Discovery of AMPs from random peptides via deep learning-based model and biological activity validation.

The ample peptide field is the best source for discovering clinically available novel antimicrobial peptides (AMPs) to address emerging drug resistance. However, discovering novel AMPs is complex and expensive, representing a major challenge. Recent advances in artificial intelligence (AI) have significantly improved the efficiency of identifying antimicrobial peptides from large libraries, whereas using random peptides as negative data increases the difficulty of discovering antimicrobial peptides from random peptides using discriminative models. In this study, we constructed three multi-discriminator models using deep learning and successfully screened twelve AMPs from a library of 30,000 random peptides. three candidate peptides (P2, P11, and P12) were screened by antimicrobial experiments, and further experiments showed that they not only possessed excellent antimicrobial activity but also had extremely low hemolytic activity. Mechanistic studies showed that these peptides exerted their bactericidal effects through membrane disruption, thus reducing the possibility of bacterial resistance. Notably, peptide 12 (P12) showed significant efficacy in a mouse model of Staphylococcus aureus wound infection with low toxicity to major organs at the highest tested dose (400 mg/kg). These results suggest deep learning-based multi-discriminator models can identify AMPs from random peptides with potential clinical applications.

The Antimicrobial, Hemostatic, and Anti-Adhesion Effects of a Peptide Hydrogel Constructed by the All-d-Enantiomer of Antimicrobial Peptide Jelleine-1.

Peptide hydrogels are believed to be potential biomaterials with wide application in the biomedical field because of their good biocompatibility, injectability, and 3D printability. Most of the previously reported polypeptide hydrogels are composed of l-peptides, while the hydrogels formed by self-assembly of d-peptides are rarely reported. Herein, a peptide hydrogel constructed by D-J-1, which is the all-d-enantiomer of antimicrobial peptide Jelleine-1 (J-1) is reported. Field emission scanning electron microscope (FE-SEM) and rheologic study are performed to characterize the hydrogel. Antimicrobial, hemostatic, and anti-adhesion studies are carried out to evaluate its biofunction. The results show that D-J-1 hydrogel is formed by self-assembly and cross-linking driven by hydrogen bonding, hydrophobic interaction, and π-π stacking force of aromatic ring in the structure of D-J-1. It exhibits promising antimicrobial activity, hemostatic activity, and anti-adhesion efficiency in a rat sidewall defect-cecum abrasion model. In addition, it also exhibits good biocompatibility. Notably, D-J-1 hydrogel shows improved in vitro and in vivo stability when compared with its l-enantiomer J-1 hydrogel. Therefore, the present study will provide new insight into the application of d-peptide hydrogel, and provides a new peptide hydrogel with antibacterial, hemostatic, and anti-adhesion efficacy for clinical use.

A carrier-free, dual-functional hydrogel constructed of antimicrobial peptide Jelleine-1 and 8Br-cAMP for MRSA infected diabetic wound healing.

Bacterial infection and local growth factor deficiency are two of the major causes of the nonunion of diabetic wounds. Antimicrobial peptides (AMPs) are believed to be alternatives to antibiotics against drug-resistant bacterial infections. 8-Bromoadenosine-3', 5'-cyclic monophosphate (8Br-cAMP) can promote cells to secrete growth factors and accelerate cell proliferation. In the present study, we constructed a hydrogel with antimicrobial peptide Jelleine-1 (J-1) and 8Br-cAMP without any other gelators or chemical crosslinking agents. The hydrogel was proved to promote the secretion of transforming growth factor-ß (TGF-ß) and vascular endothelial growth factor-A (VEGFA) in vitro and in vivo. Notably, it exhibited potent potential for wound healing in methicillin-resistant Staphylococcus aureus (MRSA) infected diabetic wounds. This would be attributed to the retention of AMPs and 8Br-cAMP on the wound site by the hydrogel system. In addition, the hydrogel also showed good biodegradability, proper stability, and good biocompatibility. This study would shed light on the development of carrier-free and multifunctional hydrogel for wound healing. STATEMENT OF SIGNIFICANCE: Bacterial infection and local growth factor deficiency are two of the major causes for the nonunion of refractory wounds. In the present study, an injectable carrier-free hydrogel was constructed of a natural antimicrobial peptide J-1 and 8Br-cAMP by eco-friendly physical crosslinking without any other gelators or chemical crosslinking agents. The hydrogel exhibited excellent antimicrobial activity and was proved to promote the secretion of TGF-ß and VEGFA in vitro and in vivo. Correspondingly, the hydrogel showed exceptionally wound healing effects in the wound model of MRSA infected diabetic rats. This study would provide an alternative strategy or a potential hydrogel dressing for the treatment of chronic or refractory wounds.

An Injectable Peptide Hydrogel Constructed of Natural Antimicrobial Peptide J-1 and ADP Shows Anti-Infection, Hemostasis, and Antiadhesion Efficacy.

Postoperative adhesion is a common complication of abdominal surgery, which always has many adverse effects in patients. At present, there is still a lack of effective treatment measures and materials to prevent adhesion in the clinics. Herein, we report the potential use of J-1-ADP hydrogel formed by natural antimicrobial peptide jelleine-1 (J-1) self-assembling in adenosine diphosphate (ADP) sodium solution to prevent postsurgery adhesion formation. J-1-ADP hydrogel was found to have good antimicrobial activity against the bacteria and fungi tested and can be used to prevent tissue infection, which was thought to be one of the incitements of adhesion. Due to ADP being a platelet-activating factor, J-1-ADP hydrogel showed significant hemostatic activity in vitro verified by whole blood coagulation, plasma coagulation, platelet activation, and platelet adhesion assays. Further, it showed potent hemostatic activity in a mouse liver hemorrhage model. Bleeding was believed to be a cause of the formation of postsurgery adhesion. J-1-ADP hydrogel had a significant antiadhesion effect in a rat side wall defect-cecum abrasion model. In addition, it had good biocompatibility and degradation properties. So the present study may provide an alternative strategy for designing antimicrobial peptide hydrogel material to prevent postoperative adhesion formation in the clinic.

GM-Pep: A High Efficiency Strategy to De Novo Design Functional Peptide Sequences.

Although peptides are regarded as ideal therapeutic agents, only a small proportion of the marketed drugs are peptides. In the past decade, pharmacists have paid great attention to the development of peptide therapeutics. Except a few approved chemically/rationally designed peptides, most attempts failed due to unsatisfactory efficacy or safety. Luckily, computation methods, such as artificial intelligence, have been utilized to accelerate the discovery of therapeutic peptides by predicting the activity, toxicity, and absorption, distribution, metabolism, and excretion of polypeptides. Usually, a specific biological activity of a peptide could be accurately determined by an interest-oriented binary classification constructed of a positive set and another un-experimentally validated negative set regardless of other characteristics, which suggests that it could be challenging to realize the comprehensive evaluation of the research object in the early stage of drug research and development. Herein, we proposed an integrated method (GM-Pep) that contained a conditional variational autoencoder model (CVAE) and a positive sample training multiclassifier (Deep-Multiclassifier) to effectively generate a single bioactive peptide sequence without toxicity and referential side effects. The results showed that our Deep-Multiclassifier model gave a sequence accuracy of up to 96.41% [toxicity (94.48%), antifungal (96.58%), antihypertensive (97.18%), and antibacterial (96.91%), respectively]. The properties of Deep-Multiclassifier and CVAE were validated through 12 first synthesized antibacterial peptides or compared to random peptides. The source code and data sets are available at https://github.com/TimothyChen225/GM-Pep.