Personalized medicine. Closing the gap between knowledge and clinical practice.

Autoimmun Rev. 2016 Jun 11;

Authors: Anaya JM, Duarte-Rey C, Sarmiento-Monroy JC, Bardey D, Castiblanco J, Rojas-Villarraga A

Abstract
Personalized medicine encompasses a broad and evolving field informed by a patient distinctive information and biomarker profile. Although terminology is evolving and some semantic interpretations exist (e.g., personalized, individualized, precision), in a broad sense personalized medicine can be coined as: "To practice medicine as it once used to be in the past using the current biotechnological tools." A humanized approach to personalized medicine would offer the possibility of exploiting systems biology and its concept of P5 medicine, where predictive factors for developing a disease should be examined within populations in order to establish preventive measures on at-risk individuals, for whom healthcare should be personalized and participatory. Herein, the process of personalized medicine is presented together with the options that can be offered in health care systems with limited resources for diseases like rheumatoid arthritis and type 1 diabetes.

PMID: 27302209 [PubMed - as supplied by publisher]

Dynamic zonation of liver polyploidy.

Cell Tissue Res. 2016 Jun 15;

Authors: Tanami S, Ben-Moshe S, Elkayam A, Mayo A, Bahar Halpern K, Itzkovitz S

Abstract
The liver is a polyploid organ, consisting of hepatocytes with one or two nuclei each containing 2, 4, 8 or more haploid chromosome sets. The dynamic changes in the spatial distributions of polyploid classes across the liver lobule, its repeating anatomical unit, have not been characterized. Identifying these spatial patterns is important for understanding liver homeostatic and regenerative turnover, as well as potential division of labor among ploidy classes. Here, we use single molecule-based tissue imaging to reconstruct the spatial zonation profiles of liver polyploid classes in mice of different ages. We find that liver polyploidy proceeds in spatial waves, advancing more rapidly in the mid-lobule zone compared to the periportal and perivenous zones. We also measure the spatial zonation profiles of S-phase entry at different ages and identify more rapid S-phase entry in the mid-lobule zone at older ages. Our findings reveal fundamental features of liver spatial heterogeneity and highlight their dynamic changes during development and aging.

PMID: 27301446 [PubMed - as supplied by publisher]

Genomic cloud computing: legal and ethical points to consider.

Eur J Hum Genet. 2015 Oct;23(10):1271-8

Authors: Dove ES, Joly Y, Tassé AM, Public Population Project in Genomics and Society (P3G) International Steering Committee, International Cancer Genome Consortium (ICGC) Ethics and Policy Committee, Knoppers BM

Abstract
The biggest challenge in twenty-first century data-intensive genomic science, is developing vast computer infrastructure and advanced software tools to perform comprehensive analyses of genomic data sets for biomedical research and clinical practice. Researchers are increasingly turning to cloud computing both as a solution to integrate data from genomics, systems biology and biomedical data mining and as an approach to analyze data to solve biomedical problems. Although cloud computing provides several benefits such as lower costs and greater efficiency, it also raises legal and ethical issues. In this article, we discuss three key 'points to consider' (data control; data security, confidentiality and transfer; and accountability) based on a preliminary review of several publicly available cloud service providers' Terms of Service. These 'points to consider' should be borne in mind by genomic research organizations when negotiating legal arrangements to store genomic data on a large commercial cloud service provider's servers. Diligent genomic cloud computing means leveraging security standards and evaluation processes as a means to protect data and entails many of the same good practices that researchers should always consider in securing their local infrastructure.

PMID: 25248396 [PubMed - indexed for MEDLINE]

Genetic and metabolic engineering of microorganisms for the development of new flavor compounds from terpenic substrates.

Crit Rev Biotechnol. 2015;35(3):313-25

Authors: Bution ML, Molina G, Abrahão MR, Pastore GM

Abstract
Throughout human history, natural products have been the basis for the discovery and development of therapeutics, cosmetic and food compounds used in industry. Many compounds found in natural organisms are rather difficult to chemically synthesize and to extract in large amounts, and in this respect, genetic and metabolic engineering are playing an increasingly important role in the production of these compounds, such as new terpenes and terpenoids, which may potentially be used to create aromas in industry. Terpenes belong to the largest class of natural compounds, are produced by all living organisms and play a fundamental role in human nutrition, cosmetics and medicine. Recent advances in systems biology and synthetic biology are allowing us to perform metabolic engineering at the whole-cell level, thus enabling the optimal design of microorganisms for the efficient production of drugs, cosmetic and food additives. This review describes the recent advances made in the genetic and metabolic engineering of the terpenes pathway with a particular focus on systems biotechnology.

PMID: 24494701 [PubMed - indexed for MEDLINE]

12 new pubmed citations were retrieved for your search. Click on the search hyperlink below to display the complete search results:

("orphan disease" OR "rare disease" OR "orphan diseases" OR "rare diseases")

These pubmed results were generated on 2016/06/15

PubMed comprises more than 24 million citations for biomedical literature from MEDLINE, life science journals, and online books. Citations may include links to full-text content from PubMed Central and publisher web sites.

19 new pubmed citations were retrieved for your search. Click on the search hyperlink below to display the complete search results:

"Cystic Fibrosis"

These pubmed results were generated on 2016/06/15

PubMed comprises more than 24 million citations for biomedical literature from MEDLINE, life science journals, and online books. Citations may include links to full-text content from PubMed Central and publisher web sites.

FALDO: a semantic standard for describing the location of nucleotide and protein feature annotation.

J Biomed Semantics. 2016;7:39

Authors: Bolleman JT, Mungall CJ, Strozzi F, Baran J, Dumontier M, Bonnal RJ, Buels R, Hoehndorf R, Fujisawa T, Katayama T, Cock PJ

Abstract
BACKGROUND: Nucleotide and protein sequence feature annotations are essential to understand biology on the genomic, transcriptomic, and proteomic level. Using Semantic Web technologies to query biological annotations, there was no standard that described this potentially complex location information as subject-predicate-object triples.
DESCRIPTION: We have developed an ontology, the Feature Annotation Location Description Ontology (FALDO), to describe the positions of annotated features on linear and circular sequences. FALDO can be used to describe nucleotide features in sequence records, protein annotations, and glycan binding sites, among other features in coordinate systems of the aforementioned "omics" areas. Using the same data format to represent sequence positions that are independent of file formats allows us to integrate sequence data from multiple sources and data types. The genome browser JBrowse is used to demonstrate accessing multiple SPARQL endpoints to display genomic feature annotations, as well as protein annotations from UniProt mapped to genomic locations.
CONCLUSIONS: Our ontology allows users to uniformly describe - and potentially merge - sequence annotations from multiple sources. Data sources using FALDO can prospectively be retrieved using federalised SPARQL queries against public SPARQL endpoints and/or local private triple stores.

PMID: 27296299 [PubMed - in process]

Review on Pharmacogenetics and Pharmacogenomics Applied to the Study of Asthma.

Methods Mol Biol. 2016;1434:255-272

Authors: Sánchez-Martín A, García-Sánchez A, Isidoro-García M

Abstract
Nearly one-half of asthmatic patients do not respond to the most common therapies. Evidence suggests that genetic factors may be involved in the heterogeneity in therapeutic response and adverse events to asthma therapies. We focus on the three major classes of asthma medication: β-adrenergic receptor agonist, inhaled corticosteroids, and leukotriene modifiers. Pharmacogenetics and pharmacogenomics studies have identified several candidate genes associated with drug response.In this chapter, the main pharmacogenetic and pharmacogenomic studies in addition to the future perspectives in personalized medicine will be reviewed. The ideal treatment of asthma would be a tailored approach to health care in which adverse effects are minimized and the therapeutic benefit for an individual asthmatic is maximized leading to a more cost-effective care.

PMID: 27300544 [PubMed - as supplied by publisher]

Verification of five pharmacogenomics-based warfarin administration models.

Indian J Pharmacol. 2016 May-Jun;48(3):258-63

Authors: Lin M, Yu L, Qiu H, Wang Q, Zhang J, Song H

Abstract
OBJECTIVE: This study aims to screen and validate five individual warfarin dosing models (four Asian model algorithms, namely, Ohno, Wen, Miao, Huang, and the algorithm of International Warfarin Pharmacogenetic Consortium, namely IWPC algorithm) with the aim of evaluating their accuracy, practicality, and safety.
MATERIALS AND METHODS: Patients' CYP2C9*3 and VKORC1-1639G >A genes were genotyped, and patient-related information and steady warfarin doses were recorded. The difference between the predicted dose and actual maintenance dose of each model was compared.
RESULTS: The prediction accuracies of the Huang and Wen models were the highest. In terms of clinical practicality, the Huang model rated the highest for the low-dose group, whereas the Ohno and IWPC models rated the highest for the middle-dose group. The models tended to markedly overpredict the doses in the low-dose group, especially the IWPC model. The Miao model tended to severely underpredict the doses in the middle-dose group, whereas no model exhibited severe overprediction.
CONCLUSIONS: Since none of the models ranked high for all the three criteria considered, the impact of various factors should be thoroughly considered before selecting the most appropriate model for the region's population.

PMID: 27298494 [PubMed - in process]

Individualized network-based drug repositioning infrastructure for precision oncology in the panomics era.

Brief Bioinform. 2016 Jun 12;

Authors: Cheng F, Hong H, Yang S, Wei Y

Abstract
Advances in next-generation sequencing technologies have generated the data supporting a large volume of somatic alterations in several national and international cancer genome projects, such as The Cancer Genome Atlas and the International Cancer Genome Consortium. These cancer genomics data have facilitated the revolution of a novel oncology drug discovery paradigm from candidate target or gene studies toward targeting clinically relevant driver mutations or molecular features for precision cancer therapy. This focuses on identifying the most appropriately targeted therapy to an individual patient harboring a particularly genetic profile or molecular feature. However, traditional experimental approaches that are used to develop new chemical entities for targeting the clinically relevant driver mutations are costly and high-risk. Drug repositioning, also known as drug repurposing, re-tasking or re-profiling, has been demonstrated as a promising strategy for drug discovery and development. Recently, computational techniques and methods have been proposed for oncology drug repositioning and identifying pharmacogenomics biomarkers, but overall progress remains to be seen. In this review, we focus on introducing new developments and advances of the individualized network-based drug repositioning approaches by targeting the clinically relevant driver events or molecular features derived from cancer panomics data for the development of precision oncology drug therapies (e.g. one-person trials) to fully realize the promise of precision medicine. We discuss several potential challenges (e.g. tumor heterogeneity and cancer subclones) for precision oncology. Finally, we highlight several new directions for the precision oncology drug discovery via biotherapies (e.g. gene therapy and immunotherapy) that target the 'undruggable' cancer genome in the functional genomics era.

PMID: 27296652 [PubMed - as supplied by publisher]

Resolving the etiology of atopic disorders by using genetic analysis of racial ancestry.

J Allergy Clin Immunol. 2016 Jun 10;

Authors: Gupta J, Johansson E, Bernstein JA, Chakraborty R, Khurana Hershey GK, Rothenberg ME, Mersha TB

Abstract
Atopic dermatitis (AD), food allergy, allergic rhinitis, and asthma are common atopic disorders of complex etiology. The frequently observed atopic march from early AD to asthma, allergic rhinitis, or both later in life and the extensive comorbidity of atopic disorders suggest common causal mechanisms in addition to distinct ones. Indeed, both disease-specific and shared genomic regions exist for atopic disorders. Their prevalence also varies among races; for example, AD and asthma have a higher prevalence in African Americans when compared with European Americans. Whether this disparity stems from true genetic or race-specific environmental risk factors or both is unknown. Thus far, the majority of the genetic studies on atopic diseases have used populations of European ancestry, limiting their generalizability. Large-cohort initiatives and new analytic methods, such as admixture mapping, are currently being used to address this knowledge gap. Here we discuss the unique and shared genetic risk factors for atopic disorders in the context of ancestry variations and the promise of high-throughput "-omics"-based systems biology approach in providing greater insight to deconstruct their genetic and nongenetic etiologies. Future research will also focus on deep phenotyping and genotyping of diverse racial ancestry, gene-environment, and gene-gene interactions.

PMID: 27297995 [PubMed - as supplied by publisher]

Can stable isotope mass spectrometry replace ‎radiolabelled approaches in metabolic studies?

Plant Sci. 2016 Aug;249:59-69

Authors: Batista Silva W, Daloso DM, Fernie AR, Nunes-Nesi A, Araújo WL

Abstract
Metabolic pathways and the key regulatory points thereof can be deduced using isotopically labelled substrates. One prerequisite is the accurate measurement of the labeling pattern of targeted metabolites. The subsequent estimation of metabolic fluxes following incubation in radiolabelled substrates has been extensively used. Radiolabelling is a sensitive approach and allows determination of total label uptake since the total radiolabel content is easy to detect. However, the incubation of cells, tissues or the whole plant in a stable isotope enriched environment and the use of either mass spectrometry or nuclear magnetic resonance techniques to determine label incorporation within specific metabolites offers the possibility to readily obtain metabolic information with higher resolution. It additionally also offers an important complement to other post-genomic strategies such as metabolite profiling providing insights into the regulation of the metabolic network and thus allowing a more thorough description of plant cellular function. Thus, although safety concerns mean that stable isotope feeding is generally preferred, the techniques are in truth highly complementary and application of both approaches in tandem currently probably provides the best route towards a comprehensive understanding of plant cellular metabolism.

PMID: 27297990 [PubMed - in process]

Next generation sequencing technology and genomewide data analysis: Perspectives for retinal research.

Prog Retin Eye Res. 2016 Jun 10;

Authors: Chaitankar V, Karakülah G, Ratnapriya R, Giuste FO, Brooks MJ, Swaroop A

Abstract
The advent of high throughput next generation sequencing (NGS) has accelerated the pace of discovery of disease-associated genetic variants and genomewide profiling of expressed sequences and epigenetic marks, thereby permitting systems-based analyses of ocular development and disease. Rapid evolution of NGS and associated methodologies presents significant challenges in acquisition, management, and analysis of large data sets and for extracting biologically or clinically relevant information. Here we illustrate the basic design of commonly used NGS-based methods, specifically whole exome sequencing, transcriptome, and epigenome profiling, and provide recommendations for data analyses. We briefly discuss systems biology approaches for integrating multiple data sets to elucidate gene regulatory or disease networks. While we provide examples from the retina, the NGS guidelines reviewed here are applicable to other tissues/cell types as well.

PMID: 27297499 [PubMed - as supplied by publisher]

Differential integrative omic analysis for mechanism insights and biomarker discovery of abnormal Savda syndrome and its unique Munziq prescription.

Sci Rep. 2016;6:27831

Authors: Guo X, Bakri I, Abudula A, Arken K, Mijit M, Mamtimin B, Upur H

Abstract
Research has shown that many cancers have acommon pathophysiological origin and often present with similar symptoms. In terms of Traditional Uighur Medicine (TUM) Hilit (body fluid) theory, abnormal Savda syndrome (ASS) formed by abnormal Hilit is the common phenotype of complex diseases and in particular tumours. Abnormal Savda Munziq (ASMq), one representative of TUM, has been effective in the treatment of cancer since ancient times. Despite the physiopathology of ASS, the relationship between causative factors and the molecular mechanism of ASMq are not fully understood. The current study expanded upon earlier work by integrating traditional diagnostic approaches with others utilizing systems biology technology for the analysis of proteomic (iTRAQ) and metabolomic ((1)H-NMR) profiles of Uighur Medicine target organ lesion (liver) tumours. The candidate proteins were analyzed by enrichment analysis of the biological process and biomarker filters. Subsequently, 3Omics web-based tools were used to determine the relationships between proteins and appropriate metabolites. ELISA assay and IHC methods were used to verify the proteomic result; the protein von Willebrand factor (vWF) may be the "therapeutic window" of ASMq and biomarkers of ASS. This study is likely to be of great significance for the standardization and modernization of TUM.

PMID: 27296761 [PubMed - in process]

Individualized network-based drug repositioning infrastructure for precision oncology in the panomics era.

Brief Bioinform. 2016 Jun 12;

Authors: Cheng F, Hong H, Yang S, Wei Y

Abstract
Advances in next-generation sequencing technologies have generated the data supporting a large volume of somatic alterations in several national and international cancer genome projects, such as The Cancer Genome Atlas and the International Cancer Genome Consortium. These cancer genomics data have facilitated the revolution of a novel oncology drug discovery paradigm from candidate target or gene studies toward targeting clinically relevant driver mutations or molecular features for precision cancer therapy. This focuses on identifying the most appropriately targeted therapy to an individual patient harboring a particularly genetic profile or molecular feature. However, traditional experimental approaches that are used to develop new chemical entities for targeting the clinically relevant driver mutations are costly and high-risk. Drug repositioning, also known as drug repurposing, re-tasking or re-profiling, has been demonstrated as a promising strategy for drug discovery and development. Recently, computational techniques and methods have been proposed for oncology drug repositioning and identifying pharmacogenomics biomarkers, but overall progress remains to be seen. In this review, we focus on introducing new developments and advances of the individualized network-based drug repositioning approaches by targeting the clinically relevant driver events or molecular features derived from cancer panomics data for the development of precision oncology drug therapies (e.g. one-person trials) to fully realize the promise of precision medicine. We discuss several potential challenges (e.g. tumor heterogeneity and cancer subclones) for precision oncology. Finally, we highlight several new directions for the precision oncology drug discovery via biotherapies (e.g. gene therapy and immunotherapy) that target the 'undruggable' cancer genome in the functional genomics era.

PMID: 27296652 [PubMed - as supplied by publisher]

A Systems Biology Approach to Reveal Putative Host-Derived Biomarkers of Periodontitis by Network Topology Characterization of MMP-REDOX/NO and Apoptosis Integrated Pathways.

Front Cell Infect Microbiol. 2015;5:102

Authors: Zeidán-Chuliá F, Gürsoy M, Neves de Oliveira BH, Özdemir V, Könönen E, Gürsoy UK

Abstract
Periodontitis, a formidable global health burden, is a common chronic disease that destroys tooth-supporting tissues. Biomarkers of the early phase of this progressive disease are of utmost importance for global health. In this context, saliva represents a non-invasive biosample. By using systems biology tools, we aimed to (1) identify an integrated interactome between matrix metalloproteinase (MMP)-REDOX/nitric oxide (NO) and apoptosis upstream pathways of periodontal inflammation, and (2) characterize the attendant topological network properties to uncover putative biomarkers to be tested in saliva from patients with periodontitis. Hence, we first generated a protein-protein network model of interactions ("BIOMARK" interactome) by using the STRING 10 database, a search tool for the retrieval of interacting genes/proteins, with "Experiments" and "Databases" as input options and a confidence score of 0.400. Second, we determined the centrality values (closeness, stress, degree or connectivity, and betweenness) for the "BIOMARK" members by using the Cytoscape software. We found Ubiquitin C (UBC), Jun proto-oncogene (JUN), and matrix metalloproteinase-14 (MMP14) as the most central hub- and non-hub-bottlenecks among the 211 genes/proteins of the whole interactome. We conclude that UBC, JUN, and MMP14 are likely an optimal candidate group of host-derived biomarkers, in combination with oral pathogenic bacteria-derived proteins, for detecting periodontitis at its early phase by using salivary samples from patients. These findings therefore have broader relevance for systems medicine in global health as well.

PMID: 26793622 [PubMed - indexed for MEDLINE]

Changes in lipid metabolism and β-adrenergic response of adipose tissues of periparturient dairy cows affected by an energy-dense diet and nicotinic acid supplementation.

J Anim Sci. 2015 Aug;93(8):4012-22

Authors: Kenéz Á, Tienken R, Locher L, Meyer U, Rizk A, Rehage J, Dänicke S, Huber K

Abstract
Dairy cattle will mobilize large amounts of body fat during early lactation as an effect of decreased lipogenesis and increased lipolysis. Regulation of lipid metabolism involves fatty acid synthesis from acetate and β-adrenergic-stimulated phosphorylation of hormone-sensitive lipase (HSL) and perilipin in adipocytes. Although basic mechanisms of mobilizing fat storage in transition cows are understood, we lack a sufficiently detailed understanding to declare the exact regulatory network of these in a broad range of dairy cattle. The objective of the present study was to quantify 1) protein abundance of fatty acid synthase (FAS), 2) extent of phosphorylation of HSL and perilipin in vivo, and 3) β-adrenergic stimulated lipolytic response of adipose tissues in vitro at different stages of the periparturient period. We fed 20 German Holstein cows an energy-dense or an energetically adequate diet prepartum and 0 or 24 g/d nicotinic acid (NA) supplementation. Biopsy samples of subcutaneous and retroperitoneal adipose tissue were obtained at d 42 prepartum (d -42) and at d 1, 21, and 100 postpartum (d +1, d +21, d +100, respectively). To assess β-adrenergic response, tissue samples were incubated with 1 μ isoproterenol for 90 min at 37°C. The NEFA and glycerol release, as well as HSL and perilipin phosphorylation, was measured as indicators of in vitro stimulated lipolysis. In addition, protein expression of FAS and extent of HSL and perilipin phosphorylation were measured in fresh, nonincubated samples. There was no effect of dietary energy density or NA on the observed variables. The extent of HSL and perilipin phosphorylation under isoproterenol stimulation was strongly correlated with the release of NEFA and glycerol, consistent with the functional link between β-adrenergic-stimulated protein phosphorylation and lipolysis. In the nonincubated samples, FAS protein expression was decreased at d +1 and d +21, whereas HSL and perilipin phosphorylation increased from d -42 to d +1 and remained at an increased level throughout the first 100 d of lactation. In vitro lipolytic response was significant in prepartum samples at times when in vivo lipolysis was only minimally activated by phosphorylation. These data extend our understanding of the complex nature of control of lipolysis and lipogenesis in dairy cows and could be useful to the ongoing development of systems biology models of metabolism to help improve our quantitative knowledge of the cow.

PMID: 26440181 [PubMed - indexed for MEDLINE]

Systematic Mapping of Kinase Addiction Combinations in Breast Cancer Cells by Integrating Drug Sensitivity and Selectivity Profiles.

Chem Biol. 2015 Aug 20;22(8):1144-55

Authors: Szwajda A, Gautam P, Karhinen L, Jha SK, Saarela J, Shakyawar S, Turunen L, Yadav B, Tang J, Wennerberg K, Aittokallio T

Abstract
Chemical perturbation screens offer the possibility to identify actionable sets of cancer-specific vulnerabilities. However, most inhibitors of kinases or other cancer targets result in polypharmacological effects, which complicate the identification of target dependencies directly from the drug-response phenotypes. In this study, we developed a chemical systems biology approach that integrates comprehensive drug sensitivity and selectivity profiling to provide functional insights into both single and multi-target oncogenic signal addictions. When applied to 21 breast cancer cell lines, perturbed with 40 kinase inhibitors, the subtype-specific addiction patterns clustered in agreement with patient-derived subtypes, while showing considerable variability between the heterogeneous breast cancers. Experimental validation of the top predictions revealed a number of co-dependencies between kinase targets that led to unexpected synergistic combinations between their inhibitors, such as dasatinib and axitinib in the triple-negative basal-like HCC1937 cell line.

PMID: 26211361 [PubMed - indexed for MEDLINE]

DermO; an ontology for the description of dermatologic disease.

J Biomed Semantics. 2016;7:38

Authors: Fisher HM, Hoehndorf R, Bazelato BS, Dadras SS, King LE, Gkoutos GV, Sundberg JP, Schofield PN

Abstract
BACKGROUND: There have been repeated initiatives to produce standard nosologies and terminologies for cutaneous disease, some dedicated to the domain and some part of bigger terminologies such as ICD-10. Recently, formally structured terminologies, ontologies, have been widely developed in many areas of biomedical research. Primarily, these address the aim of providing comprehensive working terminologies for domains of knowledge, but because of the knowledge contained in the relationships between terms they can also be used computationally for many purposes.
RESULTS: We have developed an ontology of cutaneous disease, constructed manually by domain experts. With more than 3000 terms, DermO represents the most comprehensive formal dermatological disease terminology available. The disease entities are categorized in 20 upper level terms, which use a variety of features such as anatomical location, heritability, affected cell or tissue type, or etiology, as the features for classification, in line with professional practice and nosology in dermatology. Available in OBO flatfile and OWL 2 formats, it is integrated semantically with other ontologies and terminologies describing diseases and phenotypes. We demonstrate the application of DermO to text mining the biomedical literature and in the creation of a network describing the phenotypic relationships between cutaneous diseases.
CONCLUSIONS: DermO is an ontology with broad coverage of the domain of dermatologic disease and we demonstrate here its utility for text mining and investigation of phenotypic relationships between dermatologic disorders. We envision that in the future it may be applied to the creation and mining of electronic health records, clinical training and basic research, as it supports automated inference and reasoning, and for the broader integration of skin disease information with that from other domains.

PMID: 27296450 [PubMed - in process]

A Relation Extraction Framework for Biomedical Text Using Hybrid Feature Set.

Comput Math Methods Med. 2015;2015:910423

Authors: Muzaffar AW, Azam F, Qamar U

Abstract
The information extraction from unstructured text segments is a complex task. Although manual information extraction often produces the best results, it is harder to manage biomedical data extraction manually because of the exponential increase in data size. Thus, there is a need for automatic tools and techniques for information extraction in biomedical text mining. Relation extraction is a significant area under biomedical information extraction that has gained much importance in the last two decades. A lot of work has been done on biomedical relation extraction focusing on rule-based and machine learning techniques. In the last decade, the focus has changed to hybrid approaches showing better results. This research presents a hybrid feature set for classification of relations between biomedical entities. The main contribution of this research is done in the semantic feature set where verb phrases are ranked using Unified Medical Language System (UMLS) and a ranking algorithm. Support Vector Machine and Naïve Bayes, the two effective machine learning techniques, are used to classify these relations. Our approach has been validated on the standard biomedical text corpus obtained from MEDLINE 2001. Conclusively, it can be articulated that our framework outperforms all state-of-the-art approaches used for relation extraction on the same corpus.

PMID: 26347797 [PubMed - indexed for MEDLINE]