Carly MurphyHigh throughput screening (HTS) is a standard method in pharmaceutical development for identifying bioactive small molecules crucial for drug discovery. However, HTS necessitates testing molecules before their synthesis.
Alternatively, computational approaches using AI and machine learning allow for pre-synthesis molecule testing. This method yields results that guide which molecules merit synthesis, promising improvements over HTS in terms of cost, speed, and experimental integrity.
A recent study by The Atomwise AIMS Program, published in Nature Scientific Reports on April 2, 2024, explored the potential of deep learning-based methods in identifying novel bioactive chemotypes. The study applied the AtomNet model to identify hits for 22 internal pharmaceutical targets.
Contributing to the study, Professor Keykavous Parang of Chapman University’s School of Pharmacy utilized the AtomNet model to discover drug-like hits for Src kinase, a key enzyme strongly linked to cancer development across various human cancers. Targeting Src kinase holds significant promise in anti-cancer drug discovery.
The study identified drug-like hits for 296 academic targets, followed by dose-response experiments for 49 targets, and further validation through analog exploration of initial hits. Parang shared, “Initially, a single dose was used to identify the most promising hits that interacted with selected targets. Subsequently, based on the results of these experiments, 49 targets were selected, and the effects of varying doses on responses were determined. Eventually, through these experiments, 21 targets were confirmed to interact with the initial compounds identified by the AtomNet model.”
“By showcasing the efficiency of computational techniques in locating new drug candidates, this study may represent a major advance in drug discovery. Computational methods like AtomNet can effectively find interesting compounds in a variety of therapeutic areas and protein classes. This might cause a paradigm change in drug development by increasing the accessible chemical space and decreasing the need for conventional high-throughput screening techniques.”
“While a scientist must conduct independent research in order to grow and as expected by their university, major discoveries are usually made in conjunction with other scientists. All things considered, the study highlights the need for collaboration and teamwork for scientific growth, particularly in fields as complex and multidisciplinary as drug discovery. It serves as an example of how pooling the expertise and assets of multiple stakeholders can produce high-quality data that significantly enhances our understanding and validation of computer models in real-world settings. By forming a partnership with multiple universities, organizations, and researchers, the study carried out 318 separate investigations internationally covering a wide range of targets and treatment domains.”
###
About Chapman University
Founded in 1861, Chapman University is a nationally ranked private university in Orange, California, about 30 miles south of Los Angeles. Chapman serves nearly 10,000 undergraduate and graduate students, with a 12:1 student-to-faculty ratio. Students can choose from 123 areas of study within 11 colleges for a personalized education. Chapman is categorized by the Carnegie Classification as an R2 “high research activity” institution. Students at Chapman learn directly from distinguished world-class faculty including Nobel Prize winners, MacArthur fellows, published authors and Academy Award winners. The campus has produced a Rhodes Scholar, been named a top producer of Fulbright Scholars and hosts a chapter of Phi Beta Kappa, the nation’s oldest and most prestigious honor society. Chapman also includes the Harry and Diane Rinker Health Science Campus in Irvine. The university features the No. 4 film school and No. 60 business school in the U.S. Learn more about Chapman University: www.chapman.edu.
About Atomwise– is a TechBio company leveraging AI/ML to revolutionize small molecule drug discovery. The Atomwise team invented the use of deep learning for structure-based drug design, a core technology of Atomwise’s best-in-class AI discovery and optimization engine, which is differentiated by its ability to find and optimize novel chemical matter. Atomwise has extensively verified its discovery engine, having demonstrated the ability to find compounds with therapeutic potential hundreds of times across a wide variety of protein types and multiple “hard to drug” targets. Atomwise is advancing a proprietary pipeline of small-molecule drug candidates.
