Protein Function Annotation Research Articles

High precision protein functional site detection using 3D convolutional neural networks.

MotivationAccurate annotation of protein functions is fundamental for understanding molecular and cellular physiology. Data-driven methods hold promise for systematically deriving rules underlying the relationship between protein structure and function. However, the choice of protein structural representation is critical. Pre-defined biochemical features emphasize certain aspects of protein properties while ignoring others, and therefore may fail to capture critical information in complex protein sites.ResultsIn this paper, we present a general framework that applies 3D convolutional neural networks (3DCNNs) to structure-based protein functional site detection. The framework can extract task-dependent features automatically from the raw atom distributions. We benchmarked our method against other methods and demonstrate better or comparable performance for site detection. Our deep 3DCNNs achieved an average recall of 0.955 at a precision threshold of 0.99 on PROSITE families, detected 98.89 and 92.88% of nitric oxide synthase and TRYPSIN-like enzyme sites in Catalytic Site Atlas, and showed good performance on challenging cases where sequence motifs are absent but a function is known to exist. Finally, we inspected the individual contributions of each atom to the classification decisions and show that our models successfully recapitulate known 3D features within protein functional sites.Availability and implementationThe 3DCNN models described in this paper are available at https://simtk.org/projects/fscnn.Supplementary information Supplementary data are available at Bioinformatics online.

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

Function annotation of proteins is fundamental in contemporary biology across fields including genomics, molecular biology, biochemistry, systems biology and bioinformatics. Function prediction is indispensable in providing clues for interpreting omics-scale data as well as in assisting biologists to build hypotheses for designing experiments. As sequencing genomes is now routine due to the rapid advancement of sequencing technologies, computational protein function prediction methods have become increasingly important. A conventional method of annotating a protein sequence is to transfer functions from top hits of a homology search; however, this approach has substantial short comings including a low coverage in genome annotation. Here we have developed Phylo-PFP, a new sequence-based protein function prediction method, which mines functional information from a broad range of similar sequences, including those with a low sequence similarity identified by a PSI-BLAST search. To evaluate functional similarity between identified sequences and the query protein more accurately, Phylo-PFP reranks retrieved sequences by considering their phylogenetic distance. Compared to the Phylo-PFP's predecessor, PFP, which was among the top ranked methods in the second round of the Critical Assessment of Functional Annotation (CAFA2), Phylo-PFP demonstrated substantial improvement in prediction accuracy. Phylo-PFP was further shown to outperform prediction programs to date that were ranked top in CAFA2. Phylo-PFP web server is available for at http://kiharalab.org/phylo_pfp.php. Supplementary data are available at Bioinformatics online.

Beyond Homology Transfer: Deep Learning for Automated Annotation of Proteins

Accurate annotation of protein functions is important for a profound understanding of molecular biology. A large number of proteins remain uncharacterized because of the sparsity of available supporting information. For a large set of uncharacterized proteins, the only type of information available is their amino acid sequence. This motivates the need to make sequence based computational techniques that can precisely annotate uncharacterized proteins. In this paper, we propose DeepSeq – a deep learning architecture – that utilizes only the protein sequence information to predict its associated functions. The prediction process does not require handcrafted features; rather, the architecture automatically extracts representations from the input sequence data. Results of our experiments with DeepSeq indicate significant improvements in terms of prediction accuracy when compared with other sequence-based methods. Our deep learning model achieves an overall validation accuracy of 86.72%, with an F1 score of 71.13%. We achieved improved results for protein function prediction problem through DeepSeq, by utilizing sequence only information. Moreover, using the automatically learned features and without any changes to DeepSeq, we successfully solved a different problem i.e. protein function localization, with no human intervention. Finally, we discuss how the same architecture can be used to solve even more complicated problems such as prediction of 2D and 3D structure as well as protein-protein interactions.

A novel methodology on distributed representations of proteins using their interacting ligands.

MotivationThe effective representation of proteins is a crucial task that directly affects the performance of many bioinformatics problems. Related proteins usually bind to similar ligands. Chemical characteristics of ligands are known to capture the functional and mechanistic properties of proteins suggesting that a ligand-based approach can be utilized in protein representation. In this study, we propose SMILESVec, a Simplified molecular input line entry system (SMILES)-based method to represent ligands and a novel method to compute similarity of proteins by describing them based on their ligands. The proteins are defined utilizing the word-embeddings of the SMILES strings of their ligands. The performance of the proposed protein description method is evaluated in protein clustering task using TransClust and MCL algorithms. Two other protein representation methods that utilize protein sequence, Basic local alignment tool and ProtVec, and two compound fingerprint-based protein representation methods are compared.ResultsWe showed that ligand-based protein representation, which uses only SMILES strings of the ligands that proteins bind to, performs as well as protein sequence-based representation methods in protein clustering. The results suggest that ligand-based protein description can be an alternative to the traditional sequence or structure-based representation of proteins and this novel approach can be applied to different bioinformatics problems such as prediction of new protein–ligand interactions and protein function annotation.Availability and implementation https://github.com/hkmztrk/SMILESVecProteinRepresentation Supplementary information Supplementary data are available at Bioinformatics online.

HFSP: high speed homology-driven function annotation of proteins.

MotivationThe rapid drop in sequencing costs has produced many more (predicted) protein sequences than can feasibly be functionally annotated with wet-lab experiments. Thus, many computational methods have been developed for this purpose. Most of these methods employ homology-based inference, approximated via sequence alignments, to transfer functional annotations between proteins. The increase in the number of available sequences, however, has drastically increased the search space, thus significantly slowing down alignment methods.ResultsHere we describe homology-derived functional similarity of proteins (HFSP), a novel computational method that uses results of a high-speed alignment algorithm, MMseqs2, to infer functional similarity of proteins on the basis of their alignment length and sequence identity. We show that our method is accurate (85% precision) and fast (more than 40-fold speed increase over state-of-the-art). HFSP can help correct at least a 16% error in legacy curations, even for a resource of as high quality as Swiss-Prot. These findings suggest HFSP as an ideal resource for large-scale functional annotation efforts.Supplementary information Supplementary data are available at Bioinformatics online.

COACH-D: improved protein-ligand binding sites prediction with refined ligand-binding poses through molecular docking.

The identification of protein–ligand binding sites is critical to protein function annotation and drug discovery. The consensus algorithm COACH developed by us represents one of the most efficient approaches to protein–ligand binding sites prediction. One of the most commonly seen issues with the COACH prediction are the low quality of the predicted ligand-binding poses, which usually have severe steric clashes to the protein structure. Here, we present COACH-D, an enhanced version of COACH by utilizing molecular docking to refine the ligand-binding poses. The input to the COACH-D server is the amino acid sequence or the three-dimensional structure of a query protein. In addition, the users can also submit their own ligand of interest. For each job submission, the COACH algorithm is first used to predict the protein–ligand binding sites. The ligands from the users or the templates are then docked into the predicted binding pockets to build their complex structures. Blind tests show that the algorithm significantly outperforms other ligand-binding sites prediction methods. Benchmark tests show that the steric clashes between the ligand and the protein structures in the COACH models are reduced by 85% after molecular docking in COACH-D. The COACH-D server is freely available to all users at http://yanglab.nankai.edu.cn/COACH-D/.

Identification and characterization of moonlighting long non-coding RNAs based on RNA and protein interactome.

Moonlighting proteins are a class of proteins having multiple distinct functions, which play essential roles in a variety of cellular and enzymatic functioning systems. Although there have long been calls for computational algorithms for the identification of moonlighting proteins, research on approaches to identify moonlighting long non-coding RNAs (lncRNAs) has never been undertaken. Here, we introduce a novel methodology, MoonFinder, for the identification of moonlighting lncRNAs. MoonFinder is a statistical algorithm identifying moonlighting lncRNAs without a priori knowledge through the integration of protein interactome, RNA-protein interactions and functional annotation of proteins. We identify 155 moonlighting lncRNA candidates and uncover that they are a distinct class of lncRNAs characterized by specific sequence and cellular localization features. The non-coding genes that transcript moonlighting lncRNAs tend to have shorter but more exons and the moonlighting lncRNAs have a variable localization pattern with a high chance of residing in the cytoplasmic compartment in comparison to the other lncRNAs. Moreover, moonlighting lncRNAs and moonlighting proteins are rather mutually exclusive in terms of both their direct interactions and interacting partners. Our results also shed light on how the moonlighting candidates and their interacting proteins implicated in the formation and development of cancers and other diseases. The code implementing MoonFinder is supplied as an R package in the supplementary material. Supplementary data are available at Bioinformatics online.

Functional Annotation of Proteins Encoded by the Minimal Bacterial Genome Based on Secondary Structure Element Alignment.

In synthetic biology, one of the key focuses is building a minimal artificial cell which can provide basic chassis for functional study. Recently, the J. Craig Venter Institute published the latest version of the minimal bacterial genome JCVI-syn3.0, which only encoded 438 essential proteins. However, among them functions of 149 proteins remain unknown because of the lack of effective annotation method. Here, we report a secondary structure element alignment method called SSEalign based on an effective training data set extracting from various bacterial genomes. The experimentally validated homologous genes in different species were selected as training positives, while unrelated genes in different species were selected as training negatives. Moreover, SSEalign used a set of well-defined basic alignment elements with the backtracking line search algorithm to derive the best parameters for accurate prediction. Experimental results showed that SSEalign achieved 88.2% test accuracy, which is better than the existing prediction methods. SSEalign was subsequently applied to identify the functions of those unannotated proteins in the latest published minimal bacteria genome JCVI-syn3.0. Results indicated that at least 136 proteins out of 149 unannotated proteins in the JCVI-syn3.0 genome could be annotated by SSEalign. Our method is effective for the identification of protein homology in JCVI-syn3.0 and can be used to annotate those hypothetical proteins in other bacterial genomes.

GROOLS: reactive graph reasoning for genome annotation through biological processes

BackgroundHigh quality functional annotation is essential for understanding the phenotypic consequences encoded in a genome. Despite improvements in bioinformatics methods, millions of sequences in databanks are not assigned reliable functions. The curation of protein functions in the context of biological processes is a way to evaluate and improve their annotation.ResultsWe developed an expert system using paraconsistent logic, named GROOLS (Genomic Rule Object-Oriented Logic System), that evaluates the completeness and the consistency of predicted functions through biological processes like metabolic pathways. Using a generic and hierarchical representation of knowledge, biological processes are modeled in a graph from which observations (i.e. predictions and expectations) are propagated by rules. At the end of the reasoning, conclusions are assigned to biological process components and highlight uncertainties and inconsistencies. Results on 14 microbial organisms are presented.ConclusionsGROOLS software is designed to evaluate the overall accuracy of functional unit and pathway predictions according to organism experimental data like growth phenotypes. It assists biocurators in the functional annotation of proteins by focusing on missing or contradictory observations.

Functional assignment of Structural Genomics proteins through computed chemical properties, graph representation of active sites, and biochemical validation

There are currently over 14,300 Structural Genomics (SG) protein structures deposited in the PDB by protein structure initiatives. However, most of these SG proteins have unknown or putative function annotations. This accumulated structural information represents a tremendous contribution to structural biology and genomics. Still, the addition of accurate functional annotations for these SG proteins would add substantial value to this information. Our approach to functional annotation and validation incorporates predicting functional assignments through structure‐based computed chemical properties and local structure matching followed by biochemical validation. This research focuses on four superfamilies: Crotonase, Ribulose Phosphate Binding Barrel, 6‐Hairpin Glycosidase, and Concanavlin A‐like Lectins and Glucanases. First, Partial Order Optimum Likelihood (POOL) is used to predict computationally the catalytically important residues in each protein structure. Next, Structurally Aligned Local Sites of Activity (SALSA) develops spatially‐localized consensus signatures for the proteins of known function in each functional family within each superfamily based on POOL‐predicted residues and functionally characterized residues of importance. Then, the POOL‐predicted residues for each SG protein are compared to each consensus signature and scored to determine their degree of similarity at the local active site. Finally, we introduce a new, computationally faster method for sorting protein superfamilies and annotating protein function using local structure matching in graph representation: Graph Representation of Active Sites for Prediction of Function (GRASP‐Func). Sets of tetrahedra are generated through Delaunay triangulation for each protein structure using the alpha carbon atoms of each residue. Then, sets of proteins with matched tetrahedra are grouped together and images are generated showing the relationship of each protein (node) and its neighbors (edges) with similar active sites. We compare SALSA and GRASP‐Func and show that both methods correctly sort the superfamilies into their respective functional families. Both methods also make similar functional predictions for the SG proteins, with GRASP‐Func performing in far less time. Thus GRASP‐Func enables large‐scale comparisons and functional assignments within and across superfamilies. Finally, we are able to test these predictions biochemically to confirm function. Biochemical data for the Crotonase Superfamily show that while proteins have some promiscuous functionality, our methods predict the correct dominant function for each protein tested. The goal of this project is to provide a validated approach to functional annotation to enable applications from drug target identification to green chemistry and biofuel production.Support or Funding InformationSupport from NSF‐CHE‐1305655, NSF‐MCB‐1158176, NSF‐MCB‐1517290, PhRMA Foundations (Predoctoral Fellowship in Informatics awarded to CLM), NSF‐GRFP (JSL), MathWorks, Inc., and American Cancer Society Research Scholar Grant RSG‐12‐161‐01‐DMC (PJB).This abstract is from the Experimental Biology 2018 Meeting. There is no full text article associated with this abstract published in The FASEB Journal.

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

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

The Gene-Centric Content Management System and Its Application for Cognitive Proteomics.

The Human Proteome Project is moving into the next phase of creating and/or reconsidering the functional annotations of proteins using the chromosome-centric paradigm. This challenge cannot be solved exclusively using automated means, but rather requires human intelligence for interpreting the combined data. To foster the integration between human cognition and post-genome array a number of specific tools were recently developed, among them CAPER, GenomewidePDB, and The Proteome Browser (TPB). For the purpose of tackling the task of protein functional annotating the Gene-Centric Content Management System (GenoCMS) was expanded with new features. The goal was to enable bioinformaticans to develop self-made applications and to position these applets within the generalized informational canvas supported by GenoCMS. We report the results of GenoCMS-enabled integration of the concordant informational flows in the chromosome-centric framework of the human chromosome 18 project. The workflow described in the article can be scaled to other human chromosomes, and also supplemented with new tracks created by the user. The GenoCMS is an example of a project-oriented informational system, which are important for public data sharing.

ATPbind: Accurate Protein-ATP Binding Site Prediction by Combining Sequence-Profiling and Structure-Based Comparisons.

Protein-ATP interactions are ubiquitous in a wide variety of biological processes. Correctly locating ATP binding sites from protein information is an important but challenging task for protein function annotation and drug discovery. However, there is no method that can optimally identify ATP binding sites for different proteins. In this study, we report a new composite predictor, ATPbind, for ATP binding sites by integrating the outputs of two template-based predictors (i.e., S-SITE and TM-SITE) and three discriminative sequence-driven features of proteins: position specific scoring matrix, predicted secondary structure, and predicted solvent accessibility. In ATPbind, we assembled multiple support vector machines (SVMs) based on a random undersampling technique to cope with the serious imbalance phenomenon between the numbers of ATP binding sites and of non-ATP binding sites. We also constructed a new gold-standard benchmark data set consisting of 429 ATP binding proteins from the PDB database to evaluate and compare the proposed ATPbind with other existing predictors. Starting from a query sequence and predicted I-TASSER models, ATPbind can achieve an average accuracy of 72%, covering 62% of all ATP binding sites while achieving a Matthews correlation coefficient value that is significantly higher than that of other state-of-the-art predictors.

Enrichment strategy of protein N-termini based on dioctyl labeling

The analysis of protein N-termini provides valuable information for protein structure and function annotation, and helps the profiling of proteases substrates and cleavage sites. However, most of the current N-terminal enrichment approaches involve multiple chromatographic separation processes and require a large amount of scavenger materials, which make it time and labor consuming and may induce significant sample loss. Herein, we develop a negative N-termini enrichment strategy based on dioctyl labeling. With yeast lysate digests as the sample, the strategy showed a high efficiency in dioctyl labeling and retention shift. Such a strategy was applied for the enrichment of N-terminal peptides from yeast cell lysates and enabled the identification of 237 original N-termini and 133 neo-N-termini, which was improved by 100% and 480% compared with direct analysis. Furthermore, with the combination of multi-proteases digestion, the number of protein N-termini and neo-N-termin was improved by 50% and 90%, respectively, facilitating the in-depth N-terminome analysis.

Identifying noisy functional annotations of proteins using sparse semantic similarity

Automatically annotating functions of proteins is a key task in bioinformatics. Functional annotations of proteins are collected from multiple sources; thus, noisy annotations are inevitably introduced. However, the current research in protein function prediction almost always focuses on predicting functions for completely unannotated (or incompletely annotated) proteins, and seldom identifies the noisy annotations of proteins. In this paper, we propose a method called identifying noisy functional annotations (NFAs) of proteins using sparse semantic similarity. NFA first utilizes a protein-function association matrix to store the functional annotations of proteins, differentially weighs the annotations using the evidence codes attached with these annotations, and subsequently upward propagates the weights to the expanded annotations via the hierarchical structure among the functional labels. Next, NFA measures the semantic similarity between proteins by the $l_1$-norm regularized sparse representation on the weighted protein-function association matrix. Finally, it identifies the noisy functions of a protein based on the functions annotated to its semantic neighborhood proteins. The experimental results on two model species (A. thaliana and S. cerevisiae) show that the NFA more accurately identifies noisy annotations than other related methods. Additionally, removing the identified noisy annotations improves the accuracy of the current function prediction model.

Structure, Mechanism, and Substrate Profiles of the Trinuclear Metallophosphatases from the Amidohydrolase Superfamily.

The rate of reliable protein function annotation has not kept pace with the rapid advances in genome sequencing technology. This has created a gap between the number of available protein sequences, and an accurate determination of the respective physiological functions. This investigation has attempted to bridge the gap within the confines of members of the polymerase and histidinol phosphatase family of proteins in cog1387 and cog0613, which is related to the amidohydrolase superfamily. The adopted approach relies on using the mechanistic knowledge of a known enzymatic reaction, and discovering functions of closely related homologs using various tools including bioinformatics and rational library screening. The initial enzymatic reaction was that of L-histidinol phosphate phosphatase. Extensive structural, biochemical, and bioinformatic analysis of enzymes capable of hydrolyzing L-histidinol phosphate provided useful insights in predicting substrates and mechanistic studies of related enzymes. This led to the discovery of unprecedented catalytic functions such as a cyclic phosphate dihydrolase that specifically hydrolyzed a cyclic phosphodiester to inorganic phosphate and a vicinal diol; a phosphoesterase that hydrolyzes the 3'-phosphate of 3',5'-adenosine bisphosphate and similar nucleotides; and the first reported 5'-3' exonuclease for 5'-phosphorylated oligonucleotides from Escherichia coli and related organisms. This work provides a template for developing sequence-structure-function correlations within a family of enzymes that helps expedite new enzyme function discovery and more accurate annotations in protein databases.

PVCbase: an integrated web resource for the PVC bacterial proteomes.

Interest in the Planctomycetes-Verrucomicrobia-Chlamydiae (PVC) bacterial superphylum is growing within the microbiology community. These organisms do not have a specialized web resource that gathers in silico predictions in an integrated fashion. Hence, we are providing the PVC community with PVCbase, a specialized web resource that gathers in silico predictions in an integrated fashion. PVCbase integrates protein function annotations obtained through sequence analysis and tertiary structure prediction for 39 representative PVC proteomes (PVCdb), a protein feature visualizer (Foundation) and a custom BLAST webserver (PVCBlast) that allows to retrieve the annotation of a hit directly from the DataTables. We display results from various predictors, encompassing most functional aspects, allowing users to have a more comprehensive overview of protein identities. Additionally, we illustrate how the application of PVCdb can be used to address biological questions from raw data. Database URL: PVCbase is freely accessible at www.pvcbacteria.org/pvcbase

CPredictor3.0: detecting protein complexes from PPI networks with expression data and functional annotations

BackgroundEffectively predicting protein complexes not only helps to understand the structures and functions of proteins and their complexes, but also is useful for diagnosing disease and developing new drugs. Up to now, many methods have been developed to detect complexes by mining dense subgraphs from static protein-protein interaction (PPI) networks, while ignoring the value of other biological information and the dynamic properties of cellular systems.ResultsIn this paper, based on our previous works CPredictor and CPredictor2.0, we present a new method for predicting complexes from PPI networks with both gene expression data and protein functional annotations, which is called CPredictor3.0. This new method follows the viewpoint that proteins in the same complex should roughly have similar functions and are active at the same time and place in cellular systems. We first detect active proteins by using gene express data of different time points and cluster proteins by using gene ontology (GO) functional annotations, respectively. Then, for each time point, we do set intersections with one set corresponding to active proteins generated from expression data and the other set corresponding to a protein cluster generated from functional annotations. Each resulting unique set indicates a cluster of proteins that have similar function(s) and are active at that time point. Following that, we map each cluster of active proteins of similar function onto a static PPI network, and get a series of induced connected subgraphs. We treat these subgraphs as candidate complexes. Finally, by expanding and merging these candidate complexes, the predicted complexes are obtained.We evaluate CPredictor3.0 and compare it with a number of existing methods on several PPI networks and benchmarking complex datasets. The experimental results show that CPredictor3.0 achieves the highest F1-measure, which indicates that CPredictor3.0 outperforms these existing method in overall.ConclusionCPredictor3.0 can serve as a promising tool of protein complex prediction.

Identifying functionally informative evolutionary sequence profiles.

Multiple sequence alignments (MSAs) can provide essential input to many bioinformatics applications, including protein structure prediction and functional annotation. However, the optimal selection of sequences to obtain biologically informative MSAs for such purposes is poorly explored, and has traditionally been performed manually. We present Selection of Alignment by Maximal Mutual Information (SAMMI), an automated, sequence-based approach to objectively select an optimal MSA from a large set of alternatives sampled from a general sequence database search. The hypothesis of this approach is that the mutual information among MSA columns will be maximal for those MSAs that contain the most diverse set possible of the most structurally and functionally homogeneous protein sequences. SAMMI was tested to select MSAs for functional site residue prediction by analysis of conservation patterns on a set of 435 proteins obtained from protein-ligand (peptides, nucleic acids and small substrates) and protein-protein interaction databases. Availability and implementation: A freely accessible program, including source code, implementing SAMMI is available at https://github.com/nelsongil92/SAMMI.git. andras.fiser@einstein.yu.edu. Supplementary data are available at Bioinformatics online.

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.