Deep-learning based bioactive therapeutic peptides generation and screening

Abstract

Many bioactive peptides demonstrated therapeutic effects over-complicated diseases, such as antiviral, antibacterial, anticancer, etc. Similar to the generating de novo chemical compounds, with the accumulated bioactive peptides as a training set, it is possible to generate abundant potential bioactive peptides with deep learning. Such techniques would be significant for drug development since peptides are much easier and cheaper to synthesize than compounds. However, there are very few deep learning-based peptide generating models. Here, we have created an LSTM model (named LSTM_Pep) to generate de novo peptides and finetune learning to generate de novo peptides with certain potential therapeutic effects. Remarkably, the Antimicrobial Peptide Database has fully utilized in this work to generate various kinds of potential active de novo peptide. We proposed a pipeline for screening those generated peptides for a given target, and use Main protease of SARS-COV-2 as concept-of-proof example. Moreover, we have developed a deep learning-based protein-peptide prediction model (named DeepPep) for fast screening the generated peptides for the given targets. Together with the generating model, we have demonstrated iteratively finetune training, generating and screening peptides for higher predicted binding affinity peptides can be achieved. Our work sheds light on to the development of deep learning-based methods and pipelines to effectively generating and getting bioactive peptides with a specific therapeutic effect, and showcases how artificial intelligence can help discover de novo bioactive peptides that can bind to a particular target.

Deep-learning based bioactive peptides generation and screening against Xanthine oxidase

“…Deep learning techniques have been widely applied in biological related fields. Recently, we have developed LSTM_pep for de novo potential bioactive peptide generation through finetune training over known active peptides, and DeepPep for prediction of whether given protein-peptide are binding 9 . The combination of LSTM_Pep and DeepPep can provide an effective way to generate and screen potential active peptides for given protein targets.…”

Towards a Dataset for State of the Art Protein Toxin Classification

“…Simultaneously, these enhancements have amplified both the capabilities and dualuse risks (potential risks associated with technology that can be used for both beneficial or malicious purposes) of biological design tools (BDTs) (5). BDT's are increasingly able to assist in protein engineering and design (6)(7)(8)(9). Consequently, whether inadvertently or with malicious intent, BDT's may create dangerous biomolecules.…”