EPFL BioE Talks SERIES "Protein Language Models for Protein Science, Design and Engineering: An Overview and Outlook"
Event details
| Date | 17.04.2023 |
| Hour | 16:00 › 17:00 |
| Speaker | Christian Dallago, Ph.D., Technical University Munich (TUM) & NVIDIA, Munich (DE) |
| Location | Online |
| Category | Conferences - Seminars |
| Event Language | English |
WEEKLY EPFL BIOE TALKS SERIES
Abstract:
Biology has recently seen incredible advances supported by methods from Deep Learning. In particular, protein science and engineering has benefitted both from advances in downstream deep learning models, predicting aspects of protein structure and function, and foundational models often based on the Transformer architecture, providing new ways to encode protein information in computational form. The staggering advances in accurate Deep Learning methods for protein science have led to a sprouting of new ways in which Deep Learning can be used to predict and design proteins. This talk will examine the principles that led to foundational models for protein science, the validation of these models through predictions of function and structure, and venues for their application in protein engineering and design accompanied by practical examples.
Bio:
Education:
PhD in Informatics, Technical University, Munich (TUM), Munich, DE
MSc in Informatics, TUM, Munich, DE
BSc in Computer Science and Engineering, UniBZ, Bolzano, IT.
Current positions:
Research scientist, TUM, Munich, DE
and
Senior Solution Architect, NVIDIA, Munich, DE
Zoom link (with one-time registration for the whole series) for attending remotely: https://go.epfl.ch/EPFLBioETalks
Instructions for 1st-year Ph.D. students who are under EDBB’s mandatory seminar attendance rule:
IF you are not attending in-person in the room, please make sure to
Abstract:
Biology has recently seen incredible advances supported by methods from Deep Learning. In particular, protein science and engineering has benefitted both from advances in downstream deep learning models, predicting aspects of protein structure and function, and foundational models often based on the Transformer architecture, providing new ways to encode protein information in computational form. The staggering advances in accurate Deep Learning methods for protein science have led to a sprouting of new ways in which Deep Learning can be used to predict and design proteins. This talk will examine the principles that led to foundational models for protein science, the validation of these models through predictions of function and structure, and venues for their application in protein engineering and design accompanied by practical examples.
Bio:
Education:
PhD in Informatics, Technical University, Munich (TUM), Munich, DE
MSc in Informatics, TUM, Munich, DE
BSc in Computer Science and Engineering, UniBZ, Bolzano, IT.
Current positions:
Research scientist, TUM, Munich, DE
and
Senior Solution Architect, NVIDIA, Munich, DE
Zoom link (with one-time registration for the whole series) for attending remotely: https://go.epfl.ch/EPFLBioETalks
Instructions for 1st-year Ph.D. students who are under EDBB’s mandatory seminar attendance rule:
IF you are not attending in-person in the room, please make sure to
- send D. Reinhard a note before noon on seminar day, informing that you plan to attend the talk online, and
- be signed in on Zoom with a recognizable user name (not a pseudonym making it difficult or impossible to be identified).
Practical information
- Informed public
- Registration required
Organizer
Contact
- Institute of Bioengineering (IBI), Dietrich REINHARD