QTLTableMiner++: semantic mining of QTL tables in scientific articles

Abstract

BackgroundA quantitative trait locus (QTL) is a genomic region that correlates with a phenotype. Most of the experimental information about QTL mapping studies is described in tables of scientific publications. Traditional text mining techniques aim to extract information from unstructured text rather than from tables. We present QTLTableMiner++ (QTM), a table mining tool that extracts and semantically annotates QTL information buried in (heterogeneous) tables of plant science literature.QTM is a command line tool written in the Java programming language. This tool takes scientific articles from the Europe PMC repository as input, extracts QTL tables using keyword matching and ontology-based concept identification. The tables are further normalized using rules derived from table properties such as captions, column headers and table footers. Furthermore, table columns are classified into three categories namely column descriptors, properties and values based on column headers and data types of cell entries. Abbreviations found in the tables are expanded using the Schwartz and Hearst algorithm. Finally, the content of QTL tables is semantically enriched with domain-specific ontologies (e.g. Crop Ontology, Plant Ontology and Trait Ontology) using the Apache Solr search platform and the results are stored in a relational database and a text file.ResultsThe performance of the QTM tool was assessed by precision and recall based on the information retrieved from two manually annotated corpora of open access articles, i.e. QTL mapping studies in tomato (Solanum lycopersicum) and in potato (S. tuberosum). In summary, QTM detected QTL statements in tomato with 74.53% precision and 92.56% recall and in potato with 82.82% precision and 98.94% recall.ConclusionQTM is a unique tool that aids in providing QTL information in machine-readable and semantically interoperable formats.Electronic supplementary materialThe online version of this article (10.1186/s12859-018-2165-7) contains supplementary material, which is available to authorized users.

Mining news media for understanding public health concerns

“…Apache Solr is an open source search platform built on Apache Lucene library. Apache Lucene provides rich features to handle document such as full-text search and real-time indexing for various applications [18,19]. The Reuters news data were filtered in Apache Solr to retrieve articles that mentioned the 10 public health issues.…”

Linked Data Platform for Plant Breeding and Genomics

“…This platform integrates (semi-)structured data from scientific literature and from public molecular biology databases using a Linked Data approach. On the one hand, QTLs were extracted from full-text (open access) articles, as provided by the Europe PMC database, using a recently developed tool called QTLTableMiner++ [2]. Briefly, this tool takes articles in (semi-)structured XML format as input, detects tables with QTL related information, semantically annotates the tables with biological concepts such as trait, gene, protein or genetic marker using domain-specific ontologies (e.g.…”

Genomics data integration for knowledge discovery using genome annotations from molecular databases and scientific literature

“…However, there is no established repository where experimental data on plant-specific QTL studies can be submitted. Therefore, QTL information is classified as non-RDF data and extracted from XML based scientific literature and processed to RDF graphs using the QTL TableMiner++ (QTM) tool [61] version (v1.1.0) [115]. QTM extracted 324 QTLs from a total of 21 Solanaceae-specific full-text articles in the Europe PMC literature repository.…”

“…On the one hand, NLP studies focused majorly on rulebased named entity recognition (NER) i.e. identifying and annotating biological entities such as genes or proteins [56], [57], metabolites [58], [59], traits [60], QTLs [61], diseases [62], and drugs [63] in literature. On the other hand, a few NLP studies pay attention to extracting associations (relationships and event) between these biological entities, while using NER systems under the hood [57], [64].…”

“…If the input parameter is a trait of interest, the Pbg-ld database retrieves all QTL locations for that trait in tomato. This QTL information occurs in tables of scientific literature and is compiled in Pbg-ld using the QTLTableMiner++ (QTM) tool [61].…”