ChemVA: Interactive Visual Analysis of Chemical Compound Similarity in Virtual Screening

María Virginia Sabando, Pavol Ulbrich, Matias Selzer, Jan Byška, Jan Mičan, Ignacio Ponzoni, Axel Soto, María Luján Ganuza, Barbora Kozlikova

View presentation: 2020-10-28T16:45:00Z GMT-0600 Change your timezone on the schedule page
2020-10-28T16:45:00Z
Exemplar figure
The visual interface of ChemVA, a tool for interactive visual exploration of large ensembles of chemical compounds and their properties. ChemVA consists of several linked views, showing the dimensionality reduction outcomes in the hexagonal views and the comparison of projections in our newly proposed Difference view. These are accompanied with the Table view with additional molecular properties and the 3D view illustrating the spatial organization and alignment of selected compounds.
Fast forward

Direct link to video on YouTube: https://youtu.be/vKMRGer-pAY

Keywords

Virtual screening, visual analysis, dimensionality reduction, coordinated views, cheminformatics.

Abstract

In the modern drug discovery process, medicinal chemists deal with the complexity of analysis of large ensembles of candidate molecules. Computational tools, such as dimensionality reduction (DR) and classification, are commonly used to efficiently process the multidimensional space of features. These underlying calculations often hinder interpretability of results and prevent experts from assessing the impact of individual molecular features on the resulting representations. To provide a solution for scrutinizing such complex data, we introduce ChemVA, an interactive application for the visual exploration of large molecular ensembles and their features. Our tool consists of multiple coordinated views: Hexagonal view, Detail view, 3D view, Table view, and a newly proposed Difference view designed for the comparison of DR projections. These views display DR projections combined with biological activity, selected molecular features, and confidence scores for each of these projections. This conjunction of views allows the user to drill down through the dataset and to efficiently select candidate compounds. Our approach was evaluated on two case studies of finding structurally similar ligands with similar binding affinity to a target protein, as well as on an external qualitative evaluation. The results suggest that our system allows effective visual inspection and comparison of different high-dimensional molecular representations. Furthermore, ChemVA assists in the identification of candidate compounds while providing information on the certainty behind different molecular representations.