GAPS: a geometric attention-based network for peptide binding site identification by the transfer learning approach.

Protein-peptide interactions (PPepIs) are vital to understanding cellular functions, which can facilitate the design of novel drugs. As an essential component in forming a PPepI, protein-peptide binding sites are the basis for understanding the mechanisms involved in PPepIs. Therefore, accurately identifying protein-peptide binding sites becomes a critical task. The traditional experimental methods for researching these binding sites are labor-intensive and time-consuming, and some computational tools have been invented to supplement it. However, these computational tools have limitations in generality or accuracy due to the need for ligand information, complex feature construction, or their reliance on modeling based on amino acid residues. To deal with the drawbacks of these computational algorithms, we describe a geometric attention-based network for peptide binding site identification (GAPS) in this work. The proposed model utilizes geometric feature engineering to construct atom representations and incorporates multiple attention mechanisms to update relevant biological features. In addition, the transfer learning strategy is implemented for leveraging the protein-protein binding sites information to enhance the protein-peptide binding sites recognition capability, taking into account the common structure and biological bias between proteins and peptides. Consequently, GAPS demonstrates the state-of-the-art performance and excellent robustness in this task. Moreover, our model exhibits exceptional performance across several extended experiments including predicting the apo protein-peptide, protein-cyclic peptide and the AlphaFold-predicted protein-peptide binding sites. These results confirm that the GAPS model is a powerful, versatile, stable method suitable for diverse binding site predictions.

APEX-pHLA: A novel method for accurate prediction of the binding between exogenous short peptides and HLA class I molecules.

Human leukocyte antigen (HLA) molecules play critically significant role within the realm of immunotherapy due to their capacities to recognize and bind exogenous antigens such as peptides, subsequently delivering them to immune cells. Predicting the binding between peptides and HLA molecules (pHLA) can expedite the screening of immunogenic peptides and facilitate vaccine design. However, traditional experimental methods are time-consuming and inefficient. In this study, an efficient method based on deep learning was developed for predicting peptide-HLA binding, which treated peptide sequences as linguistic entities. It combined the architectures of textCNN and BiLSTM to create a deep neural network model called APEX-pHLA. This model operated without limitations related to HLA class I allele variants and peptide segment lengths, enabling efficient encoding of sequence features for both HLA and peptide segments. On the independent test set, the model achieved Accuracy, ROC_AUC, F1, and MCC is 0.9449, 0.9850, 0.9453, and 0.8899, respectively. Similarly, on an external test set, the results were 0.9803, 0.9574, 0.8835, and 0.7863, respectively. These findings outperformed fifteen methods previously reported in the literature. The accurate prediction capability of the APEX-pHLA model in peptide-HLA binding might provide valuable insights for future HLA vaccine design.

A pharmacokinetics-pharmacodynamics study of single-dose total glucosides of paeony capsule on reducing serum total bile acid in hepatic injury rats.

CONTEXT: Total Glucosides of Paeony (TGP) capsule possesses various hepatoprotective activities. No study is available concerning TGP's concentration-effect relationship on hepatoprotection. OBJECTIVE: To establish a pharmacokinetics-pharmacodynamics (PK-PD) modelling on TGP capsule's hepatoprotection after a single oral administration in hepatic injury rats. MATERIALS AND METHODS: Male Sprague-Dawley rats were divided into five groups (n = 6): control, model (hepatic injury), treated-H (2.82 g/kg), treated-M (1.41 g/kg), and treated-L (0.705 g/kg) groups. All treated groups rats were intragastrically administered a single dose. An LC-MS/MS method was applied to determine paeoniflorin (Pae) and albiflorin (Alb) in rat serum. The effects of single-dose TGP on serum alanine transaminase (ALT), aspartate transaminase (AST) and total bile acid (TBA) were evaluated in hepatic injury rats. RESULTS: Single dose (2.82, 1.41, or 0.705 g/kg) TGP capsule could real-time down-regulate serum TBA but not ALT and AST in hepatic injury rats within 20 h. An inhibitory effect Sigmoid Emax of PK-PD modelling was established using Pae and Alb as PK markers and serum TBA as effect index. Pharmacodynamic parameters were calculated. For treated-H, treated-M and treated-L group, respectively, E0 were 158.1, 226.9 and 245.4 µmol/L for Pae, 146.1, 92.9 and 138.4 µmol/L for Alb, Emax were 53.0, 66.0, and 97.1 µmol/L for Pae, 117.4, 249.7 and 60.0 µmol/L for Alb, and EC50 were 9.3, 5.2 and 2.7 µg/mL for Pae, 2.3, 0.8, and 0.8 µg/mL for Alb. DISCUSSION AND CONCLUSIONS: Serum TBA is a sensitive effect index for TGP's single dose PK-PD modelling, and it is potential for further multi-dose studies of TGP' effect on hepatic injury. The study provides valuable information for TGP's mechanistic research and rational clinical application.

[Research advance in multi-component pharmacokinetics of Chinese herbal extracts in recent five years].

The multi-component pharmacokinetic study of Chinese herbal extracts elaborates the in vivo processes,including absorption,distribution,metabolism,and excretion,of multiple bioactive components,which is of significance in revealing pharmacodynamic material basis of Chinese herbal medicine. In recent years,with the innovation in ideas,and development of techniques and methods on traditional Chinese medicine( TCM) research,the pharmacokinetic studies of Chinese herbal extracts were extensively performed,and notable progress has been made. This paper reviewed the advancement of multi-component pharmacokinetics of Chinese herbal extracts in recent five years from analysis technology of biological sample,the pharmacokinetic characteristics of Chinese herbal medicine with complex system,and the impacts of processing and pathological state on pharmacokinetics of Chinese herbal extracts,aiming to provide a reference for quality control,product development and rational medication of Chinese herbal extracts.

[Quantitative determination and optimun extraction technique of nine compounds of Paeoniae Radix Alba].

OBJECTIVE: To establish the optimum extraction technique and high performance liquid chromatographic (HPLC) method to simultaneously quantify nine compounds of gallic acid, hydroxy-paeoniflorin, catechin, albiflorin, paeoniflorin, pentagalloylglucose, benzoic acid, benzoylpaeoniflorin and paeonol in Paeoniae Radix Alba. METHODS: Linear gradient elution was applied using water containing 0.1%phosphoric acid and acetonitrile as the mobile phase with a flow rate of 0.8 mL/min, column temperature of 30℃ and wavelength of 230 nm. The method of ultrasound extraction was used. Methanol and ethanol were used as extraction solvents, and three factors and three levels of orthogonal experiments was designed using L 9(3 4) table to investigate the effects of solvent concentration, ratio of liquid to material and extraction time on the total content of nine components of Paeoniae Radix Alba. RESULTS: HPLC method was verified to have high specificity, sensitivity and accuracy through methodological validation, and it could be used for simultaneous quantitative analysis of nine components of Paeoniae Radix Alba. The results showed that the optimum extraction technology of nine components of Paeoniae Radix Alba was using 70%ethanol as extraction solvent, ratio of liquid to material was 200 mL/g and ultrasound extraction time was 30 min. CONCLUSIONS: HPLC method for the simultaneous determination of nine components of Paeoniae Radix Alba is established, and the optimum extraction technology is confirmed.

Multi_CycGT: A Deep Learning-Based Multimodal Model for Predicting the Membrane Permeability of Cyclic Peptides.

Cyclic peptides are gaining attention for their strong binding affinity, low toxicity, and ability to target "undruggable" proteins; however, their therapeutic potential against intracellular targets is constrained by their limited membrane permeability, and researchers need much time and money to test this property in the laboratory. Herein, we propose an innovative multimodal model called Multi_CycGT, which combines a graph convolutional network (GCN) and a transformer to extract one- and two-dimensional features for predicting cyclic peptide permeability. The extensive benchmarking experiments show that our Multi_CycGT model can attain state-of-the-art performance, with an average accuracy of 0.8206 and an area under the curve of 0.8650, and demonstrates satisfactory generalization ability on several external data sets. To the best of our knowledge, it is the first deep learning-based attempt to predict the membrane permeability of cyclic peptides, which is beneficial in accelerating the design of cyclic peptide active drugs in medicinal chemistry and chemical biology applications.