Accelerating drug discovery with AI and quantum mechanics

Combining artificial intelligence (AI), quantum mechanics, and Computer Assisted Drug Design (CADD), this open-source platform aims to drastically reduce the time required for identifying potential drug candidates.

In a recent study published in the Journal of Chemical Information and Modeling, the research team demonstrated SmartCADD's capabilities in identifying promising drug candidates for HIV treatment. The development of SmartCADD is the result of a collaborative effort between SMU’s Department of Chemistry in Dedman College of Humanities and Sciences and the Computer Science Department in the Lyle School of Engineering.

“There is an urgency to discover new classes of drugs like antibiotics, cancer treatments, antivirals, and more,” said Elfi Kraka, Head of the Computational and Theoretical Chemistry Group (CATCO) at SMU. “Despite AI’s rapid adoption in many fields, there has been a hesitancy for using it in scientific research, mainly because of its opaqueness and the quality of data used for training. SmartCADD addresses those concerns and can sift through billions of chemical compounds in one day, which significantly reduces the time needed to identify promising drug candidates.”

How SmartCADD works

SmartCADD functions by integrating deep learning models, filtering techniques, and explainable AI to screen vast databases of chemical compounds. The tool comprises two primary components: the Pipeline Interface, which manages data collection and filtering, and the Filter Interface, which dictates the operation of each filter. These filters help researchers predict a drug's behaviour in the body, model drug structures using both 2D and 3D parameters, and utilise an AI model that explains the rationale behind its selections.

In the study, SmartCADD’s capabilities were tested on HIV drug discovery. Using data from the MoleculeNet library, researchers constructed a database of 800 million chemical compounds and identified 10 million that showed potential as HIV drugs. The platform's filters then narrowed down the list to compounds with the closest match to existing HIV treatments.

While the initial focus was on HIV, the researchers highlighted SmartCADD's versatility, indicating that it can be adapted for other drug discovery applications. Corey Clark, Assistant Professor of Computer Science in the Lyle School of Engineering and Deputy Director for Research at SMU Guildhall, noted: “This is a user-friendly virtual screening platform that provides researchers with a highly integrated and flexible framework for building drug discovery pipelines. We are going to continue pushing the work forward to expand chemistry and machine learning capabilities even further. The project and its opportunities are truly exciting, and I know the next phase will be an even bigger step forward than the last.”

Interdisciplinary collaboration: the key to SmartCADD’s success

The development of SmartCADD exemplifies the power of interdisciplinary collaboration. The team included researchers from both the chemistry and computer science departments at SMU. The study’s authors include Elfi Kraka and Corey Clark, as well as postdoctoral research fellow Ayesh Madushanka, supported by a grant from the O’Donnell Data Science & Research Computing Institute, and computer science graduate student Eli Laird, an O’Donnell Institute Ph.D. fellowship recipient.

Madushanka emphasised the importance of cross-disciplinary efforts in tackling complex challenges: “Fields like drug discovery require a combined effort to be truly successful. I’m certain if only the chemistry department had worked on this, the final product wouldn’t have turned out the same. Interdisciplinary collaboration brings fresh perspectives on the same idea, helping to refine and improve it.”

Laird echoed this sentiment, explaining that combining insights from different fields can lead to significant breakthroughs: “Interdisciplinary research is absolutely necessary to make major research advancements that actually impact the real world. This is a major focus of SMU and a key reason I wanted to pursue my Ph.D. here. Impactful research can't happen in the vacuum of a single field. You have to look broadly across disciplines to spark ideas that will turn into true innovations. Breakthroughs often occur at the intersection of different fields, and that's where I aim to position my research.”

The road ahead for SmartCADD

The study was funded by the National Science Foundation under grant CHE 2102461, though the findings and conclusions presented are solely those of the authors. With SmartCADD, the research team hopes to accelerate drug discovery across various medical fields, from antibiotics and cancer therapies to antiviral treatments. The platform's ability to screen billions of chemical compounds rapidly could transform how new drugs are discovered and brought to market, ultimately benefiting patients worldwide.

As researchers continue to expand SmartCADD's capabilities, they aim to push the boundaries of what AI and quantum mechanics can achieve in pharmaceutical development.