SWEETLEAD: an In Silico Database of Approved Drugs, Regulated Chemicals, and Herbal Isolates for Computer-Aided Drug Discovery

By Paul A. Novick, Oscar F. Ortiz, Jared Poelman, Amir Abdulhay, Vijay S. Pande. 2013

128 citations recorded by the source corpus.

In the face of drastically rising drug discovery costs, strategies promising to reduce development timelines and expenditures are being pursued. Computer-aided virtual screening and repurposing approved drugs are two such strategies that have shown recent success. Herein, we report the creation of a highly-curated in silico database of chemical structures representing approved drugs, chemical isolates from traditional medicinal herbs, and regulated chemicals, termed the SWEETLEAD database. The motivation for SWEETLEAD stems from the observance of conflicting information in publicly available chemical databases and the lack of a highly curated database of chemical structures for the globally approved drugs. A consensus building scheme surveying information from several publicly accessible databases was employed to identify the correct structure for each chemical. Resulting structures are filtered for the active pharmaceutical ingredient, standardized, and differing formulations of the same drug were combined in the final database. The publically available release of SWEETLEAD (https://simtk.org/home/sweetlead) provides an important tool to enable the successful completion of computer-aided repurposing and drug discovery campaigns.

Subfields: Computational Theory and Mathematics, Pharmacology, Computational Chemistry & Drug Discovery

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

In Pharmacology

In Computational Chemistry & Drug Discovery

Citations in the corpus

Strategies for Pre-training Graph Neural Networks (2019, methodology): “Qualitative data classifying drugs approved by the FDA and those that have failed clinical trials for toxicity reasons (Novick et al., 2013; AACT).”
A survey of current trends in computational drug repositioning (2016, background): “Moreover, publicly available databases of chemical structures, high-throughput screening data and literature-derived biochemical data containing massive amounts of information useful for repositioning [45–48].”
Graph Self-Supervised Learning: A Survey (2021, unknown): “36 27* [10], [16], [70], [75], [101], [108] ClinTox [148] 1,478 26.”
Pre-training Graph Neural Networks (2019, background): “Qualitative data classifying drugs approved by the FDA and those that have failed clinical trials for toxicity reasons [34, 1].”
Large Language Models on Graphs: A Comprehensive Survey (2023, unknown): “These elements pertain to the most likely second, third, and subsequent choices regarding the nodes from which a text originates and the texts that a node generates.”