Bayesian assignment of gene ontology terms to gene expression experiments

In chromosome 11, 71 out of its 1254 proteins remain functionally uncharacterized on the basis of their existence evidence (uPE1s) following the latest version of neXtProt (release 2020-01-17). Because in vivo and in vitro experimental strategies are often time-consuming and labor-intensive, there is a need for a bioinformatics tool to predict the function annotation. Here, we used I-TASSER/COFACTOR provided on the neXtProt web site, which predicts gene ontology (GO) terms based on the 3D structure of the protein. I-TASSER/COFACTOR predicted 2413 GO terms with a benchmark dataset of the 22 proteins belonging to PE1 of chromosome 11. In this study, we developed a filtering algorithm in order to select specific GO terms using the GO map generated by I-TASSER/COFACTOR. As a result, 187 specific GO terms showed a higher average precision-recall score at the least cellular component term compared to 2413 predicted GO terms. Next, we applied 65 proteins belonging to uPE1s of chromosome 11, and then 409 out of 6684 GO terms survived, where 103 and 142 GO terms of molecular function and biological process, respectively, were included. Representatively, the cellular component GO terms of CCDC90B, C11orf52, and the SMAP were predicted and validated using the overexpression system into 293T cells and immunofluorescence staining. We will further study their biological and molecular functions toward the goal of the neXt-CP50 project as a part of C-HPP. We shared all results and programs in Github (https://github.com/heeyounh/I-TASSER-COFACTOR-filtering.git).

The roles and target genes of many transcription factors (TFs) are still unknown. To predict the roles of TFs, we present a computational method for associating Gene Ontology (GO) terms with TF-binding motifs. The method works by ranking all genes as potential targets of the TF, and reporting GO terms that are significantly associated with highly ranked genes. We also present an approach, whereby these predicted GO terms can be used to improve predictions of TF target genes. This uses a novel gene-scoring function that reflects the insight that genes annotated with GO terms predicted to be associated with the TF are more likely to be its targets. We construct validation sets of GO terms highly associated with known targets of various yeast and human TF. On the yeast reference sets, our prediction method identifies at least one correct GO term for 73% of the TF, 49% of the correct GO terms are predicted and almost one-third of the predicted GO terms are correct. Results on human reference sets are similarly encouraging. Validation of our target gene prediction method shows that its accuracy exceeds that of simple motif scanning.

Ranking Gene Ontology terms for predicting non-classical secretory proteins in eukaryotes and prokaryotes

Measuring the semantic similarity between Gene Ontology (GO) terms is a fundamental step in numerous functional bioinformatics applications. To fully exploit the metadata of GO terms, word embedding-based methods have been proposed recently to map GO terms to low-dimensional feature vectors. However, these representation methods commonly overlook the key information hidden in the whole GO structure and the relationship between GO terms. In this paper, we propose a novel representation model for GO terms, named GT2Vec, which jointly considers the GO graph structure obtained by graph contrastive learning and the semantic description of GO terms based on BERT encoders. Our method is evaluated on a protein similarity task on a collection of benchmark datasets. The experimental results demonstrate the effectiveness of using a joint encoding graph structure and textual node descriptors to learn vector representations for GO terms.

BackgroundSeveral tools have been developed to explore and search Gene Ontology (GO) databases allowing efficient GO enrichment analysis and GO tree visualization. Nevertheless, identification of highly specific GO-terms in complex data sets is relatively complicated and the display of GO term assignments and GO enrichment analysis by simple tables or pie charts is not optimal. Valuable information such as the hierarchical position of a single GO term within the GO tree (topological ordering), or enrichment within a complex set of biological experiments is not displayed. Pie charts based on GO tree levels are, themselves, one-dimensional graphs, which cannot properly or efficiently represent the hierarchical specificity for the biological system being studied.ResultsHere we present a new method, which we name PCA2GO, capable of GO analysis using complex multidimensional experimental settings. We employed principal component analysis (PCA) and developed a new score, which takes into account the relative frequency of certain GO terms and their specificity (hierarchical position) within the GO graph. We evaluated the correlation between our representation score R and a standard measure of enrichment, namely p-values to convey the versatility of our approach to other methods and point out differences between our method and commonly used enrichment analyses. Although p values and the R score formally measure different quantities they should be correlated, because relative frequencies of GO terms occurrences within a dataset are an indirect measure of protein numbers related to this term. Therefore they are also related to enrichment. We showed that our score enables us to identify more specific GO-terms i.e. those positioned further down the GO-graph than other common tools used for this purpose. PCA2GO allows visualization and detection of multidimensional dependencies both within the acyclic graph (GO tree) and the experimental settings. Our method is intended for the analysis of several experimental sets, not for one set, like standard enrichment tools. To demonstrate the usefulness of our approach we performed a PCA2GO analysis of a fractionated cardiomyocyte protein dataset, which was identified by enhanced liquid chromatography-mass spectrometry (GeLC-MS). The analysis enabled us to detect distinct groups of proteins, which accurately reflect properties of biochemical cell fractions.ConclusionsWe conclude that PCA2GO is an alternative efficient GO analysis tool with unique features for detection and visualization of multidimensional dependencies within the dataset under study. PCA2GO reveals strongly correlated GO terms within the experimental setting (in this case different fractions) by PCA group formation and improves detection of more specific GO terms within experiment dependent GO term groups than standard p value calculations.

Phase-separation proteins (PSPs) are a class of proteins that play a role in the process of liquid-liquid phase separation, which is a mechanism that mediates the formation of membranelle compartments in cells. Identifying phase separation proteins and their associated function could provide insights into cellular biology and the development of diseases, such as neurodegenerative diseases and cancer. Here, PSPs and non-PSPs that have been experimentally validated in earlier studies were gathered as positive and negative samples. Each protein's corresponding Gene Ontology (GO) terms were extracted and used to create a 24,907-dimensional binary vector. The purpose was to extract essential GO terms that can describe essential functions of PSPs and build efficient classifiers to identify PSPs with these GO terms at the same time. To this end, the incremental feature selection computational framework and an integrated feature analysis scheme, containing categorical boosting, least absolute shrinkage and selection operator, light gradient-boosting machine, extreme gradient boosting, and permutation feature importance, were used to build efficient classifiers and identify GO terms with classification-related importance. A set of random forest (RF) classifiers with F1 scores over 0.960 were established to distinguish PSPs from non-PSPs. A number of GO terms that are crucial for distinguishing between PSPs and non-PSPs were found, including GO:0003723, which is related to a biological process involving RNA binding; GO:0016020, which is related to membrane formation; and GO:0045202, which is related to the function of synapses. This study offered recommendations for future research aimed at determining the functional roles of PSPs in cellular processes by developing efficient RF classifiers and identifying the representative GO terms related to PSPs.

The analysis of complex patterns of gene regulation is central to understanding the biology of cells, tissues and organisms. Patterns of gene regulation pertaining to specific biological processes can be revealed by a variety of experimental strategies, particularly microarrays and other highly parallel methods, which generate large datasets linking many genes. Although methods for detecting gene expression have improved substantially in recent years, understanding the physiological implications of complex patterns in gene expression data is a major challenge. This article presents GoSurfer, an easy-to-use graphical exploration tool with built-in statistical features that allow a rapid assessment of the biological functions represented in large gene sets. GoSurfer takes one or two list(s) of gene identifiers (Affymetrix probe set ID) as input and retrieves all the Gene Ontology (GO) terms associated with the input genes. GoSurfer visualises these GO terms in a hierarchical tree format. With GoSurfer, users can perform statistical tests to search for the GO terms that are enriched in the annotations of the input genes. These GO terms can be highlighted on the GO tree. Users can manipulate the GO tree in various ways and interactively query the genes associated with any GO term. The user-generated graphics can be saved as graphics files, and all the GO information related to the input genes can be exported as text files. GoSurfer is a Windows-based program freely available for noncommercial use and can be downloaded at http://www.gosurfer.org. Datasets used to construct the trees shown in the figures in this article are available at http://www.gosurfer.org/download/GoSurfer.zip.

The recent availability of large language models for protein sequences has spurred the development of deep learning models for prediction of protein functions, mainly in the form of gene ontology (GO) terms. We developed InterLabelGO+, a top performing deep learning-based protein GO term prediction model in the recent fifth Critical Assessment of Function Annotation (CAFA5) challenge. InterLabelGO+ uses the ESM2 protein language model to extract sequence features, which are then used as inputs to a deep learning model that was trained under a loss function that considers the potentially complex relations between different GO terms. The deep learning-predicted GO terms are then combined with GO terms from sequence homology search to derive consensus predictions. InterLabelGO+ is available at https://seq2fun.dcmb.med.umich.edu/InterLabelGO/ . In this chapter, we demonstrate procedures to perform protein GO term prediction with the InterLabelGO+ webserver and the standalone package, as well as how to retrain the model with up-to-date training data.

The number of nucleotide and protein sequences deposited in public databases has rapidly increased in recent times. To provide consistent annotation of orthologous genes across organisms, annotation using Gene Ontology (GO) terms is shared among most of these databases. GO outlines a structured vocabulary used for describing biological properties of gene products. The illustration of GO terms using complete paths to the root term on the basis of a directed acyclic graph (DAG) approach aids in the systematic grasping of the functional information related to a gene product. However, the website provided by the GO Consortium does not present DAGs for two or more GO terms due to difficulties in the depiction of the complex relationships of such GO terms. To overcome these problems, we have constructed a DAG-based browser, termed DAGViz, that shows DAG-based information of multiple GO terms assigned to one or more genes within a single screen (http://www.pgb.kazusa.or.jp/dagviz/). In the current report, we illustrate the advantages of DAGViz in analyzing GO annotation.

BackgroundIn investigating differentially expressed genes or other selected features, researchers conduct hypothesis tests to determine which biological categories, such as those of the Gene Ontology (GO), are enriched for the selected features. Multiple comparison procedures (MCPs) are commonly used to prevent excessive false positive rates. Traditional MCPs, e.g., the Bonferroni method, go to the opposite extreme: strictly controlling a family-wise error rate, resulting in excessive false negative rates. Researchers generally prefer the more balanced approach of instead controlling the false discovery rate (FDR). However, the q-values that methods of FDR control assign to biological categories tend to be too low to reliably estimate the probability that a biological category is not enriched for the preselected features. Thus, we study an application of the other estimators of that probability, which is called the local FDR (LFDR).ResultsWe considered five LFDR estimators for detecting enriched GO terms: a binomial-based estimator (BBE), a maximum likelihood estimator (MLE), a normalized MLE (NMLE), a histogram-based estimator assuming a theoretical null hypothesis (HBE), and a histogram-based estimator assuming an empirical null hypothesis (HBE-EN). Since NMLE depends not only on the data but also on the specified value of Π0, the proportion of non-enriched GO terms, it is only advantageous when either Π0 is already known with sufficient accuracy or there are data for only 1 GO term. By contrast, the other estimators work without specifying Π0 but require data for at least 2 GO terms. Our simulation studies yielded the following summaries of the relative performance of each of those four estimators. HBE and HBE-EN produced larger biases for 2, 4, 8, 32, and 100 GO terms than BBE and MLE. BBE has the lowest bias if Π0 is 1 and if the number of GO terms is between 2 and 32. The bias of MLE is no worse than that of BBE for 100 GO terms even when the ideal number of components in its underlying mixture model is unknown, but has high bias when the number of GO terms is small compared to the number of estimated parameters. For unknown values of Π0, BBE has the lowest bias for a small number of GO terms (2-32 GO terms), and MLE has the lowest bias for a medium number of GO terms (100 GO terms).ConclusionsFor enrichment detection, we recommend estimating the LFDR by MLE given at least a medium number of GO terms, by BBE given a small number of GO terms, and by NMLE given either only 1 GO term or precise knowledge of Π0.

In molecular biology, it is a general assumption that the ensemble of expressed molecules, their activities and interactions determine biological function, cellular states and phenotypes. Stable protein complexes—or macromolecular machines—are, in turn, the key functional entities mediating and modulating most biological processes. Although identifying protein complexes and their subunit composition can now be done inexpensively and at scale, determining their function remains challenging and labor intensive. This study describes Protein Complex Function predictor (PCfun), the first computational framework for the systematic annotation of protein complex functions using Gene Ontology (GO) terms. PCfun is built upon a word embedding using natural language processing techniques based on 1 million open access PubMed Central articles. Specifically, PCfun leverages two approaches for accurately identifying protein complex function, including: (i) an unsupervised approach that obtains the nearest neighbor (NN) GO term word vectors for a protein complex query vector and (ii) a supervised approach using Random Forest (RF) models trained specifically for recovering the GO terms of protein complex queries described in the CORUM protein complex database. PCfun consolidates both approaches by performing a hypergeometric statistical test to enrich the top NN GO terms within the child terms of the GO terms predicted by the RF models. The documentation and implementation of the PCfun package are available at https://github.com/sharmavaruns/PCfun. We anticipate that PCfun will serve as a useful tool and novel paradigm for the large-scale characterization of protein complex function.

A race through the maze of genomic evidence

BackgroundAutomatic functional annotation of proteins is an open research problem in bioinformatics. The growing number of protein entries in public databases, for example in UniProtKB, poses challenges in manual functional annotation. Manual annotation requires expert human curators to search and read related research articles, interpret the results, and assign the annotations to the proteins. Thus, it is a time-consuming and expensive process. Therefore, designing computational tools to perform automatic annotation leveraging the high quality manual annotations that already exist in UniProtKB/SwissProt is an important research problemResultsIn this paper, we extend and adapt the GrAPFI (graph-based automatic protein function inference) (Sarker et al. in BMC Bioinform 21, 2020; Sarker et al., in: Proceedings of 7th international conference on complex networks and their applications, Cambridge, 2018) method for automatic annotation of proteins with gene ontology (GO) terms renaming it as GrAPFI-GO. The original GrAPFI method uses label propagation in a similarity graph where proteins are linked through the domains, families, and superfamilies that they share. Here, we also explore various types of similarity measures based on common neighbors in the graph. Moreover, GO terms are arranged in a hierarchical manner according to semantic parent–child relations. Therefore, we propose an efficient pruning and post-processing technique that integrates both semantic similarity and hierarchical relations between the GO terms. We produce experimental results comparing the GrAPFI-GO method with and without considering common neighbors similarity. We also test the performance of GrAPFI-GO and other annotation tools for GO annotation on a benchmark of proteins with and without the proposed pruning and post-processing procedure.ConclusionOur results show that the proposed semantic hierarchical post-processing potentially improves the performance of GrAPFI-GO and of other annotation tools as well. Thus, GrAPFI-GO exposes an original efficient and reusable procedure, to exploit the semantic relations among the GO terms in order to improve the automatic annotation of protein functions

BackgroundAnnotation of proteins with gene ontology (GO) terms is ongoing work and a complex task. Manual GO annotation is precise and precious, but it is time-consuming. Therefore, instead of curated annotations most of the proteins come with uncurated annotations, which have been generated automatically. Text-mining systems that use literature for automatic annotation have been proposed but they do not satisfy the high quality expectations of curators.ResultsIn this paper we describe an approach that links uncurated annotations to text extracted from literature. The selection of the text is based on the similarity of the text to the term from the uncurated annotation. Besides substantiating the uncurated annotations, the extracted texts also lead to novel annotations. In addition, the approach uses the GO hierarchy to achieve high precision. Our approach is integrated into GOAnnotator, a tool that assists the curation process for GO annotation of UniProt proteins.ConclusionThe GO curators assessed GOAnnotator with a set of 66 distinct UniProt/SwissProt proteins with uncurated annotations. GOAnnotator provided correct evidence text at 93% precision. This high precision results from using the GO hierarchy to only select GO terms similar to GO terms from uncurated annotations in GOA. Our approach is the first one to achieve high precision, which is crucial for the efficient support of GO curators. GOAnnotator was implemented as a web tool that is freely available at .

Protein function prediction is one of the most important biological problems in the field of bioinformatics. The functions of proteins are generally described by a series of Gene Ontology (GO) terms that have hierarchical relationships. Two factors hinder the effective prediction of protein functions using current methods: 1) they cannot well model and learn the topological semantic similarity between residues and GO terms, resulting in a huge semantic gap; 2) they predict the functions of proteins by calculating the semantic similarity between protein-level embeddings and GO terms, which does not effectively learn the protein-function relationship. To address the above issues, we propose the Topological-aware Residue-Gene Ontology Attention Network (TRGOA) for protein function prediction. First, a topological-aware attention module is designed to leverage attention scores within this joint semantic space allowing for modeling the fine-grained semantic similarity between residues and GO terms, thereby narrowing the semantic gap. Second, a multi-head aggregator is proposed, which adeptly captures the functions relevant fine-grained semantic similarity and filters out function-irrelevant components, which effectively reveal protein-function relationships, thereby enhancing generality and robustness. Finally, TRGOA has demonstrated promising outcomes, revealing our model can understand the protein-function relationship in deep insights.