Search

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 used evaluation datasets promote methods that that favor unspecific and broad 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/. This article is protected by copyright. All rights reserved.

The Citrus genus comprises some of the most important and commonly cultivated fruit plants. Within the last decade, citrus greening disease (also known as huanglongbing or HLB) has emerged as the biggest threat for the citrus industry. This disease does not have a cure yet and, thus, many efforts have been made to find a solution to this devastating condition. There are challenges in the generation of high-yield resistant cultivars, in part due to the limited and sparse knowledge about the mechanisms that are used by the Liberibacter bacteria to proliferate the infection in Citrus plants. Here, we present GreeningDB, a database implemented to provide the annotation of Liberibacter proteomes, as well as the host–pathogen comparactomics tool, a novel platform to compare the predicted interactomes of two HLB host–pathogen systems. GreeningDB is built to deliver a user-friendly interface, including network visualization and links to other resources. We hope that by providing these characteristics, GreeningDB can become a central resource to retrieve HLB-related protein annotations, and thus, aid the community that is pursuing the development of molecular-based strategies to mitigate this disease’s impact. The database is freely available at http://bioinfo.usu.edu/GreeningDB/ (accessed on 11 August 2021).

Advances in genome sequencing have accelerated the growth of sequenced genomes but at a cost in the quality of genome annotation. At the same time, computational analysis is widely used for protein annotation, but a dearth of experimental verification has contributed to inaccurate annotation as well as to annotation error propagation. Thus, a tool to help life scientists with accurate protein annotation would be useful. In this work we describe a website we have developed, the Protein Annotation Surveillance Site (PASS), which provides such a tool. This website consists of three major components: a database of homologous clusters of more than eight million protein sequences deduced from the representative genomes of bacteria, archaea, eukarya, and viruses, together with sequence information; a machine-learning software tool which periodically queries the UniprotKB database to determine whether protein function has been experimentally verified; and a query-able webpage where the FASTA headers of sequences from the cluster best matching an input sequence are returned. The user can choose from these sequences to create a sequence similarity network to assist in annotation or else use their expert knowledge to choose an annotation from the cluster sequences. Illustrations demonstrating use of this website are presented.

International audience; In the last few decades, the explosion of genomic projects has produced huge sets of predicted genes and annotated sequences. The prediction of a gene structure can be defined as the capacity to determine the start and the stop of the gene as well as the positions of introns, if present. Despite the number of performant gene prediction programs combining ab initio and homology-based approaches (Mathe et al., 2002; Hoff and Stanke, 2015), the rate of mis-predicted genes is not negligible and can be due to several factors (Scalzitti et al., 2020). For example, unusually long introns, short exons or long genes can generate incomplete or partially predicted gene structure; short intergenic regions can lead to gene fusion; DNA sequencing errors (nucleotide deletions or insertions) introducing frameshifts can affect predictions; non-canonical splice sites, overlapping genes and genes located within introns are also a source of erroneous predictions. [...]

Motivation Genomic data are prevalent, leading to frequent encounters with uninterpreted variants or mutations with unknown mechanisms of effect. Researchers must manually aggregate data from multiple sources and across related proteins, mentally translating effects between the genome and proteome, to attempt to understand mechanisms. Materials and methods P2T2 presents diverse data and annotation types in a unified protein-centric view, facilitating the interpretation of coding variants and hypothesis generation. Information from primary sequence, domain, motif, and structural levels are presented and also organized into the first Paralog Annotation Analysis across the human proteome. Results Our tool assists research efforts to interpret genomic variation by aggregating diverse, relevant, and proteome-wide information into a unified interactive web-based interface. Additionally, we provide a REST API enabling automated data queries, or repurposing data for other studies. Conclusion The unified protein-centric interface presented in P2T2 will help researchers interpret novel variants identified through next-generation sequencing. Code and server link available at github.com/GenomicInterpretation/p2t2.

Background:Ubiquitination, as a post-translational modification, is a crucial biological process in cell signaling, apoptosis, and localization. Identification of ubiquitination proteins is of fundamental importance for understanding the molecular mechanisms in biological systems and diseases. Although high-throughput experimental studies using mass spectrometry have identified many ubiquitination proteins and ubiquitination sites, the vast majority of ubiquitination proteins remain undiscovered, even in well-studied model organisms.Objective:To reduce experimental costs, computational methods have been introduced to predict ubiquitination sites, but the accuracy is unsatisfactory. If it can be predicted whether a protein can be ubiquitinated or not, it will help in predicting ubiquitination sites. However, all the computational methods so far can only predict ubiquitination sites.Methods:In this study, the first computational method for predicting ubiquitination proteins without relying on ubiquitination site prediction has been developed. The method extracts features from sequence conservation information through a grey system model, as well as functional domain annotation and subcellular localization.Results:Together with the feature analysis and application of the relief feature selection algorithm, the results of 5-fold cross-validation on three datasets achieved a high accuracy of 90.13%, with Matthew’s correlation coefficient of 80.34%. The predicted results on an independent test data achieved 87.71% as accuracy and 75.43% of Matthew’s correlation coefficient, better than the prediction from the best ubiquitination site prediction tool available.Conclusion:Our study may guide experimental design and provide useful insights for studying the mechanisms and modulation of ubiquitination pathways. The code is available at: https://github.com/Chunhuixu/UBIPredic_QWRCHX.

Functional annotation of protein sequence with high accuracy has become one of the most important issues in modern biomedical studies, and computational approaches of significantly accelerated analysis process and enhanced accuracy are greatly desired. Although a variety of methods have been developed to elevate protein annotation accuracy, their ability in controlling false annotation rates remains either limited or not systematically evaluated. In this study, a protein encoding strategy, together with a deep learning algorithm, was proposed to control the false discovery rate in protein function annotation, and its performances were systematically compared with that of the traditional similarity-based and de novo approaches. Based on a comprehensive assessment from multiple perspectives, the proposed strategy and algorithm were found to perform better in both prediction stability and annotation accuracy compared with other de novo methods. Moreover, an in-depth assessment revealed that it possessed an improved capacity of controlling the false discovery rate compared with traditional methods. All in all, this study not only provided a comprehensive analysis on the performances of the newly proposed strategy but also provided a tool for the researcher in the fields of protein function annotation.

A high quality genome annotation greatly facilitates successful cell line engineering. Standard draft genome annotation pipelines are based largely onde novogene prediction, homology, and RNA-Seq data. However, draft annotations can suffer from incorrectly predictions of translated sequence, incorrect splice isoforms and missing genes. Here we generated a draft annotation for the newly assembled Chinese hamster genome and used RNA-Seq, proteomics, and Ribo-Seq to experimentally annotate the genome. We identified 4,333 new proteins compared to the hamster RefSeq protein annotation and 2,503 novel translational events (e.g., alternative splices, mutations, novel splices). Finally, we used this pipeline to identify the source of translated retroviruses contaminating recombinant products from Chinese hamster ovary (CHO) cell lines, including 131 type-C retroviruses, thus enabling future efforts to eliminate retroviruses by reducing the costs incurred with retroviral particle clearance. In summary, the improved annotation provides a more accurate platform for guiding CHO cell line engineering, including facilitating the interpretation of omics data, defining of cellular pathways, and engineering of complex phenotypes.

Understanding the association of genetic variation with its functional consequences in proteins is essential for the interpretation of genomic data and identifying causal variants in diseases. Integration of protein function knowledge with genome annotation can assist in rapidly comprehending genetic variation within complex biological processes. Here, we describe mapping UniProtKB human sequences and positional annotations, such as active sites, binding sites, and variants to the human genome (GRCh38) and the release of a public genome track hub for genome browsers. To demonstrate the power of combining protein annotations with genome annotations for functional interpretation of variants, we present specific biological examples in disease‐related genes and proteins. Computational comparisons of UniProtKB annotations and protein variants with ClinVar clinically annotated single nucleotide polymorphism (SNP) data show that 32% of UniProtKB variants colocate with 8% of ClinVar SNPs. The majority of colocated UniProtKB disease‐associated variants (86%) map to 'pathogenic' ClinVar SNPs. UniProt and ClinVar are collaborating to provide a unified clinical variant annotation for genomic, protein, and clinical researchers. The genome track hubs, and related UniProtKB files, are downloadable from the UniProt FTP site and discoverable as public track hubs at the UCSC and Ensembl genome browsers.

Background The rapid development of the (meta-)omics fields has produced an unprecedented amount of high-resolution and high-fidelity data. Through the use of these datasets we can infer the role of previously functionally unannotated proteins from single organisms and consortia. In this context, protein function annotation can be described as the identification of regions of interest (i.e., domains) in protein sequences and the assignment of biological functions. Despite the existence of numerous tools, challenges remain in terms of speed, flexibility, and reproducibility. In the big data era, it is also increasingly important to cease limiting our findings to a single reference, coalescing knowledge from different data sources, and thus overcoming some limitations in overly relying on computationally generated data from single sources. Results We implemented a protein annotation tool, Mantis, which uses database identifiers intersection and text mining to integrate knowledge from multiple reference data sources into a single consensus-driven output. Mantis is flexible, allowing for the customization of reference data and execution parameters, and is reproducible across different research goals and user environments. We implemented a depth-first search algorithm for domain-specific annotation, which significantly improved annotation performance compared to sequence-wide annotation. The parallelized implementation of Mantis results in short runtimes while also outputting high coverage and high-quality protein function annotations. Conclusions Mantis is a protein function annotation tool that produces high-quality consensus-driven protein annotations. It is easy to set up, customize, and use, scaling from single genomes to large metagenomes. Mantis is available under the MIT license at https://github.com/PedroMTQ/mantis.

A common approach to genome annotation involves the use of homology-based tools for the prediction of the functional role of proteins. The quality of functional annotations is dependent on the reference data used, as such, choosing the appropriate sources is crucial. Unfortunately, no single reference data source can be universally considered the gold standard, thus using multiple references could potentially increase annotation quality and coverage. However, this comes with challenges, particularly due to the introduction of redundant and exclusive annotations. Through text mining it is possible to identify highly similar functional descriptions, thus strengthening the confidence of the final protein functional annotation and providing a redundancy-free output. Here we present UniFunc, a text mining approach that is able to detect similar functional descriptions with high precision. UniFunc was built as a small module and can be independently used or integrated into protein function annotation pipelines. By removing the need to individually analyse and compare annotation results, UniFunc streamlines the complementary use of multiple reference datasets.

SARS-CoV-2 genomic sequencing efforts have scaled dramatically to address the current global pandemic and aid public health. In this work, we analyzed a corpus of 66,000 SARS-CoV-2 genome sequences. We developed a novel semi-supervised pipeline for automated gene, protein, and functional domain annotation of SARS-CoV-2 genomes that differentiates itself by not relying on use of a single reference genome and by overcoming atypical genome traits. Using this method, we identified the comprehensive set of known proteins with 98.5% set membership accuracy and 99.1% accuracy in length prediction compared to proteome references including Replicase polyprotein 1ab (with its transcriptional slippage site). Compared to other published tools such as Prokka (base) and VAPiD, we yielded an 6.4- and 1.8-fold increase in protein annotations. Our method generated 13,000,000 molecular target sequences— some conserved across time and geography while others represent emerging variants. We observed 3,362 non-redundant sequences per protein on average within this corpus and describe key D614G and N501Y variants spatiotemporally. For spike glycoprotein domains, we achieved greater than 97.9% sequence identity to references and characterized Receptor Binding Domain variants. Here, we comprehensively present the molecular targets to refine biomedical interventions for SARS-CoV-2 with a scalable high-accuracy method to analyze newly sequenced infections.

Spatial proteomics has the potential to significantly advance our understanding of biology, physiology and medicine. Matrix-assisted laser desorption/ionisation mass spectrometry imaging (MALDI-MSI) is a powerful tool in the spatial proteomics field, enabling direct detection and registration of protein abundance and distribution across tissues. MALDI-MSI preserves spatial distribution and histology allowing unbiased analysis of complex, heterogeneous tissues. However, MALDI-MSI faces the challenge of simultaneous peptide quantification and identification. To overcome this, we develop and validate HIT-MAP (High-resolution Informatics Toolbox in MALDI-MSI Proteomics), an open-source bioinformatics workflow using peptide mass fingerprint analysis and a dual scoring system to computationally assign peptide and protein annotations to high mass resolution MSI datasets and generate customisable spatial distribution maps. HIT-MAP will be a valuable resource for the spatial proteomics community for analysing newly generated and retrospective datasets, enabling robust peptide and protein annotation and visualisation in a wide array of normal and disease contexts., MALDI-mass spectrometry imaging (MSI) can reveal the distribution of proteins in tissues but tools for protein identification and annotation are sparse. Here, the authors develop an open-source bioinformatic workflow for false discovery rate-controlled protein annotation and spatial mapping from MALDI-MSI data.

MotivationAccurate automatic annotation of protein function relies on both innovative models and robust datasets. Due to their importance in biological processes, the identification of DNA-binding proteins directly from protein sequence has been the focus of many studies. However, the data sets used to train and evaluate these methods have suffered from substantial flaws. We describe some of the weaknesses of the data sets used in previous DNA-binding protein literature and provide several new data sets addressing these problems. We suggest new evaluative benchmark tasks that more realistically assess real-world performance for protein annotation models. We propose a simple new model for the prediction of DNA-binding proteins and compare its performance on the improved data sets to two previously published models. Additionally, we provide extensive tests showing how the best models predict across taxonomies.ResultsOur new gradient boosting model, which uses features derived from a published protein language model, outperforms the earlier models. Perhaps surprisingly, so does a baseline nearest neighbor model using BLAST percent identity. We evaluate the sensitivity of these models to perturbations of DNA-binding regions and control regions of protein sequences. The successful data-driven models learn to focus on DNA-binding regions. When predicting across taxonomies, the best models are highly accurate across species in the same kingdom and can provide some information when predicting across kingdoms.Code and Data AvailabilityAll the code and data for this paper can be found athttps://github.com/AZaitzeff/tools_for_dna_binding_proteins.Contactalexander.zaitzeff@twosixtech.com

Motivation Accurate automatic annotation of protein function relies on both innovative models and robust datasets. Due to their importance in biological processes, the identification of DNA-binding proteins directly from protein sequence has been the focus of many studies. However, the datasets used to train and evaluate these methods have suffered from substantial flaws. We describe some of the weaknesses of the datasets used in previous DNA-binding protein literature and provide several new datasets addressing these problems. We suggest new evaluative benchmark tasks that more realistically assess real-world performance for protein annotation models. We propose a simple new model for the prediction of DNA-binding proteins and compare its performance on the improved datasets to two previously published models. In addition, we provide extensive tests showing how the best models predict across taxa. Results Our new gradient boosting model, which uses features derived from a published protein language model, outperforms the earlier models. Perhaps surprisingly, so does a baseline nearest neighbor model using BLAST percent identity. We evaluate the sensitivity of these models to perturbations of DNA-binding regions and control regions of protein sequences. The successful data-driven models learn to focus on DNA-binding regions. When predicting across taxa, the best models are highly accurate across species in the same kingdom and can provide some information when predicting across kingdoms. Availability and Implementation The data and results for this article can be found at https://doi.org/10.5281/zenodo.5153906. The code for this article can be found at https://doi.org/10.5281/zenodo.5153683. The code, data and results can also be found at https://github.com/AZaitzeff/tools_for_dna_binding_proteins.

Background The identification of protein families is of outstanding practical importance for in silico protein annotation and is at the basis of several bioinformatic resources. Pfam is possibly the most well known protein family database, built in many years of work by domain experts with extensive use of manual curation. This approach is generally very accurate, but it is quite time consuming and it may suffer from a bias generated from the hand-curation itself, which is often guided by the available experimental evidence. Results We introduce a procedure that aims to identify automatically putative protein families. The procedure is based on Density Peak Clustering and uses as input only local pairwise alignments between protein sequences. In the experiment we present here, we ran the algorithm on about 4000 full-length proteins with at least one domain classified by Pfam as belonging to the Pseudouridine synthase and Archaeosine transglycosylase (PUA) clan. We obtained 71 automatically-generated sequence clusters with at least 100 members. While our clusters were largely consistent with the Pfam classification, showing good overlap with either single or multi-domain Pfam family architectures, we also observed some inconsistencies. The latter were inspected using structural and sequence based evidence, which suggested that the automatic classification captured evolutionary signals reflecting non-trivial features of protein family architectures. Based on this analysis we identified a putative novel pre-PUA domain as well as alternative boundaries for a few PUA or PUA-associated families. As a first indication that our approach was unlikely to be clan-specific, we performed the same analysis on the P53 clan, obtaining comparable results. Conclusions The clustering procedure described in this work takes advantage of the information contained in a large set of pairwise alignments and successfully identifies a set of putative families and family architectures in an unsupervised manner. Comparison with the Pfam classification highlights significant overlap and points to interesting differences, suggesting that our new algorithm could have potential in applications related to automatic protein classification. Testing this hypothesis, however, will require further experiments on large and diverse sequence datasets.

Advances in genome sequencing technology and computing power have brought about the explosive growth of sequenced genomes in public repositories with a concomitant increase in annotation errors. Many protein sequences are annotated using computational analysis rather than experimental verification, leading to inaccuracies in annotation. Confirmation of existing protein annotations is urgently needed before misannotation becomes even more prevalent due to error propagation. In this work we present a novel approach for automatically confirming the existence of manually curated information with experimental evidence of protein annotation. Our ensemble learning method uses a combination of recurrent convolutional neural network, logistic regression, and support vector machine models. Natural language processing in the form of word embeddings is used with journal publication titles retrieved from the UniProtKB database. Importantly, we use recall as our most significant metric to ensure the maximum number of verifications possible, results are reported to a human curator for confirmation. Our ensemble model achieves 91.25% recall, 71.26% accuracy, 65.19% precision, and an F1 score of 76.05% and outperforms the Bidirectional Encoder Representations from Transformers for Biomedical Text Mining (BioBERT) model with fine-tuning using the same data.

It is critical for biological studies to annotate amino acid sequences and understand how proteins function. Protein function is important to medical research in the health industry (e.g., drug discovery). With the advancement of deep learning, accurate protein annotation models have been developed for alignment free protein annotation. In this paper, we develop a deep learning model with an attention mechanism that can predict Gene Ontology labels given a protein sequence input. We believe this model can produce accurate predictions as well as maintain good interpretability. We further show how the model can be interpreted by examining and visualizing the intermediate layer output in our deep neural network.

MaizeMine is the data mining resource of the Maize Genetics and Genome Database (MaizeGDB; http://maizemine.maizegdb.org). It enables researchers to create and export customized annotation datasets that can be merged with their own research data for use in downstream analyses. MaizeMine uses the InterMine data warehousing system to integrate genomic sequences and gene annotations from the Zea mays B73 RefGen_v3 and B73 RefGen_v4 genome assemblies, Gene Ontology annotations, single nucleotide polymorphisms, protein annotations, homologs, pathways, and precomputed gene expression levels based on RNA-seq data from the Z. mays B73 Gene Expression Atlas. MaizeMine also provides database cross references between genes of alternative gene sets from Gramene and NCBI RefSeq. MaizeMine includes several search tools, including a keyword search, built-in template queries with intuitive search menus, and a QueryBuilder tool for creating custom queries. The Genomic Regions search tool executes queries based on lists of genome coordinates, and supports both the B73 RefGen_v3 and B73 RefGen_v4 assemblies. The List tool allows you to upload identifiers to create custom lists, perform set operations such as unions and intersections, and execute template queries with lists. When used with gene identifiers, the List tool automatically provides gene set enrichment for Gene Ontology (GO) and pathways, with a choice of statistical parameters and background gene sets. With the ability to save query outputs as lists that can be input to new queries, MaizeMine provides limitless possibilities for data integration and meta-analysis.

Recent work performed by Sberro et al. (2019) revealed a vast unexplored space of small proteins existing within the human microbiome. At present, these small open reading frames (smORFs) are unannotated in existing reference genomes and standard genome annotation tools are not able to accurately predict them. In this study, we introduce an annotation tool named SmORFinder that predicts small proteins based on those identified by Sberro et al. This tool combines profile Hidden Markov models (pHMMs) of each small protein family and deep learning models that may better generalize to smORF families not seen in the training set. We find that combining predictions of both pHMM and deep learning models leads to more precise smORF predictions and that these predicted smORFs are enriched for Ribo-Seq or MetaRibo-Seq translation signals. Feature importance analysis reveals that the deep learning models learned to identify Shine-Dalgarno sequences, deprioritize the wobble position in each codon, and group codons in a way that strongly corresponds to the codon synonyms found in the codon table. We perform a core genome analysis of 26 bacterial species and identify many core smORFs of unknown function. We pre-compute small protein annotations for thousands of RefSeq isolate genomes and HMP metagenomes, and we make these data available through a web portal along with other useful tools for small protein annotation and analysis. The systematic identification and annotation of those important small proteins will help researchers to expand our understanding of this exciting field of biology.

Recent technological advancement has ignited the biological sequencing and structural projects, and a large amount of viral genome and proteome data are made accessible to the public health community. With the exponential growth in biological data, it has raised the challenges of data storage and its timely annotation. Implementing manual and computational methods, these datasets are enhanced and integrated with their respective family, strain, gene and protein annotations, three-dimensional protein structures, immune epitope locations, protein–protein interaction network, clinical metadata, etc. are incorporated in the separate specialized database according to their family and function. During any viral epidemic, identification of causative agents and genomic analysis becomes easy with bioinformatics tools and database resources that provide information about the genomic structure and phenotypic characteristics of known viruses can make this process more efficient by supporting data mining for the development of hypothesis worthy of in-depth laboratory experimentation on the emerging strain.

Relaxase-based plasmid classification has become popular in the past 10 years. Nevertheless, it is not obvious how to assign a query protein to a relaxase MOB family. Automated protein annotation is commonly used to classify them into families, gathering evolutionarily related proteins that likely perform the same function, while circumventing the problem of different naming conventions. Here, we implement an automated method, MOBscan, to identify relaxases and classify them into any of the nine MOB families. MOBscan is a web tool that carries out a HMMER search against a curated database of MOB profile Hidden Markov models., This work was financed by the Spanish Ministry of Economy and Competitiveness (BFU2017-86378-P and RTC-2015-3184-1).

The Pathosystems Resource Integration Center (PATRIC, www.patricbrc.org) is designed to provide researchers with the tools and services that they need to perform genomic and other ‘omic’ data analyses. In response to mounting concern over antimicrobial resistance (AMR), the PATRIC team has been developing new tools that help researchers understand AMR and its genetic determinants. To support comparative analyses, we have added AMR phenotype data to over 15 000 genomes in the PATRIC database, often assembling genomes from reads in public archives and collecting their associated AMR panel data from the literature to augment the collection. We have also been using this collection of AMR metadata to build machine learning-based classifiers that can predict the AMR phenotypes and the genomic regions associated with resistance for genomes being submitted to the annotation service. Likewise, we have undertaken a large AMR protein annotation effort by manually curating data from the literature and public repositories. This collection of 7370 AMR reference proteins, which contains many protein annotations (functional roles) that are unique to PATRIC and RAST, has been manually curated so that it projects stably across genomes. The collection currently projects to 1 610 744 proteins in the PATRIC database. Finally, the PATRIC Web site has been expanded to enable AMR-based custom page views so that researchers can easily explore AMR data and design experiments based on whole genomes or individual genes.

In the UniProt Knowledgebase (UniProtKB), publications providing evidence for a specific protein annotation entry are organized across different categories, such as function, interaction and expression, based on the type of data they contain. To provide a systematic way of categorizing computationally mapped bibliographies in UniProt, we investigate a convolutional neural network (CNN) model to classify publications with accession annotations according to UniProtKB categories. The main challenge of categorizing publications at the accession annotation level is that the same publication can be annotated with multiple proteins and thus be associated with different category sets according to the evidence provided for the protein. We propose a model that divides the document into parts containing and not containing evidence for the protein annotation. Then, we use these parts to create different feature sets for each accession and feed them to separate layers of the network. The CNN model achieved a micro F1-score of 0.72 and a macro F1-score of 0.62, outperforming baseline models based on logistic regression and support vector machine by up to 22 and 18 percentage points, respectively. We believe that such an approach could be used to systematically categorize the computationally mapped bibliography in UniProtKB, which represents a significant set of the publications, and help curators to decide whether a publication is relevant for further curation for a protein accession. Database URL: https://goldorak.hesge.ch/bioexpclass/upclass/.

This chapter aims to introduce to the specifics of protein structure annotations and their fundamental position in structural bioinformatics, bioinformatics in general. Proteins are profoundly characterised by their structure in every aspect of their functioning and, while over the last decades there has been a close to exponential growth of known protein sequences, the growth of known protein structures has been closer to linear because of the high complexity and cost of determining them. Thus, protein structure predictors are among the most thoroughly assessed tools in bioinformatics (in venues such as CASP or CAMEO) because they allow the structural study of proteins on a large scale. This chapter presents the key types of protein structure annotation and the methods and algorithms for predicting them, with the aim to give both a historical perspective on their development and a snapshot of their current state of the art. From one-dimensional protein annotations – i.e. secondary structure, solvent accessibility and torsion angles – to more complex and informative two-dimensional protein abstractions, i.e. contact maps, both mature and currently developing methods for protein structure annotations are introduced. The aim of this overview is to facilitate the adoption and development of state-of-the-art protein structural predictors. Particular attention is given to some of the best performing and freely available web servers and standalone programmes to predict protein structure annotations. Irish Research Council 24 month embargo - AC

Advanced sequencing techniques have helped unveil numerous new, potential cancer driver mutations. However, manual curation and analysis of gene and protein annotation are essential to verify such discoveries. Our recent study of STK19 (Serine Threonine Kinase 19), a previously identified melanoma driver, is a clear example of the importance of such detailed analysis, with both STK19 gene and protein annotations in frequently used databases having been proven incorrect.

Transcriptome data is beneficial to explore molecular mechanisms of extreme adaptations in non- model organisms like mangroves. In this data article, five major datasets and two data sub sets of a salt secreting mangrove, Rhizophora mucronata Lam. were described. A combination of Illumina HiSeq 2500, Trinity, BLAST X, Bowtie 2 and BLAST 2GO was used for RNA Seq, de novo assembly, transcript annotation, gene expression estimation and gene ontology annotation respectively. The RNA Sequence (Read 1 and Read 2) in Sequence Read Archive amounting to 46,366,348 paired end raw reads is the first data set made open for de novo or comparative transcript assembly. Assembled sequences of 93960 gene transcripts constitute the second data set in Transcriptome Shotgun Assembly. The gene/protein annotations to the assembled transcripts give two sub data sets containing 93960 each of GenBank and GenPept entries with comprehensive cDNA and translated protein sequences of genes. Of these, predicted proteins for 87768 coding sequences, mapped to UniProtKB serve as the third data set. The gene expression levels of the annotated transcripts comprise the fourth data set in Gene Expression Omnibus. The fifth data set in Figshare includes 44,028 gene ontology terms extracted for 21,073 confident transcripts. The data sets provide a valuable resource for further analyses including transcriptomic changes in response to environmental stresses.

CRISPR-Cas systems not only play key roles in prokaryotic acquired immunity, but can also be adapted as powerful genome editing tools. Understanding the native role of CRISPR-Cas systems in providing adaptive immunity can lead to new CRISPR-based technologies. Here, we develop CRISPRminer, a knowledge base and web server to comprehensively collect and investigate the knowledge of CRISPR-Cas systems and generate instructive annotations, including CRISPR arrays and Cas protein annotation, CRISPR-Cas system classification, self-targeting events detection, microbe–phage interaction inference, and anti-CRISPR annotation. CRISPRminer is user-friendly and freely available at http://www.microbiome-bigdata.com/CRISPRminer., Fan Zhang et al. present CRISPRminer, a comprehensive database for exploring CRISPR-Cas systems in more than 3500 microbial species and a web-server for in-depth data mining. CRISPRminer allows researchers to predict CRISPR-Cas systems and investigate self-targeting CRISPRs, microbe-phage interaction networks, and anti-CRISPR features.

Automated protein annotation using the Gene Ontology (GO) plays an important role in the biosciences. Evaluation has always been considered central to developing novel annotation methods, but little attention has been paid to the evaluation metrics themselves. Evaluation metrics define how well an annotation method performs and allows for them to be ranked against one another. Unfortunately, most of these metrics were adopted from the machine learning literature without establishing whether they were appropriate for GO annotations. We propose a novel approach for comparing GO evaluation metrics called Artificial Dilution Series (ADS). Our approach uses existing annotation data to generate a series of annotation sets with different levels of correctness (referred to as their signal level). We calculate the evaluation metric being tested for each annotation set in the series, allowing us to identify whether it can separate different signal levels. Finally, we contrast these results with several false positive annotation sets, which are designed to expose systematic weaknesses in GO assessment. We compared 37 evaluation metrics for GO annotation using ADS and identified drastic differences between metrics. We show that some metrics struggle to differentiate between different signal levels, while others give erroneously high scores to the false positive data sets. Based on our findings, we provide guidelines on which evaluation metrics perform well with the Gene Ontology and propose improvements to several well-known evaluation metrics. In general, we argue that evaluation metrics should be tested for their performance and we provide software for this purpose (https://bitbucket.org/plyusnin/ads/). ADS is applicable to other areas of science where the evaluation of prediction results is non-trivial., Author summary In the biosciences, predictive methods are becoming increasingly necessary as novel sequences are generated at an ever-increasing rate. The volume of sequence data necessitates Automated Function Prediction (AFP) as manual curation is often impossible. Unfortunately, selecting the best AFP method is complicated by researchers using different evaluation metrics. Furthermore, many commonly-used metrics can give misleading results. We argue that the use of poor metrics in AFP evaluation is a result of the lack of methods to benchmark the metrics themselves. We propose an approach called Artificial Dilution Series (ADS). ADS uses existing data sets to generate multiple artificial AFP results, where each result has a controlled error rate. We use ADS to understand whether different metrics can distinguish between results with known quantities of error. Our results highlight dramatic differences in performance between evaluation metrics.

Computational assignment of function to proteins with no known homologs is still an unsolved problem. We have created a novel, function-based approach to protein annotation and discovery called D-SPACE (Deep Semantic Protein Annotation Classification and Exploration), comprised of a multi-task, multi-label deep neural network trained on over 70 million proteins. Distinct from homology and motif-based methods, D-SPACE encodes proteins in high-dimensional representations (embeddings), allowing the accurate assignment of over 180,000 labels for 13 distinct tasks. The embedding representation enables fast searches for functionally related proteins, including homologs undetectable by traditional approaches. D-SPACE annotates all 109 million proteins in UniProt in under 35 hours on a single computer and searches the entirety of these in seconds. D-SPACE further quantifies the relative functional effect of mutations, facilitating rapid in silico mutagenesis for protein engineering applications. D-SPACE incorporates protein annotation, search, and other exploratory efforts into a single cohesive model.

Public repositories for genome and proteome annotations, such as the Gene Ontology (GO), rarely stores negative annotations, i.e. proteins not possessing a given function. This leaves undefined or ill defined the set of negative examples, which is crucial for training the majority of machine learning methods inferring proteins functions. Automated techniques to choose reliable negative proteins are thereby required to train accurate function prediction models. This study proposes the first extensive analysis of the temporal evolution of protein annotations in the GO repository. Novel annotations registered through the years have been analyzed to verify the presence of annotation patterns in the GO hierarchy. Our research supplied fundamental clues about proteins likely to be unreliable as negative examples, that we verified into a novel algorithm of our own construction, validated on two organisms in a genome wide fashion against approaches proposed to choose negative examples in the context of functional prediction., Comment: 13 pages, 5 figures, 1 table

KEGG (http://www.kegg.jp/ or http://www.genome.jp/kegg/) is an integrated database resource for biological interpretation of genome sequences and other high-throughput data. Molecular functions of genes and proteins are associated with ortholog groups and stored in the KEGG Orthology (KO) database. The KEGG pathway maps, BRITE hierarchies and KEGG modules are developed as networks of KO nodes, representing high-level functions of the cell and the organism. Currently, more than 4000 complete genomes are annotated with KOs in the KEGG GENES database, which can be used as a reference data set for KO assignment and subsequent reconstruction of KEGG pathways and other molecular networks. As an annotation resource, the following improvements have been made. First, each KO record is re-examined and associated with protein sequence data used in experiments of functional characterization. Second, the GENES database now includes viruses, plasmids, and the addendum category for functionally characterized proteins that are not represented in complete genomes. Third, new automatic annotation servers, BlastKOALA and GhostKOALA, are made available utilizing the non-redundant pangenome data set generated from the GENES database. As a resource for translational bioinformatics, various data sets are created for antimicrobial resistance and drug interaction networks.

The integration of protein function knowledge in the UniProt Knowledgebase (UniProtKB) with genomic data provides unique opportunities for biomedical research by helping scientists to rapidly comprehend complex processes in biology. UniProtKB provides expert curation of functionally characterized variants reported in the literature, many of them associated with disease. Understanding the association of genetic variation with its functional consequences in proteins is essential for the interpretation of large-scale genomics data. UniProtKB protein sequences and sequence feature annotations such as active sites, modified sites, binding domains and amino acid variation have been mapped to the current build of the human genome (GRCh38). We have also created public track hubs for the Ensembl and UCSC browsers. We examine some specific biological examples in disease-related genes and proteins, illustrating the utility of combining protein and genome annotations for the functional interpretation of variants. We also present a larger comparison of UniProtKB variant and feature curation data that collocates with clinically observed SNP data from ClinVar, illustrating how protein and gene disease annotations currently compare and discuss some additional uses that might follow with combined annotation. The combination of gene and protein annotation can assist medical geneticists with the functional interpretation of variation. The genomic track hubs are downloadable from the UniProt FTP site (http://www.uniprot.org/downloads) and directly discoverable as public track hubs at the USCS and Ensembl genome browsers.

Protein functional similarity based on gene ontology (GO) annotations serves as a powerful tool when comparing proteins on a functional level in applications such as protein-protein interaction prediction, gene prioritization, and disease gene discovery. Functional similarity (FS) is usually quantified by combining the GO hierarchy with an annotation corpus that links genes and gene products to GO terms. One large group of algorithms involves calculation of GO term semantic similarity (SS) between all the terms annotating the two proteins, followed by a second step, described as “mixing strategy”, which involves combining the SS values to yield the final FS value. Due to the variability of protein annotation caused e.g. by annotation bias, this value cannot be reliably compared on an absolute scale. We therefore introduce a similarity z-score that takes into account the FS background distribution of each protein. For a selection of popular SS measures and mixing strategies we demonstrate moderate accuracy improvement when using z-scores in a benchmark that aims to separate orthologous cases from random gene pairs and discuss in this context the impact of annotation corpus choice. The approach has been implemented in Frela, a fast high-throughput public web server for protein FS calculation and interpretation.

Gene Ontology is a hierarchical controlled vocabulary for protein annotation. Its synergy with automatic classification methods, ensemble, has been widely used for the prediction of protein functions. Current classification methods use only the relation is_a and a few little part_of to generate prediction model. In this work we formalize the GO part_of, regulates; negatively_regulates and positively_regulates relationships through predicate logic. This formalization is incorporated within an ensemble method based on graph factor called Factor Graph GO Annotation. The proposed model is validated against four model organisms for GO Biological Process prediction.

Prediction of protein sub-cellular localisation by employing quantitative mass spectrometry experiments is an expanding field. Several methods have led to the assignment of proteins to specific subcellular localisations by partial separation of organelles across a fractionation scheme coupled with computational analysis. Methods developed to analyse organelle data have largely employed supervised machine learning algorithms to map unannotated abundance profiles to known protein–organelle associations. Such approaches are likely to make association errors if organelle-related groupings present in experimental output are not included in data used to create a protein–organelle classifier. Currently, there is no automated way to detect organelle-specific clusters within such datasets. In order to address the above issues we adapted a phenotype discovery algorithm, originally created to filter image-based output for RNAi screens, to identify putative subcellular groupings in organelle proteomics experiments. We were able to mine datasets to a deeper level and extract interesting phenotype clusters for more comprehensive evaluation in an unbiased fashion upon application of this approach. Organelle-related protein clusters were identified beyond those sufficiently annotated for use as training data. Furthermore, we propose avenues for the incorporation of observations made into general practice for the classification of protein–organelle membership from quantitative MS experiments. Biological significance Protein sub-cellular localisation plays an important role in molecular interactions, signalling and transport mechanisms. The prediction of protein localisation by quantitative mass-spectrometry (MS) proteomics is a growing field and an important endeavour in improving protein annotation. Several such approaches use gradient-based separation of cellular organelle content to measure relative protein abundance across distinct gradient fractions. The distribution profiles are commonly mapped in silico to known protein–organelle associations via supervised machine learning algorithms, to create classifiers that associate unannotated proteins to specific organelles. These strategies are prone to error, however, if organelle-related groupings present in experimental output are not represented, for example owing to the lack of existing annotation, when creating the protein–organelle mapping. Here, the application of a phenotype discovery approach to LOPIT gradient-based MS data identifies candidate organelle phenotypes for further evaluation in an unbiased fashion. Software implementation and usage guidelines are provided for application to wider protein–organelle association experiments. In the wider context, semi-supervised organelle discovery is discussed as a paradigm with which to generate new protein annotations from MS-based organelle proteomics experiments. This article is part of a Special Issue entitled: New Horizons and Applications for Proteomics [EuPA 2012].

Nowadays, life scientists grapple with a problem how to fast and easily access/obtain high quality data, especially for a specific research area, from a large amount of biological data deposited in public databases. In this work, we developed an effective system for managing biological data which are a class of functionally important membrane protein; they are hard to collected from the existing databases for slow progress of protein annotations, transitive annotation problem as well as low sequence similarity among them. Our preliminary system was designed with a user-friendly web interface and provides: 1) keywords retrieval against the annotation information of protein sequences, 2) recommendation of the related publications to help researchers conduct effective comparisons of experimental results with convenience, and 3) sequence alignment service (BLAST-based by NCBI blast+ and Hidden Markov Model-based by HMMER3.0). We had conducted a statistical analysis and showed it to the researchers in a visual way.

The advances of omics technologies have triggered the production of an enormous volume of data coming from thousands of species. Meanwhile, joint international efforts like the Gene Ontology (GO) consortium have worked to provide functional information for a vast amount of proteins. With these data available, we have developed FunTaxIS, a tool that is the first attempt to infer functional taxonomy (i.e. how functions are distributed over taxa) combining functional and taxonomic information. FunTaxIS is able to define a taxon specific functional space by exploiting annotation frequencies in order to establish if a function can or cannot be used to annotate a certain species. The tool generates constraints between GO terms and taxa and then propagates these relations over the taxonomic tree and the GO graph. Since these constraints nearly cover the whole taxonomy, it is possible to obtain the mapping of a function over the taxonomy. FunTaxIS can be used to make functional comparative analyses among taxa, to detect improper associations between taxa and functions and to discover how functional knowledge is either distributed or missing. A benchmark test set based on six different model species has been devised to get useful insights on the generated taxonomic rules.

International audience; Advances in DNA sequencing technologies have led to an increasing amount of protein sequence data being generated. Only a small fraction of this protein sequence data will have experimental annotation associated with them. Here, we describe a protocol for in silico homology-based annotation of large protein datasets that makes extensive use of manually curated collections of protein families. We focus on annotations provided by the Pfam database and suggest ways to identify family outliers and family variations. This protocol may be useful to people who are new to protein data analysis, or who are unfamiliar with the current computational tools that are available.

CharProtDB (http://www.jcvi.org/charprotdb/) is a curated database of biochemically characterized proteins. It provides a source of direct rather than transitive assignments of function, designed to support automated annotation pipelines. The initial data set in CharProtDB was collected through manual literature curation over the years by analysts at the J. Craig Venter Institute (JCVI) [formerly The Institute of Genomic Research (TIGR)] as part of their prokaryotic genome sequencing projects. The CharProtDB has been expanded by import of selected records from publicly available protein collections whose biocuration indicated direct rather than homology-based assignment of function. Annotations in CharProtDB include gene name, symbol and various controlled vocabulary terms, including Gene Ontology terms, Enzyme Commission number and TransportDB accession. Each annotation is referenced with the source; ideally a journal reference, or, if imported and lacking one, the original database source.

Owing to the generation of vast amounts of sequencing data by using cost-effective, high-throughput sequencing technologies with improved computational approaches, many putative proteins have been discovered after assembly and structural annotation. Putative proteins are typically annotated using a functional annotation system that uses extant databases, but the expansive size of these databases often causes a bottleneck for rapid functional annotation. We developed SFannotation, a simple and fast functional annotation system that rapidly annotates putative proteins against four extant databases, Swiss-Prot, TIGRFAMs, Pfam, and the non-redundant sequence database, by using a best-hit approach with BLASTP and HMMSEARCH.

Pharmaceutical researchers must evaluate vast numbers of protein sequences and formulate innovative strategies for identifying valid targets and discovering leads against them as a way of accelerating drug discovery. The ever increasing number and diversity of novel protein sequences identified by genomic sequencing projects and the success of worldwide structural genomics initiatives have spurred great interest and impetus in the development of methods for accurate, computationally empowered protein function prediction and active site identification. Previously, in the absence of direct experimental evidence, homology-based protein function annotation remained the gold-standard for in silico analysis and prediction of protein function. However, with the continued exponential expansion of sequence databases, this approach is not always applicable, as fewer query protein sequences demonstrate significant homology to protein gene products of known function. As a result, several non-homology based methods for protein function prediction that are based on sequence features, structure, evolution, biochemical and genetic knowledge have emerged. Herein, we review current bioinformatic programs and approaches for protein function prediction/annotation and discuss their integration into drug discovery initiatives. The development of such methods to annotate protein functional sites and their application to large protein functional families is crucial to successfully utilizing the vast amounts of genomic sequence information available to drug discovery and development processes.

NCBI's Conserved Domain Database (CDD) is a resource for the annotation of protein sequences with the location of conserved domain footprints, and functional sites inferred from these footprints. CDD includes manually curated domain models that make use of protein 3D structure to refine domain models and provide insights into sequence/structure/function relationships. Manually curated models are organized hierarchically if they describe domain families that are clearly related by common descent. As CDD also imports domain family models from a variety of external sources, it is a partially redundant collection. To simplify protein annotation, redundant models and models describing homologous families are clustered into superfamilies. By default, domain footprints are annotated with the corresponding superfamily designation, on top of which specific annotation may indicate high-confidence assignment of family membership. Pre-computed domain annotation is available for proteins in the Entrez/Protein dataset, and a novel interface, Batch CD-Search, allows the computation and download of annotation for large sets of protein queries. CDD can be accessed via http://www.ncbi.nlm.nih.gov/Structure/cdd/cdd.shtml.

In order that biological meaning may be derived and testable hypotheses may be built from proteomics experiments, assignments of proteins identified by mass spectrometry or other techniques must be supplemented with additional notation, such as information on known protein functions, protein-protein interactions, or biological pathway associations. Collecting, organizing, and interpreting this data often requires the input of experts in the biological field of study, in addition to the time-consuming search for and compilation of information from online protein databases. Furthermore, visualizing this bulk of information can be challenging due to the limited availability of easy-to-use and freely available tools for this process. In response to these constraints, we have undertaken the design of software to automate annotation and visualization of proteomics data in order to accelerate the pace of research. Here we present the Software Tool for Researching Annotations of Proteins (STRAP), a user-friendly, open-source C# application. STRAP automatically obtains gene ontology (GO) terms associated with proteins in a proteomics results ID list using the freely accessible UniProtKB and EBI GOA databases. Summarized in an easy-to-navigate tabular format, STRAP results include meta-information on the protein in addition to complementary GO terminology. Additionally, this information can be edited by the user so that in-house expertise on particular proteins may be integrated into the larger data set. STRAP provides a sortable tabular view for all terms, as well as graphical representations of GO-term association data in pie charts (biological process, cellular component, and molecular function) and bar charts (cross comparison of sample sets) to aid in the interpretation of large data sets and differential analyses experiments. Furthermore, proteins of interest may be exported as a unique FASTA-formatted file to allow for customizable re-searching of mass spectrometry data, and gene names corresponding to the proteins in the lists may be encoded in the Gaggle microformat for further characterization, including pathway analysis. STRAP, a tutorial, and the C# source code are freely available from http://cpctools.sourceforge.net.

We have developed the web based tool GOAPhAR (Gene Ontology, Annotations and Pathways for Array Research), that integrates information from disparate sources regarding gene annotations, protein annotations, identifiers associated with probe sets, functional pathways, protein interactions, Gene Ontology, publicly available microarray datasets and tools for statistically validating clusters in microarray data. Genes of interest can be input as Affymetrix probe identifiers, Genbank, or Unigene identifiers for human, mouse or rat genomes. Results are provided in a user friendly interface with hyperlinks to the sources of information. The tool is freely available at http://bioinformatics.kumc.edu/goaphar/.

An Integrated environment for biological data is valuable to the function annotation of protein sequences. In this paper, we present a protein sequence annotation system, named MAPS (Multiple Annotation for Protein Sequences), which provides a mechanism to extract multiple annotations from various types of biological data including SwissProt keywords, InterPro signatures and GO terms. Furthermore, MAPS can automatically eliminate the annotation errors generated by a pre-trained SVM classifier. It assigns an annotation to the protein sequence at question by considering not only a single similar protein but also all similar proteins with the annotation. In other words, we take account of the evolutionary information of the protein of interest to reduce the error annotations inferred from weak sequence similarities and from sequence identities in non-functional segments. The experimental results show that the error annotations can be eliminated effectively while keeping high accuracy for different types of annotations.

One of the challenges of the post-genomic era is to provide accurate function annotations for large volumes of data resulting from genome sequencing projects. Most function prediction servers utilize methods that transfer existing database annotations between orthologous sequences. In contrast, there are few methods that are independent of homology and can annotate distant and orphan protein sequences. The FFPred server adopts a machine-learning approach to perform function prediction in protein feature space using feature characteristics predicted from amino acid sequence. The features are scanned against a library of support vector machines representing over 300 Gene Ontology (GO) classes and probabilistic confidence scores returned for each annotation term. The GO term library has been modelled on human protein annotations; however, benchmark performance testing showed robust performance across higher eukaryotes. FFPred offers important advantages over traditional function prediction servers in its ability to annotate distant homologues and orphan protein sequences, and achieves greater coverage and classification accuracy than other feature-based prediction servers. A user may upload an amino acid and receive annotation predictions via email. Feature information is provided as easy to interpret graphics displayed on the sequence of interest, allowing for back-interpretation of the associations between features and function classes.

This paper presents a method that uses gene ontologies (GOs), together with the paradigm of relational subgroup discovery, to find compactly described groups of genes differentially expressed in specific cancers. The groups are described by means of relational logic features, extracted from publicly available GO information, and are straightforwardly interpretable by medical experts. We applied the proposed method to three gene expression data sets with the following respective sets of sample classes: 1) acute lymphoblastic leukemia (ALL) versus acute myeloid leukemia (AML); 2) seven subtypes of ALL; and 3) 14 different types of cancers. Significant number of discovered groups of genes had a description that highlighted the underlying biological process responsible for distinguishing one class from the other classes. The quality of the discovered descriptions was also verified by cross validation. We believe that the presented approach will significantly contribute to the application of relational machine learning to gene expression analysis, given the expected increase in both the quality and quantity of gene/protein annotations in the near future.

The wealth of transcript information that has been made publicly available in recent years has led to large pools of individual web sites offering access to bioinformatics software. However, finding out which services exist, what they can or cannot do, how to use them and how to feed results from one service to the next one in the right format can be very time and resource consuming, especially for non-experts. Automating this task, we present a suite of protein annotation pipelines (tasks) developed at the German Cancer Research Centre (DKFZ) oriented to protein annotation by homology (ProtSweep), by domain analysis (DomainSweep), and by secondary structure elements (2Dsweep). The aim of these tasks is to perform an exhaustive structural and functional analysis employing a wide variety of methods in combination with the most updated public databases. The three servers are available for academic users at the HUSAR open server http://genius.embnet.dkfz-heidelberg.de/menu/biounit/open-husar/, The program of ‘Retorno de Investigadores de la Junta de Andalucia’ financed Dr C. del Val. Funding to pay the Open Access publication charges for this article was provided by Dep. Molecular Biophysics, Deutsches Krebsforschungszentrum.