AI Scientist at @Xaira_Thera Past: PhD student in machine learning @CambridgeMLG @Cambridge_Uni. Contributor to @TuringLang.
London, United Kingdom
Joined May 2012
- Tweets295
- Following144
- Followers438
- Likes484
Tor Erlend Fjelde retweeted
When we started @Xaira_Thera we were clear that for molecular AI to make a difference for patients, it had to be able to address the hardest and most clinically relevant problems; those that traditional methods haven't been able to solve.
For that, we've been building X-Design, bringing together top-tier research, engineering and wet lab capabilities into a model focused on designing clinically progressible molecules.
Today, we showcase just some of that work; designing functional, progressible antibodies for our "undruggable" XA-4 program de novo.
bit.ly/4hAOhEW
Feeling privileged to be part of this 👀 Exciting times!
I'd like to share a small update about what we've been doing at @Xaira_Thera . We've been mostly heads down focused on making design to progress internal programs and building out our platform until now. 🧵to follow.
For antibody design to actually add value, it needs to either:
1. dramatically improve the speed and quality of antibodies over traditional discovery pipelines for easy targets
2. unlock therapeutic targets so difficult that they were previously inaccessible to traditional approaches
In this post we provide a tiny preview of two internal programs we designed antibodies to that illustrate our platform meets both of these criteria.
There is of course, a spectrum of targets in between the "easy" and the "undruggable" such as these GPCRs we made VHH and VHVL binders to which we highlight as well:
xaira.com/news/de-novo-desig…
Tor Erlend Fjelde retweeted
Rich Turner is hiring a Research Associate at Cambridge to work on AI for weather forecasting 🌥️
Strong deep learning background required, but no prior weather experience is fine. Especially relevant: spatiotemporal modelling, PDEs, time series
Tor Erlend Fjelde retweeted
We are looking for a new Research Associate for Project Cumulus at the University of Cambridge. Project Cumulus aims to develop new AI approaches to subseasonal weather forecasting, with a particular focus on supporting farming communities in Africa.
lnkd.in/p/eJZudKth
Tor Erlend Fjelde retweeted
Qiang Liu, Chris Oates, and I are writing a monograph on Probabilistic Inference and Learning with Stein’s Method, and we’d love to get your feedback on the first draft
A small life update: a few months ago, I joined a neat company called @Xaira_Thera, with the humble and easily achievable goal of solving drug design with the help of AI 👀🙃
I got hooked after an internship last summer, and it's an absolute blast. [1/2]
Aaaand we're now looking to expand our UK team further with some research engineers! So if you're an engineer-y researcher or a research-y engineer who would like nothing more than to design the bestest of proteins, shoot us an application!
job-boards.greenhouse.io/xai…
[2/2]
Tor Erlend Fjelde retweeted
Come! join us on this reading group for Molecular Simulations and Sampling.
We’re thrilled to announce the launch of the MolSS Reading Group! 🚀
🔬 MolSS = Machine Learning for Molecular Simulations and Sampling
🔥 First session: June 3rd, 3 PM (UK time) by @jmhernandez233
🗓️ Regular sessions: Every other Tuesday at 4 PM (UK time), 45–60 minutes
Tor Erlend Fjelde retweeted
✨Applications are now open for PhDs at the Cambridge Machine Learning Group!✨
We're looking for outstanding candidates interested in fundamental ML research and applications to scientific domains!
More info: mlg.eng.cam.ac.uk/phd_progra…
🧵Find more about PIs & focus areas below!
Tor Erlend Fjelde retweeted
Open #postdoc position at @UvA_Amsterdam on supporting decision making with #RL, in collaboration with @faoliehoek.
Apply here: vacatures.uva.nl/UvA/job/Pos…
Funded by @AI4REALNET and hybrid-intelligence-centre.n…
Tor Erlend Fjelde retweeted
🐑🐑🐑🐑🐑🐑🐑🐑
natesilver.net/p/theres-more…
That was fun!
Always a blast going to JuliaCon. Get to put faces to lots of people you've just interacted with through GitHub issues or Slack +
it has a tendency to attract people doing really cool stuff, sometimes because it's useful and sometimes just because they can:)
Here's @torfjelde with the obligatory first Bayes slide with the proportional posterior.
This talk is about @TuringLang, which is how I got into Julia seriously!
That was fun!
Always a blast going to JuliaCon. Get to put faces to lots of people you've just interacted with through GitHub issues or Slack +
it has a tendency to attract people doing really cool stuff, sometimes because it's useful and sometimes just because they can:)
Here's @torfjelde with the obligatory first Bayes slide with the proportional posterior.
This talk is about @TuringLang, which is how I got into Julia seriously!
Tor Erlend Fjelde retweeted
Two postdoc positions on AI for Chemistry are available under the EPSRC AI Hub "Alchemy" at Imperial:
jobs.ac.uk/job/DHJ529/resear…
I will be involved in advising the projects from machine learning side.
RT appreciated 🙏
Tor Erlend Fjelde retweeted
Pleased to announce that the datasets used to train our Timewarp model (all-atom molecular dynamics simulations of hundreds of dipeptides and tetrapeptides) are now publicly available at huggingface.co/datasets/micr…. Really excited to see the deep learning/MD research this enables!
Excited to share that our paper "Timewarp: Transferable Acceleration of Molecular Dynamics by Learning Time-Coarsened Dynamics" has been accepted as a spotlight for #NeurIPS2023.
@AndrewFoongYK @torfjelde @kayembruno @mmjb86 @sebnowozin @FrankNoeBerlin @ryotat
1/12
Tor Erlend Fjelde retweeted
Over the next few months I'll be applying* for industry positions for data science and ML software engineering. Know of any great positions or interested in working with me? Let me know! sethaxen.com/
*English- and German-speaking countries or remote
Along with @MathieuEmile and @vdutor we've cooked up a gentle introduction to flow matching, a recent method for efficiently training continuous normalizing flows (CNFs)!
Hope you find it interesting!
mlg.eng.cam.ac.uk/blog/2024/…
1/2