Toward knowledge support for analysis and interpretation of complex traits

Collier, Nigel; Oellrich, Anika; Groza, Tudor

doi:10.1186/gb-2013-14-9-214

Cited by 9 publications

(8 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although coding systems such as the Human Phenotype Ontology (HPO) [ 1 ] and the Mammalian Phenotype Ontology (MPO) [ 2 ] have made substantial progress in organising the nomenclature of phenotypes, authors typically report their observations using the full expressivity of human language. In order to fully exploit a machine understandable representation of phenotypic findings, it is necessary to develop techniques based on natural language processing that can harmonise linguistic variation [ 3 - 5 ]. Furthermore, such techniques need to operate on a range of text types such as scientific articles, clinical trials and patient records [ 6 ] in order to enable applications that require inter-operable semantics.…”

Section: Introductionmentioning

confidence: 99%

Concept selection for phenotypes and diseases using learn to rank

2015

Self Cite

View full text Add to dashboard Cite

BackgroundPhenotypes form the basis for determining the existence of a disease against the given evidence. Much of this evidence though remains locked away in text – scientific articles, clinical trial reports and electronic patient records (EPR) – where authors use the full expressivity of human language to report their observations.ResultsIn this paper we exploit a combination of off-the-shelf tools for extracting a machine understandable representation of phenotypes and other related concepts that concern the diagnosis and treatment of diseases. These are tested against a gold standard EPR collection that has been annotated with Unified Medical Language System (UMLS) concept identifiers: the ShARE/CLEF 2013 corpus for disorder detection. We evaluate four pipelines as stand-alone systems and then attempt to optimise semantic-type based performance using several learn-to-rank (LTR) approaches – three pairwise and one listwise. We observed that whilst overall Apache cTAKES tended to outperform other stand-alone systems on a strong recall (R = 0.57), precision was low (P = 0.09) leading to low-to-moderate F1 measure (F1 = 0.16). Moreover, there is substantial variation in system performance across semantic types for disorders. For example, the concept Findings (T033) seemed to be very challenging for all systems. Combining systems within LTR improved F1 substantially (F1 = 0.24) particularly for Disease or syndrome (T047) and Anatomical abnormality (T190). Whilst recall is improved markedly, precision remains a challenge (P = 0.15, R = 0.59).

show abstract

Section: Introductionmentioning

confidence: 99%

Concept selection for phenotypes and diseases using learn to rank

2015

Self Cite

View full text Add to dashboard Cite

show abstract

“…In biology phenotypes are often considered to be observable characteristics of an organism ( 8 ), whereas in medical contexts the term phenotype is usually considered to denote a deviation from normal morphology, physiology or behaviour ( 12 ). This is the working definition that we adopt here and is of particular relevance when considering the profiles of diseases recorded in the free-text literature.…”

Section: System and Methodsmentioning

confidence: 99%

“…Phenotype descriptions are syntactically and semantically complex because authors exploit the full expressivity of language. Previous computer-based approaches have employed localized patterns, either within a rule-based ( 7 ) or machine learning based framework ( 8 , 9 ). Collier et al .’s ( 10 ) previous work using a fully supervised approach highlighted the issue of overfitting on a disease domain as well as the fragility of employing the one-class-per-span assumption that is common in named entity approaches.…”

Section: Introductionmentioning

confidence: 99%

PhenoMiner: from text to a database of phenotypes associated with OMIM diseases

et al. 2015

Self Cite

View full text Add to dashboard Cite

Analysis of scientific and clinical phenotypes reported in the experimental literature has been curated manually to build high-quality databases such as the Online Mendelian Inheritance in Man (OMIM). However, the identification and harmonization of phenotype descriptions struggles with the diversity of human expressivity. We introduce a novel automated extraction approach called PhenoMiner that exploits full parsing and conceptual analysis. Apriori association mining is then used to identify relationships to human diseases. We applied PhenoMiner to the BMC open access collection and identified 13 636 phenotype candidates. We identified 28 155 phenotype-disorder hypotheses covering 4898 phenotypes and 1659 Mendelian disorders. Analysis showed: (i) the semantic distribution of the extracted terms against linked ontologies; (ii) a comparison of term overlap with the Human Phenotype Ontology (HP); (iii) moderate support for phenotype-disorder pairs in both OMIM and the literature; (iv) strong associations of phenotype-disorder pairs to known disease-genes pairs using PhenoDigm. The full list of PhenoMiner phenotypes (S1), phenotype-disorder associations (S2), association-filtered linked data (S3) and user database documentation (S5) is available as supplementary data and can be downloaded at http://github.com/nhcollier/PhenoMiner under a Creative Commons Attribution 4.0 license.Database URL: phenominer.mml.cam.ac.uk

show abstract

“…diseases or results from genome analyses. The overarching goal of interoperability is to facilitate translational research and biological discoveries [ 21 ]. Current and past work falling into this dimension can be summarized as standardization efforts, alignment of phenotypes within and across species and mapping to other resources.…”

Section: State-of-the-art Phenome Researchmentioning

confidence: 99%

“…To enable a structured navigation of the field, we map the content of the review onto the four conceptual dimensions of phenomics, considered from a computational perspective (depicted in Figure 1 ): representation, interoperability, acquisition and processing. These four dimensions have been identified and described in an earlier review [ 21 ] and are used for simplicity here. Representation focuses on semantic modeling and aspects of knowledge capturing.…”

Section: Introductionmentioning

confidence: 99%

The digital revolution in phenotyping

Oellrich¹,

Collier²,

Groza³

et al. 2015

Brief Bioinform

Self Cite

View full text Add to dashboard Cite

Phenotypes have gained increased notoriety in the clinical and biological domain owing to their application in numerous areas such as the discovery of disease genes and drug targets, phylogenetics and pharmacogenomics. Phenotypes, defined as observable characteristics of organisms, can be seen as one of the bridges that lead to a translation of experimental findings into clinical applications and thereby support ‘bench to bedside’ efforts. However, to build this translational bridge, a common and universal understanding of phenotypes is required that goes beyond domain-specific definitions. To achieve this ambitious goal, a digital revolution is ongoing that enables the encoding of data in computer-readable formats and the data storage in specialized repositories, ready for integration, enabling translational research. While phenome research is an ongoing endeavor, the true potential hidden in the currently available data still needs to be unlocked, offering exciting opportunities for the forthcoming years. Here, we provide insights into the state-of-the-art in digital phenotyping, by means of representing, acquiring and analyzing phenotype data. In addition, we provide visions of this field for future research work that could enable better applications of phenotype data.

show abstract

Toward knowledge support for analysis and interpretation of complex traits

Abstract: The systematic description of complex traits, from the organism to the cellular level, is important for hypothesis generation about underlying disease mechanisms. We discuss how intelligent algorithms might provide support, leading to faster throughput.

Cited by 9 publications

References 62 publications

Concept selection for phenotypes and diseases using learn to rank

Concept selection for phenotypes and diseases using learn to rank

PhenoMiner: from text to a database of phenotypes associated with OMIM diseases

The digital revolution in phenotyping

Contact Info

Product

Resources

About