Convolutional architectures for virtual screening

Mendolia, Isabella; Contino, Salvatore; Perricone, Ugo; Ardizzone, Edoardo; Pirrone, Roberto

doi:10.1186/s12859-020-03645-9

Cited by 14 publications

(6 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…All divisions into training/validation/test sets were performed at random and repeated four times. The only difference between the validation and test sets were the proportions between active and decoy compounds, tests sets being constructed with a small percentage of active compounds (i.e., 0.5–0.7%) which is the common case for datasets used in virtual screening [ 44 , 45 ]. To make sure that our models are not over-fitted we derived 7, 10 and 13-descriptor models and compared their performances.…”

Section: Discussionmentioning

confidence: 99%

A Comparison between Enrichment Optimization Algorithm (EOA)-Based and Docking-Based Virtual Screening

Spiegel

Senderowitz

2021

IJMS

View full text Add to dashboard Cite

Virtual screening (VS) is a well-established method in the initial stages of many drug and material design projects. VS is typically performed using structure-based approaches such as molecular docking, or various ligand-based approaches. Most docking tools were designed to be as global as possible, and consequently only require knowledge on the 3D structure of the biotarget. In contrast, many ligand-based approaches (e.g., 3D-QSAR and pharmacophore) require prior development of project-specific predictive models. Depending on the type of model (e.g., classification or regression), predictive ability is typically evaluated using metrics of performance on either the training set (e.g.,QCV2) or the test set (e.g., specificity, selectivity or QF1/F2/F32). However, none of these metrics were developed with VS in mind, and consequently, their ability to reliably assess the performances of a model in the context of VS is at best limited. With this in mind we have recently reported the development of the enrichment optimization algorithm (EOA). EOA derives QSAR models in the form of multiple linear regression (MLR) equations for VS by optimizing an enrichment-based metric in the space of the descriptors. Here we present an improved version of the algorithm which better handles active compounds and which also takes into account information on inactive (either known inactive or decoy) compounds. We compared the improved EOA in small-scale VS experiments with three common docking tools, namely, Glide-SP, GOLD and AutoDock Vina, employing five molecular targets (acetylcholinesterase, human immunodeficiency virus type 1 protease, MAP kinase p38 alpha, urokinase-type plasminogen activator, and trypsin I). We found that EOA consistently outperformed all docking tools in terms of the area under the ROC curve (AUC) and EF1% metrics that measured the overall and initial success of the VS process, respectively. This was the case when the docking metrics were calculated based on a consensus approach and when they were calculated based on two different sets of single crystal structures. Finally, we propose that EOA could be combined with molecular docking to derive target-specific scoring functions.

show abstract

Section: Discussionmentioning

confidence: 99%

A Comparison between Enrichment Optimization Algorithm (EOA)-Based and Docking-Based Virtual Screening

Spiegel

Senderowitz

2021

IJMS

View full text Add to dashboard Cite

show abstract

“…As a consequence, different fingerprints convey diverse structural information about the same molecule. Some of the authors in a recent work [37] present a comparison between different deep classifiers and ML approaches for assessing ligands' bioactivity on Ciclyn Dependent Kinase 1 (CDK1). In that work, the authors made the same assumptions expressed here, and they used seven fingerprint families: RDKit, Morgan, AtomPair, Torsion, Layered, FeatMorgan, and ECFP4.…”

Section: Ember Multi-fingerprint Embeddingmentioning

confidence: 99%

EMBER—Embedding Multiple Molecular Fingerprints for Virtual Screening

Mendolia

Contino

Simone

et al. 2022

IJMS

Self Cite

View full text Add to dashboard Cite

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.

show abstract

“…Leading pharmaceutical companies have applied AI to enhance the efficacy of their drug candidates, thereby saving time and costs on unnecessary synthesis and tests. Machine learning [ 29 , 30 , 31 ], a subfield of AI, and its subfield, deep learning [ 32 , 33 , 34 ], have been combined with the VS process [ 35 , 36 , 37 ] to improve the efficiency of similarity searching and the reliability of mining screening data in the ligand-based VS process and enhance the accuracy of scoring functions in structure-based VS [ 36 , 37 , 38 ]. The approaches also contribute to the generation of novel compounds [ 32 , 34 ].…”

Section: Introductionmentioning

confidence: 99%

Application of Computational Biology and Artificial Intelligence in Drug Design

Zhang

Luo

et al. 2022

IJMS

View full text Add to dashboard Cite

Traditional drug design requires a great amount of research time and developmental expense. Booming computational approaches, including computational biology, computer-aided drug design, and artificial intelligence, have the potential to expedite the efficiency of drug discovery by minimizing the time and financial cost. In recent years, computational approaches are being widely used to improve the efficacy and effectiveness of drug discovery and pipeline, leading to the approval of plenty of new drugs for marketing. The present review emphasizes on the applications of these indispensable computational approaches in aiding target identification, lead discovery, and lead optimization. Some challenges of using these approaches for drug design are also discussed. Moreover, we propose a methodology for integrating various computational techniques into new drug discovery and design.

show abstract

Convolutional architectures for virtual screening

Cited by 14 publications

References 16 publications

A Comparison between Enrichment Optimization Algorithm (EOA)-Based and Docking-Based Virtual Screening

A Comparison between Enrichment Optimization Algorithm (EOA)-Based and Docking-Based Virtual Screening

EMBER—Embedding Multiple Molecular Fingerprints for Virtual Screening

Application of Computational Biology and Artificial Intelligence in Drug Design

Contact Info

Product

Resources

About