DISEASES: Text mining and data integration of disease–gene associations

Text mining is a flexible technology that can be applied to numerous different tasks in biology and medicine. We present a system for extracting disease–gene associations from biomedical abstracts. The system consists of a highly efficient dictionary-based tagger for named entity recognition of human genes and diseases, which we combine with a scoring scheme that takes into account co-occurrences both within and between sentences. We show that this approach is able to extract half of all manually curated associations with a false positive rate of only 0.16%. Nonetheless, text mining should not stand alone, but be combined with other types of evidence. For this reason, we have developed the DISEASES resource, which integrates the results from text mining with manually curated disease–gene associations, cancer mutation data, and genome-wide association studies from existing databases. The DISEASES resource is accessible through a user-friendly web interface at http://diseases.jensenlab.org/, where the text-mining software and all associations are also freely available for download.

Download Full-text

DISEASES 2.0: a weekly updated database of disease–gene associations from text mining and data integration

10.1101/2021.12.07.471296 ◽

2021 ◽

Author(s):

Dhouha Grissa ◽

Alexander Junge ◽

Tudor I Oprea ◽

Lars Juhl Jensen

Keyword(s):

Text Mining ◽

Disease Gene ◽

Association Studies ◽

Named Entity Recognition ◽

Biomedical Literature ◽

Entity Recognition ◽

Genome Wide Association Studies ◽

Comprehensive Overview ◽

Genome Wide ◽

Gene Associations

The scientific knowledge about which genes are involved in which diseases grows rapidly, which makes it difficult to keep up with new publications and genetics datasets. The DISEASES database aims to provide a comprehensive overview by systematically integrating and assigning confidence scores to evidence for disease–gene associations from curated databases, genome-wide association studies (GWAS), and automatic text mining of the biomedical literature. Here, we present a major update to this resource, which greatly increases the number of associations from all these sources. This is especially true for the text-mined associations, which have increased by at least 9-fold at all confidence cutoffs. We show that this dramatic increase is primarily due to adding full-text articles to the text corpus, secondarily due to improvements to both the disease and gene dictionaries used for named entity recognition, and only to a very small extent due to the growth in number of PubMed abstracts. DISEASES now also makes use of a new GWAS database, TIGA, which considerably increased the number of GWAS-derived disease–gene associations. DISEASES itself is also integrated into several other databases and resources, including GeneCards/MalaCards, Pharos/TCRD, and the Cytoscape stringApp. All data in DISEASES is updated on a weekly basis and is available via a web interface at https://diseases.jensenlab.org, from where it can also be downloaded under open licenses.

Download Full-text

A fast mrMLM algorithm for multi-locus genome-wide association studies

10.1101/341784 ◽

2018 ◽

Cited By ~ 23

Author(s):

Cox Lwaka Tamba ◽

Yuan-Ming Zhang

Keyword(s):

False Positive ◽

Statistical Power ◽

Association Studies ◽

False Positive Rate ◽

Real Data ◽

High Accuracy ◽

Genome Wide Association ◽

Genome Wide Association Studies ◽

Genome Wide ◽

Positive Rate

AbstractBackgroundRecent developments in technology result in the generation of big data. In genome-wide association studies (GWAS), we can get tens of million SNPs that need to be tested for association with a trait of interest. Indeed, this poses a great computational challenge. There is a need for developing fast algorithms in GWAS methodologies. These algorithms must ensure high power in QTN detection, high accuracy in QTN estimation and low false positive rate.ResultsHere, we accelerated mrMLM algorithm by using GEMMA idea, matrix transformations and identities. The target functions and derivatives in vector/matrix forms for each marker scanning are transformed into some simple forms that are easy and efficient to evaluate during each optimization step. All potentially associated QTNs with P-values ≤ 0.01 are evaluated in a multi-locus model by LARS algorithm and/or EM-Empirical Bayes. We call the algorithm FASTmrMLM. Numerical simulation studies and real data analysis validated the FASTmrMLM. FASTmrMLM reduces the running time in mrMLM by more than 50%. FASTmrMLM also shows high statistical power in QTN detection, high accuracy in QTN estimation and low false positive rate as compared to GEMMA, FarmCPU and mrMLM. Real data analysis shows that FASTmrMLM was able to detect more previously reported genes than all the other methods: GEMMA/EMMA, FarmCPU and mrMLM.ConclusionsFASTmrMLM is a fast and reliable algorithm in multi-locus GWAS and ensures high statistical power, high accuracy of estimates and low false positive rate.Author SummaryThe current developments in technology result in the generation of a vast amount of data. In genome-wide association studies, we can get tens of million markers that need to be tested for association with a trait of interest. Due to the computational challenge faced, we developed a fast algorithm for genome-wide association studies. Our approach is a two stage method. In the first step, we used matrix transformations and identities to quicken the testing of each random marker effect. The target functions and derivatives which are in vector/matrix forms for each marker scanning are transformed into some simple forms that are easy and efficient to evaluate during each optimization step. In the second step, we selected all potentially associated SNPs and evaluated them in a multi-locus model. From simulation studies, our algorithm significantly reduces the computing time. The new method also shows high statistical power in detecting significant markers, high accuracy in marker effect estimation and low false positive rate. We also used the new method to identify relevant genes in real data analysis. We recommend our approach as a fast and reliable method for carrying out a multi-locus genome-wide association study.

Download Full-text

PopCluster: an algorithm to identify genetic variants with ethnicity-dependent effects

Bioinformatics ◽

10.1093/bioinformatics/btz017 ◽

2019 ◽

Vol 35 (17) ◽

pp. 3046-3054 ◽

Cited By ~ 2

Author(s):

Anastasia Gurinovich ◽

Harold Bae ◽

John J Farrell ◽

Stacy L Andersen ◽

Stefano Monti ◽

...

Keyword(s):

Genetic Variants ◽

Association Studies ◽

False Positive Rate ◽

Principal Component ◽

True Positive Rate ◽

Genome Wide Association ◽

Supplementary Information ◽

Genome Wide Association Studies ◽

Genome Wide ◽

Positive Rate

Abstract Motivation Over the last decade, more diverse populations have been included in genome-wide association studies. If a genetic variant has a varying effect on a phenotype in different populations, genome-wide association studies applied to a dataset as a whole may not pinpoint such differences. It is especially important to be able to identify population-specific effects of genetic variants in studies that would eventually lead to development of diagnostic tests or drug discovery. Results In this paper, we propose PopCluster: an algorithm to automatically discover subsets of individuals in which the genetic effects of a variant are statistically different. PopCluster provides a simple framework to directly analyze genotype data without prior knowledge of subjects’ ethnicities. PopCluster combines logistic regression modeling, principal component analysis, hierarchical clustering and a recursive bottom-up tree parsing procedure. The evaluation of PopCluster suggests that the algorithm has a stable low false positive rate (∼4%) and high true positive rate (>80%) in simulations with large differences in allele frequencies between cases and controls. Application of PopCluster to data from genetic studies of longevity discovers ethnicity-dependent heterogeneity in the association of rs3764814 (USP42) with the phenotype. Availability and implementation PopCluster was implemented using the R programming language, PLINK and Eigensoft software, and can be found at the following GitHub repository: https://github.com/gurinovich/PopCluster with instructions on its installation and usage. Supplementary information Supplementary data are available at Bioinformatics online.

Download Full-text

Improved analyses of GWAS summary statistics by reducing data heterogeneity and errors

Nature Communications ◽

10.1038/s41467-021-27438-7 ◽

2021 ◽

Vol 12 (1) ◽

Author(s):

Wenhan Chen ◽

Yang Wu ◽

Zhili Zheng ◽

Ting Qi ◽

Peter M. Visscher ◽

...

Keyword(s):

False Positive ◽

Rare Variants ◽

Control Method ◽

Association Studies ◽

False Positive Rate ◽

Reference Sample ◽

Genome Wide Association Studies ◽

Summary Statistics ◽

Positive Rate ◽

Summary Data

AbstractSummary statistics from genome-wide association studies (GWAS) have facilitated the development of various summary data-based methods, which typically require a reference sample for linkage disequilibrium (LD) estimation. Analyses using these methods may be biased by errors in GWAS summary data or LD reference or heterogeneity between GWAS and LD reference. Here we propose a quality control method, DENTIST, that leverages LD among genetic variants to detect and eliminate errors in GWAS or LD reference and heterogeneity between the two. Through simulations, we demonstrate that DENTIST substantially reduces false-positive rate in detecting secondary signals in the summary-data-based conditional and joint association analysis, especially for imputed rare variants (false-positive rate reduced from >28% to <2% in the presence of heterogeneity between GWAS and LD reference). We further show that DENTIST can improve other summary-data-based analyses such as fine-mapping analysis.

Download Full-text

Improved analyses of GWAS summary statistics by reducing data heterogeneity and errors

10.1101/2020.07.09.196535 ◽

2020 ◽

Author(s):

Wenhan Chen ◽

Yang Wu ◽

Zhili Zheng ◽

Ting Qi ◽

Peter M Visscher ◽

...

Keyword(s):

Rare Variants ◽

Control Method ◽

Association Studies ◽

False Positive Rate ◽

Reference Sample ◽

Genome Wide Association Studies ◽

Summary Statistics ◽

Positive Rate ◽

Trait Locus ◽

Summary Data

AbstractSummary statistics from genome-wide association studies (GWAS) have facilitated the development of various summary data-based methods, which typically require a reference sample for linkage disequilibrium (LD) estimation. Analyses using these methods may be biased by errors in GWAS summary data and heterogeneity between GWAS and LD reference. Here we propose a quality control method, DENTIST, that leverages LD among genetic variants to detect and eliminate errors in GWAS or LD reference and heterogeneity between the two. Through simulations, we demonstrate that DENTIST substantially reduces false-positive rate (FPR) in detecting secondary signals in the summary-data-based conditional and joint (COJO) association analysis, especially for imputed rare variants (FPR reduced from >28% to <2% in the presence of ancestral difference between GWAS and LD reference). We further show that DENTIST can improve other summary-data-based analyses such as LD score regression analysis, and integrative analysis of GWAS and expression quantitative trait locus data.

Download Full-text

Text mining of 15 million full-text scientific articles

10.1101/162099 ◽

2017 ◽

Cited By ~ 5

Author(s):

David Westergaard ◽

Hans-Henrik Stærfeldt ◽

Christian Tønsberg ◽

Lars Juhl Jensen ◽

Søren Brunak

Keyword(s):

Text Mining ◽

Full Text ◽

Disease Gene ◽

Scientific Literature ◽

Named Entity Recognition ◽

Recognition System ◽

Entity Recognition ◽

Data Sets ◽

Named Entity ◽

Benchmark Data

AbstractAcross academia and industry, text mining has become a popular strategy for keeping up with the rapid growth of the scientific literature. Text mining of the scientific literature has mostly been carried out on collections of abstracts, due to their availability. Here we present an analysis of 15 million English scientific full-text articles published during the period 1823–2016. We describe the development in article length and publication sub-topics during these nearly 250 years. We showcase the potential of text mining by extracting published protein–protein, disease–gene, and protein subcellular associations using a named entity recognition system, and quantitatively report on their accuracy using gold standard benchmark data sets. We subsequently compare the findings to corresponding results obtained on 16.5 million abstracts included in MEDLINE and show that text mining of full-text articles consistently outperforms using abstracts only.

Download Full-text

Applying meta-analysis to Genotype-Tissue Expression data from multiple tissues to identify eQTLs and increase the number of eGenes

10.1101/100701 ◽

2017 ◽

Author(s):

Dat Duong ◽

Lisa Gai ◽

Sagi Snir ◽

Eun Yong Kang ◽

Buhm Han ◽

...

Keyword(s):

Gene Expression ◽

Association Studies ◽

Meta Analysis ◽

False Positive Rate ◽

Tissue Expression ◽

Great Effort ◽

Genome Wide Association Studies ◽

Biological Insight ◽

Positive Rate ◽

Computationally Intensive

AbstractDuring the last decade, with the advent of inexpensive microarray and RNA-seq technologies, there have been many expression quantitative trait loci (eQTL) studies for identifying genetic variants called eQTLs that regulate gene expression. Discovering eQTLs has been increasingly important as they may elucidate the functional consequence of non-coding variants identified from genome-wide association studies. Recently, several eQTL studies such as the Genotype-Tissue Expression (GTEx) consortium have made a great effort to obtain gene expression from multiple tissues. One advantage of these multi-tissue eQTL datasets is that they may allow one to identify more eQTLs by combining information across multiple tissues. Although a few methods have been proposed for multi-tissue eQTL studies, they are often computationally intensive and may not achieve optimal power because they do not consider a biological insight that a genetic variant regulates gene expression similarly in related tissues. In this paper, we propose an efficient meta-analysis approach for identifying eQTLs from large multi-tissue eQTL datasets. We name our method RECOV because it uses a random effects (RE) meta-analysis with an explicit covariance (COV) term to model the correlation of effect that eQTLs have across tissues. Our approach is faster than the previous approaches and properly controls the false-positive rate. We apply our approach to the real multi-tissue eQTL dataset from GTEx that contains 44 tissues, and show that our approach detects more eQTLs and eGenes than previous approaches.

Download Full-text

SicknessMiner: a deep-learning-driven text-mining tool to abridge disease-disease associations

BMC Bioinformatics ◽

10.1186/s12859-021-04397-w ◽

2021 ◽

Vol 22 (1) ◽

Author(s):

Nícia Rosário-Ferreira ◽

Victor Guimarães ◽

Vítor S. Costa ◽

Irina S. Moreira

Keyword(s):

Text Mining ◽

Named Entity Recognition ◽

Entity Recognition ◽

Named Entity ◽

Disease Similarity ◽

Disease Associations ◽

Named Entity Normalization ◽

Mining Tool ◽

Or Gene ◽

Text Mining Tool

Abstract Background Blood cancers (BCs) are responsible for over 720 K yearly deaths worldwide. Their prevalence and mortality-rate uphold the relevance of research related to BCs. Despite the availability of different resources establishing Disease-Disease Associations (DDAs), the knowledge is scattered and not accessible in a straightforward way to the scientific community. Here, we propose SicknessMiner, a biomedical Text-Mining (TM) approach towards the centralization of DDAs. Our methodology encompasses Named Entity Recognition (NER) and Named Entity Normalization (NEN) steps, and the DDAs retrieved were compared to the DisGeNET resource for qualitative and quantitative comparison. Results We obtained the DDAs via co-mention using our SicknessMiner or gene- or variant-disease similarity on DisGeNET. SicknessMiner was able to retrieve around 92% of the DisGeNET results and nearly 15% of the SicknessMiner results were specific to our pipeline. Conclusions SicknessMiner is a valuable tool to extract disease-disease relationship from RAW input corpus.

Download Full-text

A Neural Named Entity Recognition and Multi-Type Normalization Tool for Biomedical Text Mining

IEEE Access ◽

10.1109/access.2019.2920708 ◽

2019 ◽

Vol 7 ◽

pp. 73729-73740 ◽

Cited By ~ 13

Author(s):

Donghyeon Kim ◽

Jinhyuk Lee ◽

Chan Ho So ◽

Hwisang Jeon ◽

Minbyul Jeong ◽

...

Keyword(s):

Text Mining ◽

Named Entity Recognition ◽

Entity Recognition ◽

Biomedical Text ◽

Biomedical Text Mining ◽

Named Entity

Download Full-text

Tagger: BeCalm API for rapid named entity recognition

10.1101/115022 ◽

2017 ◽

Cited By ~ 2

Author(s):

Lars Juhl Jensen

Keyword(s):

Open Access ◽

Text Mining ◽

Real Time ◽

Named Entity Recognition ◽

Entity Recognition ◽

The Real ◽

Practical Applications ◽

Named Entity ◽

Highly Efficient

AbstractMost BioCreative tasks to date have focused on assessing the quality of text-mining annotations in terms of precision of recall. Interoperability, speed, and stability are, however, other important factors to consider for practical applications of text mining. The new BioCreative/BeCalm TIPS task focuses purely on these. To participate in this task, I implemented a BeCalm API within the real-time tagging server also used by the Reflect and EXTRACT tools. In addition to retrieval of patent abstracts, PubMed abstracts, and Pub-Med Central open-access articles as required in the TIPS task, the BeCalm API implementation facilitates retrieval of documents from other sources specified as custom request parameters. As in earlier tests, the tagger proved to be both highly efficient and stable, being able to consistently process requests of 5000 abstracts in less than half a minute including retrieval of the document text.

Download Full-text