Session
Schedule FOSDEM 2022
Open Research Tools and Technologies

Ersilia, a hub of AI/ML models for infectious disease research

Democratizing the access to state-of-the-art data science to researchers worldwide.
D.research
Gemma Turon
<p>Low and Middle Income Countries (LMIC) produce less than 10% of the world's scientific output, largely relying on solutions devised in the Global North, which are often unable to meet the real needs of their population. Data science and machine learning offer a unique opportunity to empower scientists in LMIC by providing cost-effective tools ideal for underfunded settings, but there is a gap in accessibility, infrastructure and skills that must be bridged before these tools can be effectively implemented. We are developing the Ersilia Model Hub, a FLOSS platform where scientists can browse through a catalogue of AI/ML models and run them without the need to write a single line of code. The platform features both models published in the literature and models developed by us on-demand or in collaboration with researchers in LMIC. The pilot tool focuses on models for drug discovery in infectious and neglected tropical diseases, but we plan to expand to other global health.</p>
The Ersilia Model Hub is currently in alpha development, and it will be released in January 2022, containing 100 models. The MVP must be downloaded in the user’s computers and is accessible via a command-line interface. The models are fetched from our GitHub repository and run locally. They are designed to perform on regular personal computers. In the next phases, an online query system will be implemented for the most popular models, together with a user-friendly interface which does not require use of the CLI. In addition, we are working towards an end-to-end automated AI/ML pipeline to facilitate the creation and implementation of models trained on specific datasets of relevance to each of our users. This package will also be available early 2022.

Additional information

Type devroom

More sessions

2/5/22
Open Research Tools and Technologies
D.research
<p>The Open Research Tools and Technologies devroom managers welcome words announcing the schedule.</p>
2/5/22
Open Research Tools and Technologies
Ian Johnson
D.research
<p>This presentation is about the development and trajectory of Heurist (HeuristNetwork.org), a shared, integrated, extensible data infrastructure (model, build, manage, analyse, visualise, share, publish via integrated CMS) for Humanities research capable of handling the needs of many heterogeneous projects on a single standalone service*, with optional integration across multiple servers by a coordinating index (itself based on Heurist).</p> <p>Humanities data are interesting (both technically ...
2/5/22
Open Research Tools and Technologies
D.research
<p>Developed from 1995 onward, Prospero is a framework for longitudinal analysis of text corpora. Based on dictionaries and semi-automatic classification, it mainly allows its user to combine approaches of statistical computation, co-occurrence network and search for nested patterns. Inspired by pragmatic sociology, it focuses on the multiple forms of expression and argumentation used by actors, on language regimes and on the identification of transformations occurring in the research case. ...
2/5/22
Open Research Tools and Technologies
John Boy
D.research
<p>I am a social scientist who mostly teaches and conducts qualitative research, but I am also a programmer. Over the years, I have contributed to a variety of free and open source software projects, and since 2019, I have developed and maintained <code>textnets</code>, a Python package for text analysis that represents collections of texts as networks of documents and words, providing novel possibilities for the visualization and analysis of texts. In my field, such software development efforts ...
2/5/22
Open Research Tools and Technologies
D.research
<p>Discussion panel of three testimonies from academics developing software.</p>
2/5/22
Open Research Tools and Technologies
Robin De Mourat
D.research
<p>The writing of web publications mixing data visualization and textual prose opens novel opportunities for connecting evidence, arguments and narrative in social sciences communities. Such a practice poses a variety of challenges in terms of website design and development ; but also and maybe more importantly, it asks for experimenting specific workflows for coordinating a variety of expertises ranging from social sciences disciplines (history, sociology, etc.) to data science, information ...
2/5/22
Open Research Tools and Technologies
Evgeny Karev
D.research
<p>This talk will show a new Python tool called Livemark, which is designed for data journalism software education, and documentation writing. Using Livemark, you can collect and present data with interactive tables, charts, and other elements without leaving a text editor. You can also write documentation with live script execution similar to a lightweight version of a Jupiter Notebook. This talk will demo Livemark and will be well-suited for a technical and non-technical audience that is ...