ChemGenerator: a web server for generating potential ligands for specific targets

2020 ◽  
Author(s):  
Jing Yang ◽  
Ling Hou ◽  
Kun-Meng Liu ◽  
Wen-Bin He ◽  
Yong Cai ◽  
...  
Keyword(s):  
Drug Discovery ◽  
Short Term Memory ◽  
Reference Model ◽  
Growth Factor Receptor ◽  
Web Server ◽  
Biologically Active ◽  
Basic Model ◽  
Chemical Database ◽  
Efficient Alternative ◽  
Epidermal Growth

Abstract In drug discovery, one of the most important tasks is to find novel and biologically active molecules. Given that only a tip of iceberg of drugs was founded in nearly one-century’s experimental exploration, it shows great significance to use in silico methods to expand chemical database and profile drug-target linkages. In this study, a web server named ChemGenerator was proposed to generate novel activates for specific targets based on users’ input. The ChemGenerator relies on an autoencoder-based algorithm of Recurrent Neural Networks with Long Short-Term Memory by training of 7 million of molecular Simplified Molecular-Input Line-Entry System as the basic model, and further develops target guided generation by transfer learning. As results, ChemGenerator gains lower loss (<0.01) than existing reference model (0.2~0.4) and shows good performance in the case of Epidermal Growth Factor Receptor. Meanwhile, ChemGenerator is now freely accessible to the public by http://smiles.tcmobile.org. In proportion to endless molecular enumeration and time-consuming expensive experiments, this work demonstrates an efficient alternative way for the first virtual screening in drug discovery.

scholarly journals 6-Nitro-7-tosylquinazolin-4(3H)-one

Molbank ◽  
10.3390/m1168 ◽  
2020 ◽  
Vol 2020 (4) ◽  
pp. M1168
Author(s):  
Thi Ngoc Nguyen ◽  
Thi Phuong Thuy Tran ◽  
Thi Hoang Mai Vu ◽  
Hoa Binh Nguyen ◽  
Nguyet Suong Huyen Dao ◽  
...  
Keyword(s):  
Tyrosine Kinases ◽  
Quantum Coherence ◽  
Multiple Bond ◽  
Growth Factor Receptor ◽  
Functional Materials ◽  
Building Blocks ◽  
Correlation Spectroscopy ◽  
Biologically Active ◽  
Ft Ir ◽  
Epidermal Growth

Sulfones are important building blocks in the construction of biologically active molecules or functional materials. The sulfonyl functional group in sulfones is so versatile that it can act as either a nucleophile, an electrophile, or a radical in different organic reactions. Recently, quinazoline sulfones have been used to build asymmetrical ether derivatives as inhibitors of signaling pathways governed by tyrosine kinases and the epidermal growth factor-receptor. In this paper, we report a facile synthesis of a novel quinazoline sulfone, 6-nitro-7-tosylquinazolin-4(3H)-one (III), using the modified protocol from 7-chloro-6-nitroquinazolin-4(3H)-one (I) and sodium p-toluenesulfinate (II). The structure of the title compound III was determined using mass-spectrometry, FT-IR, 1H-NMR, 13C-NMR, DEPT, HSQC (Heteronuclear single quantum coherence), HMBC (Heteronuclear Multiple Bond Correlation Spectroscopy) spectroscopies, and PXRD analysis.

scholarly journals iRhom2: An Emerging Adaptor Regulating Immunity and Disease

2020 ◽  
Vol 21 (18) ◽  
pp. 6570 ◽  
Author(s):  
Mazin A. Al-Salihi ◽  
Philipp A. Lang
Keyword(s):  
Critical Role ◽  
Growth Factor Receptor ◽  
Biologically Active ◽  
Necrosis Factor Alpha ◽  
Dna Viruses ◽  
Catalytic Center ◽  
Intramembrane Proteases ◽  
Epidermal Growth ◽  
Factor Alpha

The rhomboid family are evolutionary conserved intramembrane proteases. Their inactive members, iRhom in Drosophila melanogaster and iRhom1 and iRhom2 in mammals, lack the catalytic center and are hence labelled “inactive” rhomboid family members. In mammals, both iRhoms are involved in maturation and trafficking of the ubiquitous transmembrane protease a disintegrin and metalloprotease (ADAM) 17, which through cleaving many biologically active molecules has a critical role in tumor necrosis factor alpha (TNFα), epidermal growth factor receptor (EGFR), interleukin-6 (IL-6) and Notch signaling. Accordingly, with iRhom2 having a profound influence on ADAM17 activation and substrate specificity it regulates these signaling pathways. Moreover, iRhom2 has a role in the innate immune response to both RNA and DNA viruses and in regulation of keratin subtype expression in wound healing and cancer. Here we review the role of iRhom2 in immunity and disease, both dependent and independent of its regulation of ADAM17.

Docking Study of 3-mercapto-1,2,4-triazole Derivatives as Inhibitors for VEGFR and EGFR

2017 ◽  
Vol 68 (3) ◽  
pp. 500-503
Author(s):  
Marius Mioc ◽  
Sorin Avram ◽  
Andrei Branco Tomescu ◽  
Daniela Veronica Chiriac ◽  
Alina Heghes ◽  
...  
Keyword(s):  
Drug Discovery ◽  
Growth Factor ◽  
Scoring Function ◽  
Growth Factor Receptor ◽  
Docking Study ◽  
Molecular Structures ◽  
Screening Process ◽  
Protein Targets ◽  
Epidermal Growth ◽  
Endothelial Growth Factor

Computer-aided drug design plays an important role in modern day drug discovery, because it provides a more specific range for active compound chemical synthesis in detriment of the traditional ways of drug discovery. Relevant studies proved that the epidermal growth factor receptor (EGFR) and vascular endothelial growth factor receptor (VEGFR) are important targets for inhibition, in finding new molecules with potential anticancer activity. The aim of the present study was to create a compound library and submit this set of molecules to a docking-based virtual screening process. Molecular docking was carried out using OEDocking HYBRYD, a software with an improved scoring algorithm, which uses a ligand-based scoring function. The obtained results revealed some molecular structures that showed good predicted binding affinity towards their respective protein targets.

scholarly journals LigEGFR: Spatial graph embedding and molecular descriptors assisted bioactivity prediction of ligand molecules for epidermal growth factor receptor on a cell line-based dataset

2020 ◽  
Author(s):  
Puri Virakarin ◽  
Natthakan Saengnil ◽  
Bundit Boonyarit ◽  
Jiramet Kinchagawat ◽  
Rattasat Laotaew ◽  
...  
Keyword(s):  
Machine Learning ◽  
Epidermal Growth Factor Receptor ◽  
Drug Discovery ◽  
Epidermal Growth Factor ◽  
Small Molecules ◽  
Molecular Descriptors ◽  
Growth Factor Receptor ◽  
Graph Embedding ◽  
Spatial Graph ◽  
Epidermal Growth

AbstractMotivationLung cancer is a chronic non-communicable disease and is the cancer with the world’s highest incidence in the 21st century. One of the leading mechanisms underlying the development of lung cancer in nonsmokers is an amplification of the epidermal growth factor receptor (EGFR) gene. However, laboratories employing conventional processes of drug discovery and development for such targets encounter several pain-points that are cost- and time-consuming. Moreover, high failure rates are caused by efficacy and safety problems during research and development. Therefore, it is imperative to develop improved methods for drug discovery. Herein, we developed a deep learning model with spatial graph embedding and molecular descriptors based on predicting pIC50 potency estimates of small molecules and classifying hit compounds against the human epidermal growth factor receptor (LigEGFR). The model was generated with a large-scale cell line-based dataset containing broad lists of chemical features.ResultsLigEGFR outperformed baseline machine learning models for predicting pIC50. Our model was notable for higher performance in hit compound classification, compared to molecular docking and machine learning approaches. The proposed predictive model provides a powerful strategy that potentially helps researchers overcome major challenges in drug discovery and development processes, leading to a reduction of failure to discover novel hit compounds.AvailabilityWe provide an online prediction platform and the source code that are freely available at https://ligegfr.vistec.ist, and https://github.com/scads-biochem/LigEGFR, respectively.Key pointsLigEGFR is a regression model for predicting pIC50 that was developed for the human EGFR target. It can also be applied to hit compound classification (pIC50 ≥ 6) and has a higher performance than baseline machine learning algorithms and molecular docking approaches.Our spatial graph embedding and molecular descriptors based approach notably exhibited a high performance in predicting pIC50 of small molecules against human EGFR.Non-hashed and hashed molecular descriptors were revealed to have the highest predictive performance by using in a convolutional layers and a fully connected layers, respectively.Our model used a large-scale and non-redundant dataset to enhance the diversity of the small molecules. The model showed robustness and reliability, which was evaluated by y-randomization and applicability domain analysis (ADAN), respectively.We developed a user-friendly online platform to predict pIC50 of small molecules and classify the hit compounds for the drug discovery process of the EGFR target.

Sign in / Sign up

Export Citation Format

Share Document