LigGrep: a tool for filtering docked poses to improve virtual-screening hit rates

Ha, Emily J.; Lwin, Cara T.; Durrant, Jacob D.

doi:10.1186/s13321-020-00471-2

Cited by 18 publications

(11 citation statements)

References 71 publications

(72 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although encouraging in terms of performance, these models were developed based on the DSs only (hereinafter named DS-based models), a strategy commonly employed for developing structure-based classifiers. , However, in addition to providing a score estimating the binding affinity, molecular docking simulations predict the conformation as well as the position and orientation of a given ligand (usually referred to as pose) in the target cavity. This piece of information was recently proved to be crucial to overcoming DS deficiencies in virtual screening campaigns. − These evidence prompted us to develop classifiers integrating the information provided by both scoring and posing by taking into account the IFs, namely, 1D representations of the ligand–protein interactions occurring in the top-scored docking poses. To this aim, classification models based on sparse high-dimensional data structures consisting of DSs and IFs (hereinafter called DS/IF-based models) were trained using linear models with L1-regularization constraint (LASSO) with the SVM learner and the sparsa solver (see the Materials and Methods section for details).…”

Section: Resultsmentioning

confidence: 99%

Structure-Based Prediction of hERG-Related Cardiotoxicity: A Benchmark Study

Creanza

Delre

Ancona

et al. 2021

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Drug-induced blockade of the human ether-a-go-gorelated gene (hERG) channel is today considered the main cause of cardiotoxicity in postmarketing surveillance. Hence, several ligandbased approaches were developed in the last years and are currently employed in the early stages of a drug discovery process for in silico cardiac safety assessment of drug candidates. Herein, we present the first structure-based classifiers able to discern hERG binders from nonbinders. LASSO regularized support vector machines were applied to integrate docking scores and protein−ligand interaction fingerprints. A total of 396 models were trained and validated based on: (i) high-quality experimental bioactivity information returned by 8337 curated compounds extracted from ChEMBL (version 25) and (ii) structural predictor data. Molecular docking simulations were performed using GLIDE and GOLD software programs and four different hERG structural models, namely, the recently published structures obtained by cryoelectron microscopy (PDB codes: 5VA1 and 7CN1) and two published homology models selected for comparison. Interestingly, some classifiers return performances comparable to ligand-based models in terms of area under the ROC curve (AUC MAX = 0.86 ± 0.01) and negative predictive values (NPV MAX = 0.81 ± 0.01), thus putting forward the herein proposed computational workflow as a valuable tool for predicting hERG-related cardiotoxicity without the limitations of ligand-based models, typically affected by low interpretability and a limited applicability domain. From a methodological point of view, our study represents the first example of a successful integration of docking scores and protein−ligand interaction fingerprints (IFs) through a support vector machine (SVM) LASSO regularized strategy. Finally, the study highlights the importance of using hERG structural models accounting for ligand-induced fit effects and allowed us to select the best-performing protein conformation (made available in the Supporting Information, SI) to be employed for a reliable structure-based prediction of hERG-related cardiotoxicity.

show abstract

Section: Resultsmentioning

confidence: 99%

Structure-Based Prediction of hERG-Related Cardiotoxicity: A Benchmark Study

Creanza

Delre

Ancona

et al. 2021

J. Chem. Inf. Model.

View full text Add to dashboard Cite

show abstract

“…http://zhanglab.ccmb.med.umich.edu/LS-align/ Machine learning Generate fast and accurate atom-level structural alignments of ligand molecules [ 225 ] LigGrep A tool for filtering docked poses to improve virtual-screening hit rates. http://durrantlab.com/liggrep/ Machine learning It can improve the hit rates of test VS targeting H. sapiens poly(ADPribose) polymerase 1 (HsPARP1), H. sapiens peptidyl-prolyl cis–trans isomerase NIMA-interacting 1 (HsPin1p), and S. cerevisiae hexokinase-2 (ScHxk2p) [ 226 ] AutoGrow4 De novo drug design and lead optimization. http://durrantlab.com/autogrow4 Genetic algorithm The predicted binding modes of the AutoGrow4 compounds mimic those of the known inhibitors, even when AutoGrow4 is seeded with random small molecules [ 227 ] DLIGAND2 Improved knowledge-based energy function for protein–ligand interactions.…”

Section: Applications Of Artificial Intelligence In Drug Development mentioning

confidence: 99%

Artificial intelligence to deep learning: machine intelligence approach for drug discovery

et al. 2021

View full text Add to dashboard Cite

Graphic abstract Drug designing and development is an important area of research for pharmaceutical companies and chemical scientists. However, low efficacy, off-target delivery, time consumption, and high cost impose a hurdle and challenges that impact drug design and discovery. Further, complex and big data from genomics, proteomics, microarray data, and clinical trials also impose an obstacle in the drug discovery pipeline. Artificial intelligence and machine learning technology play a crucial role in drug discovery and development. In other words, artificial neural networks and deep learning algorithms have modernized the area. Machine learning and deep learning algorithms have been implemented in several drug discovery processes such as peptide synthesis, structure-based virtual screening, ligand-based virtual screening, toxicity prediction, drug monitoring and release, pharmacophore modeling, quantitative structure–activity relationship, drug repositioning, polypharmacology, and physiochemical activity. Evidence from the past strengthens the implementation of artificial intelligence and deep learning in this field. Moreover, novel data mining, curation, and management techniques provided critical support to recently developed modeling algorithms. In summary, artificial intelligence and deep learning advancements provide an excellent opportunity for rational drug design and discovery process, which will eventually impact mankind. The primary concern associated with drug design and development is time consumption and production cost. Further, inefficiency, inaccurate target delivery, and inappropriate dosage are other hurdles that inhibit the process of drug delivery and development. With advancements in technology, computer-aided drug design integrating artificial intelligence algorithms can eliminate the challenges and hurdles of traditional drug design and development. Artificial intelligence is referred to as superset comprising machine learning, whereas machine learning comprises supervised learning, unsupervised learning, and reinforcement learning. Further, deep learning, a subset of machine learning, has been extensively implemented in drug design and development. The artificial neural network, deep neural network, support vector machines, classification and regression, generative adversarial networks, symbolic learning, and meta-learning are examples of the algorithms applied to the drug design and discovery process. Artificial intelligence has been applied to different areas of drug design and development process, such as from peptide synthesis to molecule design, virtual screening to molecular docking, quantitative structure–activity relationship to drug repositioning, protein misfolding to protein–protein interactions, and molecular pathway identification to polypharmacology. Artificial intelligence principles have been applied to the classification of active and inactive, monitoring drug release, pre-clinical and clinical development, primary and secondary drug screeni...

show abstract

“…The performance of the docking algorithm was validated in a re-docking experiment, in which the co-crystallized ligand's binding pose was reproduced with an acceptable RMSD of 0.252 Å [48]. Poses whose protonated N-methyl moiety did not come within 5.5 Å of Asp105 3.32 s carboxyl oxygens were removed by utilizing LigGrep as post-docking filter [49]. Docking results and the corresponding receptorligand interactions were analyzed with the software LigandScout 4.4.5 [22].…”

Section: Ligand Designmentioning

confidence: 99%

Design, Synthesis, and Biological Evaluation of 4,4’-Difluorobenzhydrol Carbamates as Selective M1 Antagonists

et al. 2022

View full text Add to dashboard Cite

Due to their important role in mediating a broad range of physiological functions, muscarinic acetylcholine receptors (mAChRs) have been a promising target for therapeutic and diagnostic applications alike; however, the list of truly subtype-selective ligands is scarce. Within this work, we have identified a series of twelve 4,4’-difluorobenzhydrol carbamates through a rigorous docking campaign leveraging commercially available amine databases. After synthesis, these compounds have been evaluated for their physico–chemical property profiles, including characteristics such as HPLC-logD, tPSA, logBB, and logPS. For all the synthesized carbamates, these characteristics indicate the potential for BBB permeation. In competitive radioligand binding experiments using Chinese hamster ovary cell membranes expressing the individual human mAChR subtype hM1-hM5, the most promising compound 2 displayed a high binding affinitiy towards hM1R (1.2 nM) while exhibiting modest-to-excellent selectivity versus the hM2-5R (4–189-fold). All 12 compounds were shown to act in an antagonistic fashion towards hM1R using a dose-dependent calcium mobilization assay. The structural eligibility for radiolabeling and their pharmacological and physico–chemical property profiles render compounds 2, 5, and 7 promising candidates for future position emission tomography (PET) tracer development.

show abstract

LigGrep: a tool for filtering docked poses to improve virtual-screening hit rates

Cited by 18 publications

References 71 publications

Structure-Based Prediction of hERG-Related Cardiotoxicity: A Benchmark Study

Structure-Based Prediction of hERG-Related Cardiotoxicity: A Benchmark Study

Artificial intelligence to deep learning: machine intelligence approach for drug discovery

Design, Synthesis, and Biological Evaluation of 4,4’-Difluorobenzhydrol Carbamates as Selective M1 Antagonists

Contact Info

Product

Resources

About