Text as data: using text-based features for proteins representation and for computational prediction of their characteristics

DeepAdd: Protein function prediction from k-mer embedding and additional features

With the application of new high throughput sequencing technology, a large number of protein sequences is becoming available. Determination of the functional characteristics of these proteins by experiments is an expensive endeavor that requires a lot of time. Furthermore, at the organismal level, such kind of experimental functional analyses can be conducted only for a very few selected model organisms. Computational function prediction methods can be used to fill this gap. The functions of proteins are classified by Gene Ontology (GO), which contains more than 40,000 classifications in three domains, Molecular Function (MF), Biological Process (BP), and Cellular Component (CC). Additionally, since proteins have many functions, function prediction represents a multi-label and multi-class problem. We developed a new method to predict protein function from sequence. To this end, natural language model was used to generate word embedding of sequence and learn features from it by deep learning, and additional features to locate every protein. Our method uses the dependencies between GO classes as background information to construct a deep learning model. We evaluate our method using the standards established by the Computational Assessment of Function Annotation (CAFA) and have noticeable improvement over several algorithms, such as FFPred, DeepGO, GoFDR and other methods compared on the CAFA3 datasets.

DES-ROD: Exploring Literature to Develop New Links between RNA Oxidation and Human Diseases

Normal cellular physiology and biochemical processes require undamaged RNA molecules. However, RNAs are frequently subjected to oxidative damage. Overproduction of reactive oxygen species (ROS) leads to RNA oxidation and disturbs redox (oxidation-reduction reaction) homeostasis. When oxidation damage affects RNA carrying protein-coding information, this may result in the synthesis of aberrant proteins as well as a lower efficiency of translation. Both of these, as well as imbalanced redox homeostasis, may lead to numerous human diseases. The number of studies on the effects of RNA oxidative damage in mammals is increasing by year due to the understanding that this oxidation fundamentally leads to numerous human diseases. To enable researchers in this field to explore information relevant to RNA oxidation and effects on human diseases, we developed DES-ROD, an online knowledgebase that contains processed information from 298,603 relevant documents that consist of PubMed abstracts and PubMed Central full-text articles. The system utilizes concepts/terms from 38 curated thematic dictionaries mapped to the analyzed documents. Researchers can explore enriched concepts, as well as enriched pairs of putatively associated concepts. In this way, one can explore mutual relationships between any combinations of two concepts from used dictionaries. Dictionaries cover a wide range of biomedical topics, such as human genes and proteins, pathways, Gene Ontology categories, mutations, noncoding RNAs, enzymes, toxins, metabolites, and diseases. This makes insights into different facets of the effects of RNA oxidation and the control of this process possible. The usefulness of the DES-ROD system is demonstrated by case studies on some known information, as well as potentially novel information involving RNA oxidation and diseases. DES-ROD is the first knowledgebase based on text and data mining that focused on the exploration of RNA oxidation and human diseases.

Literature-Based Enrichment Insights into Redox Control of Vascular Biology

In cellular physiology and signaling, reactive oxygen species (ROS) play one of the most critical roles. ROS overproduction leads to cellular oxidative stress. This may lead to an irrecoverable imbalance of redox (oxidation-reduction reaction) function that deregulates redox homeostasis, which itself could lead to several diseases including neurodegenerative disease, cardiovascular disease, and cancers. In this study, we focus on the redox effects related to vascular systems in mammals. To support research in this domain, we developed an online knowledge base, DES-RedoxVasc, which enables exploration of information contained in the biomedical scientific literature. The DES-RedoxVasc system analyzed 233399 documents consisting of PubMed abstracts and PubMed Central full-text articles related to different aspects of redox biology in vascular systems. It allows researchers to explore enriched concepts from 28 curated thematic dictionaries, as well as literature-derived potential associations of pairs of such enriched concepts, where associations themselves are statistically enriched. For example, the system allows exploration of associations of pathways, diseases, mutations, genes/proteins, miRNAs, long ncRNAs, toxins, drugs, biological processes, molecular functions, etc. that allow for insights about different aspects of redox effects and control of processes related to the vascular system. Moreover, we deliver case studies about some existing or possibly novel knowledge regarding redox of vascular biology demonstrating the usefulness of DES-RedoxVasc. DES-RedoxVasc is the first compiled knowledge base using text mining for the exploration of this topic.

Predicting protein functions by applying predicate logic to biomedical literature

BACKGROUND

A large number of computational methods have been proposed for predicting protein functions. The underlying techniques adopted by most of these methods revolve around predicting the functions of an unannotated protein p from already annotated proteins that have similar characteristics as p. Recent Information Extraction methods take advantage of the huge growth of biomedical literature to predict protein functions. They extract biological molecule terms that directly describe protein functions from biomedical texts. However, they consider only explicitly mentioned terms that co-occur with proteins in texts. We observe that some important biological molecule terms pertaining functional categories may implicitly co-occur with proteins in texts. Therefore, the methods that rely solely on explicitly mentioned terms in texts may miss vital functional information implicitly mentioned in the texts.

RESULTS

To overcome the limitations of methods that rely solely on explicitly mentioned terms in texts to predict protein functions, we propose in this paper an Information Extraction system called PL-PPF. The proposed system employs techniques for predicting the functions of proteins based on their co-occurrences with explicitly and implicitly mentioned biological molecule terms that pertain functional categories in biomedical literature. That is, PL-PPF employs a combination of statistical-based explicit term extraction techniques and logic-based implicit term extraction techniques. The statistical component of PL-PPF predicts some of the functions of a protein by extracting the explicitly mentioned functional terms that directly describe the functions of the protein from the biomedical texts associated with the protein. The logic-based component of PL-PPF predicts additional functions of the protein by inferring the functional terms that co-occur implicitly with the protein in the biomedical texts associated with it. First, the system employs its statistical-based component to extract the explicitly mentioned functional terms. Then, it employs its logic-based component to infer additional functions of the protein. Our hypothesis is that important biological molecule terms pertaining functional categories of proteins are likely to co-occur implicitly with the proteins in biomedical texts. We evaluated PL-PPF experimentally and compared it with five systems. Results revealed better prediction performance.

CONCLUSIONS

The experimental results showed that PL-PPF outperformed the other five systems. This is an indication of the effectiveness and practical viability of PL-PPF's combination of explicit and implicit techniques. We also evaluated two versions of PL-PPF: one adopting the complete techniques (i.e., adopting both the implicit and explicit techniques) and the other adopting only the explicit terms co-occurrence extraction techniques (i.e., without the inference rules for predicate logic). The experimental results showed that the complete version outperformed significantly the other version. This is attributed to the effectiveness of the rules of predicate logic to infer functional terms that co-occur implicitly with proteins in biomedical texts. A demo application of PL-PPF can be accessed through the following link: http://ecesrvr.kustar.ac.ae:8080/plppf/.

Exploiting MEDLINE for gene molecular function prediction via NMF based multi-label classification

Gene ontology (GO) provides a representation of terms and categories used to describe genes and their molecular functions, cellular components and biological processes. GO has been the standard for describing the functions of specific genes in different model organisms. GO annotation, or the tagging of genes with GO terms, has mostly been a manual and time-consuming curation process. Although many automated approaches have been proposed for annotation, few have utilized knowledge available in the literature. In this manuscript, we describe the development and evaluation of an innovative predictive system to automatically assign molecular functions (GO terms) to genes using the biomedical literature. Because genes could be associated with multiple molecular functions, we posed the GO molecular function annotation as a multi-label classification problem with several classes. We used non-negative matrix factorization (NMF) for feature reduction and then classified the genes. To address the multi-label aspect of the data, we used the binary-relevance method. Although we experimented with several classifiers, the combination of binary-relevance and K-nearest neighbor (KNN) classifier performed best. Our evaluation on UniProtKB/Swiss-Prot dataset showed the best performance of 0.84 in terms of F1-measure.

DeepText2GO: Improving large-scale protein function prediction with deep semantic text representation

As of April 2018, UniProtKB has collected more than 115 million protein sequences. Less than 0.15% of these proteins, however, have been associated with experimental GO annotations. As such, the use of automatic protein function prediction (AFP) to reduce this huge gap becomes increasingly important. The previous studies conclude that sequence homology based methods are highly effective in AFP. In addition, mining motif, domain, and functional information from protein sequences has been found very helpful for AFP. Other than sequences, alternative information sources such as text, however, may be useful for AFP as well. Instead of using BOW (bag of words) representation in traditional text-based AFP, we propose a new method called DeepText2GO that relies on deep semantic text representation, together with different kinds of available protein information such as sequence homology, families, domains, and motifs, to improve large-scale AFP. Furthermore, DeepText2GO integrates text-based methods with sequence-based ones by means of a consensus approach. Extensive experiments on the benchmark dataset extracted from UniProt/SwissProt have demonstrated that DeepText2GO significantly outperformed both text-based and sequence-based methods, validating its superiority.

The research on gene-disease association based on text-mining of PubMed

Background

The associations between genes and diseases are of critical significance in aspects of prevention, diagnosis and treatment. Although gene-disease relationships have been investigated extensively, much of the underpinnings of these associations are yet to be elucidated.

Methods

A novel method integrates MeSH database, term weight (TW), and co-occurrence methods to predict gene-disease associations based on the cosine similarity between gene vectors and disease vectors. Vectors are transformed from the texts of documents in the PubMed database according to the appearance and location of the gene or disease terms. The disease related text data has been optimized during the process of constructing vectors.

Results

The overall distribution of cosine similarity value was investigated. By using the gene-disease association data in OMIM database as golden standard, the performance of cosine similarity in predicting gene-disease linkage was evaluated. The effects of applying weight matrix, penalty weights for keywords (PWK), and normalization were also investigated. Finally, we demonstrated that our method outperforms heterogeneous network edge prediction (HNEP) in aspects of precision rate and recall rate.

Conclusions

Our method proposed in this paper is easy to be conducted and the results can be integrated with other models to improve the overall performance of gene-disease association predictions.

Inferring the Functions of Proteins from the Interrelationships between Functional Categories

This study proposes a new method to determine the functions of an unannotated protein. The proteins and amino acid residues mentioned in biomedical texts associated with an unannotated protein can be considered as characteristics terms for , which are highly predictive of the potential functions of . Similarly, proteins and amino acid residues mentioned in biomedical texts associated with proteins annotated with a functional category can be considered as characteristics terms of . We introduce in this paper an information extraction system called IFP_IFC that predicts the functions of an unannotated protein by representing and each functional category by a vector of weights. Each weight reflects the degree of association between a characteristic term and (or a characteristic term and ). First, IFP_IFC constructs a network, whose nodes represent the different functional categories, and its edges the interrelationships between the nodes. Then, it determines the functions of by employing random walks with restarts on the mentioned network. The walker is the vector of . Finally, is assigned to the functional categories of the nodes in the network that are visited most by the walker. We evaluated the quality of IFP_IFC by comparing it experimentally with two other systems. Results showed marked improvement.

Text Mining for Protein Docking

The rapidly growing amount of publicly available information from biomedical research is readily accessible on the Internet, providing a powerful resource for predictive biomolecular modeling. The accumulated data on experimentally determined structures transformed structure prediction of proteins and protein complexes. Instead of exploring the enormous search space, predictive tools can simply proceed to the solution based on similarity to the existing, previously determined structures. A similar major paradigm shift is emerging due to the rapidly expanding amount of information, other than experimentally determined structures, which still can be used as constraints in biomolecular structure prediction. Automated text mining has been widely used in recreating protein interaction networks, as well as in detecting small ligand binding sites on protein structures. Combining and expanding these two well-developed areas of research, we applied the text mining to structural modeling of protein-protein complexes (protein docking). Protein docking can be significantly improved when constraints on the docking mode are available. We developed a procedure that retrieves published abstracts on a specific protein-protein interaction and extracts information relevant to docking. The procedure was assessed on protein complexes from Dockground (http://dockground.compbio.ku.edu). The results show that correct information on binding residues can be extracted for about half of the complexes. The amount of irrelevant information was reduced by conceptual analysis of a subset of the retrieved abstracts, based on the bag-of-words (features) approach. Support Vector Machine models were trained and validated on the subset. The remaining abstracts were filtered by the best-performing models, which decreased the irrelevant information for ~ 25% complexes in the dataset. The extracted constraints were incorporated in the docking protocol and tested on the Dockground unbound benchmark set, significantly increasing the docking success rate.

Protein interactions are central for many cellular processes. Physical characterization of these interactions is essential for understanding of life processes and applications in biology and medicine. Because of the inherent limitations of experimental techniques and rapid development of computational power and methodology, computer modeling is a tool of choice in many studies. Publicly available information from biomedical research is readily accessible on the Internet, providing a powerful resource for modeling of proteins and protein complexes. A major paradigm shift in modeling of protein complexes is emerging due to the rapidly expanding amount of such information, which can be used as modeling constraints. Text mining has been widely used in recreating networks of protein interactions, as well as in detecting small molecule binding sites on proteins. Combining and expanding these two well-developed areas of research, we applied the text mining to physical modeling of protein complexes (protein docking). Our procedure retrieves published abstracts on a protein-protein interaction and extracts the relevant information. The results show that correct information on binding can be obtained for about half of protein complexes. The extracted constraints were incorporated in a modeling procedure, significantly improving its performance.

Using distant supervised learning to identify protein subcellular localizations from full-text scientific articles

Databases of curated biomedical knowledge, such as the protein-locations reflected in the UniProtKB database, provide an accurate and useful resource to researchers and decision makers. Our goal is to augment the manual efforts currently used to curate knowledge bases with automated approaches that leverage the increased availability of full-text scientific articles. This paper describes experiments that use distant supervised learning to identify protein subcellular localizations, which are important to understand protein function and to identify candidate drug targets. Experiments consider Swiss-Prot, the manually annotated subset of the UniProtKB protein knowledge base, and 43,000 full-text articles from the Journal of Biological Chemistry that contain just under 11.5 million sentences. The system achieves 0.81 precision and 0.49 recall at sentence level and an accuracy of 57% on held-out instances in a test set. Moreover, the approach identifies 8210 instances that are not in the UniProtKB knowledge base. Manual inspection of the 50 most likely relations showed that 41 (82%) were valid. These results have immediate benefit to researchers interested in protein function, and suggest that distant supervision should be explored to complement other manual data curation efforts.

Evaluating a variety of text-mined features for automatic protein function prediction with GOstruct

Most computational methods that predict protein function do not take advantage of the large amount of information contained in the biomedical literature. In this work we evaluate both ontology term co-mention and bag-of-words features mined from the biomedical literature and analyze their impact in the context of a structured output support vector machine model, GOstruct. We find that even simple literature based features are useful for predicting human protein function (F-max: Molecular Function =0.408, Biological Process =0.461, Cellular Component =0.608). One advantage of using literature features is their ability to offer easy verification of automated predictions. We find through manual inspection of misclassifications that some false positive predictions could be biologically valid predictions based upon support extracted from the literature. Additionally, we present a “medium-throughput” pipeline that was used to annotate a large subset of co-mentions; we suggest that this strategy could help to speed up the rate at which proteins are curated.