Intellicule Receives $217,941 NIH Grant to Develop AI-Powered Cryo-EM Software for Drug Discovery
核心洞察
Intellicule (搜索), a Purdue University-affiliated software startup, secured a $217,941 SBIR Phase I grant from the National Institutes of Health to develop advanced biomolecular modeling software.
The company's deep learning-powered technology aims to overcome current limitations in cryo-EM analysis, particularly when resolution is worse than 3 angstroms, making drug discovery more accessible to non-specialists.
The software enables detection of atoms in low-resolution cryo-EM images and could accelerate novel drug development by providing precise structural information to guide molecular design with improved efficacy.
Intellicule (搜索), a software company specializing in three-dimensional biomolecular structure determination through cryogenic-electron microscopy (cryo-EM), has secured a $217,941 Small Business Innovation Research (SBIR) Phase I grant from the National Institutes of Health. The funding will support development of advanced deep learning software designed to accelerate drug discovery and advance precision medicine.
The Purdue University-affiliated startup, led by Daisuke Kihara, professor of biological sciences and computer science in Purdue University's College of Science, aims to address critical limitations in current cryo-EM analysis methods. "It will have the potential to accelerate the development of novel drugs by offering precise structural information that can guide the design of molecules with improved efficacy," Kihara stated.
Addressing Cryo-EM Resolution Challenges
Cryo-EM has become a widely adopted experimental technique for determining three-dimensional structures of biological macromolecules, including proteins (搜索), nucleic acids (搜索), and drug molecules. The technology's impact extends beyond academic research, with biotech and pharmaceutical companies increasingly utilizing cryo-EM for detailed structural insights into biological targets.
However, a significant challenge exists in achieving high resolution better than 3 angstroms (Å) consistently. "When the resolution is worse than 3 Å, ligands (搜索) may still be visible, but the process of modeling becomes considerably more time-consuming and error-prone," Kihara explained. "This underscores the need for advanced software tools that can streamline the modeling process, reduce errors and make cryo-EM more accessible to nonspecialists in drug discovery efforts."
Deep Learning Technology at the Core
The Phase I SBIR project focuses on expanding and advancing structural modeling and analysis for drug discovery using state-of-the-art deep learning techniques. The intellectual merit of the project lies in its methodology, which overcomes current limitations in biomolecular modeling for cryo-EM data.
"Deep learning is a powerful type of artificial intelligence particularly effective in image processing," Kihara noted. "In this software, it enables the detection of atoms in low-resolution cryo-EM images, something that would otherwise be extremely difficult to achieve."
The technology specifically targets the accurate modeling of ligand-receptor complexes (搜索) at resolutions where conventional methods struggle, potentially streamlining structure-based drug design processes.
Company Background and Commercialization
Intellicule (搜索) was formerly known as Molecular Intelligence and launched in summer 2024. The company was co-founded by Kihara along with Charles Christoffer, senior computational scientist in the Rosen Center for Advanced Computing, and Genki Terashi, assistant research scientist in the Department of Biological Sciences.
The Purdue Innovates Office of Technology Commercialization issued the company an exclusive license to sell the software in January 2025. Kihara also serves as a member of the Purdue Institute for Cancer Research (搜索) and Purdue Institute for Drug Discovery (搜索).
The development work is part of Purdue's One Health initiative, which brings together research on human, animal, and plant health, highlighting the broader applications of the biomolecular modeling technology beyond pharmaceutical drug discovery.