MuCoCP: a priori chemical knowledge-based multimodal contrastive learning pre-trained neural network for the prediction of cyclic peptide membrane penetration ability.

MOTIVATION: There has been a burgeoning interest in cyclic peptide therapeutics due to their various outstanding advantages and strong potential for drug formation. However, it is undoubtedly costly and inefficient to use traditional wet lab methods to clarify their biological activities. Using artificial intelligence instead is a more energy-efficient and faster approach. MuCoCP aims to build a complete pre-trained model for extracting potential features of cyclic peptides, which can be fine-tuned to accurately predict cyclic peptide bioactivity on various downstream tasks. To maximize its effectiveness, we use a novel data augmentation method based on a priori chemical knowledge and multiple unsupervised training objective functions to greatly improve the information-grabbing ability of the model. RESULTS: To assay the efficacy of the model, we conducted validation on the membrane-permeability of cyclic peptides which achieved an accuracy of 0.87 and R-squared of 0.503 on CycPeptMPDB using semi-supervised training and obtained an accuracy of 0.84 and R-squared of 0.384 using a model with frozen parameters on an external dataset. This result has achieved state-of-the-art, which substantiates the stability and generalization capability of MuCoCP. It means that MuCoCP can fully explore the high-dimensional information of cyclic peptides and make accurate predictions on downstream bioactivity tasks, which will serve as a guide for the future de novo design of cyclic peptide drugs and promote the development of cyclic peptide drugs. AVAILABILITY AND IMPLEMENTATION: All code used in our proposed method can be found at https://github.com/lennonyu11234/MuCoCP.

The introduction of L-phenylalanine into antimicrobial peptide protonectin enhances the selective antibacterial activity of its derivative phe-Prt against Gram-positive bacteria.

Protonectin was a typical amphiphilic antimicrobial peptide with potent antimicrobial activity against Gram-positive and Gram-negative bacteria. In the present study, when its eleventh amino acid in the sequence was substituted by phenylalanine, the analog named phe-Prt showed potent antimicrobial activity against Gram-positive bacteria, but no antimicrobial activity against Gram-negative bacteria, indicating a significant selectivity between Gram-positive bacteria and Gram-negative bacteria. However, when Gram-negative bacteria were incubated with EDTA, the bacteria were susceptible to phe-Prt. Next, the binding effect of phe-Prt with LPS was determined. Our result showed that LPS could hamper the bactericidal activity of phe-Prt against Gram-positive bacteria. The result of zeta potential assay further confirmed the binding effect of phe-Prt with LPS for it could neutralize the surface charge of E. coli and LPS. Then, the effect of phe-Prt on the integrity of outer membrane of Gram-negative bacteria was determined. Our results showed that phe-Prt had a much weaker disturbance to the outer membrane of Gram-negative bacteria than the parent peptide protonectin. In summary, the introduction of L-phenylalanine into the sequence of antimicrobial peptide protonectin made phe-Prt show significant selectivity against Gram-positive bacteria, which could partly be attributed to the delay effect of LPS for phe-Prt to access to cell membrane. Although further study is still needed to clarify the exact mechanism of selectivity, the present study provided a strategy to develop antimicrobial peptides with selectivity toward Gram-positive and Gram-negative bacteria.

The Regiocontrollable Enantioselective Synthesis of Chiral Trifluoromethyl-Containing Spiro-Pyrrolidine-Pyrazolone Compounds via Amino-Regulated 1,3-Proton Migration Reaction.

An amino-controlled regiodivergent asymmetric synthesis of CF3-containing spiro-pyrrolidine-pyrazolone compounds is described. With alkaloid-derived squaramide as catalyst, the 1,3-dipolar cycloaddition of α,ß-unsaturated pyrazolone with diethyl 2-((2,2,2-trifluoroethyl)imino) malonate offered adducts in excellent yields, dr, and ee. While the cyclohexanediamine-derived squaramide was employed, the reaction afforded a series of structure isomers through a switched umpolung reaction.

The catalytic asymmetric synthesis of CF3-containing spiro-oxindole-pyrrolidine-pyrazolone compounds through squaramide-catalyzed 1,3-dipolar cycloaddition.

Pharmaceutically important compounds were synthesized through the organocatalytic 1,3-dipolar cycloaddition reaction. In the presence of a cinchonine-derived squaramide catalyst, the cycloaddition of N-2,2,2-trifluoroethylisatin ketimines with α,ß-unsaturated pyrazolones gave a spiro-pyrrolidine-linked oxindole and pyrazolone compound bearing four consecutive stereocenters and two vicinal spiroquaternary chiral centers, in excellent yields and stereoselectivities.

The asymmetric construction of CF3-containing spiro-thiazolone-pyrrolidine compounds via [3 + 2] cycloaddition.

The first organocatalytic method for the asymmetric construction of CF3-containing spiro-thiazolone-pyrrolidine compounds has been developed. This is one of the very few methods to reach spiro-thiazolones, and afforded the products in excellent yields and stereoselectivities catalysed by only 1 mol% cinchona alkaloid-derived catalyst.

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.