MolDesigner: Interactive Design of Efficacious Drugs with Deep Learning

Huang, Kexin; Fu, Tianfan; Khan, Dawood Ashraf; Ali, Abid; Abdalla, Ali; Abid, Abubakar; Glass, Lucas M.; Žitnik, Marinka; Xiao, Cao; Sun, Jimeng

doi:10.48550/arxiv.2010.03951

Cited by 5 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to determine the drug-likeness profile of 6e , detailed ADMET properties were predicted using deep learning architectures. MolDesigner is an advanced tool used for designing efficacious drugs with neural networks [ 35 ]. It utilizes the message-passing neural network (MPNN) for predicting the ADMET profile of a drug-like candidate.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Design, Synthesis, Kinetic Analysis and Pharmacophore-Directed Discovery of 3-Ethylaniline Hybrid Imino-Thiazolidinone as Potential Inhibitor of Carbonic Anhydrase II: An Emerging Biological Target for Treatment of Cancer

et al. 2022

View full text Add to dashboard Cite

Carbonic anhydrases (CA), having Zn2+ metal atoms, are responsible for the catalysis of CO2 and water to bicarbonate and protons. Any abnormality in the functioning of these enzymes may lead to morbidities such as glaucoma and different types of cancers including brain, renal and pancreatic carcinomas. To cope with the lack of presence of a promising therapeutic agent against these cancers, searching for an efficient and suitable carbonic anhydrase inhibitor is crucial. In the current study, ten novel 3-ethylaniline hybrid imino-thiazolidinones were synthesized and characterized by FTIR, NMR (1H, 13C), and mass spectrometry. Synthesis was carried out by diethyl but-2-ynedioate cyclization and different acyl thiourea substitutions of 3-ethyl amine. The CA (II) enzyme inhibition profile for all synthesized derivatives was determined. It was observed that compound 6e demonstrated highest inhibition of CA-II with an IC50 value of 1.545 ± 0.016 µM. In order to explore the pharmacophoric properties and develop structure activity relationship, in silico screening was performed. In silico investigations included density functional theory (DFT) studies, pharmacophore-guided model development, molecular docking, molecular dynamic (MD) simulations, and prediction of drug likeness scores. DFT investigations provided insight into the electronic characteristics of compounds, while molecular docking determined the binding orientation of derivatives within the CA-II active site. Compounds 6a, 6e, and 6g had a reactive profile and generated stable protein-ligand interactions with respective docking scores of −6.12, −6.99, and −6.76 kcal/mol. MD simulations were used to evaluate the stability of the top-ranked complex. In addition, pharmacophore-guided modeling demonstrated that compound 6e produced the best pharmacophore model (HHAAARR) compared to standard brinzolamide. In vitro and in silico investigations anticipated that compound 6e would be an inhibitor of carbonic anhydrase II with high efficacy. Compound 6e may serve as a potential lead for future synthesis that can be investigated at the molecular level, and additional in vivo studies are strongly encouraged.

show abstract

Section: Resultsmentioning

confidence: 99%

“…In silico ADMET predictions substantially reduced the time of drug development in cost effective manner. In the current study, advanced deep learning models were used predict the ADMET profile of potent derivatives [ 35 ]. Specifically, the message-passing neural network model (MPNN) was deployed to assess the ADMET profile.…”

Section: Materials and Methodologymentioning

confidence: 99%

Design, Synthesis, Kinetic Analysis and Pharmacophore-Directed Discovery of 3-Ethylaniline Hybrid Imino-Thiazolidinone as Potential Inhibitor of Carbonic Anhydrase II: An Emerging Biological Target for Treatment of Cancer

et al. 2022

View full text Add to dashboard Cite

show abstract

“…DL and Structure-Based Virtual Screening (SBVS) techniques therefore not only facilitate the screening of vast chemical libraries but also provide valuable insights into the intricate relationships between molecular structure and biological activity, particularly in identifying cancer inhibitors (Andricopulo et al, 2008;Lavecchia and Di Giovanni, 2013;Abdolmaleki and Ghasemi, 2017). DL models can examine the associations between molecular characteristics and biological activities (Lo et al, 2018), thereby providing significant insights for lead optimization and developing more potent and selective compounds (Kim et al, 2016;Huang et al, 2020b). Cancer is a profoundly debilitating condition affecting many individuals worldwide, leading to significant illness and death (Liamputtong and Suwankhong, 2015;Al-Jumaili et al, 2023a).…”

Section: Introductionmentioning

confidence: 99%

Revisiting methotrexate and phototrexate Zinc15 library-based derivatives using deep learning in-silico drug design approach

Siddique,

Anwaar,

Bashir

et al. 2024

Front. Chem.

View full text Add to dashboard Cite

Introduction: Cancer is the second most prevalent cause of mortality in the world, despite the availability of several medications for cancer treatment. Therefore, the cancer research community emphasized on computational techniques to speed up the discovery of novel anticancer drugs.Methods: In the current study, QSAR-based virtual screening was performed on the Zinc15 compound library (271 derivatives of methotrexate (MTX) and phototrexate (PTX)) to predict their inhibitory activity against dihydrofolate reductase (DHFR), a potential anticancer drug target. The deep learning-based ADMET parameters were employed to generate a 2D QSAR model using the multiple linear regression (MPL) methods with Leave-one-out cross-validated (LOO-CV) Q2 and correlation coefficient R2 values as high as 0.77 and 0.81, respectively.Results: From the QSAR model and virtual screening analysis, the top hits (09, 27, 41, 68, 74, 85, 99, 180) exhibited pIC50 ranging from 5.85 to 7.20 with a minimum binding score of -11.6 to -11.0 kcal/mol and were subjected to further investigation. The ADMET attributes using the message-passing neural network (MPNN) model demonstrated the potential of selected hits as an oral medication based on lipophilic profile Log P (0.19-2.69) and bioavailability (76.30% to 78.46%). The clinical toxicity score was 31.24% to 35.30%, with the least toxicity score (8.30%) observed with compound 180. The DFT calculations were carried out to determine the stability, physicochemical parameters and chemical reactivity of selected compounds. The docking results were further validated by 100 ns molecular dynamic simulation analysis.Conclusion: The promising lead compounds found endorsed compared to standard reference drugs MTX and PTX that are best for anticancer activity and can lead to novel therapies after experimental validations. Furthermore, it is suggested to unveil the inhibitory potential of identified hits via in-vitro and in-vivo approaches.

show abstract