational analysis revealed the vaccine docked favorably with EBV indicted TLR 1, 2, 4 & 9 with satisfactory interaction patterns. With global coverage of 85.75% and the stable molecular dynamics result obtained for the best two interactions, we are optimistic that our nontoxic, non-allergenic multi-epitope vaccine will help to ameliorate the EBV-associated diseases-which include various malignancies, tumors, and cancers-preventively.

A large-scale assessment of sequence database search tools for homology-based protein function prediction

Sequence database searches followed by homology-based function transfer form one of the oldest and most popular approaches for predicting protein functions, such as Gene Ontology (GO) terms. These searches are also a critical component in most state-of-the-art machine learning and deep learning-based protein function predictors. Although sequence search tools are the basis of homology-based protein function prediction, previous studies have scarcely explored how to select the optimal sequence search tools and configure their parameters to achieve the best function prediction. In this paper, we evaluate the effect of using different options from among popular search tools, as well as the impacts of search parameters, on protein function prediction. When predicting GO terms on a large benchmark dataset, we found that BLASTp and MMseqs2 consistently exceed the performance of other tools, including DIAMOND-one of the most popular tools for function prediction-under default search parameters. However, with the correct parameter settings, DIAMOND can perform comparably to BLASTp and MMseqs2 in function prediction. Additionally, we developed a new scoring function to derive GO prediction from homologous hits that consistently outperform previously proposed scoring functions. These findings enable the improvement of almost all protein function prediction algorithms with a few easily implementable changes in their sequence homolog-based component. This study emphasizes the critical role of search parameter settings in homology-based function transfer and should have an important contribution to the development of future protein function prediction algorithms.

Computational Approaches to Predict Protein-Protein Interactions in Crowded Cellular Environments

Investigating protein-protein interactions is crucial for understanding cellular biological processes because proteins often function within molecular complexes rather than in isolation. While experimental and computational methods have provided valuable insights into these interactions, they often overlook a critical factor: the crowded cellular environment. This environment significantly impacts protein behavior, including structural stability, diffusion, and ultimately the nature of binding. In this review, we discuss theoretical and computational approaches that allow the modeling of biological systems to guide and complement experiments and can thus significantly advance the investigation, and possibly the predictions, of protein-protein interactions in the crowded environment of cell cytoplasm. We explore topics such as statistical mechanics for lattice simulations, hydrodynamic interactions, diffusion processes in high-viscosity environments, and several methods based on molecular dynamics simulations. By synergistically leveraging methods from biophysics and computational biology, we review the state of the art of computational methods to study the impact of molecular crowding on protein-protein interactions and discuss its potential revolutionizing effects on the characterization of the human interactome.

GO2Sum: generating human-readable functional summary of proteins from GO terms

Understanding the biological functions of proteins is of fundamental importance in modern biology. To represent a function of proteins, Gene Ontology (GO), a controlled vocabulary, is frequently used, because it is easy to handle by computer programs avoiding open-ended text interpretation. Particularly, the majority of current protein function prediction methods rely on GO terms. However, the extensive list of GO terms that describe a protein function can pose challenges for biologists when it comes to interpretation. In response to this issue, we developed GO2Sum (Gene Ontology terms Summarizer), a model that takes a set of GO terms as input and generates a human-readable summary using the T5 large language model. GO2Sum was developed by fine-tuning T5 on GO term assignments and free-text function descriptions for UniProt entries, enabling it to recreate function descriptions by concatenating GO term descriptions. Our results demonstrated that GO2Sum significantly outperforms the original T5 model that was trained on the entire web corpus in generating Function, Subunit Structure, and Pathway paragraphs for UniProt entries.

Chromosome level genome assembly of the Etruscan shrew Suncus etruscus

Suncus etruscus is one of the world's smallest mammals, with an average body mass of about 2 grams. The Etruscan shrew's small body is accompanied by a very high energy demand and numerous metabolic adaptations. Here we report a chromosome-level genome assembly using PacBio long read sequencing, 10X Genomics linked short reads, optical mapping, and Hi-C linked reads. The assembly is partially phased, with the 2.472 Gbp primary pseudohaplotype and 1.515 Gbp alternate. We manually curated the primary assembly and identified 22 chromosomes, including X and Y sex chromosomes. The NCBI genome annotation pipeline identified 39,091 genes, 19,819 of them protein-coding. We also identified segmental duplications, inferred GO term annotations, and computed orthologs of human and mouse genes. This reference-quality genome will be an important resource for research on mammalian development, metabolism, and body size control.

In Silico Characterization of Intracellular Localization Signals and Structural Features of Mosquito Densovirus (MDV) Viral Proteins

As entomopathogenic viruses, mosquito densoviruses (MDVs) are widely studied for their potential as biocontrol agents and molecular laboratory tools for mosquito manipulation. The nucleus of the mosquito cell is the site for MDV genome replication and capsid assembly, however the nuclear localization signals (NLSs) and nuclear export signals (NES) for MDV proteins have not yet been identified. We carried out an in silico analysis to identify putative NLSs and NESs in the viral proteins of densoviruses that infect diverse mosquito genera (Aedes, Anopheles, and Culex) and identified putative phosphorylation and glycosylation sites on these proteins. These analyses lead to a more comprehensive understanding of how MDVs are transported into and out of the nucleus and lay the foundation for the potential use of densoviruses in mosquito control and basic research.

GO2Sum: Generating Human Readable Functional Summary of Proteins from GO Terms

Understanding the biological functions of proteins is of fundamental importance in modern biology. To represent function of proteins, Gene Ontology (GO), a controlled vocabulary, is frequently used, because it is easy to handle by computer programs avoiding open-ended text interpretation. Particularly, the majority of current protein function prediction methods rely on GO terms. However, the extensive list of GO terms that describe a protein function can pose challenges for biologists when it comes to interpretation. In response to this issue, we developed GO2Sum (Gene Ontology terms Summarizer), a model that takes a set of GO terms as input and generates a human-readable summary using the T5 large language model. GO2Sum was developed by fine-tuning T5 on GO term assignments and free-text function descriptions for UniProt entries, enabling it to recreate function descriptions by concatenating GO term descriptions. Our results demonstrated that GO2Sum significantly outperforms the original T5 model that was trained on the entire web corpus in generating Function, Subunit Structure, and Pathway paragraphs for UniProt entries.

Domain-PFP allows protein function prediction using function-aware domain embedding representations

Domains are functional and structural units of proteins that govern various biological functions performed by the proteins. Therefore, the characterization of domains in a protein can serve as a proper functional representation of proteins. Here, we employ a self-supervised protocol to derive functionally consistent representations for domains by learning domain-Gene Ontology (GO) co-occurrences and associations. The domain embeddings we constructed turned out to be effective in performing actual function prediction tasks. Extensive evaluations showed that protein representations using the domain embeddings are superior to those of large-scale protein language models in GO prediction tasks. Moreover, the new function prediction method built on the domain embeddings, named Domain-PFP, substantially outperformed the state-of-the-art function predictors. Additionally, Domain-PFP demonstrated competitive performance in the CAFA3 evaluation, achieving overall the best performance among the top teams that participated in the assessment.

Domain-PFP: Protein Function Prediction Using Function-Aware Domain Embedding Representations

Domains are functional and structural units of proteins that govern various biological functions performed by the proteins. Therefore, the characterization of domains in a protein can serve as a proper functional representation of proteins. Here, we employ a self-supervised protocol to derive functionally consistent representations for domains by learning domain-Gene Ontology (GO) co-occurrences and associations. The domain embeddings we constructed turned out to be effective in performing actual function prediction tasks. Extensive evaluations showed that protein representations using the domain embeddings are superior to those of large-scale protein language models in GO prediction tasks. Moreover, the new function prediction method built on the domain embeddings, named Domain-PFP, significantly outperformed the state-of-the-art function predictors. Additionally, Domain-PFP demonstrated competitive performance in the CAFA3 evaluation, achieving overall the best performance among the top teams that participated in the assessment.

Large-scale predicting protein functions through heterogeneous feature fusion

As the volume of protein sequence and structure data grows rapidly, the functions of the overwhelming majority of proteins cannot be experimentally determined. Automated annotation of protein function at a large scale is becoming increasingly important. Existing computational prediction methods are typically based on expanding the relatively small number of experimentally determined functions to large collections of proteins with various clues, including sequence homology, protein-protein interaction, gene co-expression, etc. Although there has been some progress in protein function prediction in recent years, the development of accurate and reliable solutions still has a long way to go. Here we exploit AlphaFold predicted three-dimensional structural information, together with other non-structural clues, to develop a large-scale approach termed PredGO to annotate Gene Ontology (GO) functions for proteins. We use a pre-trained language model, geometric vector perceptrons and attention mechanisms to extract heterogeneous features of proteins and fuse these features for function prediction. The computational results demonstrate that the proposed method outperforms other state-of-the-art approaches for predicting GO functions of proteins in terms of both coverage and accuracy. The improvement of coverage is because the number of structures predicted by AlphaFold is greatly increased, and on the other hand, PredGO can extensively use non-structural information for functional prediction. Moreover, we show that over 205 000 ($\sim $100%) entries in UniProt for human are annotated by PredGO, over 186 000 ($\sim $90%) of which are based on predicted structure. The webserver and database are available at http://predgo.denglab.org/.

Targeting Essential Hypothetical Proteins of Pseudomonas aeruginosa PAO1 for Mining of Novel Therapeutics: An In Silico Approach

As an omnipresent opportunistic bacterium, Pseudomonas aeruginosa PAO1 is responsible for acute and chronic infection in immunocompromised individuals. Currently, this bacterium is on WHO's red list where new antibiotics are urgently required for the treatment. Finding essential genes and essential hypothetical proteins (EHP) can be crucial in identifying novel druggable targets and therapeutics. This study is aimed at characterizing these EHPs and analyzing subcellular and physiochemical properties, PPI network, nonhomologous analysis against humans, virulence factor and novel drug target prediction, and finally structural analysis of the identified target employing around 42 robust bioinformatics tools/databases, the output of which was evaluated using the ROC analysis. The study discovered 18 EHPs from 336 essential genes, with domain and functional annotation revealing that 50% of these proteins belong to the enzyme category. The majority are cytoplasmic and cytoplasmic membrane proteins, with half being stable proteins subjected to PPIs network analysis. The network contains 261 nodes and 269 edges for 9 proteins of interest, with 11 hubs containing at least three nodes each. Finally, a pipeline builder predicts 7 proteins with novel drug targets, 5 nonhomologous proteins against human proteome, human antitargets, and human gut flora, and 3 virulent proteins. Among these, homology modeling of NP_249450 and NP_251676 was done, and the Ramachandran plot analysis revealed that more than 94% of the residues were in the preferred region. By analyzing functional attributes and virulence characteristics, the findings of this study may facilitate the development of innovative antibacterial drug targets and drugs of Pseudomonas aeruginosa PAO1.

ContactPFP: Protein Function Prediction Using Predicted Contact Information

Computational function prediction is one of the most important problems in bioinformatics as elucidating the function of genes is a central task in molecular biology and genomics. Most of the existing function prediction methods use protein sequences as the primary source of input information because the sequence is the most available information for query proteins. There are attempts to consider other attributes of query proteins. Among these attributes, the three-dimensional (3D) structure of proteins is known to be very useful in identifying the evolutionary relationship of proteins, from which functional similarity can be inferred. Here, we report a novel protein function prediction method, ContactPFP, which uses predicted residue-residue contact maps as input structural features of query proteins. Although 3D structure information is known to be useful, it has not been routinely used in function prediction because the 3D structure is not experimentally determined for many proteins. In ContactPFP, we overcome this limitation by using residue-residue contact prediction, which has become increasingly accurate due to rapid development in the protein structure prediction field. ContactPFP takes a query protein sequence as input and uses predicted residue-residue contact as a proxy for the 3D protein structure. To characterize how predicted contacts contribute to function prediction accuracy, we compared the performance of ContactPFP with several well-established sequence-based function prediction methods. The comparative study revealed the advantages and weaknesses of ContactPFP compared to contemporary sequence-based methods. There were many cases where it showed higher prediction accuracy. We examined factors that affected the accuracy of ContactPFP using several illustrative cases that highlight the strength of our method.

Integrated bioinformatics based subtractive genomics approach to decipher the therapeutic function of hypothetical proteins from Salmonella typhi XDR H-58 strain

Purpose

The efficacy of drugs against Salmonella infection have compromised due to emerging XDR H58 strain. There is a dire need to find novel antimicrobial drug targets as well as drug candidates to cure by the XDR strain of Salmonella. It is observed that the complete genome sequence of the XDR H58 strain contains a large number of hypothetical proteins with unknown cellular and biological functions. Hence, it is indispensable to annotate these proteins functionally as well as structurally to identify novel drug targets.

Methods

In the current study, a comparative genomics and proteomics based approach was applied to find the novel drug targets in XDR strain while comparing the MDR and NR strains of Salmonella typhi.

Results

The characterization of ~ 350 hypothetical proteins were performed through determination of their physio-chemical properties, sub-cellular localization, functional annotation, and structure-based studies. As a result, only five proteins were prioritized as essential, druggable, and virulent proteins. Moreover, only one protein i.e. WP_000916613.1 was functionally annotated with high confidence and subjected to further structure-based analysis.

Conclusion

The current study presents a hypothetical protein from the XDR S. typhi proteome as a potential pharmacological target against which novel therapeutic candidates may be predicted. The outcome of the current study may lead to formulate a general set of pipelines for better understanding of the role of hypothetical proteins in pathogenesis of not only Salmonella but also for other pathogens.

Supplementary Information

The online version contains supplementary material available at 10.1007/s10529-021-03219-6.

PANNZER-A practical tool for protein function prediction

The facility of next-generation sequencing has led to an explosion of gene catalogs for novel genomes, transcriptomes and metagenomes, which are functionally uncharacterized. Computational inference has emerged as a necessary substitute for first-hand experimental evidence. PANNZER (Protein ANNotation with Z-scoRE) is a high-throughput functional annotation web server that stands out among similar publically accessible web servers in supporting submission of up to 100,000 protein sequences at once and providing both Gene Ontology (GO) annotations and free text description predictions. Here, we demonstrate the use of PANNZER and discuss future plans and challenges. We present two case studies to illustrate problems related to data quality and method evaluation. Some commonly used evaluation metrics and evaluation datasets promote methods that favor unspecific and broad functional classes over more informative and specific classes. We argue that this can bias the development of automated function prediction methods. The PANNZER web server and source code are available at http://ekhidna2.biocenter.helsinki.fi/sanspanz/.

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

Protein function prediction is a crucial part of genome annotation. Prediction methods have recently witnessed rapid development, owing to the emergence of high-throughput sequencing technologies. Among the available databases for identifying protein function terms, Gene Ontology (GO) is an important resource that describes the functional properties of proteins. Researchers are employing various approaches to efficiently predict the GO terms. Meanwhile, deep learning, a fast-evolving discipline in data-driven approach, exhibits impressive potential with respect to assigning GO terms to amino acid sequences. Herein, we reviewed the currently available computational GO annotation methods for proteins, ranging from conventional to deep learning approach. Further, we selected some suitable predictors from among the reviewed tools and conducted a mini comparison of their performance using a worldwide challenge dataset. Finally, we discussed the remaining major challenges in the field, and emphasized the future directions for protein function prediction with GO.

Analysis of readability and structural accuracy in SNOMED CT

Background

The increasing adoption of ontologies in biomedical research and the growing number of ontologies available have made it necessary to assure the quality of these resources. Most of the well-established ontologies, such as the Gene Ontology or SNOMED CT, have their own quality assurance processes. These have demonstrated their usefulness for the maintenance of the resources but are unable to detect all of the modelling flaws in the ontologies. Consequently, the development of efficient and effective quality assurance methods is needed.

Methods

Here, we propose a series of quantitative metrics based on the processing of the lexical regularities existing in the content of the ontology, to analyse readability and structural accuracy. The readability metrics account for the ratio of labels, descriptions, and synonyms associated with the ontology entities. The structural accuracy metrics evaluate how two ontology modelling best practices are followed: (1) lexically suggest locally define (LSLD), that is, if what is expressed in natural language for humans is available as logical axioms for machines; and (2) systematic naming, which accounts for the amount of label content of the classes in a given taxonomy shared.

Results

We applied the metrics to different versions of SNOMED CT. Both readability and structural accuracy metrics remained stable in time but could capture some changes in the modelling decisions in SNOMED CT. The value of the LSLD metric increased from 0.27 to 0.31, and the value of the systematic naming metric was around 0.17. We analysed the readability and structural accuracy in the SNOMED CT July 2019 release. The results showed that the fulfilment of the structural accuracy criteria varied among the SNOMED CT hierarchies. The value of the metrics for the hierarchies was in the range of 0–0.92 (LSLD) and 0.08–1 (systematic naming). We also identified the cases that did not meet the best practices.

Conclusions

We generated useful information about the engineering of the ontology, making the following contributions: (1) a set of readability metrics, (2) the use of lexical regularities to define structural accuracy metrics, and (3) the generation of quality assurance information for SNOMED CT.

Bioinformatics Methods for Mass Spectrometry-Based Proteomics Data Analysis

Recent advances in mass spectrometry (MS)-based proteomics have enabled tremendous progress in the understanding of cellular mechanisms, disease progression, and the relationship between genotype and phenotype. Though many popular bioinformatics methods in proteomics are derived from other omics studies, novel analysis strategies are required to deal with the unique characteristics of proteomics data. In this review, we discuss the current developments in the bioinformatics methods used in proteomics and how they facilitate the mechanistic understanding of biological processes. We first introduce bioinformatics software and tools designed for mass spectrometry-based protein identification and quantification, and then we review the different statistical and machine learning methods that have been developed to perform comprehensive analysis in proteomics studies. We conclude with a discussion of how quantitative protein data can be used to reconstruct protein interactions and signaling networks.

Prediction of protein group function by iterative classification on functional relevance network

MOTIVATION

Biological experiments including proteomics and transcriptomics approaches often reveal sets of proteins that are most likely to be involved in a disease/disorder. To understand the functional nature of a set of proteins, it is important to capture the function of the proteins as a group, even in cases where function of individual proteins is not known. In this work, we propose a model that takes groups of proteins found to work together in a certain biological context, integrates them into functional relevance networks, and subsequently employs an iterative inference on graphical models to identify group functions of the proteins, which are then extended to predict function of individual proteins.

RESULTS

The proposed algorithm, iterative group function prediction (iGFP), depicts proteins as a graph that represents functional relevance of proteins considering their known functional, proteomics and transcriptional features. Proteins in the graph will be clustered into groups by their mutual functional relevance, which is iteratively updated using a probabilistic graphical model, the conditional random field. iGFP showed robust accuracy even when substantial amount of GO annotations were missing. The perspective of 'group' function annotation opens up novel approaches for understanding functional nature of proteins in biological systems.Availability and implementation: http://kiharalab.org/iGFP/.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Phylo-PFP: improved automated protein function prediction using phylogenetic distance of distantly related sequences

MOTIVATION

Function annotation of proteins is fundamental in contemporary biology across fields including genomics, molecular biology, biochemistry, systems biology and bioinformatics. Function prediction is indispensable in providing clues for interpreting omics-scale data as well as in assisting biologists to build hypotheses for designing experiments. As sequencing genomes is now routine due to the rapid advancement of sequencing technologies, computational protein function prediction methods have become increasingly important. A conventional method of annotating a protein sequence is to transfer functions from top hits of a homology search; however, this approach has substantial short comings including a low coverage in genome annotation.

RESULTS

Here we have developed Phylo-PFP, a new sequence-based protein function prediction method, which mines functional information from a broad range of similar sequences, including those with a low sequence similarity identified by a PSI-BLAST search. To evaluate functional similarity between identified sequences and the query protein more accurately, Phylo-PFP reranks retrieved sequences by considering their phylogenetic distance. Compared to the Phylo-PFP's predecessor, PFP, which was among the top ranked methods in the second round of the Critical Assessment of Functional Annotation (CAFA2), Phylo-PFP demonstrated substantial improvement in prediction accuracy. Phylo-PFP was further shown to outperform prediction programs to date that were ranked top in CAFA2.

AVAILABILITY AND IMPLEMENTATION

Phylo-PFP web server is available for at http://kiharalab.org/phylo_pfp.php.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

NNTox: Gene Ontology-Based Protein Toxicity Prediction Using Neural Network

With advancements in synthetic biology, the cost and the time needed for designing and synthesizing customized gene products have been steadily decreasing. Many research laboratories in academia as well as industry routinely create genetically engineered proteins as a part of their research activities. However, manipulation of protein sequences could result in unintentional production of toxic proteins. Therefore, being able to identify the toxicity of a protein before the synthesis would reduce the risk of potential hazards. Existing methods are too specific, which limits their application. Here, we extended general function prediction methods for predicting the toxicity of proteins. Protein function prediction methods have been actively studied in the bioinformatics community and have shown significant improvement over the last decade. We have previously developed successful function prediction methods, which were shown to be among top-performing methods in the community-wide functional annotation experiment, CAFA. Based on our function prediction method, we developed a neural network model, named NNTox, which uses predicted GO terms for a target protein to further predict the possibility of the protein being toxic. We have also developed a multi-label model, which can predict the specific toxicity type of the query sequence. Together, this work analyses the relationship between GO terms and protein toxicity and builds predictor models of protein toxicity.

In silico characterization of hypothetical proteins from Orientia tsutsugamushi str. Karp uncovers virulence genes

Scrub typhus also known as bush typhus is a disease with symptoms similar to Chikungunya infection. It is caused by a gram-negative bacterium Orientia tsutsugamushi which resides in its vertebrate host, Mites. The genome of Orientia tsutsugamushi str. Karp encodes for 1,563 proteins, of which 344 are characterized as hypothetical ones. In the present study, we tried to identify the probable functions of these 344 hypothetical proteins (HPs). All the characterized hypothetical proteins (HPs) belong to the various protein classes like enzymes, transporters, binding proteins, metabolic process and catalytic activity and kinase activity. These hypothetical proteins (HPs) were further analyzed for virulence factors with 62 proteins identified as the most virulent proteins among these hypothetical proteins (HPs). In addition, we studied the protein sequence similarity network for visualizing functional trends across protein superfamilies from the context of sequence similarity and it shows great potential for generating testable hypotheses about protein structure-function relationships. Furthermore, we calculated toplogical properties of the network and found them to obey network power law distributions showing a fractal nature. We also identifed two highly interconnected modules in the main network which contained five hub proteins (KJV55465, KJV56211, KJV57212, KJV57203 and KJV57216) having 1.0 clustering coefficient. The structural modeling (2D and 3D structure) of these five hub proteins was carried out and the catalytic site essential for its functioning was analyzed. The outcome of the present study may facilitate a better understanding of the mechanism of virulence, pathogenesis, adaptability to host and up-to-date annotations will make unknown genes easy to identify and target for experimentation. The information on the functional attributes and virulence characteristic of these hypothetical proteins (HPs) are envisaged to facilitate effective development of novel antibacterial drug targets of Orientia tsutsugamushi.

Multitask Protein Function Prediction through Task Dissimilarity

Automated protein function prediction is a challenging problem with distinctive features, such as the hierarchical organization of protein functions and the scarcity of annotated proteins for most biological functions. We propose a multitask learning algorithm addressing both issues. Unlike standard multitask algorithms, which use task (protein functions) similarity information as a bias to speed up learning, we show that dissimilarity information enforces separation of rare class labels from frequent class labels, and for this reason is better suited for solving unbalanced protein function prediction problems. We support our claim by showing that a multitask extension of the label propagation algorithm empirically works best when the task relatedness information is represented using a dissimilarity matrix as opposed to a similarity matrix. Moreover, the experimental comparison carried out on three model organism shows that our method has a more stable performance in both "protein-centric" and "function-centric" evaluation settings.

Computational identification of protein-protein interactions in model plant proteomes

Protein-protein interactions (PPIs) play essential roles in many biological processes. A PPI network provides crucial information on how biological pathways are structured and coordinated from individual protein functions. In the past two decades, large-scale PPI networks of a handful of organisms were determined by experimental techniques. However, these experimental methods are time-consuming, expensive, and are not easy to perform on new target organisms. Large-scale PPI data is particularly sparse in plant organisms. Here, we developed a computational approach for detecting PPIs trained and tested on known PPIs of Arabidopsis thaliana and applied to three plants, Arabidopsis thaliana, Glycine max (soybean), and Zea mays (maize) to discover new PPIs on a genome-scale. Our method considers a variety of features including protein sequences, gene co-expression, functional association, and phylogenetic profiles. This is the first work where a PPI prediction method was developed for is the first PPI prediction method applied on benchmark datasets of Arabidopsis. The method showed a high prediction accuracy of over 90% and very high precision of close to 1.0. We predicted 50,220 PPIs in Arabidopsis thaliana, 13,175,414 PPIs in corn, and 13,527,834 PPIs in soybean. Newly predicted PPIs were classified into three confidence levels according to the availability of existing supporting evidence and discussed. Predicted PPIs in the three plant genomes are made available for future reference.

Prediction of Enzyme Function Based on Three Parallel Deep CNN and Amino Acid Mutation

During the past decade, due to the number of proteins in PDB database being increased gradually, traditional methods cannot better understand the function of newly discovered enzymes in chemical reactions. Computational models and protein feature representation for predicting enzymatic function are more important. Most of existing methods for predicting enzymatic function have used protein geometric structure or protein sequence alone. In this paper, the functions of enzymes are predicted from many-sided biological information including sequence information and structure information. Firstly, we extract the mutation information from amino acids sequence by the position scoring matrix and express structure information with amino acids distance and angle. Then, we use histogram to show the extracted sequence and structural features respectively. Meanwhile, we establish a network model of three parallel Deep Convolutional Neural Networks (DCNN) to learn three features of enzyme for function prediction simultaneously, and the outputs are fused through two different architectures. Finally, The proposed model was investigated on a large dataset of 43,843 enzymes from the PDB and achieved 92.34% correct classification when sequence information is considered, demonstrating an improvement compared with the previous result.

Identification of Moonlighting Proteins in Genomes Using Text Mining Techniques

Moonlighting proteins is an emerging concept for considering protein functions, which indicate proteins with two or more independent and distinct functions. An increasing number of moonlighting proteins have been reported in the past years; however, a systematic study of the topic has been hindered because the secondary functions of proteins are usually found serendipitously by experiments. Toward systematic identification and study of moonlighting proteins, computational methods for identifying moonlighting proteins from several different information sources, database entries, literature, and large-scale omics data have been developed. In this study, an overview for finding moonlighting proteins is discussed. Then, the literature-mining method, DextMP, is applied to find new moonlighting proteins in three genomes, Arabidopsis thaliana, Caenorhabditis elegans, and Drosophila melanogaster. Potential moonlighting proteins identified by DextMP are further examined by a two-step manual literature checking procedure, which finally yielded 13 new moonlighting proteins. Identified moonlighting proteins are categorized into two classes based on the clarity of the distinctness of two functions of the proteins. A few cases of the identified moonlighting proteins are described in detail. Further direction for improving the DextMP algorithm is also discussed.

HPO2GO: prediction of human phenotype ontology term associations for proteins using cross ontology annotation co-occurrences

Analysing the relationships between biomolecules and the genetic diseases is a highly active area of research, where the aim is to identify the genes and their products that cause a particular disease due to functional changes originated from mutations. Biological ontologies are frequently employed in these studies, which provides researchers with extensive opportunities for knowledge discovery through computational data analysis. In this study, a novel approach is proposed for the identification of relationships between biomedical entities by automatically mapping phenotypic abnormality defining HPO terms with biomolecular function defining GO terms, where each association indicates the occurrence of the abnormality due to the loss of the biomolecular function expressed by the corresponding GO term. The proposed HPO2GO mappings were extracted by calculating the frequency of the co-annotations of the terms on the same genes/proteins, using already existing curated HPO and GO annotation sets. This was followed by the filtering of the unreliable mappings that could be observed due to chance, by statistical resampling of the co-occurrence similarity distributions. Furthermore, the biological relevance of the finalized mappings were discussed over selected cases, using the literature. The resulting HPO2GO mappings can be employed in different settings to predict and to analyse novel gene/protein—ontology term—disease relations. As an application of the proposed approach, HPO term—protein associations (i.e., HPO2protein) were predicted. In order to test the predictive performance of the method on a quantitative basis, and to compare it with the state-of-the-art, CAFA2 challenge HPO prediction target protein set was employed. The results of the benchmark indicated the potential of the proposed approach, as HPO2GO performance was among the best (Fmax = 0.35). The automated cross ontology mapping approach developed in this work may be extended to other ontologies as well, to identify unexplored relation patterns at the systemic level. The datasets, results and the source code of HPO2GO are available for download at: https://github.com/cansyl/HPO2GO.

Computational Methods for Predicting Protein-Protein Interactions Using Various Protein Features

Understanding protein-protein interactions (PPIs) in a cell is essential for learning protein functions, pathways, and mechanism of diseases. PPIs are also important targets for developing drugs. Experimental methods, both small-scale and large-scale, have identified PPIs in several model organisms. However, results cover only a part of PPIs of organisms; moreover, there are many organisms whose PPIs have not yet been investigated. To complement experimental methods, many computational methods have been developed that predict PPIs from various characteristics of proteins. Here we provide an overview of literature reports to classify computational PPI prediction methods that consider different features of proteins, including protein sequence, genomes, protein structure, function, PPI network topology, and those which integrate multiple methods. © 2018 by John Wiley & Sons, Inc.

IAS: Interaction Specific GO Term Associations for Predicting Protein-Protein Interaction Networks

Proteins carry out their function in a cell through interactions with other proteins. A large scale protein-protein interaction (PPI) network of an organism provides static yet an essential structure of interactions, which is valuable clue for understanding the functions of proteins and pathways. PPIs are determined primarily by experimental methods; however, computational PPI prediction methods can supplement or verify PPIs identified by experiment. Here, we developed a novel scoring method for predicting PPIs from Gene Ontology (GO) annotations of proteins. Unlike existing methods that consider functional similarity as an indication of interaction between proteins, the new score, named the protein-protein Interaction Association Score (IAS), was computed from GO term associations of known interacting protein pairs in 49 organisms. IAS was evaluated on PPI data of six organisms and found to outperform existing GO term-based scoring methods. Moreover, consensus scoring methods that combine different scores further improved performance of PPI prediction.

DextMP: deep dive into text for predicting moonlighting proteins

Motivation

Moonlighting proteins (MPs) are an important class of proteins that perform more than one independent cellular function. MPs are gaining more attention in recent years as they are found to play important roles in various systems including disease developments. MPs also have a significant impact in computational function prediction and annotation in databases. Currently MPs are not labeled as such in biological databases even in cases where multiple distinct functions are known for the proteins. In this work, we propose a novel method named DextMP, which predicts whether a protein is a MP or not based on its textual features extracted from scientific literature and the UniProt database.

Results

DextMP extracts three categories of textual information for a protein: titles, abstracts from literature, and function description in UniProt. Three language models were applied and compared: a state-of-the-art deep unsupervised learning algorithm along with two other language models of different types, Term Frequency-Inverse Document Frequency in the bag-of-words and Latent Dirichlet Allocation in the topic modeling category. Cross-validation results on a dataset of known MPs and non-MPs showed that DextMP successfully predicted MPs with over 91% accuracy with significant improvement over existing MP prediction methods. Lastly, we ran DextMP with the best performing language models and text-based feature combinations on three genomes, human, yeast and Xenopus laevis, and found that about 2.5–35% of the proteomes are potential MPs.

Availability and Implementation

Code available at http://kiharalab.org/DextMP.

MetaGO: Predicting Gene Ontology of Non-homologous Proteins Through Low-Resolution Protein Structure Prediction and Protein-Protein Network Mapping

Homology-based transferal remains the major approach to computational protein function annotations, but it becomes increasingly unreliable when the sequence identity between query and template decreases below 30%. We propose a novel pipeline, MetaGO, to deduce Gene Ontology attributes of proteins by combining sequence homology-based annotation with low-resolution structure prediction and comparison, and partner's homology-based protein-protein network mapping. The pipeline was tested on a large-scale set of 1000 non-redundant proteins from the CAFA3 experiment. Under the stringent benchmark conditions where templates with >30% sequence identity to the query are excluded, MetaGO achieves average F-measures of 0.487, 0.408, and 0.598, for Molecular Function, Biological Process, and Cellular Component, respectively, which are significantly higher than those achieved by other state-of-the-art function annotations methods. Detailed data analysis shows that the major advantage of the MetaGO lies in the new functional homolog detections from partner's homology-based network mapping and structure-based local and global structure alignments, the confidence scores of which can be optimally combined through logistic regression. These data demonstrate the power of using a hybrid model incorporating protein structure and interaction networks to deduce new functional insights beyond traditional sequence homology-based referrals, especially for proteins that lack homologous function templates. The MetaGO pipeline is available at http://zhanglab.ccmb.med.umich.edu/MetaGO/.

Computing and Visualizing Gene Function Similarity and Coherence with NaviGO

Gene ontology (GO) is a controlled vocabulary of gene functions across all species, which is widely used for functional analyses of individual genes and large-scale proteomic studies. NaviGO is a webserver for visualizing and quantifying the relationship and similarity of GO annotations. Here, we walk through functionality of the NaviGO webserver ( http://kiharalab.org/web/navigo/ ) using an example input and explain what can be learned from analysis results. NaviGO has four main functions, accessed from each page of the webserver: "GO Parents," "GO Set", "GO Enrichment", and "Protein Set." For a given list of GO terms, the "GO Parents" tab visualizes the hierarchical relationship of GO terms, and the "GO Set" tab calculates six functional similarity and association scores and presents results in a network and a multidimensional scaling plot. For a set of proteins and their associated GO terms, the "GO Enrichment" tab calculates protein GO functional enrichment, while the "Protein Set" tab calculates functional association between proteins. The NaviGO source code can be also downloaded and used locally or integrated into other software pipelines.

Large-scale automated function prediction of protein sequences and an experimental case study validation on PTEN transcript variants

Recent advances in computing power and machine learning empower functional annotation of protein sequences and their transcript variations. Here, we present an automated prediction system UniGOPred, for GO annotations and a database of GO term predictions for proteomes of several organisms in UniProt Knowledgebase (UniProtKB). UniGOPred provides function predictions for 514 molecular function (MF), 2909 biological process (BP), and 438 cellular component (CC) GO terms for each protein sequence. UniGOPred covers nearly the whole functionality spectrum in Gene Ontology system and it can predict both generic and specific GO terms. UniGOPred was run on CAFA2 challenge target protein sequences and it is categorized within the top 10 best performing methods for the molecular function category. In addition, the performance of UniGOPred is higher compared to the baseline BLAST classifier in all categories of GO. UniGOPred predictions are compared with UniProtKB/TrEMBL database annotations as well. Furthermore, the proposed tool's ability to predict negatively associated GO terms that defines the functions that a protein does not possess, is discussed. UniGOPred annotations were also validated by case studies on PTEN protein variants experimentally and on CHD8 protein variants with literature. UniGOPred protein functional annotation system is available as an open access tool at http://cansyl.metu.edu.tr/UniGOPred.html.

ProLanGO: Protein Function Prediction Using Neural Machine Translation Based on a Recurrent Neural Network

With the development of next generation sequencing techniques, it is fast and cheap to determine protein sequences but relatively slow and expensive to extract useful information from protein sequences because of limitations of traditional biological experimental techniques. Protein function prediction has been a long standing challenge to fill the gap between the huge amount of protein sequences and the known function. In this paper, we propose a novel method to convert the protein function problem into a language translation problem by the new proposed protein sequence language “ProLan” to the protein function language “GOLan”, and build a neural machine translation model based on recurrent neural networks to translate “ProLan” language to “GOLan” language. We blindly tested our method by attending the latest third Critical Assessment of Function Annotation (CAFA 3) in 2016, and also evaluate the performance of our methods on selected proteins whose function was released after CAFA competition. The good performance on the training and testing datasets demonstrates that our new proposed method is a promising direction for protein function prediction. In summary, we first time propose a method which converts the protein function prediction problem to a language translation problem and applies a neural machine translation model for protein function prediction.

NaviGO: interactive tool for visualization and functional similarity and coherence analysis with gene ontology

Background

The number of genomics and proteomics experiments is growing rapidly, producing an ever-increasing amount of data that are awaiting functional interpretation. A number of function prediction algorithms were developed and improved to enable fast and automatic function annotation. With the well-defined structure and manual curation, Gene Ontology (GO) is the most frequently used vocabulary for representing gene functions. To understand relationship and similarity between GO annotations of genes, it is important to have a convenient pipeline that quantifies and visualizes the GO function analyses in a systematic fashion.

Results

NaviGO is a web-based tool for interactive visualization, retrieval, and computation of functional similarity and associations of GO terms and genes. Similarity of GO terms and gene functions is quantified with six different scores including protein-protein interaction and context based association scores we have developed in our previous works. Interactive navigation of the GO function space provides intuitive and effective real-time visualization of functional groupings of GO terms and genes as well as statistical analysis of enriched functions.

Conclusions

We developed NaviGO, which visualizes and analyses functional similarity and associations of GO terms and genes. The NaviGO webserver is freely available at: http://kiharalab.org/web/navigo.

Computational Methods for Annotation Transfers from Sequence

Surveys of public sequence resources show that experimentally supported functional information is still completely missing for a considerable fraction of known proteins and is clearly incomplete for an even larger portion. Bioinformatics methods have long made use of very diverse data sources alone or in combination to predict protein function, with the understanding that different data types help elucidate complementary biological roles. This chapter focuses on methods accepting amino acid sequences as input and producing GO term assignments directly as outputs; the relevant biological and computational concepts are presented along with the advantages and limitations of individual approaches.

Using PFP and ESG Protein Function Prediction Web Servers

Elucidating biological function of proteins is a fundamental problem in molecular biology and bioinformatics. Conventionally, protein function is annotated based on homology using sequence similarity search tools such as BLAST and FASTA. These methods perform well when obvious homologs exist for a query sequence; however, they will not provide any functional information otherwise. As a result, the functions of many genes in newly sequenced genomes are left unknown, which await functional interpretation. Here, we introduce two webservers for function prediction methods, which effectively use distantly related sequences to improve function annotation coverage and accuracy: Protein Function Prediction (PFP) and Extended Similarity Group (ESG). These two methods have been tested extensively in various benchmark studies and ranked among the top in community-based assessments for computational function annotation, including Critical Assessment of Function Annotation (CAFA) in 2010-2011 (CAFA1) and 2013-2014 (CAFA2). Both servers are equipped with user-friendly visualizations of predicted GO terms, which provide intuitive illustrations of relationships of predicted GO terms. In addition to PFP and ESG, we also introduce NaviGO, a server for the interactive analysis of GO annotations of proteins. All the servers are available at http://kiharalab.org/software.php .

MPFit: Computational Tool for Predicting Moonlighting Proteins

An increasing number of proteins have been found which are capable of performing two or more distinct functions. These proteins, known as moonlighting proteins, have drawn much attention recently as they may play critical roles in disease pathways and development. However, because moonlighting proteins are often found serendipitously, our understanding of moonlighting proteins is still quite limited. In order to lay the foundation for systematic moonlighting proteins studies, we developed MPFit, a software package for predicting moonlighting proteins from their omics features including protein-protein and gene interaction networks. Here, we describe and demonstrate the algorithm of MPFit, the idea behind it, and provide instruction for using the software.

Exploring Mouse Protein Function via Multiple Approaches

Although the number of available protein sequences is growing exponentially, functional protein annotations lag far behind. Therefore, accurate identification of protein functions remains one of the major challenges in molecular biology. In this study, we presented a novel approach to predict mouse protein functions. The approach was a sequential combination of a similarity-based approach, an interaction-based approach and a pseudo amino acid composition-based approach. The method achieved an accuracy of about 0.8450 for the 1st-order predictions in the leave-one-out and ten-fold cross-validations. For the results yielded by the leave-one-out cross-validation, although the similarity-based approach alone achieved an accuracy of 0.8756, it was unable to predict the functions of proteins with no homologues. Comparatively, the pseudo amino acid composition-based approach alone reached an accuracy of 0.6786. Although the accuracy was lower than that of the previous approach, it could predict the functions of almost all proteins, even proteins with no homologues. Therefore, the combined method balanced the advantages and disadvantages of both approaches to achieve efficient performance. Furthermore, the results yielded by the ten-fold cross-validation indicate that the combined method is still effective and stable when there are no close homologs are available. However, the accuracy of the predicted functions can only be determined according to known protein functions based on current knowledge. Many protein functions remain unknown. By exploring the functions of proteins for which the 1st-order predicted functions are wrong but the 2nd-order predicted functions are correct, the 1st-order wrongly predicted functions were shown to be closely associated with the genes encoding the proteins. The so-called wrongly predicted functions could also potentially be correct upon future experimental verification. Therefore, the accuracy of the presented method may be much higher in reality.

Missing gene identification using functional coherence scores

Reconstructing metabolic and signaling pathways is an effective way of interpreting a genome sequence. A challenge in a pathway reconstruction is that often genes in a pathway cannot be easily found, reflecting current imperfect information of the target organism. In this work, we developed a new method for finding missing genes, which integrates multiple features, including gene expression, phylogenetic profile, and function association scores. Particularly, for considering function association between candidate genes and neighboring proteins to the target missing gene in the network, we used Co-occurrence Association Score (CAS) and PubMed Association Score (PAS), which are designed for capturing functional coherence of proteins. We showed that adding CAS and PAS substantially improve the accuracy of identifying missing genes in the yeast enzyme-enzyme network compared to the cases when only the conventional features, gene expression, phylogenetic profile, were used. Finally, it was also demonstrated that the accuracy improves by considering indirect neighbors to the target enzyme position in the network using a proper network-topology-based weighting scheme.

Extensive complementarity between gene function prediction methods

MOTIVATION

The number of sequenced genomes rises steadily but we still lack the knowledge about the biological roles of many genes. Automated function prediction (AFP) is thus a necessity. We hypothesized that AFP approaches that draw on distinct genome features may be useful for predicting different types of gene functions, motivating a systematic analysis of the benefits gained by obtaining and integrating such predictions.

RESULTS

Our pipeline amalgamates 5 133 543 genes from 2071 genomes in a single massive analysis that evaluates five established genomic AFP methodologies. While 1227 Gene Ontology (GO) terms yielded reliable predictions, the majority of these functions were accessible to only one or two of the methods. Moreover, different methods tend to assign a GO term to non-overlapping sets of genes. Thus, inferences made by diverse genomic AFP methods display a striking complementary, both gene-wise and function-wise. Because of this, a viable integration strategy is to rely on a single most-confident prediction per gene/function, rather than enforcing agreement across multiple AFP methods. Using an information-theoretic approach, we estimate that current databases contain 29.2 bits/gene of known Escherichia coli gene functions. This can be increased by up to 5.5 bits/gene using individual AFP methods or by 11 additional bits/gene upon integration, thereby providing a highly-ranking predictor on the Critical Assessment of Function Annotation 2 community benchmark. Availability of more sequenced genomes boosts the predictive accuracy of AFP approaches and also the benefit from integrating them.

AVAILABILITY AND IMPLEMENTATION

The individual and integrated GO predictions for the complete set of genes are available from http://gorbi.irb.hr/ CONTACT: fran.supek@irb.hrSupplementary information: Supplementary materials are available at Bioinformatics online.

Integrated protein function prediction by mining function associations, sequences, and protein-protein and gene-gene interaction networks

MOTIVATIONS

Protein function prediction is an important and challenging problem in bioinformatics and computational biology. Functionally relevant biological information such as protein sequences, gene expression, and protein-protein interactions has been used mostly separately for protein function prediction. One of the major challenges is how to effectively integrate multiple sources of both traditional and new information such as spatial gene-gene interaction networks generated from chromosomal conformation data together to improve protein function prediction.

RESULTS

In this work, we developed three different probabilistic scores (MIS, SEQ, and NET score) to combine protein sequence, function associations, and protein-protein interaction and spatial gene-gene interaction networks for protein function prediction. The MIS score is mainly generated from homologous proteins found by PSI-BLAST search, and also association rules between Gene Ontology terms, which are learned by mining the Swiss-Prot database. The SEQ score is generated from protein sequences. The NET score is generated from protein-protein interaction and spatial gene-gene interaction networks. These three scores were combined in a new Statistical Multiple Integrative Scoring System (SMISS) to predict protein function. We tested SMISS on the data set of 2011 Critical Assessment of Function Annotation (CAFA). The method performed substantially better than three base-line methods and an advanced method based on protein profile-sequence comparison, profile-profile comparison, and domain co-occurrence networks according to the maximum F-measure.

UNIPred: Unbalance-Aware Network Integration and Prediction of Protein Functions

The proper integration of multiple sources of data and the unbalance between annotated and unannotated proteins represent two of the main issues of the automated function prediction (AFP) problem. Most of supervised and semisupervised learning algorithms for AFP proposed in literature do not jointly consider these items, with a negative impact on both sensitivity and precision performances, due to the unbalance between annotated and unannotated proteins that characterize the majority of functional classes and to the specific and complementary information content embedded in each available source of data. We propose UNIPred (unbalance-aware network integration and prediction of protein functions), an algorithm that properly combines different biomolecular networks and predicts protein functions using parametric semisupervised neural models. The algorithm explicitly takes into account the unbalance between unannotated and annotated proteins both to construct the integrated network and to predict protein annotations for each functional class. Full-genome and ontology-wide experiments with three eukaryotic model organisms show that the proposed method compares favorably with state-of-the-art learning algorithms for AFP.

The PFP and ESG protein function prediction methods in 2014: effect of database updates and ensemble approaches

BACKGROUND

Functional annotation of novel proteins is one of the central problems in bioinformatics. With the ever-increasing development of genome sequencing technologies, more and more sequence information is becoming available to analyze and annotate. To achieve fast and automatic function annotation, many computational (automated) function prediction (AFP) methods have been developed. To objectively evaluate the performance of such methods on a large scale, community-wide assessment experiments have been conducted. The second round of the Critical Assessment of Function Annotation (CAFA) experiment was held in 2013-2014. Evaluation of participating groups was reported in a special interest group meeting at the Intelligent Systems in Molecular Biology (ISMB) conference in Boston in 2014. Our group participated in both CAFA1 and CAFA2 using multiple, in-house AFP methods. Here, we report benchmark results of our methods obtained in the course of preparation for CAFA2 prior to submitting function predictions for CAFA2 targets.

RESULTS

For CAFA2, we updated the annotation databases used by our methods, protein function prediction (PFP) and extended similarity group (ESG), and benchmarked their function prediction performances using the original (older) and updated databases. Performance evaluation for PFP with different settings and ESG are discussed. We also developed two ensemble methods that combine function predictions from six independent, sequence-based AFP methods. We further analyzed the performances of our prediction methods by enriching the predictions with prior distribution of gene ontology (GO) terms. Examples of predictions by the ensemble methods are discussed.

CONCLUSIONS

Updating the annotation database was successful, improving the Fmax prediction accuracy score for both PFP and ESG. Adding the prior distribution of GO terms did not make much improvement. Both of the ensemble methods we developed improved the average Fmax score over all individual component methods except for ESG. Our benchmark results will not only complement the overall assessment that will be done by the CAFA organizers, but also help elucidate the predictive powers of sequence-based function prediction methods in general.