Royal Society of Chemistry’s journal archives now available to companies for Text and Data Mining

The Royal Society of Chemistry has launched its new Text and Data Mining (TDM) solution, making its full collection of research journals available to companies for AI and machine learning applications. 

With the volume of published research available growing hourly, access to the RSC’s collection in machine-readable format offers companies the opportunity to extract, pinpoint and apply insights from research that stretches across 160 years, covering the full breadth of chemical science.

Companies are increasing looking to AI and machine learning to accelerate their R&D projects and need to be able to integrate published research with public and corporate resources.

Richard Kidd, Head of Chemistry Data at the Royal Society of Chemistry said: “It’s near impossible for researchers to be sure they’ve read all the relevant material, let alone set it in context with their companies’ knowledge.  An important but hidden piece of information, or new connection, could enable new leaps of progress to a programme.

“TDM can reach into the literature and, like pulling ingredients out of a cake, infer structure and results to integrate with other resources to build knowledge. Being able to do this with our high-quality scientific research opens new possibilities and can significantly enhance large-scale research projects.”

The RSC’s research collection delivers this as highly-structured XML, tables, and images – allowing for integration with cross-discipline research projects. Practical licensing tackles one of the key issues raised by users of existing TDM services.

This also allows for integration to machine learning applications, supporting the growth of chemical science knowledge.

Richard continued: “The Royal Society of Chemistry’s Digital Futures report highlighted the significant opportunity presented by smart technology, with AI and machine learning absolutely key to accelerating research and innovation.

“We are working towards a future in which science can be easily interrogated by machine applications as soon as it is published – making our publications available as XML to our industry customers is the first step to achieving this.”

More information on the Royal Society of Chemistry’s Text and Data Mining service can be found at: rsc.li/tdm