Sveriges mest populära poddar
Molecular Modelling and Drug Discovery
Vetenskap

Do Machines Dream of Atoms? Crippen’s logP as a Quantitative Molecular Benchmark for Explainable AI Heatmaps | Jan Jensen

54 min•2 november 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: While there is a great deal of interest in methods aimed at explaining machine learning predictions of chemical properties, it is difficult to quantitatively benchmark such methods, especially for regression tasks. We show that the Crippen logP model provides an excellent benchmark for atomic attribution/heatmap approaches, especially if the ground truth heatmaps can be adjusted to reflect the molecular representation. I give some examples of how this benchmark can be used to get a better understanding of ML models work and how it can be used to determine which techniques for generating XAI heatmaps works the best.

Slides from the talk: https://speakerdeck.com/jhjensen/jensen-xai

Speakers: Jan Jensen

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.