Skip to main content


We are in the process of rolling out a soft launch of the RDA website, which includes a new member platform. Existing RDA members PLEASE REACTIVATE YOUR ACCOUNT using this link: Visitors may encounter functionality issues with group pages, navigation, missing content, broken links, etc. As you explore the new site, please provide your feedback using the UserSnap tool on the bottom right corner of each page. Thank you for your understanding and support as we work through all issues as quickly as possible. Stay updated about upcoming features and functionalities:

Homepage Forums RDA COVID-19 Main Forum RDA COVID-19 Posts RDA COVID Group – some things to note RDA COVID Group – some things to note


Hi All,
With regards to text mining, and in case you missed it, Kaggle are currently running a research challenge ( on the CORD-19 dataset (
All the best,
– Show quoted text -From: ***@***.***
Sent: 25 March 2020 19:38
Subject: Re: [rda-covid19] RDA COVID Group – some things to note
Dear All,
I do have some experience to organize data and knowledge for an entire indication area; my team at Fraunhofer SCAI has – in collaboration with colleagues at Fraunhofer IME in Hamburg – started to create a MindMap that captures various aspects of SARS-CoV-2 biology, epidemiology and information about the drug-target space. Another team (lead by Alpha Tom Kodamullil) in my Department has started to work on a terminology for COVID concepts and terms. Ultimately, we will generate a knowledge-based model of SARS-CoV-2; the network models recently published help us to move fast in this area.
Furthermore, under the guidance of Juliane Fluck (Information Center Life Sciences, ZBMED, Cologne), we have started to generate a text mining machine for COVID. This text mining machine has a focus on the identification and extraction of chemical entities in relevant publications; the idea is that we want to systematically extract all potential repurposing candidate compounds from the literature (and there is a strong need for this, as everywhere in the world, supercomputer folks are running docking-MD like crazy and they need promising input structures).
Colleagues from Fraunhofer IME are currently looking into clinical studies in this area; as usual, they identified challenges with respect to variable names, spelling, lack of reference mappings …. the usual mess. If anybody here is already working on harmonizing the clinical study data available (including “related” studies like MERS and SARS CoV-1); I am happy to mediate contacts.
@Wei (Luxembourg): are you working on a text mining pipeline for COVID-19 ? Would be cool to align efforts …
best wishes

Full post:
Manage my subscriptions:
Stop emails for this post:
Elsevier Limited. Registered Office: The Boulevard, Langford Lane, Kidlington, Oxford, OX5 1GB, United Kingdom, Registration No. 1982084, Registered in England and Wales.