Unfortunately we don't fully support your browser. If you have the option to, please upgrade to a newer version or use Mozilla Firefox, Microsoft Edge, Google Chrome, or Safari 14 or newer. If you are unable to, and need support, please send us your feedback.
We'd appreciate your feedback.Tell us what you think!(opens in new tab/window)
Go beyond abstracts and open-source data and get the full story. Datasets from full-text scientific literature give you comprehensive, direct access to the most impactful research for your industry. Unlock the full potential of your AI and advanced analytics projects.
Full-text literature has been shown to provide richer data for a more complete research picture. If your data pipeline pulls only from abstracts, you will miss co-occurrences that only appear in the full text. It can often take years for co-occurrences to appear in the abstracts of other articles, which means you could be missing crucial insights in your data.
Using data from open-source scientific literature for your R&D or AI projects can lead to gaps in your data pipeline and hamper these projects during development. In most industries, the majority of relevant scientific literature is not open source or available through free channels. This includes some of the most frequently cited scientific research being published today.
What percentage of full-text scientific literature is not open-source in your industry?*
Pharmaceuticals: 63%
Medical Devices: 69%
Chemicals and Materials: 77%
Energy and Natural Resources: 74%
*Source: Scopus. These numbers represent relevant published scientific literature between 2017-2021.
Recently, an oncology team at AstraZeneca wanted to predict novel drug targets in the context of epigenetic regulation of specific cancers. However, it is difficult to navigate and contextualize the huge and growing body of literature on this subject.
The AstraZeneca team approached Elsevier to find a solution. They provided specific research questions, guiding Elsevier’s data mining from full-text peer-reviewed articles on the ScienceDirect platform. This data was integrated into a subset of Elsevier’s Biology Knowledge Graph to create the “EpiMap,” a custom knowledge graph built specifically for AstraZeneca. An AI workbench was also developed to house computational resources and visualization tools for in-depth data analysis.
Download and read the full case study here.(opens in new tab/window)
How is data science changing R&D and operational excellence in the energy and natural resources industry? We've collected three recent articles from some of the top scientific journals in the industry to explore this question, now available as a free download.
Click below to access the following articles:
A new hybrid approach model for predicting burst pressure of corroded pipelines of gas and oil. Engineering Failure Analysis,Volume 149, July 2023. Haonan Ma, Hantong Wang, Mengying Geng, Yibo Ai, Weidong Zhang, Wenyue Zheng
Data science for building energy efficiency: A comprehensive text-mining driven review of scientific literature. Energy and Buildings, Volume 242, 1 July 2021. Mahmoud M. Abdelrahman, Sicheng Zhan, Clayton Miller, Adrian Chong
A text mining framework for screening catalysts and critical process parameters from scientific literature – A study on Hydrogen production from alcohol. Chemical Engineering Research and Design, Volume 184, August 2022. Avan Kumar, Swathi Ganesh, Divyanshi Gupta, Hariprasad Kodamana
How is data science changing R&D and operational excellence in the chemicals and materials industry? We've collected three recent articles from some of the top scientific journals in the industry to explore this question, now available as a free download.
Click below to access the following articles:
Natural language processing-guided meta-analysis and structure factor database extraction from glass literature. Journal of Non-Crystalline Solids: X, Volume 15, September 2022. Mohd Zaki, Sahith Reddy Namireddy, Tanu Pittie, Vaibhav Bihani, Shweta Rani Keshri, Vineeth Venugopal, Nitya Nand Gosvami, Jayadeva, N.M. Anoop Krishnan
History and trends in solar irradiance and PV power forecasting: A preliminary assessment and review using text mining. Solar Energy, Volume 169, 1 July 2018. Dazhi Yang, Jan Kleissl, Christian A. Gueymard, Hugo T.C. Pedro, Carlos F.M. Coimbra
Machine learning models representing catalytic activity for direct catalytic CO2 hydrogenation to methanol. Materials Today: Proceedings, Volume 72, Part 1, 2023. Pallavi Vanjari, Reddi Kamesh, K. Yamuna Rani
When it comes to using scientific literature in your data pipeline, you can only get the full story from the full study. With direct access to full-text scientific datasets from Elsevier(opens in new tab/window), you can proceed with confidence that you aren’t missing the data and insights that can mean the difference between data science success and failure.
