RLIMS-P 2.0: A Generalizable Rule-Based Information Extraction System for Literature Mining of Protein Phosphorylation Information

IDPpub: Illuminating the Dark Phosphoproteome Through PubMed Mining

Global phosphoproteomics experiments quantify tens of thousands of phosphorylation sites. However, data interpretation is hampered by our limited knowledge on functions, biological contexts, or precipitating enzymes of the phosphosites. This study establishes a repository of phosphosites with associated evidence in biomedical abstracts, using deep learning-based natural language processing techniques. Our model for illuminating the dark phosphoproteome through PubMed mining (IDPpub) was generated by fine-tuning BioBERT, a deep learning tool for biomedical text mining. Trained using sentences containing protein substrates and phosphorylation site positions from 3000 abstracts, the IDPpub model was then used to extract phosphorylation sites from all MEDLINE abstracts. The extracted proteins were normalized to gene symbols using the National Center for Biotechnology Information gene query, and sites were mapped to human UniProt sequences using ProtMapper and mouse UniProt sequences by direct match. Precision and recall were calculated using 150 curated abstracts, and utility was assessed by analyzing the CPTAC (Clinical Proteomics Tumor Analysis Consortium) pan-cancer phosphoproteomics datasets and the PhosphoSitePlus database. Using 10-fold cross validation, pairs of correct substrates and phosphosite positions were extracted with an average precision of 0.93 and recall of 0.94. After entity normalization and site mapping to human reference sequences, an independent validation achieved a precision of 0.91 and recall of 0.77. The IDPpub repository contains 18,458 unique human phosphorylation sites with evidence sentences from 58,227 abstracts and 5918 mouse sites in 14,610 abstracts. This included evidence sentences for 1803 sites identified in CPTAC studies that are not covered by manually curated functional information in PhosphoSitePlus. Evaluation results demonstrate the potential of IDPpub as an effective biomedical text mining tool for collecting phosphosites. Moreover, the repository (http://idppub.ptmax.org), which can be automatically updated, can serve as a powerful complement to existing resources.

KSFinder-a knowledge graph model for link prediction of novel phosphorylated substrates of kinases

Background

Aberrant protein kinase regulation leading to abnormal substrate phosphorylation is associated with several human diseases. Despite the promise of therapies targeting kinases, many human kinases remain understudied. Most existing computational tools predicting phosphorylation cover less than 50% of known human kinases. They utilize local feature selection based on protein sequences, motifs, domains, structures, and/or functions, and do not consider the heterogeneous relationships of the proteins. In this work, we present KSFinder, a tool that predicts kinase-substrate links by capturing the inherent association of proteins in a network comprising 85% of the known human kinases. We also postulate the potential role of two understudied kinases based on their substrate predictions from KSFinder.

Methods

KSFinder learns the semantic relationships in a phosphoproteome knowledge graph using a knowledge graph embedding algorithm and represents the nodes in low-dimensional vectors. A multilayer perceptron (MLP) classifier is trained to discern kinase-substrate links using the embedded vectors. KSFinder uses a strategic negative generation approach that eliminates biases in entity representation and combines data from experimentally validated non-interacting protein pairs, proteins from different subcellular locations, and random sampling. We assess KSFinder's generalization capability on four different datasets and compare its performance with other state-of-the-art prediction models. We employ KSFinder to predict substrates of 68 "dark" kinases considered understudied by the Illuminating the Druggable Genome program and use our text-mining tool, RLIMS-P along with manual curation, to search for literature evidence for the predictions. In a case study, we performed functional enrichment analysis for two dark kinases - HIPK3 and CAMKK1 using their predicted substrates.

Results

KSFinder shows improved performance over other kinase-substrate prediction models and generalized prediction ability on different datasets. We identified literature evidence for 17 novel predictions involving an understudied kinase. All of these 17 predictions had a probability score ≥0.7 (nine at >0.9, six at 0.8-0.9, and two at 0.7-0.8). The evaluation of 93,593 negative predictions (probability ≤0.3) identified four false negatives. The top enriched biological processes of HIPK3 substrates relate to the regulation of extracellular matrix and epigenetic gene expression, while CAMKK1 substrates include lipid storage regulation and glucose homeostasis.

Conclusions

KSFinder outperforms the current kinase-substrate prediction tools with higher kinase coverage. The strategically developed negatives provide a superior generalization ability for KSFinder. We predicted substrates of 432 kinases, 68 of which are understudied, and hypothesized the potential functions of two dark kinases using their predicted substrates.

Automated assembly of molecular mechanisms at scale from text mining and curated databases

The analysis of omic data depends on machine-readable information about protein interactions, modifications, and activities as found in protein interaction networks, databases of post-translational modifications, and curated models of gene and protein function. These resources typically depend heavily on human curation. Natural language processing systems that read the primary literature have the potential to substantially extend knowledge resources while reducing the burden on human curators. However, machine-reading systems are limited by high error rates and commonly generate fragmentary and redundant information. Here, we describe an approach to precisely assemble molecular mechanisms at scale using multiple natural language processing systems and the Integrated Network and Dynamical Reasoning Assembler (INDRA). INDRA identifies full and partial overlaps in information extracted from published papers and pathway databases, uses predictive models to improve the reliability of machine reading, and thereby assembles individual pieces of information into non-redundant and broadly usable mechanistic knowledge. Using INDRA to create high-quality corpora of causal knowledge we show it is possible to extend protein-protein interaction databases and explain co-dependencies in the Cancer Dependency Map.

Identification of Novel Kinases of Tau Using Fluorescence Complementation Mass Spectrometry (FCMS)

Hyperphosphorylation of the microtubule-associated protein Tau is a major hallmark of Alzheimer's disease and other tauopathies. Understanding the protein kinases that phosphorylate Tau is critical for the development of new drugs that target Tau phosphorylation. At present, the repertoire of the Tau kinases remains incomplete, and methods to uncover novel upstream protein kinases are still limited. Here, we apply our newly developed proteomic strategy, fluorescence complementation mass spectrometry, to identify novel kinase candidates of Tau. By constructing Tau- and kinase-fluorescent fragment library, we detected 59 Tau-associated kinases, including 23 known kinases of Tau and 36 novel candidate kinases. In the validation phase using in vitro phosphorylation, among 15 candidate kinases we attempted to purify and test, four candidate kinases, OXSR1 (oxidative-stress responsive gene 1), DAPK2 (death-associated protein kinase 2), CSK (C-terminal SRC kinase), and ZAP70 (zeta chain of T-cell receptor-associated protein kinase 70), displayed the ability to phosphorylate Tau in time-course experiments. Furthermore, coexpression of these four kinases along with Tau increased the phosphorylation of Tau in human neuroglioma H4 cells. We demonstrate that fluorescence complementation mass spectrometry is a powerful proteomic strategy to systematically identify potential kinases that can phosphorylate Tau in cells. Our discovery of new candidate kinases of Tau can present new opportunities for developing Alzheimer's disease therapeutic strategies.

Expanding a database-derived biomedical knowledge graph via multi-relation extraction from biomedical abstracts

BACKGROUND

Knowledge graphs support biomedical research efforts by providing contextual information for biomedical entities, constructing networks, and supporting the interpretation of high-throughput analyses. These databases are populated via manual curation, which is challenging to scale with an exponentially rising publication rate. Data programming is a paradigm that circumvents this arduous manual process by combining databases with simple rules and heuristics written as label functions, which are programs designed to annotate textual data automatically. Unfortunately, writing a useful label function requires substantial error analysis and is a nontrivial task that takes multiple days per function. This bottleneck makes populating a knowledge graph with multiple nodes and edge types practically infeasible. Thus, we sought to accelerate the label function creation process by evaluating how label functions can be re-used across multiple edge types.

RESULTS

We obtained entity-tagged abstracts and subsetted these entities to only contain compounds, genes, and disease mentions. We extracted sentences containing co-mentions of certain biomedical entities contained in a previously described knowledge graph, Hetionet v1. We trained a baseline model that used database-only label functions and then used a sampling approach to measure how well adding edge-specific or edge-mismatch label function combinations improved over our baseline. Next, we trained a discriminator model to detect sentences that indicated a biomedical relationship and then estimated the number of edge types that could be recalled and added to Hetionet v1. We found that adding edge-mismatch label functions rarely improved relationship extraction, while control edge-specific label functions did. There were two exceptions to this trend, Compound-binds-Gene and Gene-interacts-Gene, which both indicated physical relationships and showed signs of transferability. Across the scenarios tested, discriminative model performance strongly depends on generated annotations. Using the best discriminative model for each edge type, we recalled close to 30% of established edges within Hetionet v1.

CONCLUSIONS

Our results show that this framework can incorporate novel edges into our source knowledge graph. However, results with label function transfer were mixed. Only label functions describing very similar edge types supported improved performance when transferred. We expect that the continued development of this strategy may provide essential building blocks to populating biomedical knowledge graphs with discoveries, ensuring that these resources include cutting-edge results.

Band gap information extraction from materials science literature – a pilot study

Purpose

The purpose of this paper is to present a preliminary work on extracting band gap information of materials from academic papers. With increasing demand for renewable energy, band gap information will help material scientists design and implement novel photovoltaic (PV) cells.

Design/methodology/approach

The authors collected 1.44 million titles and abstracts of scholarly articles related to materials science, and then filtered the collection to 11,939 articles that potentially contain relevant information about materials and their band gap values. ChemDataExtractor was extended to extract information about PV materials and their band gap information. Evaluation was performed on randomly sampled information records of 415 papers.

Findings

The findings of this study show that the current system is able to correctly extract information for 51.32% articles, with partially correct extraction for 36.62% articles and incorrect for 12.04%. The authors have also identified the errors belonging to three main categories pertaining to chemical entity identification, band gap information and interdependency resolution. Future work will focus on addressing these errors to improve the performance of the system.

Originality/value

The authors did not find any literature to date on band gap information extraction from academic text using automated methods. This work is unique and original. Band gap information is of importance to materials scientists in applications such as solar cells, light emitting diodes and laser diodes.

Large-scale protein-protein post-translational modification extraction with distant supervision and confidence calibrated BioBERT

MOTIVATION

Protein-protein interactions (PPIs) are critical to normal cellular function and are related to many disease pathways. A range of protein functions are mediated and regulated by protein interactions through post-translational modifications (PTM). However, only 4% of PPIs are annotated with PTMs in biological knowledge databases such as IntAct, mainly performed through manual curation, which is neither time- nor cost-effective. Here we aim to facilitate annotation by extracting PPIs along with their pairwise PTM from the literature by using distantly supervised training data using deep learning to aid human curation.

METHOD

We use the IntAct PPI database to create a distant supervised dataset annotated with interacting protein pairs, their corresponding PTM type, and associated abstracts from the PubMed database. We train an ensemble of BioBERT models-dubbed PPI-BioBERT-x10-to improve confidence calibration. We extend the use of ensemble average confidence approach with confidence variation to counteract the effects of class imbalance to extract high confidence predictions.

RESULTS AND CONCLUSION

The PPI-BioBERT-x10 model evaluated on the test set resulted in a modest F1-micro 41.3 (P =5 8.1, R = 32.1). However, by combining high confidence and low variation to identify high quality predictions, tuning the predictions for precision, we retained 19% of the test predictions with 100% precision. We evaluated PPI-BioBERT-x10 on 18 million PubMed abstracts and extracted 1.6 million (546507 unique PTM-PPI triplets) PTM-PPI predictions, and filter [Formula: see text] (4584 unique) high confidence predictions. Of the 5700, human evaluation on a small randomly sampled subset shows that the precision drops to 33.7% despite confidence calibration and highlights the challenges of generalisability beyond the test set even with confidence calibration. We circumvent the problem by only including predictions associated with multiple papers, improving the precision to 58.8%. In this work, we highlight the benefits and challenges of deep learning-based text mining in practice, and the need for increased emphasis on confidence calibration to facilitate human curation efforts.

A Text Mining and Machine Learning Protocol for Extracting Posttranslational Modifications of Proteins from PubMed: A Special Focus on Glycosylation, Acetylation, Methylation, Hydroxylation, and Ubiquitination

Posttranslational modifications (PTMs) of proteins impart a significant role in human cellular functions ranging from localization to signal transduction. Hundreds of PTMs act in a human cell. Among them, only the selected PTMs are well established and documented. PubMed includes thousands of papers on the selected PTMs, and it is a challenge for the biomedical researchers to assimilate useful information manually. Alternatively, text mining approaches and machine learning algorithm automatically extract the relevant information from PubMed. Protein phosphorylation is a well-established PTM and several research works are under way. Many existing systems are there for protein phosphorylation information extraction. A recent approach uses a hybrid approach using text mining and machine learning to extract protein phosphorylation information from PubMed. Some of the other common PTMs that exhibit similar features in terms of entities that are involved in PTM process, that is, the substrate, the enzymes, and the amino acid residues, are glycosylation, acetylation, methylation, hydroxylation, and ubiquitination. This has motivated us to repurpose and extend the text mining protocol and machine learning information extraction methodology developed for protein phosphorylation to these PTMs. In this chapter, the chemistry behind each of the PTMs is briefly outlined and the text mining protocol and machine learning algorithm adaption is explained for the same.

Text Mining and Machine Learning Protocol for Extracting Human-Related Protein Phosphorylation Information from PubMed

In the modern health care research, protein phosphorylation has gained an enormous attention from the researchers across the globe and requires automated approaches to process a huge volume of data on proteins and their modifications at the cellular level. The data generated at the cellular level is unique as well as arbitrary, and an accumulation of massive volume of information is inevitable. Biological research has revealed that a huge array of cellular communication aided by protein phosphorylation and other similar mechanisms imply different and diverse meanings. This led to a collection of huge volume of data to understand the biological functions of human evolution, especially for combating diseases in a better way. Text mining, an automated approach to mine the information from an unstructured data, finds its application in extracting protein phosphorylation information from the biomedical literature databases such as PubMed. This chapter outlines a recent text mining protocol that applies natural language parsing (NLP) for named entity recognition and text processing, and support vector machines (SVM), a machine learning algorithm for classifying the processed text related human protein phosphorylation. We discuss on evaluating the text mining system which is the outcome of the protocol on three corpora, namely, human Protein Phosphorylation (hPP) corpus, Integrated Protein Literature Information and Knowledge corpus (iProLink), and Phosphorylation Literature corpus (PLC). We also present a basic understanding on the chemistry and biology that drive the protein phosphorylation process in a human body. We believe that this basic understanding will be useful to advance the existing text mining systems for extracting protein phosphorylation information from PubMed.

ProteoSushi: A Software Tool to Biologically Annotate and Quantify Modification-Specific, Peptide-Centric Proteomics Data Sets

Large-scale proteomic profiling of protein post-translational modifications has provided important insights into the regulation of cell signaling and disease. These modification-specific proteomics workflows nearly universally enrich modified peptides prior to mass spectrometry analysis, but protein-centric proteomic software tools have many limitations evaluating and interpreting these peptide-centric data sets. We, therefore, developed ProteoSushi, a software tool tailored to analysis of each modified site in peptide-centric proteomic data sets that is compatible with any post-translational modification or chemical label. ProteoSushi uses a unique approach to assign identified peptides to shared proteins and genes, minimizing redundancy by prioritizing shared assignments based on UniProt annotation score and optional user-supplied protein/gene lists. ProteoSushi simplifies quantitation by summing or averaging intensities for each modified site, merging overlapping peptide charge states, missed cleavages, spectral matches, and variable modifications into a single value. ProteoSushi also annotates each PTM site with the most up-to-date biological information available from UniProt, such as functional roles or known modifications, the protein domain in which the site resides, the protein's subcellular location and function, and more. ProteoSushi has a graphical user interface for ease of use. ProteoSushi's flexibility and combination of analysis features streamlines peptide-centric data processing and knowledge mining of large modification-specific proteomics data sets.

ANDDigest: a new web-based module of ANDSystem for the search of knowledge in the scientific literature

BACKGROUND

The rapid growth of scientific literature has rendered the task of finding relevant information one of the critical problems in almost any research. Search engines, like Google Scholar, Web of Knowledge, PubMed, Scopus, and others, are highly effective in document search; however, they do not allow knowledge extraction. In contrast to the search engines, text-mining systems provide extraction of knowledge with representations in the form of semantic networks. Of particular interest are tools performing a full cycle of knowledge management and engineering, including automated retrieval, integration, and representation of knowledge in the form of semantic networks, their visualization, and analysis. STRING, Pathway Studio, MetaCore, and others are well-known examples of such products. Previously, we developed the Associative Network Discovery System (ANDSystem), which also implements such a cycle. However, the drawback of these systems is dependence on the employed ontologies describing the subject area, which limits their functionality in searching information based on user-specified queries.

RESULTS

The ANDDigest system is a new web-based module of the ANDSystem tool, permitting searching within PubMed by using dictionaries from the ANDSystem tool and sets of user-defined keywords. ANDDigest allows performing the search based on complex queries simultaneously, taking into account many types of objects from the ANDSystem's ontology. The system has a user-friendly interface, providing sorting, visualization, and filtering of the found information, including mapping of mentioned objects in text, linking to external databases, sorting of data by publication date, citations number, journal H-indices, etc. The system provides data on trends for identified entities based on dynamics of interest according to the frequency of their mentions in PubMed by years.

CONCLUSIONS

The main feature of ANDDigest is its functionality, serving as a specialized search for information about multiple associative relationships of objects from the ANDSystem's ontology vocabularies, taking into account user-specified keywords. The tool can be applied to the interpretation of experimental genetics data, the search for associations between molecular genetics objects, and the preparation of scientific and analytical reviews. It is presently available at https://anddigest.sysbio.ru/ .

Selective Neuronal Vulnerability in Alzheimer's Disease: A Network-Based Analysis

A major obstacle to treating Alzheimer's disease (AD) is our lack of understanding of the molecular mechanisms underlying selective neuronal vulnerability, a key characteristic of the disease. Here, we present a framework integrating high-quality neuron-type-specific molecular profiles across the lifetime of the healthy mouse, which we generated using bacTRAP, with postmortem human functional genomics and quantitative genetics data. We demonstrate human-mouse conservation of cellular taxonomy at the molecular level for neurons vulnerable and resistant in AD, identify specific genes and pathways associated with AD neuropathology, and pinpoint a specific functional gene module underlying selective vulnerability, enriched in processes associated with axonal remodeling, and affected by amyloid accumulation and aging. We have made all cell-type-specific profiles and functional networks available at http://alz.princeton.edu. Overall, our study provides a molecular framework for understanding the complex interplay between Aβ, aging, and neurodegeneration within the most vulnerable neurons in AD.

Constructing knowledge graphs and their biomedical applications

Knowledge graphs can support many biomedical applications. These graphs represent biomedical concepts and relationships in the form of nodes and edges. In this review, we discuss how these graphs are constructed and applied with a particular focus on how machine learning approaches are changing these processes. Biomedical knowledge graphs have often been constructed by integrating databases that were populated by experts via manual curation, but we are now seeing a more robust use of automated systems. A number of techniques are used to represent knowledge graphs, but often machine learning methods are used to construct a low-dimensional representation that can support many different applications. This representation is designed to preserve a knowledge graph's local and/or global structure. Additional machine learning methods can be applied to this representation to make predictions within genomic, pharmaceutical, and clinical domains. We frame our discussion first around knowledge graph construction and then around unifying representational learning techniques and unifying applications. Advances in machine learning for biomedicine are creating new opportunities across many domains, and we note potential avenues for future work with knowledge graphs that appear particularly promising.

RESTful API for iPTMnet: a resource for protein post-translational modification network discovery

iPTMnet is a bioinformatics resource that integrates protein post-translational modification (PTM) data from text mining and curated databases and ontologies to aid in knowledge discovery and scientific study. The current iPTMnet website can be used for querying and browsing rich PTM information but does not support automated iPTMnet data integration with other tools. Hence, we have developed a RESTful API utilizing the latest developments in cloud technologies to facilitate the integration of iPTMnet into existing tools and pipelines. We have packaged iPTMnet API software in Docker containers and published it on DockerHub for easy redistribution. We have also developed Python and R packages that allow users to integrate iPTMnet for scientific discovery, as demonstrated in a use case that connects PTM sites to kinase signaling pathways.

iPTMnet: an integrated resource for protein post-translational modification network discovery

Protein post-translational modifications (PTMs) play a pivotal role in numerous biological processes by modulating regulation of protein function. We have developed iPTMnet (http://proteininformationresource.org/iPTMnet) for PTM knowledge discovery, employing an integrative bioinformatics approach—combining text mining, data mining, and ontological representation to capture rich PTM information, including PTM enzyme-substrate-site relationships, PTM-specific protein-protein interactions (PPIs) and PTM conservation across species. iPTMnet encompasses data from (i) our PTM-focused text mining tools, RLIMS-P and eFIP, which extract phosphorylation information from full-scale mining of PubMed abstracts and full-length articles; (ii) a set of curated databases with experimentally observed PTMs; and iii) Protein Ontology that organizes proteins and PTM proteoforms, enabling their representation, annotation and comparison within and across species. Presently covering eight major PTM types (phosphorylation, ubiquitination, acetylation, methylation, glycosylation, S-nitrosylation, sumoylation and myristoylation), iPTMnet knowledgebase contains more than 654 500 unique PTM sites in over 62 100 proteins, along with more than 1200 PTM enzymes and over 24 300 PTM enzyme-substrate-site relations. The website supports online search, browsing, retrieval and visual analysis for scientific queries. Several examples, including functional interpretation of phosphoproteomic data, demonstrate iPTMnet as a gateway for visual exploration and systematic analysis of PTM networks and conservation, thereby enabling PTM discovery and hypothesis generation.

Mining protein phosphorylation information from biomedical literature using NLP parsing and Support Vector Machines

BACKGROUND

Extraction of protein phosphorylation information from biomedical literature has gained much attention because of the importance in numerous biological processes.

OBJECTIVE

In this study, we propose a text mining methodology which consists of two phases, NLP parsing and SVM classification to extract phosphorylation information from literature.

METHODS

First, using NLP parsing we divide the data into three base-forms depending on the biomedical entities related to phosphorylation and further classify into ten sub-forms based on their distribution with phosphorylation keyword. Next, we extract the phosphorylation entity singles/pairs/triplets and apply SVM to classify the extracted singles/pairs/triplets using a set of features applicable to each sub-form.

RESULTS

The performance of our methodology was evaluated on three corpora namely PLC, iProLink and hPP corpus. We obtained promising results of >85% F-score on ten sub-forms of training datasets on cross validation test. Our system achieved overall F-score of 93.0% on iProLink and 96.3% on hPP corpus test datasets. Furthermore, our proposed system achieved best performance on cross corpus evaluation and outperformed the existing system with recall of 90.1%.

CONCLUSIONS

The performance analysis of our unique system on three corpora reveals that it extracts protein phosphorylation information efficiently in both non-organism specific general datasets such as PLC and iProLink, and human specific dataset such as hPP corpus.

iTextMine: integrated text-mining system for large-scale knowledge extraction from the literature

Numerous efforts have been made for developing text-mining tools to extract information from biomedical text automatically. They have assisted in many biological tasks, such as database curation and hypothesis generation. Text-mining tools are usually different from each other in terms of programming language, system dependency and input/output format. There are few previous works that concern the integration of different text-mining tools and their results from large-scale text processing. In this paper, we describe the iTextMine system with an automated workflow to run multiple text-mining tools on large-scale text for knowledge extraction. We employ parallel processing with dockerized text-mining tools with a standardized JSON output format and implement a text alignment algorithm to solve the text discrepancy for result integration. iTextMine presently integrates four relation extraction tools, which have been used to process all the Medline abstracts and PMC open access full-length articles. The website allows users to browse the text evidence and view integrated results for knowledge discovery through a network view. We demonstrate the utilities of iTextMine with two use cases involving the gene PTEN and breast cancer and the gene SATB1.

Multiple kernels learning-based biological entity relationship extraction method

Background

Automatic extracting protein entity interaction information from biomedical literature can help to build protein relation network and design new drugs. There are more than 20 million literature abstracts included in MEDLINE, which is the most authoritative textual database in the field of biomedicine, and follow an exponential growth over time. This frantic expansion of the biomedical literature can often be difficult to absorb or manually analyze. Thus efficient and automated search engines are necessary to efficiently explore the biomedical literature using text mining techniques.

Results

The P, R, and F value of tag graph method in Aimed corpus are 50.82, 69.76, and 58.61%, respectively. The P, R, and F value of tag graph kernel method in other four evaluation corpuses are 2–5% higher than that of all-paths graph kernel. And The P, R and F value of feature kernel and tag graph kernel fuse methods is 53.43, 71.62 and 61.30%, respectively. The P, R and F value of feature kernel and tag graph kernel fuse methods is 55.47, 70.29 and 60.37%, respectively. It indicated that the performance of the two kinds of kernel fusion methods is better than that of simple kernel.

Conclusion

In comparison with the all-paths graph kernel method, the tag graph kernel method is superior in terms of overall performance. Experiments show that the performance of the multi-kernels method is better than that of the three separate single-kernel method and the dual-mutually fused kernel method used hereof in five corpus sets.

MPTM: A tool for mining protein post-translational modifications from literature

Due to the importance of post-translational modifications (PTMs) in human health and diseases, PTMs are regularly reported in the biomedical literature. However, the continuing and rapid pace of expansion of this literature brings a huge challenge for researchers and database curators. Therefore, there is a pressing need to aid them in identifying relevant PTM information more efficiently by using a text mining system. So far, only a few web servers are available for mining information of a very limited number of PTMs, which are based on simple pattern matching or pre-defined rules. In our work, in order to help researchers and database curators easily find and retrieve PTM information from available text, we have developed a text mining tool called MPTM, which extracts and organizes valuable knowledge about 11 common PTMs from abstracts in PubMed by using relations extracted from dependency parse trees and a heuristic algorithm. It is the first web server that provides literature mining service for hydroxylation, myristoylation and GPI-anchor. The tool is also used to find new publications on PTMs from PubMed and uncovers potential PTM information by large-scale text analysis. MPTM analyzes text sentences to identify protein names including substrates and protein-interacting enzymes, and automatically associates them with the UniProtKB protein entry. To facilitate further investigation, it also retrieves PTM-related information, such as human diseases, Gene Ontology terms and organisms from the input text and related databases. In addition, an online database (MPTMDB) with extracted PTM information and a local MPTM Lite package are provided on the MPTM website. MPTM is freely available online at http://bioinformatics.ustc.edu.cn/mptm/ and the source codes are hosted on GitHub: https://github.com/USTC-HILAB/MPTM .

StemTextSearch: Stem cell gene database with evidence from abstracts

BACKGROUND

Previous studies have used many methods to find biomarkers in stem cells, including text mining, experimental data and image storage. However, no text-mining methods have yet been developed which can identify whether a gene plays a positive or negative role in stem cells.

DESCRIPTION

StemTextSearch identifies the role of a gene in stem cells by using a text-mining method to find combinations of gene regulation, stem-cell regulation and cell processes in the same sentences of biomedical abstracts.

CONCLUSIONS

The dataset includes 5797 genes, with 1534 genes having positive roles in stem cells, 1335 genes having negative roles, 1654 genes with both positive and negative roles, and 1274 with an uncertain role. The precision of gene role in StemTextSearch is 0.66, and the recall is 0.78. StemTextSearch is a web-based engine with queries that specify (i) gene, (ii) category of stem cell, (iii) gene role, (iv) gene regulation, (v) cell process, (vi) stem-cell regulation, and (vii) species. StemTextSearch is available through http://bio.yungyun.com.tw/StemTextSearch.aspx.

A Review of Recent Advancement in Integrating Omics Data with Literature Mining towards Biomedical Discoveries

In the past decade, the volume of "omics" data generated by the different high-throughput technologies has expanded exponentially. The managing, storing, and analyzing of this big data have been a great challenge for the researchers, especially when moving towards the goal of generating testable data-driven hypotheses, which has been the promise of the high-throughput experimental techniques. Different bioinformatics approaches have been developed to streamline the downstream analyzes by providing independent information to interpret and provide biological inference. Text mining (also known as literature mining) is one of the commonly used approaches for automated generation of biological knowledge from the huge number of published articles. In this review paper, we discuss the recent advancement in approaches that integrate results from omics data and information generated from text mining approaches to uncover novel biomedical information.

Protein Ontology (PRO): enhancing and scaling up the representation of protein entities

The Protein Ontology (PRO; http://purl.obolibrary.org/obo/pr) formally defines and describes taxon-specific and taxon-neutral protein-related entities in three major areas: proteins related by evolution; proteins produced from a given gene; and protein-containing complexes. PRO thus serves as a tool for referencing protein entities at any level of specificity. To enhance this ability, and to facilitate the comparison of such entities described in different resources, we developed a standardized representation of proteoforms using UniProtKB as a sequence reference and PSI-MOD as a post-translational modification reference. We illustrate its use in facilitating an alignment between PRO and Reactome protein entities. We also address issues of scalability, describing our first steps into the use of text mining to identify protein-related entities, the large-scale import of proteoform information from expert curated resources, and our ability to dynamically generate PRO terms. Web views for individual terms are now more informative about closely-related terms, including for example an interactive multiple sequence alignment. Finally, we describe recent improvement in semantic utility, with PRO now represented in OWL and as a SPARQL endpoint. These developments will further support the anticipated growth of PRO and facilitate discoverability of and allow aggregation of data relating to protein entities.

Analysis of Protein Phosphorylation and Its Functional Impact on Protein-Protein Interactions via Text Mining of the Scientific Literature

Post-translational modifications (PTMs) are one of the main contributors to the diversity of proteoforms in the proteomic landscape. In particular, protein phosphorylation represents an essential regulatory mechanism that plays a role in many biological processes. Protein kinases, the enzymes catalyzing this reaction, are key participants in metabolic and signaling pathways. Their activation or inactivation dictate downstream events: what substrates are modified and their subsequent impact (e.g., activation state, localization, protein-protein interactions (PPIs)). The biomedical literature continues to be the main source of evidence for experimental information about protein phosphorylation. Automatic methods to bring together phosphorylation events and phosphorylation-dependent PPIs can help to summarize the current knowledge and to expose hidden connections. In this chapter, we demonstrate two text mining tools, RLIMS-P and eFIP, for the retrieval and extraction of kinase-substrate-site data and phosphorylation-dependent PPIs from the literature. These tools offer several advantages over a literature search in PubMed as their results are specific for phosphorylation. RLIMS-P and eFIP results can be sorted, organized, and viewed in multiple ways to answer relevant biological questions, and the protein mentions are linked to UniProt identifiers.

Protein Bioinformatics Databases and Resources

Many publicly available data repositories and resources have been developed to support protein-related information management, data-driven hypothesis generation, and biological knowledge discovery. To help researchers quickly find the appropriate protein-related informatics resources, we present a comprehensive review (with categorization and description) of major protein bioinformatics databases in this chapter. We also discuss the challenges and opportunities for developing next-generation protein bioinformatics databases and resources to support data integration and data analytics in the Big Data era.

iPTMnet: Integrative Bioinformatics for Studying PTM Networks

Protein post-translational modification (PTM) is an essential cellular regulatory mechanism, and disruptions in PTM have been implicated in disease. PTMs are an active area of study in many fields, leading to a wealth of PTM information in the scientific literature. There is a need for user-friendly bioinformatics resources that capture PTM information from the literature and support analyses of PTMs and their functional consequences. This chapter describes the use of iPTMnet ( http://proteininformationresource.org/iPTMnet/ ), a resource that integrates PTM information from text mining, curated databases, and ontologies and provides visualization tools for exploring PTM networks, PTM crosstalk, and PTM conservation across species. We present several PTM-related queries and demonstrate how they can be addressed using iPTMnet.

Citizen Science for Mining the Biomedical Literature

Biomedical literature represents one of the largest and fastest growing collections of unstructured biomedical knowledge. Finding critical information buried in the literature can be challenging. To extract information from free-flowing text, researchers need to: 1. identify the entities in the text (named entity recognition), 2. apply a standardized vocabulary to these entities (normalization), and 3. identify how entities in the text are related to one another (relationship extraction). Researchers have primarily approached these information extraction tasks through manual expert curation and computational methods. We have previously demonstrated that named entity recognition (NER) tasks can be crowdsourced to a group of non-experts via the paid microtask platform, Amazon Mechanical Turk (AMT), and can dramatically reduce the cost and increase the throughput of biocuration efforts. However, given the size of the biomedical literature, even information extraction via paid microtask platforms is not scalable. With our web-based application Mark2Cure (http://mark2cure.org), we demonstrate that NER tasks also can be performed by volunteer citizen scientists with high accuracy. We apply metrics from the Zooniverse Matrices of Citizen Science Success and provide the results here to serve as a basis of comparison for other citizen science projects. Further, we discuss design considerations, issues, and the application of analytics for successfully moving a crowdsourcing workflow from a paid microtask platform to a citizen science platform. To our knowledge, this study is the first application of citizen science to a natural language processing task.

The BioGRID interaction database: 2017 update

The Biological General Repository for Interaction Datasets (BioGRID: https://thebiogrid.org) is an open access database dedicated to the annotation and archival of protein, genetic and chemical interactions for all major model organism species and humans. As of September 2016 (build 3.4.140), the BioGRID contains 1 072 173 genetic and protein interactions, and 38 559 post-translational modifications, as manually annotated from 48 114 publications. This dataset represents interaction records for 66 model organisms and represents a 30% increase compared to the previous 2015 BioGRID update. BioGRID curates the biomedical literature for major model organism species, including humans, with a recent emphasis on central biological processes and specific human diseases. To facilitate network-based approaches to drug discovery, BioGRID now incorporates 27 501 chemical-protein interactions for human drug targets, as drawn from the DrugBank database. A new dynamic interaction network viewer allows the easy navigation and filtering of all genetic and protein interaction data, as well as for bioactive compounds and their established targets. BioGRID data are directly downloadable without restriction in a variety of standardized formats and are freely distributed through partner model organism databases and meta-databases.

Scalable Text Mining Assisted Curation of Post-Translationally Modified Proteoforms in the Protein Ontology

The Protein Ontology (PRO) defines protein classes and their interrelationships from the family to the protein form (proteoform) level within and across species. One of the unique contributions of PRO is its representation of post-translationally modified (PTM) proteoforms. However, progress in adding PTM proteoform classes to PRO has been relatively slow due to the extensive manual curation effort required. Here we report an automated pipeline for creation of PTM proteoform classes that leverages two phosphorylation-focused text mining tools (RLIMS-P, which detects mentions of kinases, substrates, and phosphorylation sites, and eFIP, which detects phosphorylation-dependent protein-protein interactions (PPIs)) and our integrated PTM database, iPTMnet. By applying this pipeline, we obtained a set of ~820 substrate-site pairs that are suitable for automated PRO term generation with literature-based evidence attribution. Inclusion of these terms in PRO will increase PRO coverage of species-specific PTM proteoforms by 50%. Many of these new proteoforms also have associated kinase and/or PPI information. Finally, we show a phosphorylation network for the human and mouse peptidyl-prolyl cis-trans isomerase (PIN1/Pin1) derived from our dataset that demonstrates the biological complexity of the information we have extracted. Our approach addresses scalability in PRO curation and will be further expanded to advance PRO representation of phosphorylated proteoforms.

Mining clinical attributes of genomic variants through assisted literature curation in Egas

The veritable deluge of biological data over recent years has led to the establishment of a considerable number of knowledge resources that compile curated information extracted from the literature and store it in structured form, facilitating its use and exploitation. In this article, we focus on the curation of inherited genetic variants and associated clinical attributes, such as zygosity, penetrance or inheritance mode, and describe the use of Egas for this task. Egas is a web-based platform for text-mining assisted literature curation that focuses on usability through modern design solutions and simple user interactions. Egas offers a flexible and customizable tool that allows defining the concept types and relations of interest for a given annotation task, as well as the ontologies used for normalizing each concept type. Further, annotations may be performed on raw documents or on the results of automated concept identification and relation extraction tools. Users can inspect, correct or remove automatic text-mining results, manually add new annotations, and export the results to standard formats. Egas is compatible with the most recent versions of Google Chrome, Mozilla Firefox, Internet Explorer and Safari and is available for use at https://demo.bmd-software.com/egas/.

Database URL: https://demo.bmd-software.com/egas/

miRTex: A Text Mining System for miRNA-Gene Relation Extraction

MicroRNAs (miRNAs) regulate a wide range of cellular and developmental processes through gene expression suppression or mRNA degradation. Experimentally validated miRNA gene targets are often reported in the literature. In this paper, we describe miRTex, a text mining system that extracts miRNA-target relations, as well as miRNA-gene and gene-miRNA regulation relations. The system achieves good precision and recall when evaluated on a literature corpus of 150 abstracts with F-scores close to 0.90 on the three different types of relations. We conducted full-scale text mining using miRTex to process all the Medline abstracts and all the full-length articles in the PubMed Central Open Access Subset. The results for all the Medline abstracts are stored in a database for interactive query and file download via the website at http://proteininformationresource.org/mirtex. Using miRTex, we identified genes potentially regulated by miRNAs in Triple Negative Breast Cancer, as well as miRNA-gene relations that, in conjunction with kinase-substrate relations, regulate the response to abiotic stress in Arabidopsis thaliana. These two use cases demonstrate the usefulness of miRTex text mining in the analysis of miRNA-regulated biological processes.

MicroRNAs (miRNAs) are an important class of RNAs that regulate a wide range of biological processes by post-transcriptional regulation of gene expression. The amount of literature describing experimentally validated miRNA targets is increasing rapidly, which poses a challenge to researchers and biocurators to stay up-to-date with the available information. Text mining methods have been used to extract miRNA-gene associated pairs and assist in curation. In this paper, we describe miRTex, a text mining system that extracts miRNA-target, miRNA-gene regulation and gene-miRNA regulation relations. We evaluate miRTex performance on two corpora, and show that the elaborate use of lexico-syntactic information and linguistic generalizations enables it to achieve the state-of-the-art performance. We have processed the all the Medline abstracts and all the full-length articles in the PubMed Central Open Access Subset with miRTex, and provide a website to access the extraction results from all the Medline abstracts. The full-scale text mining results will be a useful resource for miRNA researchers, while the miRTex tool itself can be integrated into literature-based curation pipelines. We present two use cases (for animal and plant miRNAs, respectively) that show how the full-scale text mining can be used in combination with other bioinformatics resources to gain insight into biological processes.