Sveriges mest populära poddar
Molecular Modelling and Drug Discovery
Vetenskap

Diffusion probabilistic modelling of protein backbones in 3D for the motif-scaffolding problem | Brian Trippe & Jason Yim

1 tim 3 min•12 oktober 2022

[DISCLAIMER] - For the full visual experience, we recommend you tune in through our YouTube channel to see the presented slides.

If you enjoyed this talk, consider joining the Molecular Modeling and Drug Discovery (M2D2) talks live.

Also consider joining the M2D2 Slack

Abstract: The construction of a scaffold structure that supports a desired motif, conferring protein function, shows promise for the design of vaccines and enzymes. But a general solution to this motif-scaffolding problem remains open. Current machine-learning techniques for scaffold design are either limited to unrealistically small scaffolds (up to length 20) or struggle to produce multiple diverse scaffolds. We propose to learn a distribution over diverse and longer protein backbone structures via an E(3)-equivariant graph neural network. We develop SMCDiff to efficiently sample scaffolds from this distribution conditioned on a given motif; our algorithm is the first to theoretically guarantee conditional samples from a diffusion model in the large-compute limit. We evaluate our designed backbones by how well they align with AlphaFold2-predicted structures. We show that our method can (1) sample scaffolds up to 80 residues and (2) achieve structurally diverse scaffolds for a fixed motif.

Full Paper

Speakers: Brian Trippe and Jason Yim

Twitter Prudencio   

Twitter Therence

Twitter Cas  

Twitter Valence Discovery

Fler avsnitt av Molecular Modelling and Drug Discovery

Visa alla avsnitt av Molecular Modelling and Drug Discovery
Structure-Independent Peptide Binder Design via Generative Language Models | Pranam Chatterjee
•1 tim 1 min
Learning Local Equivariant Representations for Large-Scale Atomistic Dynamics | Albert Musaelian
•1 tim 9 min
Multimodal Deep Learning for Protein Engineering | Kevin K. Yang
•1 tim 3 min
Systematic Analysis of Biomolecular Conformational Ensembles with PENSA | Martin Vögele
•51 min
Training Neural Network Potentials: Bayesian and Simulation-based Approaches | Stephan Thaler
•1 tim 4 min
Accelerating Cryptic Pocket Discovery Using Alphafold and Markov State Modelling | Soumendranath Bhakat
•32 min
Machine Learning Molecules | Gianni De Fabritiis
•57 min
Protein Representation Learning by Geometric Structure Pretraining | Zuobai Zhang
•53 min
There’s no free lunch, but you can get a discount – applying active learning in drug discovery | Pat Walters & James Thompson
•53 min
Cell Morphology-Guided De Novo Hit Design by Conditioning GANs on Phenotypic Image Features | Paula A. Marin Zapata
•49 min

Molecular Modelling and Drug Discovery med Valence Discovery finns tillgänglig på flera plattformar. Informationen på denna sida kommer från offentliga podd-flöden.