Background: A Virtual Screening algorithm has to adapt to the different stages of this process. Early screening needs to ensure that all bioactive compounds are ranked in the first positions despite of the number of false positives, while a second screening round is aimed at increasing the prediction accuracy. Results: A novel CNN architecture is presented to this aim, which predicts bioactivity of candidate compounds on CDK1 using a combination of molecular fingerprints as their vector representation, and has been trained suitably to achieve good results as regards both enrichment factor and accuracy in different screening modes (98.55% accuracy in active-only selection, and 98.88% in high precision discrimination). Conclusion: The proposed architecture outperforms state-of-the-art ML approaches, and some interesting insights on molecular fingerprints are devised.

Mendolia I., Contino S., Perricone U., Ardizzone E., & Pirrone R. (2020). Convolutional architectures for virtual screening. BMC BIOINFORMATICS, 21(Suppl 8), 1-14 [10.1186/s12859-020-03645-9].

Convolutional architectures for virtual screening

Mendolia I.
;
Contino S.
Membro del Collaboration Group
;
Ardizzone E.;Pirrone R.
2020-09-16

Abstract

Background: A Virtual Screening algorithm has to adapt to the different stages of this process. Early screening needs to ensure that all bioactive compounds are ranked in the first positions despite of the number of false positives, while a second screening round is aimed at increasing the prediction accuracy. Results: A novel CNN architecture is presented to this aim, which predicts bioactivity of candidate compounds on CDK1 using a combination of molecular fingerprints as their vector representation, and has been trained suitably to achieve good results as regards both enrichment factor and accuracy in different screening modes (98.55% accuracy in active-only selection, and 98.88% in high precision discrimination). Conclusion: The proposed architecture outperforms state-of-the-art ML approaches, and some interesting insights on molecular fingerprints are devised.
Settore ING-INF/05 - Sistemi Di Elaborazione Delle Informazioni
https://bmcbioinformatics.biomedcentral.com/articles/10.1186/s12859-020-03645-9
Mendolia I., Contino S., Perricone U., Ardizzone E., & Pirrone R. (2020). Convolutional architectures for virtual screening. BMC BIOINFORMATICS, 21(Suppl 8), 1-14 [10.1186/s12859-020-03645-9].
File in questo prodotto:
File Dimensione Formato  
s12859-020-03645-9.pdf

accesso aperto

Tipologia: Versione Editoriale
Dimensione 1.77 MB
Formato Adobe PDF
1.77 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/10447/514063
Citazioni
  • ???jsp.display-item.citation.pmc??? 3
  • Scopus 7
  • ???jsp.display-item.citation.isi??? 7
social impact