Text Mining Of Biomedical Literature Research Articles

A Novel Text-Mining Approach for Retrieving Pharmacogenomics Associations From the Literature.

Text mining in biomedical literature is an emerging field which has already been shown to have a variety of implementations in many research areas, including genetics, personalized medicine, and pharmacogenomics. In this study, we describe a novel text-mining approach for the extraction of pharmacogenomics associations. The code that was used toward this end was implemented using R programming language, either through custom scripts, where needed, or through utilizing functions from existing libraries. Articles (abstracts or full texts) that correspond to a specified query were extracted from PubMed, while concept annotations were derived by PubTator Central. Terms that denote a Mutation or a Gene as well as Chemical compound terms corresponding to drug compounds were normalized and the sentences containing the aforementioned terms were filtered and preprocessed to create appropriate training sets. Finally, after training and adequate hyperparameter tuning, four text classifiers were created and evaluated (FastText, Linear kernel SVMs, XGBoost, Lasso, and Elastic-Net Regularized Generalized Linear Models) with regard to their performance in identifying pharmacogenomics associations. Although further improvements are essential toward proper implementation of this text-mining approach in the clinical practice, our study stands as a comprehensive, simplified, and up-to-date approach for the identification and assessment of research articles enriched in clinically relevant pharmacogenomics relationships. Furthermore, this work highlights a series of challenges concerning the effective application of text mining in biomedical literature, whose resolution could substantially contribute to the further development of this field.

Improving SNP prioritization and pleiotropic architecture estimation by incorporating prior knowledge using graph-GPA.

Integration of genetic studies for multiple phenotypes is a powerful approach to improving the identification of genetic variants associated with complex traits. Although it has been shown that leveraging shared genetic basis among phenotypes, namely pleiotropy, can increase statistical power to identify risk variants, it remains challenging to effectively integrate genome-wide association study (GWAS) datasets for a large number of phenotypes. We previously developed graph-GPA, a Bayesian hierarchical model that integrates multiple GWAS datasets to boost statistical power for the identification of risk variants and to estimate pleiotropic architecture within a unified framework. Here we propose a novel improvement of graph-GPA which incorporates external knowledge about phenotype-phenotype relationship to guide the estimation of genetic correlation and the association mapping. The application of graph-GPA to GWAS datasets for 12 complex diseases with a prior disease graph obtained from a text mining of biomedical literature illustrates its power to improve the identification of risk genetic variants and to facilitate understanding of genetic relationship among complex diseases. graph-GPA is implemented as an R package 'GGPA', which is publicly available at http://dongjunchung.github.io/GGPA/. DDNet, a web interface to query diseases of interest and download a prior disease graph obtained from a text mining of biomedical literature, is publicly available at http://www.chunglab.io/ddnet/. Supplementary data are available at Bioinformatics online.

Abstract LB-114: Monogenic autoimmune diseases as a starting point for new immunooncology targets

Abstract Cyclic dinucleotide (CDN) analogs and small molecule agonists of STING (STimulator of INterferon Genes protein) are currently being developed as immuno-oncology agents based on their ability to stimulate potent anti-tumoral responses in the tumor micro-environment (TME) (1,2). STING agonists act primarily on APCs such as dendritic cells (DCs), resulting in enhanced type I interferon signalling and resulting cytotoxic T cell (CTL) responses (3). Germline gain of function mutations in STING (gene name TMEM173) exist and cause the rare disease SAVI (4). Patients with SAVI present as infants with symptoms such as chronic rash, lesions, and systemic inflammation and eventually succumb to more serious complications such as lung disease. At the functional level, they display elevated levels of interferon responsive genes indicative of constitutive STING activation. Thus, while chronic agonism of this pathway leads to an autoimmune/autoinflammatory phenotype, acute dosing has benefit in a tumor setting as an immunological stimulant. We designed an in silico approach to identify other genes with the same potential disease/phenotype profile as STING. We combined knowledge of Mendelian disease genetics with pathway phenotype associations such as involvement in immune cell anergy, activation, costimulation, chemotaxis, and migration. In addition, we determined a putative set of genes associated with immune privileged sites by combining textmining of biomedical literature with mRNA gene expression analysis. Taken together, these approaches provided a list of potential immuno-oncology targets that also included several well-known targets such as CTLA4, ICOS, and OX40 which are either approved or in clinical trials as immuno-oncology agents. This list was then manually curated and prioritized based on literature, and will be functionally validated in ongoing experimental systems.

An Active Co-Training Algorithm for Biomedical Named-Entity Recognition

Exploiting unlabeled text data with a relatively small labeled corpus has been an active and challenging research topic in text mining, due to the recent growth of the amount of biomedical literature. Biomedical named-entity recognition is an essential prerequisite task before effective text mining of biomedical literature can begin. This paper proposes an Active Co-Training (ACT) algorithm for biomedical named-entity recognition. ACT is a semi-supervised learning method in which two classifiers based on two different feature sets iteratively learn from informative examples that have been queried from the unlabeled data. We design a new classification problem to measure the informativeness of an example in unlabeled data. In this classification problem, the examples are classified based on a joint view of a feature set to be informative/non-informative to both classifiers. To form the training data for the classification problem, we adopt a query-by-committee method. Therefore, in the ACT, both classifiers are considered to be one committee, which is used on the labeled data to give the informativeness label to each example. The ACT method outperforms the traditional co-training algorithm in terms of f-measure as well as the number of training iterations performed to build a good classification model. The proposed method tends to efficiently exploit a large amount of unlabeled data by selecting a small number of examples having not only useful information but also a comprehensive pattern.

ChemTextMiner: An open source tool kit for mining medical literature abstracts

Text mining involves recognizing patterns from a wealth of information hidden latent in unstructured text and deducing explicit relationships among data entities by using data mining tools. Text mining of Biomedical literature is essential for building biological network connecting genes, proteins, drugs, therapeutic categories, side effects etc. related to diseases of interest. We present an approach for textmining biomedical literature mostly in terms of not so obvious hidden relationships and build biological network applied for the textmining of important human diseases like MTB, Malaria, Alzheimer and Diabetes. The methods, tools and data used for building biological networks using a distributed computing environment previously used for ChemXtreme[1] and ChemStar[2] applications are also described.

ChemTextMiner: An open source tool kit for mining medical literature abstracts

AbstractText mining involves recognizing patterns from a wealth of information hidden latent in unstructured text and deducing explicit relationships among data entities by using data mining tools. Text mining of Biomedical literature is essential for building biological network connecting genes, proteins, drugs, therapeutic categories, side effects etc. related to diseases of interest. We present an approach for textmining biomedical literature mostly in terms of not so obvious hidden relationships and build biological network applied for the textmining of important human diseases like MTB, Malaria, Alzheimer and Diabetes. The methods, tools and data used for building biological networks using a distributed computing environment previously used for ChemXtreme[1] and ChemStar[2] applications are also described.

Combining multiple disambiguation methods for gene mention normalization

The rapid growth of biomedical literature prompts pervasive concentrations of biomedical text mining community to explore methodology for accessing and managing this ever-increasing knowledge. One important task of text mining in biomedical literature is gene mention normalization which recognizes the biomedical entities in biomedical texts and maps each gene mention discussed in the text to unique organic database identifiers. In this work, we employ an information retrieval based method which extracts gene mention’s semantic profile from PubMed abstracts for gene mention disambiguation. This disambiguation method focuses on generating a more comprehensive representation of gene mention rather than the organic clues such as gene ontology which has fewer co-occurrences with the gene mention. Furthermore, we use an existing biomedical resource as another disambiguation method. Then we extract features from gene mention detection system’s outcome to build a false positive filter according to Wikipedia’s retrieved documents. Our system achieved F-measure of 83.1% on BioCreative II GN test data.

Incorporating rich background knowledge for gene named entity classification and recognition

BackgroundGene named entity classification and recognition are crucial preliminary steps of text mining in biomedical literature. Machine learning based methods have been used in this area with great success. In most state-of-the-art systems, elaborately designed lexical features, such as words, n-grams, and morphology patterns, have played a central part. However, this type of feature tends to cause extreme sparseness in feature space. As a result, out-of-vocabulary (OOV) terms in the training data are not modeled well due to lack of information.ResultsWe propose a general framework for gene named entity representation, called feature coupling generalization (FCG). The basic idea is to generate higher level features using term frequency and co-occurrence information of highly indicative features in huge amount of unlabeled data. We examine its performance in a named entity classification task, which is designed to remove non-gene entries in a large dictionary derived from online resources. The results show that new features generated by FCG outperform lexical features by 5.97 F-score and 10.85 for OOV terms. Also in this framework each extension yields significant improvements and the sparse lexical features can be transformed into both a lower dimensional and more informative representation. A forward maximum match method based on the refined dictionary produces an F-score of 86.2 on BioCreative 2 GM test set. Then we combined the dictionary with a conditional random field (CRF) based gene mention tagger, achieving an F-score of 89.05, which improves the performance of the CRF-based tagger by 4.46 with little impact on the efficiency of the recognition system. A demo of the NER system is available at .

BioNMF: a versatile tool for non-negative matrix factorization in biology.

BackgroundIn the Bioinformatics field, a great deal of interest has been given to Non-negative matrix factorization technique (NMF), due to its capability of providing new insights and relevant information about the complex latent relationships in experimental data sets. This method, and some of its variants, has been successfully applied to gene expression, sequence analysis, functional characterization of genes and text mining. Even if the interest on this technique by the bioinformatics community has been increased during the last few years, there are not many available simple standalone tools to specifically perform these types of data analysis in an integrated environment.ResultsIn this work we propose a versatile and user-friendly tool that implements the NMF methodology in different analysis contexts to support some of the most important reported applications of this new methodology. This includes clustering and biclustering gene expression data, protein sequence analysis, text mining of biomedical literature and sample classification using gene expression. The tool, which is named bioNMF, also contains a user-friendly graphical interface to explore results in an interactive manner and facilitate in this way the exploratory data analysis process.ConclusionbioNMF is a standalone versatile application which does not require any special installation or libraries. It can be used for most of the multiple applications proposed in the bioinformatics field or to support new research using this method. This tool is publicly available at .

Guest Editors' Introduction: Special Issue on Mining Biological Data

MINING biological data is an emerging area of intersection between data mining and bioinformatics. Bioinformaticians have been working on the research and development of computational methodologies and tools for expanding the use of biological, medical, behavioral, or health-related data. Data mining researchers have been making substantial contribution to the development of models and algorithms to meet challenges posed by the bioinformatics research. Some successful examples are frequent pattern discovery on biological molecules, text mining in biomedical literature, information integration, probabilistic modeling of genome sequences, etc. This special issue of the IEEE Transactions on Knowledge and Data Engineering features a collection of 11 papers, selected from 54 submissions, representing recent advances at the frontier of mining biological data. Mining frequent trees is very useful in bioinformatics applications. The first paper, “Efficiently Mining Frequent Trees in a Forest: Algorithms and Applications” by Mohammed J. Zaki, formulates the problem of mining (embedded) subtrees in a forest of rooted, labeled, and ordered trees. The author presents TreeMiner, a novel algorithm to discover all frequent subtrees in a forest, using a new data structure called scope-list. TreeMiner has been proven to be superior to previous methods such as PatternMatcher and has shown promising results in analyzing RNA structure and phylogenetics data sets. In the second paper, “Frequent Substructure-Based Approaches for Classifying Chemical Compounds” by Mukund Deshpande, Michihiro Kuramochi, Nikil Wale, and George Karypis, the authors devise a substructurebased classification algorithm that decouples the substructure discovery process from the classification model construction and uses frequent subgraph discovery algorithms to find all topological and geometric substructures present in the data set. The advantage of this approach is that, during classification model construction, all relevant substructures are available and thus allow the classifier to intelligently select the most discriminating ones. This approach is employed to build models to correctly assign chemical compounds to various classes of interests, which have many applications in pharmaceutical research and are used extensively at various phases during the drug development process. Glycans, or carbohydrate sugar chains, are regarded as the third class of biological molecules, subsequent to DNA and proteins, and the recent advent of glycome informatics has generated an increasing number of glycan structures and annotation data. Glycans play important roles in the development and functioning of multicellular organisms and their structures can be represented by labeled ordered trees. The third paper, “A Probabilistic Model for Mining Labeled Ordered Trees: Capturing Patterns in Carbohydrate Sugar Chains” byNobuhisaUeda, Kiyoko F. Aoki-Kinoshita, Atsuko Yamaguchi, Tatsuya Akustu, and Hiroshi Mamitsuka, proposes a probabilistic model for mining labeled ordered trees and an EM algorithm for efficient learning. Proteins are the machinery of life. A number of techniques have been developed to classify proteins according to important features in their sequences, secondary structures, or three-dimensional structures. The fourth paper, “Finding Patterns on Protein Surfaces: Algorithms and Applications to Protein Classification” by Xiong Wang, introduces a novel approach to protein classification based on significant geometric patterns on the surface of a protein. The binding in protein-protein interactions exhibits a kind of biochemical stability in cells, which can be described by the mathematical notion of the fixed points. In the fifth paper, “Using Fixed Point Theorems to Model the Binding in Protein-Protein Interactions” by Jinyan Li and Haiquan Li, the authors define a point as a protein motif pair consisting of two traditional protein motifs. They propose a method to discover stable motif pairs of a given function from a large protein interaction sequence data set. With the rapid growth of articles on genomics research, it has become a challenge for biomedical researchers to access this ever-increasing quantity of information to understand the newest discovery of functions of proteins they are studying. To facilitate functional annotation of proteins by utilizing the huge amounts of biomedical literature and transforming the knowledge into easily accessible database formats, the text mining technique thus becomes essential. The sixth paper, “Literature Extraction of Protein Functions Using Sentence Pattern Mining” by Jung-Hsien Chiang and Hsu-Chun Yu, proposes the method of sentence pattern mining to extract protein functions from biomedical literature. Identifying concepts that have already been patented is essential for undertaking new biomedical research. Traditional keyword-based search on patent databases may not be sufficient enough to retrieve all the relevant information, especially for the biomedical domain. The seventh paper, “Information Retrieval and Knowledge Discovery Utilizing a BioMedical Patent Semantic Web” by Sougata Mukherjea, Bhuvan Bamba, and Pankaj Kankar, presents BioPatentMiner, a system that facilitates information retrieval and knowledge discovery from biomedical patents. BioPatentMiner first identifies biological terms IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, VOL. 17, NO. 8, AUGUST 2005 1019