This workshop introduces tools and approaches used to discover biologically relevant data in the research literature. Participants will be introduced to the basics of programmatic analysis of scientific literature and explore the principles of dictionary-based text-mining, explained using relevant case studies. The workshop has a strong focus on practical exercises and group project work to give participants hands-on experience, tackling biologically relevant problems based on what they have learnt in this workshop.

Do you want to identify publicly available datasets cited in research literature to use them in your future analyses? Do you want to develop basic skills to programmatically access and analyse scientific literature? Do you want to learn about the basics of text analytics to make the most of literature review?

Published research contains a wealth of new data and evidence. Automating literature review and text analysis can help extract valuable knowledge from millions of research publications. Modern tools for literature analysis can help you identify potential drug targets, predict host-pathogen interactions, or infer growth regulators for crops, based on published findings.

Who is this course for?

This workshop is aimed at life science researchers, who are interested in extracting data and evidence from research literature. It will help those who want to identify cited datasets for reuse, further analyses, background research, or as supporting data for own hypotheses. The workshop would also be of interest to those who are applying or planning to apply literature analysis/text-mining in their own research projects.

Participants will benefit from an undergraduate level knowledge of biology. Participants should ideally have some bioinformatics experience and/or basic understanding of programmatic access. Please note that this workshop requires no prior knowledge of text analytics or computer programming skills.

Regardless of your current knowledge, we encourage participants to explore this short series of recorded webinars on an introduction to programmatic access.

What will I learn?

Learning outcomes

At the end of the workshop you should be able to:

• Search and locate publicly-available open-access datasets from the scientific literature
• Use programmatic tools to search for data in the literature
• Appreciate the value and limitations of text-mining approaches
• Develop basic sets of heuristics for text analytics
• Apply the information you have discovered in the context of your own research

Course content

During this workshop you will learn about:

• How researchers share and cite data
• How to search for data cited in the literature
• Basics of dictionary-based text mining
• Basics of ontologies
• Programmatic tools to find data and evidence in the literature

Tools and resources covered include: 

• Europe PMC advanced search
• Europe PMC Articles API
• Europe PMC Annotations API

Please note that this workshop does not cover text mining.

Trainers

Attendance at this workshop is allocated on a first come, first served basis.

The registration fee covers your lunch, refreshments and a shuttle between Shuttle to Bus Stop 5, Cambridge Station  and the Wellcome Genome Campus. Accommodation is not included and you will need to make your own arrangements.

Please note that registration closes two weeks prior to the workshop, so please register as soon as you can. Once you have registered and we have received payment we can provide a letter of support should you require a visa to travel to the UK. Applying for a visa can take several weeks, and it might not be possible to be granted a visa if you register just before the closing date. If you are unable to attend, then please notify us as quickly as possible so that we can offer your place to someone else.

Once you have registered please send Meredith Willmott (meredith@ebi.ac.uk) a picture of yourself and a Microsoft Word (.docx) document containing three short paragraphs with a biography, work history and description of your current research interests; each paragraph should be no more than 100 words.

Further reading

More information on the topics covered in the workshop can be found in these papers:

• Kafkas Ş, Kim JH, McEntyre JR. Database citation in full text biomedical articles. PloS one. 2013 ;8(5):e63184.
• Kafkas Ş, Dunham I, McEntyre J. Literature evidence in open targets - a target validation platform. Journal of biomedical semantics. 2017 Jun;8(1):20.

Additional information can also be viewed in these webinars:

• Navigating the data-rich literature: finding evidence in biomedical publications
• Europe PMC, programmatically
• Text mining: Key concepts and applications
• Extracting research evidence from publications