1
|
Madan S, Kühnel L, Fröhlich H, Hofmann-Apitius M, Fluck J. Dataset of miRNA-disease relations extracted from textual data using transformer-based neural networks. Database (Oxford) 2024; 2024:baae066. [PMID: 39104284 DOI: 10.1093/database/baae066] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/21/2024] [Revised: 06/23/2024] [Accepted: 07/10/2024] [Indexed: 08/07/2024]
Abstract
MicroRNAs (miRNAs) play important roles in post-transcriptional processes and regulate major cellular functions. The abnormal regulation of expression of miRNAs has been linked to numerous human diseases such as respiratory diseases, cancer, and neurodegenerative diseases. Latest miRNA-disease associations are predominantly found in unstructured biomedical literature. Retrieving these associations manually can be cumbersome and time-consuming due to the continuously expanding number of publications. We propose a deep learning-based text mining approach that extracts normalized miRNA-disease associations from biomedical literature. To train the deep learning models, we build a new training corpus that is extended by distant supervision utilizing multiple external databases. A quantitative evaluation shows that the workflow achieves an area under receiver operator characteristic curve of 98% on a holdout test set for the detection of miRNA-disease associations. We demonstrate the applicability of the approach by extracting new miRNA-disease associations from biomedical literature (PubMed and PubMed Central). We have shown through quantitative analysis and evaluation on three different neurodegenerative diseases that our approach can effectively extract miRNA-disease associations not yet available in public databases. Database URL: https://zenodo.org/records/10523046.
Collapse
Affiliation(s)
- Sumit Madan
- Department of Bioinformatics, Fraunhofer Institute for Algorithms and Scientific Computing (SCAI), Schloss Birlinghoven, 53757 Sankt Augustin, Germany
| | - Lisa Kühnel
- Knowledge Management, German National Library of Medicine (ZB MED)-Information Centre for Life Sciences, Friedrich-Hirzebruch-Allee 4, Bonn 53115, Germany
- Graduate School DILS, Bielefeld Institute for Bioinformatics Infrastructure (BIBI), Faculty of Technology, Bielefeld University, Postfach 10 01 31, Bielefeld, Nordrhein-Westfalen 33501, Germany
| | - Holger Fröhlich
- Department of Bioinformatics, Fraunhofer Institute for Algorithms and Scientific Computing (SCAI), Schloss Birlinghoven, 53757 Sankt Augustin, Germany
- Bonn-Aachen International Center for Information Technology (B-IT), University of Bonn, Friedrich-Hirzebruch-Allee 6, Bonn 53113, Germany
| | - Martin Hofmann-Apitius
- Department of Bioinformatics, Fraunhofer Institute for Algorithms and Scientific Computing (SCAI), Schloss Birlinghoven, 53757 Sankt Augustin, Germany
- Bonn-Aachen International Center for Information Technology (B-IT), University of Bonn, Friedrich-Hirzebruch-Allee 6, Bonn 53113, Germany
| | - Juliane Fluck
- Knowledge Management, German National Library of Medicine (ZB MED)-Information Centre for Life Sciences, Friedrich-Hirzebruch-Allee 4, Bonn 53115, Germany
- Graduate School DILS, Bielefeld Institute for Bioinformatics Infrastructure (BIBI), Faculty of Technology, Bielefeld University, Postfach 10 01 31, Bielefeld, Nordrhein-Westfalen 33501, Germany
- Information management, Institute of Geodesy and Geoinformation, University of Bonn, Katzenburgweg 1a, Bonn 53115, Germany
| |
Collapse
|
2
|
Sun Y, Li J, Xu Z, Liu Y, Hou L, Huang Z. Exploring relationship between emotion and probiotics with knowledge graphs. Health Inf Sci Syst 2022; 10:27. [PMID: 36101548 PMCID: PMC9464290 DOI: 10.1007/s13755-022-00179-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/13/2022] [Accepted: 06/02/2022] [Indexed: 10/14/2022] Open
Abstract
Purpose Researchers have identified gut microbiota that interact with brain regions associated with emotion and mood. Literature reviews of those associations rely on rigorous systematic approaches and labor-intensive investments. Here we explore how knowledge graph, a large scale semantic network consisting of entities and concepts as well as the semantic relationships among them, is incorporated into the emotion-probiotic relationship exploration work. Method We propose an end-to-end emotion-probiotics relationship exploration method with an integrated medical knowledge graph, which incorporates the text mining output of knowledge graph, concept reasoning and evidence classification. Specifically, a knowledge graph for probiotics is built based on a text-mining analysis of PubMed, and further used to retrieve triples of relationships with reasoning logistics. Then specific relationships are annotated and evidence levels are retrieved to form a new evidence-based emotion-probiotic knowledge graph. Results Based on the probiotics knowledge graph with 40,442,404 triples, totally 1453 PubMed articles were annotated in both the title level and abstract level, and the evidence levels were incorporated to the visualization of the explored emotion-probiotic relationships. Finally, we got 4131 evidenced emotion-probiotic associations. Conclusions The evidence-based emotion-probiotic knowledge graph construction work demonstrates an effective reasoning based pipeline of relationship exploration. The annotated relationship associations are supposed be used to help researchers generate scientific hypotheses or create their own semantic graphs for their research interests.
Collapse
Affiliation(s)
- Yueping Sun
- Institute of Medical Information, Chinese Academy of Medical Sciences/Peking Union Medical College, Beijing, 100020 China
| | - Jiao Li
- Institute of Medical Information, Chinese Academy of Medical Sciences/Peking Union Medical College, Beijing, 100020 China
| | - Zidu Xu
- Institute of Medical Information, Chinese Academy of Medical Sciences/Peking Union Medical College, Beijing, 100020 China
| | - Yan Liu
- Institute of Medical Information, Chinese Academy of Medical Sciences/Peking Union Medical College, Beijing, 100020 China
| | - Li Hou
- Institute of Medical Information, Chinese Academy of Medical Sciences/Peking Union Medical College, Beijing, 100020 China
| | - Zhisheng Huang
- Knowledge Representation and Reasoning (KR\&R) Group, Computer Science, Vrije Universiteit Amsterdam, Amsterdam, The Netherlands
| |
Collapse
|
3
|
Zhao Y, Qin F, Han S, Li S, Zhao Y, Wang H, Tian J, Cen X. MicroRNAs in drug addiction: Current status and future perspectives. Pharmacol Ther 2022; 236:108215. [DOI: 10.1016/j.pharmthera.2022.108215] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/18/2022] [Revised: 05/11/2022] [Accepted: 05/16/2022] [Indexed: 12/21/2022]
|
4
|
Yang M, Huang ZA, Gu W, Han K, Pan W, Yang X, Zhu Z. Prediction of biomarker-disease associations based on graph attention network and text representation. Brief Bioinform 2022; 23:6651308. [PMID: 35901464 DOI: 10.1093/bib/bbac298] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/03/2022] [Revised: 06/28/2022] [Accepted: 06/30/2022] [Indexed: 02/06/2023] Open
Abstract
MOTIVATION The associations between biomarkers and human diseases play a key role in understanding complex pathology and developing targeted therapies. Wet lab experiments for biomarker discovery are costly, laborious and time-consuming. Computational prediction methods can be used to greatly expedite the identification of candidate biomarkers. RESULTS Here, we present a novel computational model named GTGenie for predicting the biomarker-disease associations based on graph and text features. In GTGenie, a graph attention network is utilized to characterize diverse similarities of biomarkers and diseases from heterogeneous information resources. Meanwhile, a pretrained BERT-based model is applied to learn the text-based representation of biomarker-disease relation from biomedical literature. The captured graph and text features are then integrated in a bimodal fusion network to model the hybrid entity representation. Finally, inductive matrix completion is adopted to infer the missing entries for reconstructing relation matrix, with which the unknown biomarker-disease associations are predicted. Experimental results on HMDD, HMDAD and LncRNADisease data sets showed that GTGenie can obtain competitive prediction performance with other state-of-the-art methods. AVAILABILITY The source code of GTGenie and the test data are available at: https://github.com/Wolverinerine/GTGenie.
Collapse
Affiliation(s)
- Minghao Yang
- College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, 518000, China
| | - Zhi-An Huang
- Center for Computer Science and Information Technology, City University of Hong Kong Dongguan Research Institute, Dongguan, China
| | - Wenhao Gu
- College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, 518000, China.,GeneGenieDx Corp, 160 E Tasman Dr, San Jose, CA 95134
| | - Kun Han
- GeneGenieDx Corp, 160 E Tasman Dr, San Jose, CA 95134
| | - Wenying Pan
- GeneGenieDx Corp, 160 E Tasman Dr, San Jose, CA 95134
| | - Xiao Yang
- GeneGenieDx Corp, 160 E Tasman Dr, San Jose, CA 95134
| | - Zexuan Zhu
- College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, 518000, China
| |
Collapse
|
5
|
Literature Mining of Disease Associated Noncoding RNA in the Omics Era. Molecules 2022; 27:molecules27154710. [PMID: 35897884 PMCID: PMC9331993 DOI: 10.3390/molecules27154710] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/16/2022] [Revised: 07/20/2022] [Accepted: 07/22/2022] [Indexed: 02/01/2023] Open
Abstract
Noncoding RNAs (ncRNA) are transcripts without protein-coding potential that play fundamental regulatory roles in diverse cellular processes and diseases. The application of deep sequencing experiments in ncRNA research have generated massive omics datasets, which require rapid examination, interpretation and validation based on exiting knowledge resources. Thus, text-mining methods have been increasingly adapted for automatic extraction of relations between an ncRNA and its target or a disease condition from biomedical literature. These bioinformatics tools can also assist in more complex research, such as database curation of candidate ncRNAs and hypothesis generation with respect to pathophysiological mechanisms. In this concise review, we first introduced basic concepts and workflow of literature mining systems. Then, we compared available bioinformatics tools tailored for ncRNA studies, including the tasks, applicability, and limitations. Their powerful utilities and flexibility are demonstrated by examples in a variety of diseases, such as Alzheimer’s disease, atherosclerosis and cancers. Finally, we outlined several challenges from the viewpoints of both system developers and end users. We concluded that the application of text-mining techniques will booster disease-associated ncRNA discoveries in the biomedical literature and enable integrative biology in the current omics era.
Collapse
|
6
|
Roychowdhury D, Gupta S, Qin X, Arighi CN, Vijay-Shanker K. emiRIT: a text-mining-based resource for microRNA information. DATABASE-THE JOURNAL OF BIOLOGICAL DATABASES AND CURATION 2021; 2021:6287648. [PMID: 34048547 PMCID: PMC8163238 DOI: 10.1093/database/baab031] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 11/23/2020] [Revised: 03/15/2021] [Accepted: 05/04/2021] [Indexed: 01/18/2023]
Abstract
microRNAs (miRNAs) are essential gene regulators, and their dysregulation often leads to diseases. Easy access to miRNA information is crucial for interpreting generated experimental data, connecting facts across publications and developing new hypotheses built on previous knowledge. Here, we present extracting miRNA Information from Text (emiRIT), a text-miningbased resource, which presents miRNA information mined from the literature through a user-friendly interface. We collected 149 ,233 miRNA –PubMed ID pairs from Medline between January 1997 and May 2020. emiRIT currently contains ‘miRNA –gene regulation’ (69 ,152 relations), ‘miRNA disease (cancer)’ (12 ,300 relations), ‘miRNA –biological process and pathways’ (23, 390 relations) and circulatory ‘miRNAs in extracellular locations’ (3782 relations). Biological entities and their relation to miRNAs were extracted from Medline abstracts using publicly available and in-house developed text-mining tools, and the entities were normalized to facilitate querying and integration. We built a database and an interface to store and access the integrated data, respectively. We provide an up-to-date and user-friendly resource to facilitate access to comprehensive miRNA information from the literature on a large scale, enabling users to navigate through different roles of miRNA and examine them in a context specific to their information needs. To assess our resource’s information coverage, we have conducted two case studies focusing on the target and differential expression information of miRNAs in the context of cancer and a third case study to assess the usage of emiRIT in the curation of miRNA information. Database URL: https://research.bioinformatics.udel.edu/emirit/
Collapse
Affiliation(s)
- Debarati Roychowdhury
- Department of Computer and Information Sciences, University of Delaware, 101 Smith Hall, 18 Amstel Ave, Newark, DE 19716, USA
| | - Samir Gupta
- Department of Computer and Information Sciences, University of Delaware, 101 Smith Hall, 18 Amstel Ave, Newark, DE 19716, USA
| | - Xihan Qin
- Department of Computer and Information Sciences, Center of Bioinformatics and Computational Biology, University of Delaware, 15 Innovation Way, Room 205, Newark, DE 19711, USA
| | - Cecilia N Arighi
- Department of Computer and Information Sciences, Center of Bioinformatics and Computational Biology, University of Delaware, 15 Innovation Way, Room 205, Newark, DE 19711, USA
| | - K Vijay-Shanker
- Department of Computer and Information Sciences, University of Delaware, 101 Smith Hall, 18 Amstel Ave, Newark, DE 19716, USA
| |
Collapse
|
7
|
Le DH, Tran TTH. RWRMTN: a tool for predicting disease-associated microRNAs based on a microRNA-target gene network. BMC Bioinformatics 2020; 21:244. [PMID: 32539680 PMCID: PMC7296691 DOI: 10.1186/s12859-020-03578-3] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/04/2019] [Accepted: 06/01/2020] [Indexed: 12/13/2022] Open
Abstract
BACKGROUND The misregulation of microRNA (miRNA) has been shown to cause diseases. Recently, we have proposed a computational method based on a random walk framework on a miRNA-target gene network to predict disease-associated miRNAs. The prediction performance of our method is better than that of some existing state-of-the-art network- and machine learning-based methods since it exploits the mutual regulation between miRNAs and their target genes in the miRNA-target gene interaction networks. RESULTS To facilitate the use of this method, we have developed a Cytoscape app, named RWRMTN, to predict disease-associated miRNAs. RWRMTN can work on any miRNA-target gene network. Highly ranked miRNAs are supported with evidence from the literature. They then can also be visualized based on the rankings and in relationships with the query disease and their target genes. In addition, automation functions are also integrated, which allow RWRMTN to be used in workflows from external environments. We demonstrate the ability of RWRMTN in predicting breast and lung cancer-associated miRNAs via workflows in Cytoscape and other environments. CONCLUSIONS Considering a few computational methods have been developed as software tools for convenient uses, RWRMTN is among the first GUI-based tools for the prediction of disease-associated miRNAs which can be used in workflows in different environments.
Collapse
Affiliation(s)
- Duc-Hau Le
- Department of Computational Biomedicine, Vingroup Big Data Institute, No 7, Bang Lang 1 Street, Viet Hung Ward, Long Bien District, Hanoi, Vietnam.
| | - Trang T H Tran
- Department of Computational Biomedicine, Vingroup Big Data Institute, No 7, Bang Lang 1 Street, Viet Hung Ward, Long Bien District, Hanoi, Vietnam
| |
Collapse
|
8
|
Wang S, Talukder A, Cha M, Li X, Hu H. Computational annotation of miRNA transcription start sites. Brief Bioinform 2020; 22:380-392. [PMID: 32003428 PMCID: PMC7820843 DOI: 10.1093/bib/bbz178] [Citation(s) in RCA: 17] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [Abstract] [Key Words] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/04/2019] [Revised: 12/13/2019] [Accepted: 12/29/2019] [Indexed: 12/26/2022] Open
Abstract
Motivation MicroRNAs (miRNAs) are small noncoding RNAs that play important roles in gene regulation and phenotype development. The identification of miRNA transcription start sites (TSSs) is critical to understand the functional roles of miRNA genes and their transcriptional regulation. Unlike protein-coding genes, miRNA TSSs are not directly detectable from conventional RNA-Seq experiments due to miRNA-specific process of biogenesis. In the past decade, large-scale genome-wide TSS-Seq and transcription activation marker profiling data have become available, based on which, many computational methods have been developed. These methods have greatly advanced genome-wide miRNA TSS annotation. Results In this study, we summarized recent computational methods and their results on miRNA TSS annotation. We collected and performed a comparative analysis of miRNA TSS annotations from 14 representative studies. We further compiled a robust set of miRNA TSSs (RSmirT) that are supported by multiple studies. Integrative genomic and epigenomic data analysis on RSmirT revealed the genomic and epigenomic features of miRNA TSSs as well as their relations to protein-coding and long non-coding genes. Contact xiaoman@mail.ucf.edu, haihu@cs.ucf.edu
Collapse
Affiliation(s)
- Saidi Wang
- Computer Science, University of Central Florida, Orlando, FL-32816, US
| | - Amlan Talukder
- Computer Science, University of Central Florida, Orlando, FL-32816, US
| | - Mingyu Cha
- Computer Science, University of Central Florida, Orlando, FL-32816, US
| | - Xiaoman Li
- Burnett School of Biomedical Science, University of Central Florida, Orlando, FL-32816, US
| | - Haiyan Hu
- Computer Science, University of Central Florida, Orlando, FL-32816, US
| |
Collapse
|
9
|
Correlation of Circulating miR-765, miR-93-5p, and miR-433-3p to Obstructive Coronary Heart Disease Evaluated by Cardiac Computed Tomography. Am J Cardiol 2019; 124:176-182. [PMID: 31084998 DOI: 10.1016/j.amjcard.2019.04.016] [Citation(s) in RCA: 26] [Impact Index Per Article: 5.2] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/18/2019] [Revised: 04/01/2019] [Accepted: 04/05/2019] [Indexed: 12/13/2022]
Abstract
Epigenetic-sensitive mechanisms may be correlated both to pathogenesis and prognosis of coronary heart disease (CHD). We prospectively investigated some plasma circulating microRNA levels in patients undergoing cardiac computed tomography for suspected CHD (n = 95). We show that let-7c-5p, miR-765, miR-483-5p, miR-31-5p, and miR-206 were upregulated in CHD patients (n = 66) versus healthy subjects HS (n = 29); moreover, let-7c-5p, miR-765, miR- 483-5p showed higher expression in obstructive CHD (n = 36) compared to no obstructive CHD patients (n = 66). Remarkably, miR-765, miR-93-5p, and miR-433-3p showed an upregulation in patients with critical coronary stenosis. Multivariate regression analysis demonstrated that miR-765, miR-31-5p, and miR-206 were independently associated with CHD while circulating levels of miR-765 (p = 0.035), miR-433-3p (p = 0.043), and miR-93-5p (p = 0.041) were significantly higher in critical stenosis patients. Receiver operating characteristic curve analysis revealed a good performance for miR-765, miR-93-5p, and miR-433-3p on predicting CHD severity. In conclusion, our study represents a combined epigenetic/imaging approach useful to support the diagnosis and prediction of CHD.
Collapse
|
10
|
Dai HJ, Wang CK, Chang NW, Huang MS, Jonnagaddala J, Wang FD, Hsu WL. Statistical principle-based approach for recognizing and normalizing microRNAs described in scientific literature. DATABASE-THE JOURNAL OF BIOLOGICAL DATABASES AND CURATION 2019; 2019:5365313. [PMID: 30809637 PMCID: PMC6391575 DOI: 10.1093/database/baz030] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 02/28/2018] [Revised: 02/01/2019] [Accepted: 02/06/2019] [Indexed: 01/08/2023]
Abstract
The detection of MicroRNA (miRNA) mentions in scientific literature facilitates researchers with the ability to find relevant and appropriate literature based on queries formulated using miRNA information. Considering most published biological studies elaborated on signal transduction pathways or genetic regulatory information in the form of figure captions, the extraction of miRNA from both the main content and figure captions of a manuscript is useful in aggregate analysis and comparative analysis of the studies published. In this study, we present a statistical principle-based miRNA recognition and normalization method to identify miRNAs and link them to the identifiers in the Rfam database. As one of the core components in the text mining pipeline of the database miRTarBase, the proposed method combined the advantages of previous works relying on pattern, dictionary and supervised learning and provided an integrated solution for the problem of miRNA identification. Furthermore, the knowledge learned from the training data was organized in a human-interpretable manner to understand the reason why the system considers a span of text as a miRNA mention, and the represented knowledge can be further complemented by domain experts. We studied the ambiguity level of miRNA nomenclature to connect the miRNA mentions to the Rfam database and evaluated the performance of our approach on two datasets: the BioCreative VI Bio-ID corpus and the miRNA interaction corpus by extending the later corpus with additional Rfam normalization information. Our study highlights and also proposes a better understanding of the challenges associated with miRNA identification and normalization in scientific literature and the research gap that needs to be further explored in prospective studies.
Collapse
Affiliation(s)
- Hong-Jie Dai
- Department of Electrical Engineering, National Kaohsiung University of Science and Technology, Kaohsiung, Taiwan, ROC
| | - Chen-Kai Wang
- Big Data Laboratories, Chunghwa Telecom Co., Taoyuan, Taiwan, ROC
| | - Nai-Wen Chang
- Graduate Institute of Biomedical Electronics and Bioinformatics, National Taiwan University, Taipei, Taiwan.,Institute of Information Science, Academia Sinica, Taipei, Taiwan
| | - Ming-Siang Huang
- Institute of Information Science, Academia Sinica, Taipei, Taiwan
| | - Jitendra Jonnagaddala
- School of Public Health and Community Medicine, University of New South Wales, Sydney, Australia
| | - Feng-Duo Wang
- Department of Computer Science and Information Engineering, National Taitung University, Taitung, Taiwan
| | - Wen-Lian Hsu
- Institute of Information Science, Academia Sinica, Taipei, Taiwan
| |
Collapse
|
11
|
Liu S, Shen F, Komandur Elayavilli R, Wang Y, Rastegar-Mojarad M, Chaudhary V, Liu H. Extracting chemical-protein relations using attention-based neural networks. DATABASE-THE JOURNAL OF BIOLOGICAL DATABASES AND CURATION 2018; 2018:5122756. [PMID: 30295724 PMCID: PMC6174551 DOI: 10.1093/database/bay102] [Citation(s) in RCA: 18] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 02/28/2018] [Accepted: 09/10/2018] [Indexed: 11/14/2022]
Abstract
Relation extraction is an important task in the field of natural language processing. In this paper, we describe our approach for the BioCreative VI Task 5: text mining chemical-protein interactions. We investigate multiple deep neural network (DNN) models, including convolutional neural networks, recurrent neural networks (RNNs) and attention-based (ATT-) RNNs (ATT-RNNs) to extract chemical-protein relations. Our experimental results indicate that ATT-RNN models outperform the same models without using attention and the ATT-gated recurrent unit (ATT-GRU) achieves the best performing micro average F1 score of 0.527 on the test set among the tested DNNs. In addition, the result of word-level attention weights also shows that attention mechanism is effective on selecting the most important trigger words when trained with semantic relation labels without the need of semantic parsing and feature engineering. The source code of this work is available at https://github.com/ohnlp/att-chemprot.
Collapse
Affiliation(s)
- Sijia Liu
- Department of Health Sciences Research, Mayo Clinic, Rochester, MN, USA.,Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY, USA
| | - Feichen Shen
- Department of Health Sciences Research, Mayo Clinic, Rochester, MN, USA
| | | | - Yanshan Wang
- Department of Health Sciences Research, Mayo Clinic, Rochester, MN, USA
| | - Majid Rastegar-Mojarad
- Department of Health Sciences Research, Mayo Clinic, Rochester, MN, USA.,University of Wisconsin-Milwaukee, Milwaukee, WI, USA
| | - Vipin Chaudhary
- Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY, USA
| | - Hongfang Liu
- Department of Health Sciences Research, Mayo Clinic, Rochester, MN, USA
| |
Collapse
|
12
|
Mahmood ASMA, Rao S, McGarvey P, Wu C, Madhavan S, Vijay-Shanker K. eGARD: Extracting associations between genomic anomalies and drug responses from text. PLoS One 2017; 12:e0189663. [PMID: 29261751 PMCID: PMC5738129 DOI: 10.1371/journal.pone.0189663] [Citation(s) in RCA: 14] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/26/2017] [Accepted: 11/29/2017] [Indexed: 12/25/2022] Open
Abstract
Tumor molecular profiling plays an integral role in identifying genomic anomalies which may help in personalizing cancer treatments, improving patient outcomes and minimizing risks associated with different therapies. However, critical information regarding the evidence of clinical utility of such anomalies is largely buried in biomedical literature. It is becoming prohibitive for biocurators, clinical researchers and oncologists to keep up with the rapidly growing volume and breadth of information, especially those that describe therapeutic implications of biomarkers and therefore relevant for treatment selection. In an effort to improve and speed up the process of manually reviewing and extracting relevant information from literature, we have developed a natural language processing (NLP)-based text mining (TM) system called eGARD (extracting Genomic Anomalies association with Response to Drugs). This system relies on the syntactic nature of sentences coupled with various textual features to extract relations between genomic anomalies and drug response from MEDLINE abstracts. Our system achieved high precision, recall and F-measure of up to 0.95, 0.86 and 0.90, respectively, on annotated evaluation datasets created in-house and obtained externally from PharmGKB. Additionally, the system extracted information that helps determine the confidence level of extraction to support prioritization of curation. Such a system will enable clinical researchers to explore the use of published markers to stratify patients upfront for 'best-fit' therapies and readily generate hypotheses for new clinical trials.
Collapse
Affiliation(s)
- A. S. M. Ashique Mahmood
- Department of Computer and Information Science, University of Delaware, Newark, Delaware, United States of America
- * E-mail:
| | - Shruti Rao
- Innovation Center For Biomedical Informatics, Georgetown University, Washington D.C, United States of America
| | - Peter McGarvey
- Innovation Center For Biomedical Informatics, Georgetown University, Washington D.C, United States of America
- Protein Information Resource, Georgetown University Medical Center, Washington D.C, United States of America
| | - Cathy Wu
- Department of Computer and Information Science, University of Delaware, Newark, Delaware, United States of America
- Protein Information Resource, Georgetown University Medical Center, Washington D.C, United States of America
- Center for Bioinformatics and Computational Biology, University of Delaware, Newark, Delaware, United States of America
| | - Subha Madhavan
- Innovation Center For Biomedical Informatics, Georgetown University, Washington D.C, United States of America
- Lombardi Comprehensive Cancer Center, Georgetown University Medical Center, Washington D.C, United States of America
| | - K. Vijay-Shanker
- Department of Computer and Information Science, University of Delaware, Newark, Delaware, United States of America
| |
Collapse
|
13
|
Roy S, Curry BC, Madahian B, Homayouni R. Prioritization, clustering and functional annotation of MicroRNAs using latent semantic indexing of MEDLINE abstracts. BMC Bioinformatics 2016; 17:350. [PMID: 27766940 PMCID: PMC5073981 DOI: 10.1186/s12859-016-1223-2] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/07/2023] Open
Abstract
Background The amount of scientific information about MicroRNAs (miRNAs) is growing exponentially, making it difficult for researchers to interpret experimental results. In this study, we present an automated text mining approach using Latent Semantic Indexing (LSI) for prioritization, clustering and functional annotation of miRNAs. Results For approximately 900 human miRNAs indexed in miRBase, text documents were created by concatenating titles and abstracts of MEDLINE citations which refer to the miRNAs. The documents were parsed and a weighted term-by-miRNA frequency matrix was created, which was subsequently factorized via singular value decomposition to extract pair-wise cosine values between the term (keyword) and miRNA vectors in reduced rank semantic space. LSI enables derivation of both explicit and implicit associations between entities based on word usage patterns. Using miR2Disease as a gold standard, we found that LSI identified keyword-to-miRNA relationships with high accuracy. In addition, we demonstrate that pair-wise associations between miRNAs can be used to group them into categories which are functionally aligned. Finally, term ranking by querying the LSI space with a group of miRNAs enabled annotation of the clusters with functionally related terms. Conclusions LSI modeling of MEDLINE abstracts provides a robust and automated method for miRNA related knowledge discovery. The latest collection of miRNA abstracts and LSI model can be accessed through the web tool miRNA Literature Network (miRLiN) at http://bioinfo.memphis.edu/mirlin. Electronic supplementary material The online version of this article (doi:10.1186/s12859-016-1223-2) contains supplementary material, which is available to authorized users.
Collapse
Affiliation(s)
- Sujoy Roy
- Bioinformatics Program, University of Memphis, Memphis, 38152, USA.,Center for Translational Informatics, University of Memphis, Memphis, 38152, USA
| | - Brandon C Curry
- Bioinformatics Program, University of Memphis, Memphis, 38152, USA
| | - Behrouz Madahian
- Department of Mathematical Sciences, University of Memphis, Memphis, 38152, USA
| | - Ramin Homayouni
- Bioinformatics Program, University of Memphis, Memphis, 38152, USA. .,Center for Translational Informatics, University of Memphis, Memphis, 38152, USA. .,Department of Biology, University of Memphis, Memphis, 38152, USA.
| |
Collapse
|