Biomolecular Relationships Discovered from Biological Labyrinth and Lost in Ocean of Literature: Community Efforts Can Rescue Until Automated Artificial Intelligence Takes Over

摘要

Many brilliant minds are at work to decipher the biological labyrinth and as a result immense amount of information about biological entities and their relationships is getting accumulated in the form of published literature (Hunter and Cohen, 2006 ). To cater the needs of a researcher, many tools are designed to perform tasks of Named Entity Recognition (NER), Information Retrieval (IR), and Information Extraction (IE) viz. A Combined Clinical Concept Annotator (Kang et al., 2012 ), BANNER (Leaman and Gonzalez, 2008 ), Biblio-MetReS (Usie et al., 2014 ), BioTextQuest+ (Papanikolaou et al., 2014 ), BIOSMILE Web Search (Dai et al., 2008 ), E3Miner (Lee et al., 2008 ), EBIMed (Rebholz-Schuhmann et al., 2007 ), eFIP (Arighi et al., 2011 ), FACTA+ (Tsuruoka et al., 2008 ), GNSuite ~(1) , iHOP (Hoffmann and Valencia, 2004 ), MyMiner (Salgado et al., 2012 ), RLIMS-P(Hu et al., 2005 ), Anni (Jelier et al., 2008 ), CoPub (Frijters et al., 2008 ), MedScan (Novichkova et al., 2003 ), PPInterFinder (Raja et al., 2012 ), pGenN (Ding et al., 2015 ), SciMiner (Hur et al., 2009 ), BIGNER (Li et al., 2009 ), hybrid named entity tagger (Raja et al., 2014 ), and more such tools can be obtained from BIONLP resource ~(2) and in detail analysis of many NLP tools is given by Krallinger et al. ( 2008 ) and Fleuren and Alkema ( 2015 ). Table 1 gives an informational and statistical insight into some of these literature mining tools, shedding light on their efficiency translated by statistical parameters viz. F-score, recall, and precision. Many tools are domain specific like kinase family specific but still calls for human intervention for exactitude and thus limit their usage. Moreover, the data output formats are sometimes too vague as name highlighting; to be put to use for bigger literature searches. Table 1 Informational (viz. data used, parameters for evaluation and working platform) and statistical (viz. f -value, recall and precision) insights for a few literature mining tools with their brief description and links to the tools' home page . Tool Event/Data used Parameters Platform F -value (%) Recall (%) Precision (%) Link Description A Combined Clinical Concept Annotator (Kang et al., 2012 ) i2b2 challenge Concept exact match task Web ~(**) 82.1 81.2 83.3 http://www.biosemantics.org/ACCCA_WEB Concept annotation system for clinical records Banner (Leaman and Gonzalez, 2008 ) BioCreative 2 GM task NER Desktop 81.96 79.06 85.09 http://banner.sourceforge.net Named entity recognition system, primarily intended for biomedical text Biblio-MetReS (Usie et al., 2014 ) Literature Databases and Journals Biological entities and relationships Desktop 37 27 ~(*) 58 http://metres.udl.cat/ To reconstruct networks from an always up to date set of scientific documents BIOSMILE Web Search (Dai et al., 2008 ) BioCreAtIvE II GM tagging task and IAS task NER and PPI article classifier Web ~(**) 85.76 89.12 82.59 http://bws.iis.sinica.edu.tw/BWS/ Analyze articles for selected biomedical verbs and lists abstracts along with snippets by order of relevancy to protein–protein interaction E3Miner (Lee et al., 2008 ) 100 random abstracts E3 related data Web 8 ~(*) 74 97 http://e3miner.biopathway.org/e3miner.html Extracts novel E3 discoveries and important findings related to specific E3s from the literature RLIMS-P (Jelier et al., 2008 ) BioCreative IV (BioCreative IAT) Kinase, substrate and site Web 92 96 ~(*) 88 http://research.bioinformatics.udel.edu/rlimsp/ Rule-based text-mining program designed to extract protein phosphorylation information on protein kinase, substrate and phosphorylation sites from biomedical literature Anni 2.0 (Frijters et al., 2008 ) Micro-array data and multiple publications Associations between biological entities Web ~(**) 75.5 ~(*) 76 75 http://biosemantics.org/anni/ Ontology-based interface to MEDLINE and retrieves documents and associations for several classes of biomedical concepts, including genes, drugs and diseases PPInterFinder (Ding et al., 2015 ) BioCreative workshop 2012 NER, IR Web ~(**) 78.07 70.58 87.33 http://www.biominingbu.org/ppinterfinder/ Extracts human PPIs from biomedical literature using relation keyword co-occurrences with protein names to extract information on PPIs from MEDLINE abstracts pGenN (Hur et al., 2009 ) 104 plant relevant abstracts NER Web 88.9 87.2 90.9 http://biotm.cis.udel.edu/gn/ A gene normalization tool for plant genes and proteins in scientific literature SciMiner (Li et al., 2009 ) BioCreAtIvE II NER, IR Desktop/Web 75.8 87.1 71.3 http://141.214.81.219/SciMiner/ Identifies genes and proteins using a context specific analysis of MEDLINE abstracts and full texts BIGNER (Raja et al., 2014 ) BioCreative 2 GM NER Web ~(**) 89.05 87.63 90.52 http://202.118.75.18:8080/bioner To locate gene/protein names in biomedical literature * These values were self calculated from the given values . ** Out of order web-interfaces . i2b2, Informatics for Integrating Biology and the Bedside; GM, Ge