Hierarchical deep learning for predicting GO annotations by integrating protein knowledge.

MOTIVATION: Experimental testing and manual curation are the most precise ways for assigning Gene Ontology (GO) terms describing protein functions. However, they are expensive, time-consuming and cannot cope with the exponential growth of data generated by high-throughput sequencing methods. Hence, researchers need reliable computational systems to help fill the gap with automatic function prediction. The results of the last Critical Assessment of Function Annotation challenge revealed that GO-terms prediction remains a very challenging task. Recent developments on deep learning are significantly breaking out the frontiers leading to new knowledge in protein research thanks to the integration of data from multiple sources. However, deep models hitherto developed for functional prediction are mainly focused on sequence data and have not achieved breakthrough performances yet. RESULTS: We propose DeeProtGO, a novel deep-learning model for predicting GO annotations by integrating protein knowledge. DeeProtGO was trained for solving 18 different prediction problems, defined by the three GO sub-ontologies, the type of proteins, and the taxonomic kingdom. Our experiments reported higher prediction quality when more protein knowledge is integrated. We also benchmarked DeeProtGO against state-of-the-art methods on public datasets, and showed it can effectively improve the prediction of GO annotations. AVAILABILITY AND IMPLEMENTATION: DeeProtGO and a case of use are available at https://github.com/gamerino/DeeProtGO. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

CROssBAR: comprehensive resource of biomedical relations with knowledge graph representations.

Systemic analysis of available large-scale biological/biomedical data is critical for studying biological mechanisms, and developing novel and effective treatment approaches against diseases. However, different layers of the available data are produced using different technologies and scattered across individual computational resources without any explicit connections to each other, which hinders extensive and integrative multi-omics-based analysis. We aimed to address this issue by developing a new data integration/representation methodology and its application by constructing a biological data resource. CROssBAR is a comprehensive system that integrates large-scale biological/biomedical data from various resources and stores them in a NoSQL database. CROssBAR is enriched with the deep-learning-based prediction of relationships between numerous data entries, which is followed by the rigorous analysis of the enriched data to obtain biologically meaningful modules. These complex sets of entities and relationships are displayed to users via easy-to-interpret, interactive knowledge graphs within an open-access service. CROssBAR knowledge graphs incorporate relevant genes-proteins, molecular interactions, pathways, phenotypes, diseases, as well as known/predicted drugs and bioactive compounds, and they are constructed on-the-fly based on simple non-programmatic user queries. These intensely processed heterogeneous networks are expected to aid systems-level research, especially to infer biological mechanisms in relation to genes, proteins, their ligands, and diseases.

Effect of sequence padding on the performance of deep learning models in archaeal protein functional prediction.

The use of raw amino acid sequences as input for deep learning models for protein functional prediction has gained popularity in recent years. This scheme obliges to manage proteins with different lengths, while deep learning models require same-shape input. To accomplish this, zeros are usually added to each sequence up to a established common length in a process called zero-padding. However, the effect of different padding strategies on model performance and data structure is yet unknown. We propose and implement four novel types of padding the amino acid sequences. Then, we analysed the impact of different ways of padding the amino acid sequences in a hierarchical Enzyme Commission number prediction problem. Results show that padding has an effect on model performance even when there are convolutional layers implied. Contrastingly to most of deep learning works which focus mainly on architectures, this study highlights the relevance of the deemed-of-low-importance process of padding and raises awareness of the need to refine it for better performance. The code of this analysis is publicly available at https://github.com/b2slab/padding_benchmark .

UniRule: a unified rule resource for automatic annotation in the UniProt Knowledgebase.

MOTIVATION: The number of protein records in the UniProt Knowledgebase (UniProtKB: https://www.uniprot.org) continues to grow rapidly as a result of genome sequencing and the prediction of protein-coding genes. Providing functional annotation for these proteins presents a significant and continuing challenge. RESULTS: In response to this challenge, UniProt has developed a method of annotation, known as UniRule, based on expertly curated rules, which integrates related systems (RuleBase, HAMAP, PIRSR, PIRNR) developed by the members of the UniProt consortium. UniRule uses protein family signatures from InterPro, combined with taxonomic and other constraints, to select sets of reviewed proteins which have common functional properties supported by experimental evidence. This annotation is propagated to unreviewed records in UniProtKB that meet the same selection criteria, most of which do not have (and are never likely to have) experimentally verified functional annotation. Release 2020_01 of UniProtKB contains 6496 UniRule rules which provide annotation for 53 million proteins, accounting for 30% of the 178 million records in UniProtKB. UniRule provides scalable enrichment of annotation in UniProtKB. AVAILABILITY AND IMPLEMENTATION: UniRule rules are integrated into UniProtKB and can be viewed at https://www.uniprot.org/unirule/. UniRule rules and the code required to run the rules, are publicly available for researchers who wish to annotate their own sequences. The implementation used to run the rules is known as UniFIRE and is available at https://gitlab.ebi.ac.uk/uniprot-public/unifire.

The CAFA challenge reports improved protein function prediction and new functional annotations for hundreds of genes through experimental screens.

BACKGROUND: The Critical Assessment of Functional Annotation (CAFA) is an ongoing, global, community-driven effort to evaluate and improve the computational annotation of protein function. RESULTS: Here, we report on the results of the third CAFA challenge, CAFA3, that featured an expanded analysis over the previous CAFA rounds, both in terms of volume of data analyzed and the types of analysis performed. In a novel and major new development, computational predictions and assessment goals drove some of the experimental assays, resulting in new functional annotations for more than 1000 genes. Specifically, we performed experimental whole-genome mutation screening in Candida albicans and Pseudomonas aureginosa genomes, which provided us with genome-wide experimental data for genes associated with biofilm formation and motility. We further performed targeted assays on selected genes in Drosophila melanogaster, which we suspected of being involved in long-term memory. CONCLUSION: We conclude that while predictions of the molecular function and biological process annotations have slightly improved over time, those of the cellular component have not. Term-centric prediction of experimental annotations remains equally challenging; although the performance of the top methods is significantly better than the expectations set by baseline methods in C. albicans and D. melanogaster, it leaves considerable room and need for improvement. Finally, we report that the CAFA community now involves a broad range of participants with expertise in bioinformatics, biological experimentation, biocuration, and bio-ontologies, working together to improve functional annotation, computational function prediction, and our ability to manage big data in the era of large experimental screens.

Efficiently Mining Recurrent Substructures from Protein Three-Dimensional Structure Graphs.

Studying protein structures is a major asset for understanding the molecular mechanisms of life. The number of publicly available protein structures has increasingly become extremely large. Yet, the classification of a protein structure remains a difficult, costly, and time-consuming task. Exploring spatial information on protein structures can provide important functional and structural insights. In this context, spatial motifs may correspond to relevant fragments, which might be very useful for a better understanding of proteins. In this article, we propose AntMot, a fast algorithm, to find spatial motifs from protein three-dimensional structures by extending the Karp-Miller-Rosenberg repetition finder, originally dedicated to sequences. The extracted motifs, termed ant-motifs, follow an ant-like shape that is composed of a backbone fragment from the primary structure, enriched with spatial refinements. We show that these motifs are biologically sound, and we used them as descriptors in the classification of several benchmark datasets. Experimental results show that our approach presents a trade-off between sequential motifs and subgraph motifs in terms of the number of extracted substructures, while providing a significant enhancement in the classification accuracy over sequential and frequent-subgraph motifs as well as alignment-based approaches.

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.

Rule Mining Techniques to Predict Prokaryotic Metabolic Pathways.

It is becoming more evident that computational methods are needed for the identification and the mapping of pathways in new genomes. We introduce an automatic annotation system (ARBA4Path Association Rule-Based Annotator for Pathways) that utilizes rule mining techniques to predict metabolic pathways across wide range of prokaryotes. It was demonstrated that specific combinations of protein domains (recorded in our rules) strongly determine pathways in which proteins are involved and thus provide information that let us very accurately assign pathway membership (with precision of 0.999 and recall of 0.966) to proteins of a given prokaryotic taxon. Our system can be used to enhance the quality of automatically generated annotations as well as annotating proteins with unknown function. The prediction models are represented in the form of human-readable rules, and they can be used effectively to add absent pathway information to many proteins in UniProtKB/TrEMBL database.

Prediction of Metabolic Pathway Involvement in Prokaryotic UniProtKB Data by Association Rule Mining.

The widening gap between known proteins and their functions has encouraged the development of methods to automatically infer annotations. Automatic functional annotation of proteins is expected to meet the conflicting requirements of maximizing annotation coverage, while minimizing erroneous functional assignments. This trade-off imposes a great challenge in designing intelligent systems to tackle the problem of automatic protein annotation. In this work, we present a system that utilizes rule mining techniques to predict metabolic pathways in prokaryotes. The resulting knowledge represents predictive models that assign pathway involvement to UniProtKB entries. We carried out an evaluation study of our system performance using cross-validation technique. We found that it achieved very promising results in pathway identification with an F1-measure of 0.982 and an AUC of 0.987. Our prediction models were then successfully applied to 6.2 million UniProtKB/TrEMBL reference proteome entries of prokaryotes. As a result, 663,724 entries were covered, where 436,510 of them lacked any previous pathway annotations.

UniProt-DAAC: domain architecture alignment and classification, a new method for automatic functional annotation in UniProtKB.

MOTIVATION: Similarity-based methods have been widely used in order to infer the properties of genes and gene products containing little or no experimental annotation. New approaches that overcome the limitations of methods that rely solely upon sequence similarity are attracting increased attention. One of these novel approaches is to use the organization of the structural domains in proteins. RESULTS: We propose a method for the automatic annotation of protein sequences in the UniProt Knowledgebase (UniProtKB) by comparing their domain architectures, classifying proteins based on the similarities and propagating functional annotation. The performance of this method was measured through a cross-validation analysis using the Gene Ontology (GO) annotation of a sub-set of UniProtKB/Swiss-Prot. The results demonstrate the effectiveness of this approach in detecting functional similarity with an average F-score: 0.85. We applied the method on nearly 55.3 million uncharacterized proteins in UniProtKB/TrEMBL resulted in 44 818 178 GO term predictions for 12 172 114 proteins. 22% of these predictions were for 2 812 016 previously non-annotated protein entries indicating the significance of the value added by this approach. AVAILABILITY AND IMPLEMENTATION: The results of the method are available at: ftp://ftp.ebi.ac.uk/pub/contrib/martin/DAAC/ CONTACT: tdogan@ebi.ac.uk SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Smoothing 3D protein structure motifs through graph mining and amino acid similarities.

One of the most powerful techniques to study proteins is to look for recurrent fragments (also called substructures), then use them as patterns to characterize the proteins under study. Although protein sequences have been extensively studied in the literature, studying protein three-dimensional (3D) structures can reveal relevant structural and functional information that may not be derived from protein sequences alone. An emergent trend consists of parsing proteins 3D structures into graphs of amino acids. Hence, the search of recurrent substructures is formulated as a process of frequent subgraph discovery where each subgraph represents a 3D motif. In this scope, several efficient approaches for frequent 3D motif discovery have been proposed in the literature. However, the set of discovered 3D motifs is too large to be efficiently analyzed and explored in any further process. In this article, we propose a novel pattern selection approach that shrinks the large number of frequent 3D motifs by selecting a subset of representative ones. Existing pattern selection approaches do not exploit the domain knowledge. Yet, in our approach, we incorporate the evolutionary information of amino acids defined in the substitution matrices in order to select the representative 3D motifs. We show the effectiveness of our approach on a number of real datasets. The results issued from our experiments show that considering the substitution between amino acids allows our approach to detect many similarities between patterns that are ignored by current subgraph selection approaches, and that it is able to considerably decrease the number of 3D motifs while enhancing their interestingness.

Protein sequences classification by means of feature extraction with substitution matrices.

BACKGROUND: This paper deals with the preprocessing of protein sequences for supervised classification. Motif extraction is one way to address that task. It has been largely used to encode biological sequences into feature vectors to enable using well-known machine-learning classifiers which require this format. However, designing a suitable feature space, for a set of proteins, is not a trivial task. For this purpose, we propose a novel encoding method that uses amino-acid substitution matrices to define similarity between motifs during the extraction step. RESULTS: In order to demonstrate the efficiency of such approach, we compare several encoding methods using some machine learning classifiers. The experimental results showed that our encoding method outperforms other ones in terms of classification accuracy and number of generated attributes. We also compared the classifiers in term of accuracy. Results indicated that SVM generally outperforms the other classifiers with any encoding method. We showed that SVM, coupled with our encoding method, can be an efficient protein classification system. In addition, we studied the effect of the substitution matrices variation on the quality of our method and hence on the classification quality. We noticed that our method enables good classification accuracies with all the substitution matrices and that the variances of the obtained accuracies using various substitution matrices are slight. However, the number of generated features varies from a substitution matrix to another. Furthermore, the use of already published datasets allowed us to carry out a comparison with several related works. CONCLUSIONS: The outcomes of our comparative experiments confirm the efficiency of our encoding method to represent protein sequences in classification tasks.