While the many concepts in artificial intelligence date back to the 20th century, the revolution in deep learning started around 2014-2015 when AI systems started outperforming humans in many tasks ranging from video games and image recognition to autonomous driving. The concept of Generative Adversarial Networks (GANs) was only introduced in 2014 and went mainstream in 2016 with the publication of the first “AI-imagined” images generated using GANs from natural language. However, due to the gap in domain expertise between chemists, biologists, and next-generation AI scientists and the lengthy validation cycles, only today we start noticing the propagation of deep learning into these fields. While there is still a gap in domain expertise in biology and chemistry in the machine learning community, it is rapidly closing and many advances are propagating into drug discovery and biomarker development. The special issue on deep learning for drug discovery and biomarker development provides an overview of the recent applications of modern AI.
Today, Insilico Medicine, one of the industry leaders bridging deep learning for biology, chemistry and digital medicine, announced the publication of a special issue dedicated to “Deep Learing for Drug Discovery and Biomarker Development” in one of the top industry journals celebrating its 15th anniversary published by the American Chemical Society, Molecular Pharmaceutics. The special issue starts with an article by the founder and CEO of Insilico Medicine, Alex Zhavoronkov, PhD, titled “Artificial Intelligence for Drug Discovery, Biomarker Development, and Generation of Novel Chemistry”.
“The special issue dedicated to deep learning for drug discovery and biomarker development brings together the contributions made by some of the top academics and industry experts. The collection of papers in the special issue may provide a quick introduction into the field and specifically into generative chemistry. We are very happy to see this special issue “, said Alex Zhavoronkov, PhD, founder, and CEO of Insilico Medicine.
The special issue is mostly focused on generative chemistry using GANs and Reinforcement Learning (RL) for de-novo molecular design. Some of the articles, including the “Entangled Conditional Adversarial Autoencoder (ECAAE) for de-novo Drug Discovery” demonstrate for the first time the experimental validation of the molecules generated using these architectures. 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.
Molecular Pharmaceutics is one of the first journals to recognize the trend in deep learning for biomedicine with the publication of the first review paper on this emerging subject in 2016.