An integrated text mining framework for metabolic interaction network reconstruction

Patumcharoenpol, Preecha; Doungpan, Narumol; Meechai, Asawin; Shen, Bairong; Chan, Jonathan H.; Vongsangnak, Wanwipa

doi:10.7717/peerj.1811

Cited by 11 publications

(4 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, there are resources on protein–protein interactions, including the PPI ( 15 ) corpus used in BioCreative II and the BioInfer ( 16 ) corpus. Specialized corpora on drug–drug interactions, exemplified by the DDI corpus ( 17 ) released as part of SemEval2013; chemical diseased interactions, like the CDR corpus ( 18 ), a component part of the BioCreative V venue; or enzyme–metabolite interactions, such as ME corpus ( 19 )), among many others.…”

Section: Introductionmentioning

confidence: 99%

Overview of DrugProt task at BioCreative VII: data and methods for large-scale text mining and knowledge graph generation of heterogenous chemical–protein relations

Miranda-Escalada,

Mehryary,

Luoma

et al. 2023

Database

View full text Add to dashboard Cite

It is getting increasingly challenging to efficiently exploit drug-related information described in the growing amount of scientific literature. Indeed, for drug–gene/protein interactions, the challenge is even bigger, considering the scattered information sources and types of interactions. However, their systematic, large-scale exploitation is key for developing tools, impacting knowledge fields as diverse as drug design or metabolic pathway research. Previous efforts in the extraction of drug–gene/protein interactions from the literature did not address these scalability and granularity issues. To tackle them, we have organized the DrugProt track at BioCreative VII. In the context of the track, we have released the DrugProt Gold Standard corpus, a collection of 5000 PubMed abstracts, manually annotated with granular drug–gene/protein interactions. We have proposed a novel large-scale track to evaluate the capacity of natural language processing systems to scale to the range of millions of documents, and generate with their predictions a silver standard knowledge graph of 53 993 602 nodes and 19 367 406 edges. Its use exceeds the shared task and points toward pharmacological and biological applications such as drug discovery or continuous database curation. Finally, we have created a persistent evaluation scenario on CodaLab to continuously evaluate new relation extraction systems that may arise. Thirty teams from four continents, which involved 110 people, sent 107 submission runs for the Main DrugProt track, and nine teams submitted 21 runs for the Large Scale DrugProt track. Most participants implemented deep learning approaches based on pretrained transformer-like language models (LMs) such as BERT or BioBERT, reaching precision and recall values as high as 0.9167 and 0.9542 for some relation types. Finally, some initial explorations of the applicability of the knowledge graph have shown its potential to explore the chemical–protein relations described in the literature, or chemical compound–enzyme interactions. Database URL: https://doi.org/10.5281/zenodo.4955410

show abstract

Section: Introductionmentioning

confidence: 99%

Overview of DrugProt task at BioCreative VII: data and methods for large-scale text mining and knowledge graph generation of heterogenous chemical–protein relations

Miranda-Escalada,

Mehryary,

Luoma

et al. 2023

Database

View full text Add to dashboard Cite

show abstract

“…A TM framework for the detection of metabolic interactions, that is, enzyme–metabolite interactions, was recently developed by Patumcharoenpol and colleagues . They differentiated between four classes of metabolic relation types or events, metabolic production, metabolic consumption, metabolic reaction, and positive regulation relationships.…”

Section: Integration Of Chemical and Biological Datamentioning

confidence: 99%

“…Similarly, another hybrid metabolite NER system combining mainly dictionary-lookup with CRFs was recently presented by Kongburan et al 747 A TM framework for the detection of metabolic interactions, that is, enzyme−metabolite interactions, was recently developed by Patumcharoenpol and colleagues. 748 They differentiated between four classes of metabolic relation types or events, metabolic production, metabolic consumption, metabolic reaction, and positive regulation relationships. The used framework integrated existing NER systems to detect genes/ proteins and metabolite compounds from the CheEBI dictionary.…”

Section: Chemical Reviewsmentioning

confidence: 99%

Information Retrieval and Text Mining Technologies for Chemistry

et al. 2017

View full text Add to dashboard Cite

Efficient access to chemical information contained in scientific literature, patents, technical reports, or the web is a pressing need shared by researchers and patent attorneys from different chemical disciplines. Retrieval of important chemical information in most cases starts with finding relevant documents for a particular chemical compound or family. Targeted retrieval of chemical documents is closely connected to the automatic recognition of chemical entities in the text, which commonly involves the extraction of the entire list of chemicals mentioned in a document, including any associated information. In this Review, we provide a comprehensive and in-depth description of fundamental concepts, technical implementations, and current technologies for meeting these information demands. A strong focus is placed on community challenges addressing systems performance, more particularly CHEMDNER and CHEMDNER patents tasks of BioCreative IV and V, respectively. Considering the growing interest in the construction of automatically annotated chemical knowledge bases that integrate chemical information and biological data, cheminformatics approaches for mapping the extracted chemical names into chemical structures and their subsequent annotation together with text mining applications for linking chemistry with biological information are also presented. Finally, future trends and current challenges are highlighted as a roadmap proposal for research in this emerging field.

show abstract

“…It can be used as a generic check-lists useful for planning the project [15]. Some are very specific in purpose such as in [11]. This paper proposes a framework in doing a text mining in a scientometric study which has a focus on the role of the domain experts.…”

Section: Frameworkmentioning

confidence: 99%

A Framework for Text Mining in Scientometric Study: A Case Study in Biomedicine Publications

Silalahi

Hardiyati

Nadhiroh

et al. 2018

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Abstract. The data of Indonesians research publications in the domain of biomed icine has been collected to be text mined for the purpose of a scientometric study. The goal is to build a predictive model that provides a classification of research publications on the potency for downstreaming. The model is based on the drug development process es adapted from the literatures. An effort is described to build the conceptual model and the development of a corpus on the research publications in the domain of Indonesian biomedicine. Then an investigation is conducted relating to the problems associated with building a corpus and validating the model. Based on our experience, a framework is proposed to manage the scientometric study based on text min ing. Our method shows the effectiveness of conducting a scientometric study based on text min ing in order to get a valid classification model. Th is valid model is main ly supported by the iterative and close interactions with the domain experts starting from identifying the issues, building a conceptual model, to the labelling, validation and results interpretation.

show abstract

An integrated text mining framework for metabolic interaction network reconstruction

Cited by 11 publications

References 33 publications

Overview of DrugProt task at BioCreative VII: data and methods for large-scale text mining and knowledge graph generation of heterogenous chemical–protein relations

Overview of DrugProt task at BioCreative VII: data and methods for large-scale text mining and knowledge graph generation of heterogenous chemical–protein relations

Information Retrieval and Text Mining Technologies for Chemistry

A Framework for Text Mining in Scientometric Study: A Case Study in Biomedicine Publications

Contact Info

Product

Resources

About