PyData Cambridge - 46th Meetup

Agenda

📣📣We are happy to announce the 46th PyData Cambridge meetup!📣📣

Agenda:

18:45 - 🚪 Doors open (Please do not arrive earlier)

19:00 - ▶️ Introduction

19:15 - 🗣 "The new NumFOCUS program prioritizing the place of open-source software in scientific discovery (OSSci)", by Tim Bonnemann, IBM Research.

19:50 - 🍕 Interval - pizza and drinks provided

20:15 - 🗣 "Current Methods in AI for Drug Discovery", by Jacob Green, Deep Mirror.

20:50 - 🍻 End (Pub - Station Tavern, Station Square, map here).

This event is sponsored by the Raspberry Pi Foundation.

----------------------------------------------------------------

Abstracts

The new NumFOCUS program prioritizing the place of open-source software in scientific discovery (OSSci)

Speaker: Tim Bonnemann

Open-Source Science (OSSci) is a new NumFOCUS initiative – in partnership with IBM – that aims to accelerate scientific research and discovery by improving the way open-source software gets done in science. OSSci connects scientists, OSS developers, and other stakeholders to share best practices, identify common pain points, and explore solutions together.
Launched in July 2022, the OSSci interest groups have been getting underway, focused initially on three domains:

• Chemistry/material science
• Life sciences/healthcare
• Climate and sustainability

In our conversation, we will go over OSSci’s goals and longer-term vision, progress to date, and the plans for the coming year. We will also discuss how we can create a stronger ecosystem for open-source scientific software and how you can get involved.

Current Methods in AI for Drug Discovery

Speaker: Jacob Green

The transformative power of AI has been widely discussed in the context of drug discovery. Unlike in other domains that have seen major advances in recent years, such as Language Modelling and Computer Vision, so far there doesn't appear to be a silver bullet approach for predicting drug properties in silico: a crucial step in drug development to de-risk laboratory testing of assets before clinical trials. In this talk, we'll discuss how to put together ML models for drug property prediction, the important job of providing predictive uncertainty to facilitate decision-making, as well as some of our findings on how to build an optimal model for the task at hand with confidence.

----------------------------------------------------------------

Speakers Bios

Tim Bonnemann is the Community Lead for Open-Source Science (OSSci) initiative of IBM Research.

Jacob Green is a Founding Machine Learning Engineer at DeepMirror, the AI co-pilot for drug discovery. Coming from a General Engineering background at the University of Oxford, he entered industry as a data scientist for a global surgical robotics company, developing AI solutions spanning Computer Vision, NLP and MLOps. He now spends his time building robust Chem/Bio ML pipelines for DeepMirror.

----------------------------------------------------------------

Code of Conduct

PyData is dedicated to providing a harassment-free event experience for everyone, regardless of gender, sexual orientation, gender identity, and expression, disability, physical appearance, body size, race, or religion. We do not tolerate harassment of participants in any form.

The PyData Code of Conduct governs this meetup. ( http://pydata.org/code-of-conduct.html ) To discuss any issues or concerns relating to the code of conduct or the behaviour of anyone at a PyData meetup, please contact NumFOCUS Executive Director Leah Silen (leah@numfocus.org) or organizers.