corona-ml VS covasim

That's incredibly hard for a layperson to do effectively. The sheer volume of information to digest is absolutely overwhelming - we're at over 250,000 papers published on covid since the start of the pandemic. It's good that we have these in the public domain, so we can check the content as a greater community effort, but we have to be careful not to let our individual efforts sway our personal judgement too far.

Hi, we're recruiting a PhD student to research methods for extracting the impact of SARS-CoV-2 mutations from the research literature. This builds upon our existing work on CoronaCentral (https://coronacentral.ai) and is an industry collaborative PhD with Biorelate (https://biorelate.com/). Unfortunately it is only open to UK students.

The SARS-CoV-2 pandemic has caused a surge in research exploring all aspects of the virus and its effects on human health. The overwhelming publication rate means that researchers are unable to keep abreast of the literature. To ameliorate this, we present the CoronaCentral resource that uses machine learning to process the research literature on SARS-CoV-2 together with SARS-CoV and MERS-CoV. We categorize the literature into useful topics and article types and enable analysis of the contents, pace, and emphasis of research during the crisis with integration of Altmetric data. These topics include therapeutics, disease forecasting, as well as growing areas such as “long COVID” and studies of inequality. This resource, available at https://coronacentral.ai, is updated daily.

Locations are found in published and preprint articles from the CoronaCentral resource (https://coronacentral.ai). Locations include cities, countries, states, provinces, etc. This takes text from PubMed, preprint servers and others (including the CORD-19 dataset). Locations are extracted using synonyms pulled from Wikidata. More details are in the preprint: https://www.biorxiv.org/content/10.1101/2020.12.21.423860v1 and the code is available at: https://github.com/jakelever/corona-ml. The visualization was made using maps and gganimate in R. I found this tutorial helpful: https://d4tagirl.com/2017/05/how-to-plot-animated-maps-with-gganimate

The data is from CoronaCentral (https://coronacentral.ai). The topics are identified using a BERT-based supervised learning method. We've annotated about ~3200 articles with topics and article types and trained a classifier on them. More details are in the preprint: https://www.biorxiv.org/content/10.1101/2020.12.21.423860v1 and the code is available at: https://github.com/jakelever/corona-ml. The visualization was made using ggplot and gganimate.

It's used a lot in epidemiology. Eg: https://github.com/InstituteforDiseaseModeling/covasim