China
Africa
Explore chapters and articles related to this topic
Integrating CADD and Herbal Informatics Approach to Explore Potential Drug Candidates Against HPV E6 Associated With Cervical Cancer
Published in Shazia Rashid, Ankur Saxena, Sabia Rashid, Latest Advances in Diagnosis and Treatment of Women-Associated Cancers, 2022
Arushi Verma, Jyoti Bala, Navkiran Kaur, Anupama Avasthi
Ligand preparation: Identification and analysis done thorough literature search through NCBI indicated Luteolin [15] and Daphnoretin [16] as anti-neoplastic, antiviral agents and apoptosis inducing. Physiochemical analysis were done using PubChem [17] and 3-D structures of both the hits were built and visualized. ChEMBL [18] and Drugbank [19] were used to gather relevant information about the ligands like its sources, alternative forms, activity charts, clinical data and so forth.
Ligand efficiency indices for effective drug discovery: a unifying vector formulation
Published in Expert Opinion on Drug Discovery, 2021
Independently, the teams at the various SAR-Databases were developing their own applications to keep pace with rapidly growing number of entries, frequent updates, and the new computational and internet-based resources, combined with the widespread availability of rapid computational and graphic resources. In this context, the team at ChEMBL developed MyCHEMBL [19,20], an independent, user-controlled application that makes use of the most current content of the database and additional tools, e.g. KNIME workflows, available to the user. Employing these tools, it is very easy to create your own AtlasCBS modules and workflows and apply them to your specific project needs. Examples of workflows have been presented and are available from the KNIME site (version 3.0) [18]. In addition, established software packages like StarDropTM now include, among their additional scripts, links to the ChEMBL database which, combined with the AtlasCBS module, permit the friendly and expedient incorporation of the LEI variables into the individual drug discovery projects within the context of Multiple Parameter Optimization (MPO) [6].
The application of machine learning techniques to innovative antibacterial discovery and development
Published in Expert Opinion on Drug Discovery, 2020
Mateus Sá Magalhães Serafim, Thales Kronenberger, Patrícia Rufino Oliveira, Antti Poso, Káthia Maria Honório, Bruno Eduardo Fernandes Mota, Vinícius Gonçalves Maltarollo
The development of MLT-based models requires a dataset of known compounds for the training step and another set to test the predictability of models, those compounds should have activity values for a specific endpoint prediction. In this sense, research groups generally use a previously reported series of compounds to generate a model that can be later applied on the discovery of new hit compounds. Publicly available data sets are also commonly employed in MLT studies and there are several useful sources that can be exemplified (Table 2). Among those datasets, the two most popular are ChEMBL and BindingDB. ChEMBL [76] is a manually curated database of bioactive molecules with approximately 1.9 millions of compounds with a reported activity of 12,500 targets (ranging from enzymatic assays to cell-lines and microorganisms). BindingDB [77] is a complementary database reporting binding affinities, containing information about 805 thousands of compounds from 7.5 thousand protein targets. Therefore, another interesting database is AntibioticDB [78], which includes approximately 1,100 compounds currently in pre-clinical development, in phases 1–4 of clinical trials, and compounds which have been discontinued.
Transforming cancer drug discovery with Big Data and AI
Published in Expert Opinion on Drug Discovery, 2019
Paul Workman, Albert A. Antolin, Bissan Al-Lazikani
ChEMBL is the gold standard, curated database of small molecules and experimentally determined bioactivities [18]. The latest version contains >1.6M compounds and >14M bioactivities. PubChem is a wider, community-driven effort and currently contains chemical data on 97M compounds with associated bioassay results [19]. These major chemical/pharmacological databases also contain some data on absorption, distribution, metabolism, excretion and toxicity (ADMET), but they are sparse and small. Moreover, data sources that focus on ADMET information remain modest and limited (Table 1).