Today, Insilico Medicine, Inc., a Rockville-based next-generation artificial intelligence company specializing in the application of deep learning for target identification, drug discovery and aging research announces the publication of a new research paper “Entangled Conditional Adversarial Autoencoder for de-novo Drug Discovery” in Molecular Pharmaceutics, the leading American Chemical Society journal covering research on the molecular mechanistic understanding of drug delivery and drug delivery systems. The authors presented an original deep neural network architecture, Entangled Conditional Adversarial Autoencoder (ECAAE), which generates molecular structures based on various properties such as activity against a specific protein, solubility, and ease of synthesis. ECAAE was used to generate a novel inhibitor of Janus Kinase 3 (JAK3), implicated in rheumatoid arthritis, psoriasis, and vitiligo. The discovered molecule was tested in vitro and demonstrated high activity and selectivity.
Generative Adversarial Networks (GANs) proposed by Ian Goodfellow and colleagues in 2014 and commonly referred to as AI imagination, are among the most exciting areas of AI research. Since 2015 these networks were demonstrated unprecedented results in generating novel photorealistic images and even videos. They hold a substantial promise for drug discovery, biomarker development, and design of novel materials.
Insilico Medicine is one of the pioneers in the applications of GAN architectures to the generation of novel molecular structures and generation of synthetic patient data. The group’s first peer-reviewed paper demonstrating the application of generative models to molecules applied an adversarial autoencoder (AAE) to the generation of new promising anti-cancer compounds in 2016.
Unlike the GAN-generated images and videos, which can be quickly and cheaply validated manually, it takes months to synthesize and validate the GAN-generated molecules. In this work, Insilico Medicine scientists demonstrated the ability to generate novel JAK kinases inhibitors, which were validated by experimental assays.
This paper is one of GAN and GAN-RL research papers describing the birth of the new field of AI-powered drug discovery to be published in the special issue of Molecular Pharmaceutics titled “Deep Learning in Drug Discovery and Biomarker Development”.
For its pioneering work in the field of artificial intelligence for drug discovery, Insilico Medicine received the Frost & Sullivan 2018 North American Artificial Intelligence for Aging Research and Drug Development Technology Innovation Award. The company dedicates it AI technology to to target age-related diseases and extend human health longevity.
“Technology leadership in artificial intelligence for drug discovery and biomarker development, academic excellence, extensive collaborations with pharmaceutical and consumer companies, novel methods of attracting top talent, and increasing global reach have allowed Insilico Medicine to build a credible and sustainable business model in the nascent longevity biotechnology industry,” noted Neelotpal Goswami. “In recognition of its pioneering research and ability to introduce novel products and solutions for age management, Frost & Sullivan is pleased to present it with the 2018 Technology Innovation Award.”
Insilico Medicine is regularly publishing research papers in peer-reviewed journals. The company was first who applied deep generative adversarial networks (GANs) to the generation of new molecular structures with specified parameters and published seminal proof of concept papers in the field. The paper published in Molecular Pharmaceutics in 2016 demonstrated the proof of concept of the application of deep neural networks for predicting the therapeutic class of the molecule using the transcriptional response data, received the American Chemical Society Editors’ Choice Award. A recent paper published in November 2017 described the application of the next-generation AI and blockchain technologies to return the control over personal data back to the individual. One of the latest papers published in the Journals of Gerontology demonstrated the application of the deep neural networks to assess the biological age of the patients.