Protein Binding Site Representation in Latent Space
Abstract: Interpretability and reliability of deep learning models are important for computer‐based drug discovery. Aiming to understand feature perception by such a model, we investigate a graph neural network for affinity prediction of protein‐ligand complexes. We assess a latent representation of ligand binding sites and investigate underlying geometric structure in this latent space and its relation to protein function. We introduce an automated computational pipeline for dimensionality reduction, clustering, hypothesis testing, and visualization of latent space. The results indicate that the learned protein latent space is inherently structured and not randomly distributed. Several of the identified protein binding site clusters in latent space correspond to functional protein families. Ligand size was found to be a determinant of cluster geometry. The computational pipeline proved applicable to latent space analysis and interpretation and can be adapted to work for different datasets and deep learning models.
- Standort
-
Deutsche Nationalbibliothek Frankfurt am Main
- Umfang
-
Online-Ressource
- Sprache
-
Englisch
- Erschienen in
-
Protein Binding Site Representation in Latent Space ; day:18 ; month:12 ; year:2024 ; extent:7
Molecular informatics ; (18.12.2024) (gesamt 7)
- Urheber
-
Lohmann, Frederieke
Allenspach, Stephan
Atz, Kenneth
Schiebroek, Carl C. G.
Hiß, Jan Alexander
Schneider, Gisbert
- DOI
-
10.1002/minf.202400205
- URN
-
urn:nbn:de:101:1-2412181329119.532829680471
- Rechteinformation
-
Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
- Letzte Aktualisierung
-
15.08.2025, 07:21 MESZ
Datenpartner
Deutsche Nationalbibliothek. Bei Fragen zum Objekt wenden Sie sich bitte an den Datenpartner.
Beteiligte
- Lohmann, Frederieke
- Allenspach, Stephan
- Atz, Kenneth
- Schiebroek, Carl C. G.
- Hiß, Jan Alexander
- Schneider, Gisbert
Ähnliche Objekte (12)
Multimodal sensor fusion in the latent representation space
PocketGraph: graph representation of binding site volumes
Latent Space Reinforcement Learning
Deep learning based CETSA feature prediction cross multiple cell lines with latent space representation
Predicting transcription factor binding sites using local over-representation and comparative genomics
Latent Class Analysis : wandering in Latent Space [[Elektronische Ressource]]
Latent State-Space Models for Control
Comparing the latent space of generative models
Biological representation of chemicals using latent target interaction profile
Hierarchical representation for PPI sites prediction
Cartographies of culture : memory, space, representation
$${\mathrm Latent}}Out}$$ Latent O u t : an unsupervised deep anomaly detection approach exploiting latent space distribution
Multimodal sensor fusion in the latent representation space
PocketGraph: graph representation of binding site volumes
Latent Space Reinforcement Learning
Deep learning based CETSA feature prediction cross multiple cell lines with latent space representation
Predicting transcription factor binding sites using local over-representation and comparative genomics
Latent Class Analysis : wandering in Latent Space [[Elektronische Ressource]]
Latent State-Space Models for Control
Comparing the latent space of generative models
Biological representation of chemicals using latent target interaction profile
Hierarchical representation for PPI sites prediction
Cartographies of culture : memory, space, representation
$${\mathrm Latent}}Out}$$ Latent O u t : an unsupervised deep anomaly detection approach exploiting latent space distribution
Multimodal sensor fusion in the latent representation space
PocketGraph: graph representation of binding site volumes
Latent Space Reinforcement Learning
Deep learning based CETSA feature prediction cross multiple cell lines with latent space representation
Predicting transcription factor binding sites using local over-representation and comparative genomics
Latent Class Analysis : wandering in Latent Space [[Elektronische Ressource]]
Latent State-Space Models for Control
Comparing the latent space of generative models
Biological representation of chemicals using latent target interaction profile
Hierarchical representation for PPI sites prediction
Cartographies of culture : memory, space, representation