Model Agnostic Generation of Counterfactual Explanations for Molecules - Geemi Wellawatte
Molecular Modelling and Drug Discovery2 Feb 2022

Model Agnostic Generation of Counterfactual Explanations for Molecules - Geemi Wellawatte

If you enjoyed this talk, consider joining the Molecular Modeling and Drug Discovery (M2D2) talks live: https://valence-discovery.github.io/M...

Abstract: One of the challenges with deep learning is lack of model interpretability. This is a significant drawback in the chemistry domain as lack of knowledge why a certain prediction was made dissuades chemists to trust predictions from deep learning. In this work we propose a method that can provide local explanations for arbitrary models with the use of molecular counterfactuals. These are sparse explanations composed of molecular structures. A counterfactual is an example as close to the original, but with a different outcome. Although relatively new to AI, counterfactual explanations are a mature topic in philosophy and mathematics. We use counterfactuals to answer, “what is the smallest change to the features that would alter the prediction". Our Molecular Model Agnostic Counterfactual Explanations (MMACE), method is built on the STONED (Nigam et al., 2021) algorithm to traverse a local chemical space around a given base molecule to identify counterfactuals. Further, we introduce an open-source software named “exmol” that implements the MMACE algorithm for generating counterfactual explanations.

Speaker: Geemi Wellawatte - https://geemi725.github.io/

Twitter Prudencio: https://twitter.com/tossouprudencio

Twitter Therence: https://twitter.com/Therence_mtl

Twitter Cas: https://twitter.com/cas_wognum

Twitter Valence Discovery: https://twitter.com/valence_ai

Denne episoden er hentet fra en åpen RSS-feed og er ikke publisert av Podme. Den kan derfor inneholde annonser.

Episoder(60)

Structure-Independent Peptide Binder Design via Generative Language Models | Pranam Chatterjee

Structure-Independent Peptide Binder Design via Generative Language Models | Pranam Chatterjee

[DISCLAIMER] - For the full visual experience, we recommend you tune in through our ⁠⁠⁠⁠⁠⁠⁠⁠YouTube channel ⁠⁠⁠⁠⁠⁠⁠⁠to see the presented slides. Try datamol.io - the open source toolkit that simplifie...

20 Jun 20231h

Learning Local Equivariant Representations for Large-Scale Atomistic Dynamics | Albert Musaelian

Learning Local Equivariant Representations for Large-Scale Atomistic Dynamics | Albert Musaelian

[DISCLAIMER] - For the full visual experience, we recommend you tune in through our ⁠⁠⁠⁠⁠⁠⁠⁠⁠YouTube channel ⁠⁠⁠⁠⁠⁠⁠⁠⁠to see the presented slides. Try datamol.io - the open source toolkit that simplif...

13 Jun 20231h 9min

Multimodal Deep Learning for Protein Engineering | Kevin K. Yang

Multimodal Deep Learning for Protein Engineering | Kevin K. Yang

[DISCLAIMER] - For the full visual experience, we recommend you tune in through our ⁠⁠⁠⁠⁠⁠⁠⁠YouTube channel ⁠⁠⁠⁠⁠⁠⁠⁠to see the presented slides. Try datamol.io - the open source toolkit that simplifie...

7 Jun 20231h 2min

Systematic Analysis of Biomolecular Conformational Ensembles with PENSA | Martin Vögele

Systematic Analysis of Biomolecular Conformational Ensembles with PENSA | Martin Vögele

[DISCLAIMER] - For the full visual experience, we recommend you tune in through our ⁠⁠⁠⁠⁠⁠⁠YouTube channel ⁠⁠⁠⁠⁠⁠⁠to see the presented slides. Try datamol.io - the open source toolkit that simplifies ...

30 Mai 202350min

Training Neural Network Potentials: Bayesian and Simulation-based Approaches | Stephan Thaler

Training Neural Network Potentials: Bayesian and Simulation-based Approaches | Stephan Thaler

[DISCLAIMER] - For the full visual experience, we recommend you tune in through our ⁠⁠⁠⁠⁠⁠YouTube channel ⁠⁠⁠⁠⁠⁠to see the presented slides. Try datamol.io - the open source toolkit that simplifies mo...

16 Mai 20231h 3min

Accelerating Cryptic Pocket Discovery Using Alphafold and Markov State Modelling | Soumendranath Bhakat

Accelerating Cryptic Pocket Discovery Using Alphafold and Markov State Modelling | Soumendranath Bhakat

[DISCLAIMER] - For the full visual experience, we recommend you tune in through our ⁠⁠⁠⁠⁠YouTube channel ⁠⁠⁠⁠⁠to see the presented slides. Try datamol.io - the open source toolkit that simplifies mole...

9 Mai 202331min

Machine Learning Molecules | Gianni De Fabritiis

Machine Learning Molecules | Gianni De Fabritiis

[DISCLAIMER] - For the full visual experience, we recommend you tune in through our ⁠⁠⁠⁠⁠YouTube channel ⁠⁠⁠⁠⁠to see the presented slides. Try datamol.io - the open source toolkit that simplifies mole...

25 Apr 202357min

Protein Representation Learning by Geometric Structure Pretraining | Zuobai Zhang

Protein Representation Learning by Geometric Structure Pretraining | Zuobai Zhang

[DISCLAIMER] - For the full visual experience, we recommend you tune in through our ⁠⁠⁠⁠YouTube channel ⁠⁠⁠⁠to see the presented slides. Try datamol.io - the open source toolkit that simplifies molecu...

19 Apr 202353min

Populært innen Vitenskap

fastlegen
tingenes-tilstand
forskningno
vett-og-vitenskap-med-gaute-einevoll
liberal-halvtime
rekommandert
sinnsyn
rss-paradigmepodden
jss
fjellsportpodden
villmarksliv
dekodet-2
hva-er-greia-med
rss-inn-til-kjernen-med-sunniva-rose
tomprat-med-gunnar-tjomlid
rss-rekommandert
kvinnehelsepodden
diagnose
grunnstoffene
rss-zahid-ali-hjelper-deg