6533b7d9fe1ef96bd126c39c
RESEARCH PRODUCT
EMBER—Embedding Multiple Molecular Fingerprints for Virtual Screening
Ugo PerriconeIsabella MendoliaSalvatore ContinoGiada De SimoneRoberto Pirronesubject
Settore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniBinding SitesMolecular StructureDeep learning Drug design Embedding Virtual screeningResearchOrganic ChemistryGeneral MedicineLigandsCatalysisComputer Science ApplicationsInorganic ChemistryCDC2 Protein KinaseDrug DiscoveryMass Screeningdeep learning; drug design; virtual screening; embeddingNeural Networks ComputerPhysical and Theoretical ChemistryProtein KinasesMolecular BiologySpectroscopydescription
In recent years, the debate in the field of applications of Deep Learning to Virtual Screening has focused on the use of neural embeddings with respect to classical descriptors in order to encode both structural and physical properties of ligands and/or targets. The attention on embeddings with the increasing use of Graph Neural Networks aimed at overcoming molecular fingerprints that are short range embeddings for atomic neighborhoods. Here, we present EMBER, a novel molecular embedding made by seven molecular fingerprints arranged as different “spectra” to describe the same molecule, and we prove its effectiveness by using deep convolutional architecture that assesses ligands’ bioactivity on a data set containing twenty protein kinases with similar binding sites to CDK1. The data set itself is presented, and the architecture is explained in detail along with its training procedure. We report experimental results and an explainability analysis to assess the contribution of each fingerprint to different targets.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2022-02-15 |