Hierarchical ensemble methods for protein function prediction

Using interpretable boosting algorithms for modeling environmental and agricultural data

We describe how interpretable boosting algorithms based on ridge-regularized generalized linear models can be used to analyze high-dimensional environmental data. We illustrate this by using environmental, social, human and biophysical data to predict the financial vulnerability of farmers in Chile and Tunisia against climate hazards. We show how group structures can be considered and how interactions can be found in high-dimensional datasets using a novel 2-step boosting approach. The advantages and efficacy of the proposed method are shown and discussed. Results indicate that the presence of interaction effects only improves predictive power when included in two-step boosting. The most important variable in predicting all types of vulnerabilities are natural assets. Other important variables are the type of irrigation, economic assets and the presence of crop damage of near farms.

A Network-Based Approach for Improving Annotation of Transcription Factor Functions and Binding Sites in Arabidopsis thaliana

Transcription factors are an integral component of the cellular machinery responsible for regulating many biological processes, and they recognize distinct DNA sequence patterns as well as internal/external signals to mediate target gene expression. The functional roles of an individual transcription factor can be traced back to the functions of its target genes. While such functional associations can be inferred through the use of binding evidence from high-throughput sequencing technologies available today, including chromatin immunoprecipitation sequencing, such experiments can be resource-consuming. On the other hand, exploratory analysis driven by computational techniques can alleviate this burden by narrowing the search scope, but the results are often deemed low-quality or non-specific by biologists. In this paper, we introduce a data-driven, statistics-based strategy to predict novel functional associations for transcription factors in the model plant Arabidopsis thaliana. To achieve this, we leverage one of the largest available gene expression compendia to build a genome-wide transcriptional regulatory network and infer regulatory relationships among transcription factors and their targets. We then use this network to build a pool of likely downstream targets for each transcription factor and query each target pool for functionally enriched gene ontology terms. The results exhibited sufficient statistical significance to annotate most of the transcription factors in Arabidopsis with highly specific biological processes. We also perform DNA binding motif discovery for transcription factors based on their target pool. We show that the predicted functions and motifs strongly agree with curated databases constructed from experimental evidence. In addition, statistical analysis of the network revealed interesting patterns and connections between network topology and system-level transcriptional regulation properties. We believe that the methods demonstrated in this work can be extended to other species to improve the annotation of transcription factors and understand transcriptional regulation on a system level.

Gene function finding through cross-organism ensemble learning

Background

Structured biological information about genes and proteins is a valuable resource to improve discovery and understanding of complex biological processes via machine learning algorithms. Gene Ontology (GO) controlled annotations describe, in a structured form, features and functions of genes and proteins of many organisms. However, such valuable annotations are not always reliable and sometimes are incomplete, especially for rarely studied organisms. Here, we present GeFF (Gene Function Finder), a novel cross-organism ensemble learning method able to reliably predict new GO annotations of a target organism from GO annotations of another source organism evolutionarily related and better studied.

Results

Using a supervised method, GeFF predicts unknown annotations from random perturbations of existing annotations. The perturbation consists in randomly deleting a fraction of known annotations in order to produce a reduced annotation set. The key idea is to train a supervised machine learning algorithm with the reduced annotation set to predict, namely to rebuild, the original annotations. The resulting prediction model, in addition to accurately rebuilding the original known annotations for an organism from their perturbed version, also effectively predicts new unknown annotations for the organism. Moreover, the prediction model is also able to discover new unknown annotations in different target organisms without retraining.We combined our novel method with different ensemble learning approaches and compared them to each other and to an equivalent single model technique. We tested the method with five different organisms using their GO annotations: Homo sapiens, Mus musculus, Bos taurus, Gallus gallus and Dictyostelium discoideum. The outcomes demonstrate the effectiveness of the cross-organism ensemble approach, which can be customized with a trade-off between the desired number of predicted new annotations and their precision.A Web application to browse both input annotations used and predicted ones, choosing the ensemble prediction method to use, is publicly available at http://tiny.cc/geff/.

Conclusions

Our novel cross-organism ensemble learning method provides reliable predicted novel gene annotations, i.e., functions, ranked according to an associated likelihood value. They are very valuable both to speed the annotation curation, focusing it on the prioritized new annotations predicted, and to complement known annotations available.

A Literature Review of Gene Function Prediction by Modeling Gene Ontology

Annotating the functional properties of gene products, i.e., RNAs and proteins, is a fundamental task in biology. The Gene Ontology database (GO) was developed to systematically describe the functional properties of gene products across species, and to facilitate the computational prediction of gene function. As GO is routinely updated, it serves as the gold standard and main knowledge source in functional genomics. Many gene function prediction methods making use of GO have been proposed. But no literature review has summarized these methods and the possibilities for future efforts from the perspective of GO. To bridge this gap, we review the existing methods with an emphasis on recent solutions. First, we introduce the conventions of GO and the widely adopted evaluation metrics for gene function prediction. Next, we summarize current methods of gene function prediction that apply GO in different ways, such as using hierarchical or flat inter-relationships between GO terms, compressing massive GO terms and quantifying semantic similarities. Although many efforts have improved performance by harnessing GO, we conclude that there remain many largely overlooked but important topics for future research.

Integrating multi-network topology for gene function prediction using deep neural networks

MOTIVATION

The emergence of abundant biological networks, which benefit from the development of advanced high-throughput techniques, contributes to describing and modeling complex internal interactions among biological entities such as genes and proteins. Multiple networks provide rich information for inferring the function of genes or proteins. To extract functional patterns of genes based on multiple heterogeneous networks, network embedding-based methods, aiming to capture non-linear and low-dimensional feature representation based on network biology, have recently achieved remarkable performance in gene function prediction. However, existing methods do not consider the shared information among different networks during the feature learning process.

RESULTS

Taking the correlation among the networks into account, we design a novel semi-supervised autoencoder method to integrate multiple networks and generate a low-dimensional feature representation. Then we utilize a convolutional neural network based on the integrated feature embedding to annotate unlabeled gene functions. We test our method on both yeast and human datasets and compare with three state-of-the-art methods. The results demonstrate the superior performance of our method. We not only provide a comprehensive analysis of the performance of the newly proposed algorithm but also provide a tool for extracting features of genes based on multiple networks, which can be used in the downstream machine learning task.

AVAILABILITY

DeepMNE-CNN is freely available at https://github.com/xuehansheng/DeepMNE-CNN.

CONTACT

jiajiepeng@nwpu.edu.cn; shang@nwpu.edu.cn; jianye.hao@tju.edu.cn.

Multitask Protein Function Prediction through Task Dissimilarity

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

FunPred 3.0: improved protein function prediction using protein interaction network

Proteins are the most versatile macromolecules in living systems and perform crucial biological functions. In the advent of the post-genomic era, the next generation sequencing is done routinely at the population scale for a variety of species. The challenging problem is to massively determine the functions of proteins that are yet not characterized by detailed experimental studies. Identification of protein functions experimentally is a laborious and time-consuming task involving many resources. We therefore propose the automated protein function prediction methodology using in silico algorithms trained on carefully curated experimental datasets. We present the improved protein function prediction tool FunPred 3.0, an extended version of our previous methodology FunPred 2, which exploits neighborhood properties in protein–protein interaction network (PPIN) and physicochemical properties of amino acids. Our method is validated using the available functional annotations in the PPIN network of Saccharomyces cerevisiae in the latest Munich information center for protein (MIPS) dataset. The PPIN data of S. cerevisiae in MIPS dataset includes 4,554 unique proteins in 13,528 protein–protein interactions after the elimination of the self-replicating and the self-interacting protein pairs. Using the developed FunPred 3.0 tool, we are able to achieve the mean precision, the recall and the F-score values of 0.55, 0.82 and 0.66, respectively. FunPred 3.0 is then used to predict the functions of unpredicted protein pairs (incomplete and missing functional annotations) in MIPS dataset of S. cerevisiae. The method is also capable of predicting the subcellular localization of proteins along with its corresponding functions. The code and the complete prediction results are available freely at: https://github.com/SovanSaha/FunPred-3.0.git.

Protein function prediction from protein-protein interaction network using gene ontology based neighborhood analysis and physico-chemical features

Protein Function Prediction from Protein-Protein Interaction Network (PPIN) and physico-chemical features using the Gene Ontology (GO) classification are indeed very useful for assigning biological or biochemical functions to a protein. They also lead to the identification of those significant proteins which are responsible for the generation of various diseases whose drugs are still yet to be discovered. So, the prediction of GO functional terms from PPIN and sequence is an important field of study. In this work, we have proposed a methodology, Multi Label Protein Function Prediction (ML_PFP) which is based on Neighborhood analysis empowered with physico-chemical features of constituent amino acids to predict the functional group of unannotated protein. A protein does not perform functions in isolation rather it performs functions in a group by interacting with others. So a protein is involved in many functions or, in other words, may be associated with multiple functional groups or labels or GO terms. Though functional group of other known interacting partner protein and its physico-chemical features provide useful information, assignment of multiple labels to unannotated protein is a very challenging task. Here, we have taken Homo sapiens or Human PPIN as well as Saccharomyces cerevisiae or yeast PPIN along with their GO terms to predict functional groups or GO terms of unannotated proteins. This work has become very challenging as both Human and Yeast protein dataset are voluminous and complex in nature and multi-label functional groups assignment has also added a new dimension to this challenge. Our algorithm has been observed to achieve a better performance in Cellular Function, Molecular Function and Biological Process of both yeast and human network when compared with the other existing state-of-the-art methodologies which will be discussed in detail in the results section.

A postprocessing method in the HMC framework for predicting gene function based on biological instrumental data

Predicting gene function based on biological instrumental data is a complicated and challenging hierarchical multi-label classification (HMC) problem. When using local approach methods to solve this problem, a preliminary results processing method is usually needed. This paper proposed a novel preliminary results processing method called the nodes interaction method. The nodes interaction method revises the preliminary results and guarantees that the predictions are consistent with the hierarchy constraint. This method exploits the label dependency and considers the hierarchical interaction between nodes when making decisions based on the Bayesian network in its first phase. In the second phase, this method further adjusts the results according to the hierarchy constraint. Implementing the nodes interaction method in the HMC framework also enhances the HMC performance for solving the gene function prediction problem based on the Gene Ontology (GO), the hierarchy of which is a directed acyclic graph that is more difficult to tackle. The experimental results validate the promising performance of the proposed method compared to state-of-the-art methods on eight benchmark yeast data sets annotated by the GO.

A Hierarchical Multi-Label Classification Algorithm for Gene Function Prediction

Gene function prediction is a complicated and challenging hierarchical multi-label classification (HMC) task, in which genes may have many functions at the same time and these functions are organized in a hierarchy. This paper proposed a novel HMC algorithm for solving this problem based on the Gene Ontology (GO), the hierarchy of which is a directed acyclic graph (DAG) and is more difficult to tackle. In the proposed algorithm, the HMC task is firstly changed into a set of binary classification tasks. Then, two measures are implemented in the algorithm to enhance the HMC performance by considering the hierarchy structure during the learning procedures. Firstly, negative instances selecting policy associated with the SMOTE approach are proposed to alleviate the imbalanced data set problem. Secondly, a nodes interaction method is introduced to combine the results of binary classifiers. It can guarantee that the predictions are consistent with the hierarchy constraint. The experiments on eight benchmark yeast data sets annotated by the Gene Ontology show the promising performance of the proposed algorithm compared with other state-of-the-art algorithms.

Prediction of Human Phenotype Ontology terms by means of hierarchical ensemble methods

BACKGROUND

The prediction of human gene-abnormal phenotype associations is a fundamental step toward the discovery of novel genes associated with human disorders, especially when no genes are known to be associated with a specific disease. In this context the Human Phenotype Ontology (HPO) provides a standard categorization of the abnormalities associated with human diseases. While the problem of the prediction of gene-disease associations has been widely investigated, the related problem of gene-phenotypic feature (i.e., HPO term) associations has been largely overlooked, even if for most human genes no HPO term associations are known and despite the increasing application of the HPO to relevant medical problems. Moreover most of the methods proposed in literature are not able to capture the hierarchical relationships between HPO terms, thus resulting in inconsistent and relatively inaccurate predictions.

RESULTS

We present two hierarchical ensemble methods that we formally prove to provide biologically consistent predictions according to the hierarchical structure of the HPO. The modular structure of the proposed methods, that consists in a "flat" learning first step and a hierarchical combination of the predictions in the second step, allows the predictions of virtually any flat learning method to be enhanced. The experimental results show that hierarchical ensemble methods are able to predict novel associations between genes and abnormal phenotypes with results that are competitive with state-of-the-art algorithms and with a significant reduction of the computational complexity.

CONCLUSIONS

Hierarchical ensembles are efficient computational methods that guarantee biologically meaningful predictions that obey the true path rule, and can be used as a tool to improve and make consistent the HPO terms predictions starting from virtually any flat learning method. The implementation of the proposed methods is available as an R package from the CRAN repository.

NegGOA: negative GO annotations selection using ontology structure

MOTIVATION

Predicting the biological functions of proteins is one of the key challenges in the post-genomic era. Computational models have demonstrated the utility of applying machine learning methods to predict protein function. Most prediction methods explicitly require a set of negative examples-proteins that are known not carrying out a particular function. However, Gene Ontology (GO) almost always only provides the knowledge that proteins carry out a particular function, and functional annotations of proteins are incomplete. GO structurally organizes more than tens of thousands GO terms and a protein is annotated with several (or dozens) of these terms. For these reasons, the negative examples of a protein can greatly help distinguishing true positive examples of the protein from such a large candidate GO space.

RESULTS

In this paper, we present a novel approach (called NegGOA) to select negative examples. Specifically, NegGOA takes advantage of the ontology structure, available annotations and potentiality of additional annotations of a protein to choose negative examples of the protein. We compare NegGOA with other negative examples selection algorithms and find that NegGOA produces much fewer false negatives than them. We incorporate the selected negative examples into an efficient function prediction model to predict the functions of proteins in Yeast, Human, Mouse and Fly. NegGOA also demonstrates improved accuracy than these comparing algorithms across various evaluation metrics. In addition, NegGOA is less suffered from incomplete annotations of proteins than these comparing methods.

AVAILABILITY AND IMPLEMENTATION

The Matlab and R codes are available at https://sites.google.com/site/guoxian85/neggoa

CONTACT

gxyu@swu.edu.cn

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Predicting Protein Function via Semantic Integration of Multiple Networks

Determining the biological functions of proteins is one of the key challenges in the post-genomic era. The rapidly accumulated large volumes of proteomic and genomic data drives to develop computational models for automatically predicting protein function in large scale. Recent approaches focus on integrating multiple heterogeneous data sources and they often get better results than methods that use single data source alone. In this paper, we investigate how to integrate multiple biological data sources with the biological knowledge, i.e., Gene Ontology (GO), for protein function prediction. We propose a method, called SimNet, to Semantically integrate multiple functional association Networks derived from heterogenous data sources. SimNet firstly utilizes GO annotations of proteins to capture the semantic similarity between proteins and introduces a semantic kernel based on the similarity. Next, SimNet constructs a composite network, obtained as a weighted summation of individual networks, and aligns the network with the kernel to get the weights assigned to individual networks. Then, it applies a network-based classifier on the composite network to predict protein function. Experiment results on heterogenous proteomic data sources of Yeast, Human, Mouse, and Fly show that, SimNet not only achieves better (or comparable) results than other related competitive approaches, but also takes much less time. The Matlab codes of SimNet are available at https://sites.google.com/site/guoxian85/simnet.

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

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

Predicting protein function and other biomedical characteristics with heterogeneous ensembles

Prediction problems in biomedical sciences, including protein function prediction (PFP), are generally quite difficult. This is due in part to incomplete knowledge of the cellular phenomenon of interest, the appropriateness and data quality of the variables and measurements used for prediction, as well as a lack of consensus regarding the ideal predictor for specific problems. In such scenarios, a powerful approach to improving prediction performance is to construct heterogeneous ensemble predictors that combine the output of diverse individual predictors that capture complementary aspects of the problems and/or datasets. In this paper, we demonstrate the potential of such heterogeneous ensembles, derived from stacking and ensemble selection methods, for addressing PFP and other similar biomedical prediction problems. Deeper analysis of these results shows that the superior predictive ability of these methods, especially stacking, can be attributed to their attention to the following aspects of the ensemble learning process: (i) better balance of diversity and performance, (ii) more effective calibration of outputs and (iii) more robust incorporation of additional base predictors. Finally, to make the effective application of heterogeneous ensembles to large complex datasets (big data) feasible, we present DataSink, a distributed ensemble learning framework, and demonstrate its sound scalability using the examined datasets. DataSink is publicly available from https://github.com/shwhalen/datasink.

Predicting protein function via downward random walks on a gene ontology

Background

High-throughput bio-techniques accumulate ever-increasing amount of genomic and proteomic data. These data are far from being functionally characterized, despite the advances in gene (or gene’s product proteins) functional annotations. Due to experimental techniques and to the research bias in biology, the regularly updated functional annotation databases, i.e., the Gene Ontology (GO), are far from being complete. Given the importance of protein functions for biological studies and drug design, proteins should be more comprehensively and precisely annotated.

Results

We proposed downward Random Walks (dRW) to predict missing (or new) functions of partially annotated proteins. Particularly, we apply downward random walks with restart on the GO directed acyclic graph, along with the available functions of a protein, to estimate the probability of missing functions. To further boost the prediction accuracy, we extend dRW to dRW-kNN. dRW-kNN computes the semantic similarity between proteins based on the functional annotations of proteins; it then predicts functions based on the functions estimated by dRW, together with the functions associated with the k nearest proteins. Our proposed models can predict two kinds of missing functions: (i) the ones that are missing for a protein but associated with other proteins of interest; (ii) the ones that are not available for any protein of interest, but exist in the GO hierarchy. Experimental results on the proteins of Yeast and Human show that dRW and dRW-kNN can replenish functions more accurately than other related approaches, especially for sparse functions associated with no more than 10 proteins.

Conclusion

The empirical study shows that the semantic similarity between GO terms and the ontology hierarchy play important roles in predicting protein function. The proposed dRW and dRW-kNN can serve as tools for replenishing functions of partially annotated proteins.

Electronic supplementary material

The online version of this article (doi:10.1186/s12859-015-0713-y) contains supplementary material, which is available to authorized users.

Integrating multiple networks for protein function prediction

Background

High throughput techniques produce multiple functional association networks. Integrating these networks can enhance the accuracy of protein function prediction. Many algorithms have been introduced to generate a composite network, which is obtained as a weighted sum of individual networks. The weight assigned to an individual network reflects its benefit towards the protein functional annotation inference. A classifier is then trained on the composite network for predicting protein functions. However, since these techniques model the optimization of the composite network and the prediction tasks as separate objectives, the resulting composite network is not necessarily optimal for the follow-up protein function prediction.

Results

We address this issue by modeling the optimization of the composite network and the prediction problems within a unified objective function. In particular, we use a kernel target alignment technique and the loss function of a network based classifier to jointly adjust the weights assigned to the individual networks. We show that the proposed method, called MNet, can achieve a performance that is superior (with respect to different evaluation criteria) to related techniques using the multiple networks of four example species (yeast, human, mouse, and fly) annotated with thousands (or hundreds) of GO terms.

Conclusion

MNet can effectively integrate multiple networks for protein function prediction and is robust to the input parameters. Supplementary data is available at https://sites.google.com/site/guoxian85/home/mnet. The Matlab code of MNet is available upon request.

Predicting protein functions using incomplete hierarchical labels

BACKGROUND

Protein function prediction is to assign biological or biochemical functions to proteins, and it is a challenging computational problem characterized by several factors: (1) the number of function labels (annotations) is large; (2) a protein may be associated with multiple labels; (3) the function labels are structured in a hierarchy; and (4) the labels are incomplete. Current predictive models often assume that the labels of the labeled proteins are complete, i.e. no label is missing. But in real scenarios, we may be aware of only some hierarchical labels of a protein, and we may not know whether additional ones are actually present. The scenario of incomplete hierarchical labels, a challenging and practical problem, is seldom studied in protein function prediction.

RESULTS

In this paper, we propose an algorithm to Predict protein functions using Incomplete hierarchical LabeLs (PILL in short). PILL takes into account the hierarchical and the flat taxonomy similarity between function labels, and defines a Combined Similarity (ComSim) to measure the correlation between labels. PILL estimates the missing labels for a protein based on ComSim and the known labels of the protein, and uses a regularization to exploit the interactions between proteins for function prediction. PILL is shown to outperform other related techniques in replenishing the missing labels and in predicting the functions of completely unlabeled proteins on publicly available PPI datasets annotated with MIPS Functional Catalogue and Gene Ontology labels.

CONCLUSION

The empirical study shows that it is important to consider the incomplete annotation for protein function prediction. The proposed method (PILL) can serve as a valuable tool for protein function prediction using incomplete labels. The Matlab code of PILL is available upon request.

Predicting Protein Function Using Multiple Kernels

High-throughput experimental techniques provide a wide variety of heterogeneous proteomic data sources. To exploit the information spread across multiple sources for protein function prediction, these data sources are transformed into kernels and then integrated into a composite kernel. Several methods first optimize the weights on these kernels to produce a composite kernel, and then train a classifier on the composite kernel. As such, these approaches result in an optimal composite kernel, but not necessarily in an optimal classifier. On the other hand, some approaches optimize the loss of binary classifiers and learn weights for the different kernels iteratively. For multi-class or multi-label data, these methods have to solve the problem of optimizing weights on these kernels for each of the labels, which are computationally expensive and ignore the correlation among labels. In this paper, we propose a method called Predicting Protein Function using Multiple Kernels (ProMK). ProMK iteratively optimizes the phases of learning optimal weights and reduces the empirical loss of multi-label classifier for each of the labels simultaneously. ProMK can integrate kernels selectively and downgrade the weights on noisy kernels. We investigate the performance of ProMK on several publicly available protein function prediction benchmarks and synthetic datasets. We show that the proposed approach performs better than previously proposed protein function prediction approaches that integrate multiple data sources and multi-label multiple kernel learning methods. The codes of our proposed method are available at https://sites.google.com/site/guoxian85/promk.