Molecular fingerprint similarity search in virtual screening

Methods ◽  
2015 ◽  
Vol 71 ◽  
pp. 58-63 ◽  
Author(s):  
Adrià Cereto-Massagué ◽  
María José Ojeda ◽  
Cristina Valls ◽  
Miquel Mulero ◽  
Santiago Garcia-Vallvé ◽  
...  
Keyword(s):  
Virtual Screening ◽  
Similarity Search ◽  
Molecular Fingerprint

Peptide Similarity Search Based and Virtual Screening Based Strategies to Identify Small Molecules to Inhibit CarD–RNAP Interaction in M. tuberculosis

2018 ◽  
Vol 25 (2) ◽  
pp. 697-709 ◽  
Author(s):  
V. G. Shanmuga Priya ◽  
Priya Swaminathan ◽  
Uday M. Muddapur ◽  
Prayagraj M. Fandilolu ◽  
Rishikesh S. Parulekar ◽  
...  
Keyword(s):  
Virtual Screening ◽  
Small Molecules ◽  
Similarity Search

scholarly journals Combination of 2D/3D Ligand-Based Similarity Search in Rapid Virtual Screening from Multimillion Compound Repositories. Selection and Biological Evaluation of Potential PDE4 and PDE5 Inhibitors

Molecules ◽  
2014 ◽  
Vol 19 (6) ◽  
pp. 7008-7039 ◽  
Author(s):  
Krisztina Dobi ◽  
István Hajdú ◽  
Beáta Flachner ◽  
Gabriella Fabó ◽  
Mária Szaszkó ◽  
...  
Keyword(s):  
Virtual Screening ◽  
Similarity Search ◽  
Biological Evaluation ◽  
Pde5 Inhibitors

scholarly journals Using Domain-specific Fingerprints Generated Through Neural Networks to Enhance Ligand-based Virtual Screening.

2020 ◽  
Author(s):  
Janosch Menke ◽  
Oliver Koch
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Virtual Screening ◽  
Molecular Fingerprint ◽  
Molecular Fingerprints ◽  
Domain Specific ◽  
Trained Neural Network ◽  
Hidden Layer ◽  
Graph Neural Networks ◽  
Combine Information

Molecular fingerprints are essential for different cheminformatics approaches like similarity-based virtual screening. In this work, the concept of neural (network) fingerprints in the context of similarity search is introduced in which the activation of the last hidden layer of a trained neural network represents the molecular fingerprint. The neural fingerprint performance of five different neural network architectures was analyzed and compared to the well-established Extended Connectivity Fingerprint (ECFP) and an autoencoder-based fingerprint. This is done using a published compound dataset with known bioactivity on 160 different kinase targets. We expect neural networks to combine information about the molecular space of<br>already known bioactive compounds together with the information on the molecular structure of the query and by doing so enrich the fingerprint. The results show that indeed neural fingerprints can greatly improve the performance of similarity searches. Most importantly, it could be shown that the neural fingerprint performs well even for kinase targets that were not included in the training. Surprisingly, while Graph Neural Networks (GNNs) are thought to offer an advantageous alternative, the best performing neural fingerprints were based on traditional fully connected layers using the ECFP4 as input. The best performing kinase-specific neural fingerprint will be provided for public use.

Similarity Search Profiling Reveals Effects of Fingerprint Scaling in Virtual Screening.

ChemInform ◽  
2005 ◽  
Vol 36 (6) ◽  
Author(s):  
Ling Xue ◽  
Florence L. Stahura ◽  
Juergen Bajorath
Keyword(s):  
Virtual Screening ◽  
Similarity Search

Identification of novel JMJD2A inhibitor scaffold using shape and electrostatic similarity search combined with docking method and MM-GBSA approach

RSC Advances ◽  
2015 ◽  
Vol 5 (101) ◽  
pp. 82936-82946 ◽  
Author(s):  
Taotao Feng ◽  
Weilin Chen ◽  
Dongdong Li ◽  
Hongzhi Lin ◽  
Fang Liu ◽  
...  
Keyword(s):  
Virtual Screening ◽  
Similarity Search ◽  
Docking Method ◽  
Electrostatic Similarity

We present a hierarchical workflow combining shape- and electrostatic-based virtual screening for the identification of novel Jumonji domain-containing protein 2A (JMJD2A) inhibitors.

scholarly journals Exploring Different Virtual Screening Strategies for Acetylcholinesterase Inhibitors

2013 ◽  
Vol 2013 ◽  
pp. 1-8 ◽  
Author(s):  
Nibha Mishra ◽  
Arijit Basu
Keyword(s):  
Molecular Docking ◽  
Virtual Screening ◽  
Similarity Search ◽  
Acetylcholinesterase Inhibitors ◽  
Enrichment Factors ◽  
Pharmacophore Modeling ◽  
Receiver Operating Curve ◽  
Ache Inhibitors ◽  
Docking Protocol ◽  
Screening Strategies

The virtual screening problems associated with acetylcholinesterase (AChE) inhibitors were explored using multiple shape, and structure-based modeling strategies. The employed strategies include molecular docking, similarity search, and pharmacophore modeling. A subset from directory of useful decoys (DUD) related to AChE inhibitors was considered, which consists of 105 known inhibitors and 3732 decoys. Statistical quality of the models was evaluated by enrichment factor (EF) metrics and receiver operating curve (ROC) analysis. The results revealed that electrostatic similarity search protocol using EON (ET_combo) outperformed all other protocols with outstanding enrichment of>95% in top 1% and 2% of the dataset with an AUC of 0.958. Satisfactory performance was also observed for shape-based similarity search protocol using ROCS and PHASE. In contrast, the molecular docking protocol performed poorly with enrichment factors<30% in all cases. The shape- and electrostatic-based similarity search protocol emerged as a plausible solution for virtual screening of AChE inhibitors.

Sign in / Sign up

Export Citation Format

Share Document