Filters








3,320 Hits in 7.9 sec

Using association rule mining to determine promising secondary phenotyping hypotheses

Anika Oellrich, Julius Jacobsen, Irene Papatheodorou, Damian Smedley
2014 Computer applications in the biosciences : CABIOS  
Results: In this study, we applied an association rule mining approach to the identification of promising secondary phenotype candidates.  ...  Applying an association rule mining approach, we could identify 1967 secondary phenotype hypotheses that cover 244 genes and 136 phenotypes.  ...  ACKNOWLEDGEMENTS A.O.E. designed the experimental setup, implemented the secondary phenotype prediction pipeline, and executed part of the automated and manual evaluation.  ... 
doi:10.1093/bioinformatics/btu260 pmid:24932005 pmcid:PMC4059059 fatcat:ifl7qzq5kren3dn27yvw64opry

Towards Similarity-based Differential Diagnostics For Common Diseases

Luke T. Slater, Andreas Karwath, John A. Williams, Sophie Russell, Silver Makepeace, Alexander Carberry, Robert Hoehndorf, Georgios V. Gkoutos
2021 Computers in Biology and Medicine  
In this work, we describe the development of an approach for deriving patient phenotype profiles from clinical narrative text, and apply this to text associated with MIMIC-III patient visits.  ...  We then explore the use of semantic similarity with those text-derived phenotypes to classify primary patient diagnosis, comparing the use of patient-patient similarity and patient-disease similarity using  ...  In particular, measurements of semantic similarity between phenotype profiles have been used to generate hypotheses and predict diagnoses [12] .  ... 
doi:10.1016/j.compbiomed.2021.104360 pmid:33836447 fatcat:4pkrwz6v3vfypklg5awjrqugrq

Natural Language Processing for EHR-Based Computational Phenotyping

Zexian Zeng, Yu Deng, Xiaoyu Li, Tristan Naumann, Yuan Luo
2018 IEEE/ACM Transactions on Computational Biology & Bioinformatics  
However, the construction of keyword and rule lists requires significant manual effort, which is difficult to scale.  ...  This article reviews recent advances in applying natural language processing (NLP) to Electronic Health Records (EHRs) for computational phenotyping.  ...  Statistical tests were then carried out to determine associations between single nucleotide polymorphisms and multiple disease phenotypes.  ... 
doi:10.1109/tcbb.2018.2849968 pmid:29994486 pmcid:PMC6388621 fatcat:wsksxvr7lfbgjowrsymghld64u

Natural Language Processing for EHR-Based Computational Phenotyping [article]

Zexian Zeng, Yu Deng, Xiaoyu Li, Tristan Naumann, Yuan Luo
2018 arXiv   pre-print
However, the construction of keyword and rule lists requires significant manual effort, which is difficult to scale.  ...  This article reviews recent advances in applying natural language processing (NLP) to Electronic Health Records (EHRs) for computational phenotyping.  ...  Statistical tests were then carried out to determine associations between single nucleotide polymorphisms and multiple disease phenotypes.  ... 
arXiv:1806.04820v2 fatcat:fo5ck7rpgzhb7dgmqfjc3bdw7y

Menagerie: A text-mining tool to support animal-human translation in neurodegeneration research

Caroline J. Zeiss, Dongwook Shin, Brent Vander Wyk, Amanda P. Beck, Natalie Zatz, Charles A. Sneiderman, Halil Kilicoglu, Gianluigi Forloni
2019 PLoS ONE  
We describe a text-mining approach that extracts translationally useful data from PubMed abstracts.  ...  As previously noted, the majority of studies reported promising outcomes.  ...  Acknowledgments The authors gratefully acknowledge the advice and guidance of Thomas Rindflesch (NLM intramural research program), without whose support this work would not have progressed from vision to  ... 
doi:10.1371/journal.pone.0226176 pmid:31846471 pmcid:PMC6917268 fatcat:n72jggcl2zg4dpjvsimyn3xz54

Towards Similarity-based Differential Diagnostics For Common Diseases [article]

Luke T Slater, Andreas Karwath, John A Williams, Sophie Russell, Silver Makepeace, Alexander Carberry, Robert Hoehndorf, Georgios V Gkoutos
2021 bioRxiv   pre-print
We thenexplore the use of semantic similarity with those text-derived phenotypes to classifyprimary patient diagnosis, comparing the use of patient-patient similarity and patient-disease similarity using  ...  In this work, we describe thedevelopment of an approach for deriving patient phenotype profiles from clinicalnarrative text, and apply this to text associated with MIMIC-III patient visits.  ...  We then evaluate and contrast two methods of predicting diagnosis: comparison to other patients in the cohort, and secondary use of definitional phenotype profiles previously mined from literature. 2  ... 
doi:10.1101/2021.01.26.428269 fatcat:uxf4lgi3rjamvpamyzti2o6da4

Recent progress in automatically extracting information from the pharmacogenomic literature

Yael Garten, Adrien Coulet, Russ B Altman
2010 Pharmacogenomics (London)  
Acknowledgements The authors would like to thank Connie M Oshiro for comments on the manuscript and Nicholas P Tatonetti for useful discussions and assistance creating the figures.  ...  In this article, we use the latter definition. For example, how can text mining assist researchers to identify new gene variants associated with drug response?  ...  Literature-based discovery (LBD) systems automatically induce novel promising hypotheses by processing existing publications, and extracting indirect relationships.  ... 
doi:10.2217/pgs.10.136 pmid:21047206 pmcid:PMC3035632 fatcat:7g3jwc4hjfetbb5phmzstzhjeu

Extracting knowledge networks from plant scientific literature: potato tuber flesh color as an exemplary trait

Gurnoor Singh, Evangelia A Papoutsoglou, Frederique Keijts-Lalleman, Bilyana Vencheva, Mark Rice, Richard G F Visser, Christian W B Bachem, Richard Finkers
2021 BMC Plant Biology  
We focused on the flesh color of potato, a well-studied trait with known associations, and we investigated whether these knowledge networks can assist us in formulating new hypotheses on the underlying  ...  For this pilot, we developed a pipeline that uses NLP on biological literature to produce knowledge networks.  ...  Additionally, we are thankful to IBM Technical Support for their continued support.  ... 
doi:10.1186/s12870-021-02943-5 pmid:33894758 fatcat:kord2py2jrfgnnvob5d5ucjvby

Current State and Future Directions of Genetics and Genomics of Endophytic Fungi for Bioprospecting Efforts

Rosa Sagita, Wim J. Quax, Kristina Haslinger
2021 Frontiers in Bioengineering and Biotechnology  
In this review we want to discuss the current approaches and tools used to associate phenotype and genotype to elucidate biosynthetic pathways of secondary metabolites in endophytic fungi through the lens  ...  However, only very few studies also report the genetic basis for these phenotypic observations.  ...  Genome mining allows the exploration of the entire genome and thus enables us to discover novel secondary metabolites.  ... 
doi:10.3389/fbioe.2021.649906 pmid:33791289 pmcid:PMC8005728 fatcat:352waj7zxngt5do4v74eao6i3i

Genome-wide association studies and the genetic dissection of complex traits

Paola Sebastiani, Nadia Timofeev, Daniel A. Dworkis, Thomas T. Perls, Martin H. Steinberg
2009 American Journal of Hematology  
Genome-wide association studies (GWAS) of common diseases have begun to propel us toward this goal.  ...  The CD-CV model hypothesized that the genetic profile of common diseases is determined by genetic variants that are common in the population (frequency > 0.05) and have, individually, a small effect on  ...  The principle of Bayesian tests of association is to first assume prior probabilities on the two hypotheses of no association and association, then use the data to update the prior probabilities of the  ... 
doi:10.1002/ajh.21440 pmid:19569043 pmcid:PMC2895326 fatcat:ns7wg3jimjfnbmb2qpwulyphwq

Improved mutation tagging with gene identifiers applied to membrane protein stability prediction

Rainer Winnenburg, Conrad Plake, Michael Schroeder
2009 BMC Bioinformatics  
For five G protein-coupled receptors we identified 35 relevant single mutations and associated phenotypes, of which none had been annotated in the UniProt or PDB database.  ...  The automated retrieval and integration of information about protein point mutations in combination with structure, domain and interaction data from literature and databases promises to be a valuable approach  ...  Therefore, the biomedical literature can be systematically searched for information about mutation-phenotype associations by text mining, which may lead to new insights beyond information in existing databases  ... 
doi:10.1186/1471-2105-10-s8-s3 pmid:19758467 pmcid:PMC2745585 fatcat:i2xqvejgrra35eln6wutviepsq

Mining Electronic Health Records (EHRs)

Pranjul Yadav, Michael Steinbach, Vipin Kumar, Gyorgy Simon
2018 ACM Computing Surveys  
Next, we describe major approaches used for EHR mining, the metrics associated with EHRs, and the various study designs.  ...  With this foundation, we then provide a systematic and methodological organization of existing data mining techniques used to model EHRs and discuss ideas for future research.  ...  Using the association rule mining framework, Shin et al.  ... 
doi:10.1145/3127881 fatcat:xil7qev3xbf3pmfv5vtak4f2jq

Detecting and prioritizing biosynthetic gene clusters for bioactive compounds in bacteria and fungi

Phuong Nguyen Tran, Ming-Ren Yen, Chen-Yu Chiang, Hsiao-Ching Lin, Pao-Yang Chen
2019 Applied Microbiology and Biotechnology  
Secondary metabolites (SM) produced by fungi and bacteria have long been of exceptional interest owing to their unique biomedical ramifications.  ...  Our review points to a direction that the biological hypotheses should be systematically incorporated into the BGC prediction and assist the prioritization of candidate BGC.  ...  The extent to which gliT and gliA contribute to A. fumigatus self-protection remains difficult to determine.  ... 
doi:10.1007/s00253-019-09708-z fatcat:gvfwc3y26zefxkjwzzept3yp2m

Deep learning for plant genomics and crop improvement

Hai Wang, Emre Cimen, Nisha Singh, Edward Buckler
2020 Current opinion in plant biology  
More importantly, genomics is not merely acquiring molecular phenotypes, but also leveraging powerful data mining tools to predict and explain them.  ...  can we identify functional variants in natural populations using deep learning models?  ...  The authors discuss approaches to avoid the curse of dimensionality, by involving intermediate phenotypes such as molecular traits and component traits related to plant morphology or physiology.  ... 
doi:10.1016/j.pbi.2019.12.010 pmid:31986354 fatcat:662jdxxtkfcmvcbiror4cquydm

DISEASE GENE DISCOVERY THROUGH INTEGRATIVE GENOMICS

Cosmas Giallourakis, Charlotte Henson, Michael Reich, Xiaohui Xie, Vamsi K. Mootha
2005 Annual review of genomics and human genetics (Print)  
Here we review some of the emerging genomics technologies and data resources that can be used to infer gene function to prioritize candidate genes.  ...  Finally, we discuss future prospects and challenges for using integrative genomics to systematically discover not only single genes but also entire gene networks that underlie and modify human disease.  ...  When combined with improved data-mining tools, such data sets promise to help us construct informative and structured mappings among human diseases.  ... 
doi:10.1146/annurev.genom.6.080604.162234 pmid:16124867 fatcat:vpxrnmiwhnhxxd5bkvkfyv5tr4
« Previous Showing results 1 — 15 out of 3,320 results