openVirus team welcomes you to the Hackathon! Jointly run by ContentMine(Dr. Peter Murray-Rust) and NIPGR(Dr. Gita Yadav), openVirus is a collection of tools to generate knowledge from open Scientific literature.

To begin with, let’s try to understand what it means to extract knowledge from literature and why it’s important:
Roughly, one Million articles get published each year(in the biomedical field alone). Imagine having to read so many articles to make sense out of it. Seems impossible for one person to do it all, doesn’t it? That’s where software tools like getpapers, ami that we are developing, come into the picture. These tools can help us make sense from the vastness that exists without having to read all the papers individually i.e., to extract knowledge from the distributed scientific literature and develop useful inferences. (More information here)

We are currently working on viral epidemics(not just COVID -19). We aim to develop a toolkit that anybody who wants to ask their questions and search the literature to find answers on their own. (To know more, click here)

The team mainly consists of young interns from all around the world and we are excited that we are going to be joined by more people from diverse backgrounds! Anybody from beginners to experts can join us and be a part of this amazing project! Don’t worry if you are new to programming. We know from experience that anybody can learn to use all the software pretty quickly. With perseverance, commitment and collaboration, we all can learn new exciting things and contribute towards extraction of knowledge from the literature.

If you find the project interesting and want to know more, here is a schematic overview:

All the interns are currently working on their mini-projects and, we have been able to achieve a lot in a small time-frame. We have created our dictionaries (using wiki data) and mini-corpora (using EUPMC). The table below summarises our work thus far:

You can either use these dictionaries, mini-corpus for your project, or you can make your own(more info about that in How to Get Started section)

After having a brief overview of the project, it’s time that you get started with your own mini-project. It can be a bit overwhelming at the beginning. To make it easy, here are the links that can help you get started:

• Materials for the Hackathon
• Install getpapers
• Installing ami
• Dictionary: Overview
• A video tutorial on how to run ami search can be found here
• Tools: Docker
• Jupyter Notebooks

• Natural Language Processing(Machine Learning)
• Dockerised Containers
• Data display
• Multilinguality

Our interns have shown that you don’t need fancy high-end workstations to do science. Most of us were beginners and were able to pick up the tech pretty speedily. There is extensive documentation, tutorials and explanation on openVirus wiki pages. Feel free to explore to get a sense of how the project works and what it aims to do. If you have any doubts, queries or even new ideas, we are always there! You can leave your questions on our GitHub page or ask us directly, during the HACKATHON. We look forward to seeing you!