Name
Abstract | ||
|---|---|---|
BackgroundA 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.ResultsA 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).ConclusionThe proposed architecture outperforms state-of-the-art ML approaches, and some interesting insights on molecular fingerprints are devised. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1186/s12859-020-03645-9 | BMC BIOINFORMATICS |
Keywords | DocType | Volume |
Deep learning,Drug design,Molecular fingerprints,Bioactivity prediction,Virtual screening | Journal | 21 |
Issue | ISSN | Citations |
SUPnan | 1471-2105 | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Isabella Mendolia | 1 | 0 | 0.34 |
| Salvatore Contino | 2 | 0 | 0.34 |
| Ugo Perricone | 3 | 0 | 0.34 |
| E. Ardizzone | 4 | 158 | 22.06 |
| Roberto Pirrone | 5 | 140 | 36.09 |