Convolutional architectures for virtual screening

Risultato della ricerca: Articlepeer review

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.
Lingua originaleEnglish
pagine (da-a)1-14
Numero di pagine14
RivistaBMC Bioinformatics
Volume21
Stato di pubblicazionePublished - 2020

All Science Journal Classification (ASJC) codes

  • ???subjectarea.asjc.1300.1315???
  • ???subjectarea.asjc.1300.1303???
  • ???subjectarea.asjc.1300.1312???
  • ???subjectarea.asjc.1700.1706???
  • ???subjectarea.asjc.2600.2604???

Fingerprint

Entra nei temi di ricerca di 'Convolutional architectures for virtual screening'. Insieme formano una fingerprint unica.

Cita questo