PubMedPortable: A Framework for Supporting the Development of Text Mining Applications

Döring, Kersten; Grüning, Björn; Telukunta, Kiran K.; Thomas, Philippe; Günther, Stefan

doi:10.1371/journal.pone.0163794

Cited by 8 publications

(8 citation statements)

References 31 publications

(52 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, the automated query optimization needs very much computation power, eg, it requires approximately 13 hours for the ILD corpus, because the optimization algorithm uses the PubMed E-Utilities interface. By applying the algorithm to a local PubMed database as suggested by Döring et al, 58 the procedure could be substantially accelerated.…”

Section: The Mismatch Between the Query Derived Frommentioning

confidence: 99%

Potential Technologies Review: A hybrid information retrieval framework to accelerate demand‐pull innovation in biomedical engineering

Schmitz

Bukowski

Koschmieder

et al. 2019

Research Synthesis Methods

View full text Add to dashboard Cite

Launching biomedical innovations based on clinical demands instead of translating basic research findings to practice reduces the risk that the results will not fit the clinical routine. To realize this type of innovation, a meta‐analysis of the body of research is necessary to reveal demand‐matching concepts. However, both the data deluge and the narrow time constraints for innovation make it impossible to perform such reviews manually. Thus, this paper proposes a specifically adapted “Potential Technologies Review” approach focusing on automated text mining and information retrieval techniques. The novel framework combines features from both systematic and scoping reviews. It aims at high coverage and reproducibility while mapping technologies—even with a fuzzy initial scope. To achieve these goals for search and triage, a set of closely interrelated methods has been developed: (a) automated query optimization, (b) screening prioritization, and (c) recall estimation. To determine appropriate parameters, a variety of published literature corpora were used and compared with an evaluation on a real‐world dataset. Our results show that it is feasible to automate the identification of relevant works using this newly introduced framework. It achieved a workload reduction of up to 91% “Work‐saved‐over Sampling (WSS)” with a 76% overall recall compared with manually screening search results. Reducing the workload is a prerequisite for a rapid Potential Technologies Review when conducting demand‐pull innovations. Moreover, it facilitates the updating and closer monitoring of latest findings. Studying the robustness of the framework and expanding it to patent documents are future tasks.

show abstract

Section: The Mismatch Between the Query Derived Frommentioning

confidence: 99%

Potential Technologies Review: A hybrid information retrieval framework to accelerate demand‐pull innovation in biomedical engineering

Schmitz

Bukowski

Koschmieder

et al. 2019

Research Synthesis Methods

View full text Add to dashboard Cite

show abstract

“…Central) allow papers to be downloaded and read individually, but connection to natural language processing tools needed for effective TDM is limited to the open access subset of the collection [Doring et al, 2016].…”

Section: Future Directions For Swm-related Kmmentioning

confidence: 99%

Perspectives from a water research institute on Knowledge Management for Sustainable Water Management

Hering

Nunnenmacher

Waldow

2018

Handbook of Knowledge Management for Sustainable Water Systems

View full text Add to dashboard Cite

A sizeable, and sometimes overwhelming, array of knowledge is available and relevant to Sustainable Water Management (SWM). This knowledge derives not only from the natural, social and engineering sciences but also from practical experiences in water management, which is defined broadly to include all forms of water use as well as the protection of water resources and reduction of risk from water-related hazards. As a publically-funded water research institute, Eawag (the Swiss Federal Institute of Aquatic Science and Technology) faces the challenges of integrating and synthesizing available knowledge, creating new knowledge through research projects and making knowledge available in an accessible form to support engineering practice, water resources management and related policy-making. This chapter examines these challenges from an organizational perspective, discussing measures taken within Eawag to meet them and identifying remaining gaps and possible ways to address them.

show abstract

“…OntoGene is a text mining web service for the detection of proteins, 23 genes, drugs, diseases, chemicals, and their relationships [12]. The identification 24 methods contain rule-based and machine learning approaches, which were successfully 25 applied in the BioCreative challenges, e.g. in the triage task in 2012 [13].…”

mentioning

confidence: 99%

“…The complete compound-protein-interaction benchmark dataset (CPI-DS) was 75 generated from the first 40,000 abstracts of all PubMed articles published in 2009, using 76 PubMedPortable [25]. For further manual annotation, all sentences were transferred to an HTML form.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Automated recognition of functional compound-protein relationships in literature

Döring

Qaseem

Telukunta

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

Motivation: Much effort has been invested in the identification of protein-protein interactions using text mining and machine learning methods. The extraction of functional relationships between chemical compounds and proteins from literature has received much less attention, and no ready-to-use open-source software is so far available for this task. Method: We created a new benchmark dataset of 2,753 sentences from abstracts containing annotations of proteins, small molecules, and their relationships. Two kernel methods were applied to classify these relationships as functional or non-functional, named shallow linguistic and all-paths graph kernel. Furthermore, the benefit of interaction verbs in sentences was evaluated. Results: The cross-validation of the all-paths graph kernel (AUC value: 84.2%, F1 score: 81.8%) shows slightly better results than the shallow linguistic kernel (AUC value: 81.6%, F1 score: 79.7%) on our benchmark dataset. Both models achieve state-of-the-art performance in the research area of relation extraction. Furthermore, the combination of shallow linguistic and all-paths graph kernel could further increase the overall performance. We used each of the two kernels to identify functional relationships in all PubMed abstracts (28 million) and provide the results, including recorded processing time. Availability: The software for the tested kernels, the benchmark, the processed 28 million PubMed abstracts, all evaluation scripts, as well as the scripts for processing the complete PubMed database are freely available at https://github.com/KerstenDoering/CPI-Pipeline. Author summaryText mining aims at organizing large sets of unstructured text data to provide efficient information extraction. Particularly in the area of drug discovery, the knowledge about small molecules and their interactions with proteins is of crucial importance to understand the drug effects on cells, tissues, and organisms. This data is normally hidden in written articles, which are published in journals with a focus on life sciences. In this publication, we show how text mining methods can be used to extract data about functional interactions between small molecules and proteins from texts. We July 24, 2019 1/13 created a new dataset with annotated sentences of scientific abstracts for the purpose of training two diverse machine learning methods (kernels), and successfully classified compound-protein pairs as functional and non-functional relations, i.e. no interactions. Our newly developed benchmark dataset and the pipeline for information extraction are freely available for download. Furthermore, we show that the software can be easily up-scaled to process large datasets by applying the approach to 28 million abstracts. 37 Both kernels have been successfully applied in different domains, including drug-drug 38 interaction extraction [15], the extraction of neuroanatomical connectivity 39 statements [16], and the I2B2 relation extraction challenge [17]. 40 If two biomolecules appear together in a text or a sentence, they...

show abstract

PubMedPortable: A Framework for Supporting the Development of Text Mining Applications

Cited by 8 publications

References 31 publications

Potential Technologies Review: A hybrid information retrieval framework to accelerate demand‐pull innovation in biomedical engineering

Potential Technologies Review: A hybrid information retrieval framework to accelerate demand‐pull innovation in biomedical engineering

Perspectives from a water research institute on Knowledge Management for Sustainable Water Management

Automated recognition of functional compound-protein relationships in literature

Contact Info

Product

Resources

About