Artificial intelligence (AI) is booming. Among various AI approaches, generative models have received much attention in recent years. Inspired by these successes, researchers are now applying generative model techniques to de novo drug design, which has been considered as the “holy grail” of drug discovery. In this Perspective, we first focus on describing models such as recurrent neural network, autoencoder, generative adversarial network, transformer, and hybrid models with reinforcement learning. Next, we summarize the applications of generative models to drug design, including generating various compounds to expand the compound library and designing compounds with specific properties, and we also list a few publicly available molecular design tools based on generative models which can be used directly to generate molecules. In addition, we also introduce current benchmarks and metrics frequently used for generative models. Finally, we discuss the challenges and prospects of using generative models to aid drug design.

No abstract

No abstract

Separation of iron-binding peptides derived from shrimp processing by-products (SPB) by Alacase hydrolysis was investigated. The highest iron-binding capacity of the hydrolysate (17.5 μmol/g of protein) was obtained with Alacase at a degree of hydrolysis of 8%. The molecular weight (MW) distribution on gel permeation chromatography (GPC) showed that it was ranging from 1 to 6 kDa. By separating with ion-exchange chromatography on SPSepharose Fast Flow and gel filtration on Sephadex G-25, one fraction with highest iron-binding capacity of 8,800μmol/g of protein was purified, and the purification fold of 502 was obtained. When the highest iron-binding capacity fraction was applied on RP-HPLC column, there were four main peaks. By comparing with the infrared spectra of the iron-binding peptides and iron-peptides complex, it was suggested that the principal site of iron-binding corresponded primarily to the carboxylate groups and to a lesser extent to the peptide bonds.