PPPred: Classifying Protein-phenotype Co-mentions Extracted from Biomedical Literature

The MEDLINE database provides an extensive source of scientific articles and heterogeneous biomedical information in the form of unstructured text. One of the most important knowledge present within articles are the relations between human proteins and their phenotypes, which can stay hidden due to the exponential growth of publications. This has presented a range of opportunities for the development of computational methods to extract these biomedical relations from the articles. However, currently, no such method exists for the automated extraction of relations involving human proteins and human phenotype ontology (HPO) terms. In our previous work, we developed a comprehensive database composed of all co-mentions of proteins and phenotypes. In this study, we present a supervised machine learning approach called PPPred (Protein-Phenotype Predictor) for classifying the validity of a given sentence-level co-mention. Using an in-house developed gold standard dataset, we demonstrate that PPPred significantly outperforms several baseline methods. This two-step approach of co-mention extraction and classification constitutes a complete biomedical relation extraction pipeline for extracting protein-phenotype relations. CCS CONCEPTS •Computing methodologies → Information extraction; Supervised learning by classification; •Applied computing →Bioinformatics;

• Publication year

  2019

• Venue

  bioRxiv

• Publication date

  2019-05-31

• Fields of study

  Biology, Medicine, Computer Science

• Identifiers
  DOI 10.1101/654475
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Ontology based text mining of gene-phenotype associations: application to candidate gene prediction

  2019influential reference
• Extracting chemical–protein interactions from literature using sentence structure analysis and feature engineering

  2019cited by this paper
• ProPheno 1.0: An Online Dataset for Accelerating the Complete Characterization of the Human Protein-Phenotype Landscape in Biomedical Literature

  2019cited by this paper
• Extracting Co-mention Features from Biomedical Literature for Automated Protein Phenotype Prediction using PHENOstruct

  2018cited by this paper
• A population genetic interpretation of GWAS findings for human quantitative traits

  2018cited by this paper
• A hybrid model based on neural networks for biomedical relation extraction

  2018cited by this paper
• Extracting chemical–protein relations with ensembles of SVM and deep learning models

  2018cited by this paper
• Biocuration: Distilling data into knowledge

  2018cited by this paper
• SNPPhenA: a corpus for extracting ranked associations of single-nucleotide polymorphisms and phenotypes from literature

  2017cited by this paper
• Extracting microRNA-gene relations from biomedical literature using distant supervision

  2017cited by this paper
• Identifying genotype-phenotype relationships in biomedical text

  2017influential reference
• What is precision medicine?

  2017cited by this paper
• Proteome-Scale Investigation of Protein Allosteric Regulation Perturbed by Somatic Mutations in 7,000 Cancer Genomes.

  2017cited by this paper
• Protein Misfolding Diseases.

  2017cited by this paper
• BELMiner: adapting a rule-based relation extraction system to extract biological expression language statements from bio-medical literature evidence sentences

  2017cited by this paper
• Protein Misfolding, Amyloid Formation, and Human Disease: A Summary of Progress Over the Last Decade.

  2017cited by this paper
• DiMeX: A Text Mining System for Mutation-Disease Association Extraction

  2016cited by this paper
• Molecular interaction between type 2 diabetes and Alzheimer’s disease through cross-seeding of protein misfolding

  2016cited by this paper
• Protein misfolding and aggregation: Mechanism, factors and detection

  2016cited by this paper
• Text mining for precision medicine: automating disease-mutation relationship extraction from biomedical literature

  2016cited by this paper
• Text Mining Genotype-Phenotype Relationships from Biomedical Literature for Database Curation and Precision Medicine

  2016cited by this paper
• Multidimensional proteomics for cell biology

  2015cited by this paper
• Methods of integrating data to uncover genotype–phenotype interactions

  2015cited by this paper
• The Human Phenotype Ontology project: linking molecular biology and disease through phenotype data

  2014cited by this paper
• The evolution of gene expression and the transcriptome-phenotype relationship.

  2012cited by this paper
• Interrater reliability: the kappa statistic

  2012cited by this paper
• Deep phenotyping for precision medicine

  2012cited by this paper
• A hybrid approach to extract protein-protein interactions

  2011cited by this paper
• Using text to build semantic networks for pharmacogenomics

  2010cited by this paper
• Bayesian inference of protein-protein interactions from biological literature

  2009cited by this paper
• Automated acquisition of disease drug knowledge from biomedical and clinical documents: an initial study.

  2008cited by this paper
• A fast SCOP fold classification system using content-based E-Predict algorithm

  2006cited by this paper
• Learning Relations from Biomedical Corpora Using Dependency Trees

  2006cited by this paper
• Data and text mining Clustering microarray-derived gene lists through implicit literature relationships

  2006cited by this paper
• Systematic Association of Genes to Phenotypes by Genome and Literature Mining

  2005cited by this paper
• Discovering patterns to extract protein-protein interactions from full texts

  2004cited by this paper
• Classifying Semantic Relations in Bioscience Texts

  2004cited by this paper
• Extraction of protein interaction information from unstructured text using a context-free grammar

  2003cited by this paper
• Semantic Relations Asserting the Etiology of Genetic Diseases

  2003cited by this paper
• Mining literature for protein-protein interactions

  2001cited by this paper
• Event Extraction from Biomedical Papers Using a Full Parser

  2000cited by this paper
• Learning to Extract Relations from MEDLINE

  1999cited by this paper
• Toward Routine Automatic Pathway Discovery from On-line Scientific Text Abstracts.

  1999cited by this paper
• Identifying the Interaction between Genes and Gene Products Based on Frequently Seen Verbs in Medline Abstracts.

  1998cited by this paper

• A review of semi-supervised learning for text classification

  2023influential citation
• Deep semi-supervised learning ensemble framework for classifying co-mentions of human proteins and phenotypes

  2021influential citation
• DeepPPPred: An Ensemble of BERT, CNN, and RNN for Classifying Co-mentions of Proteins and Phenotypes

  2020influential citation
• ProPheno 1.0: An Online Dataset for Accelerating the Complete Characterization of the Human Protein-Phenotype Landscape in Biomedical Literature

  2019cites this paper