Search

Traditional antiviral peptide (AVP) discovery is a time-consuming and expensive process. This study introduces AVP-GPT, a novel deep learning method utilizing transformer-based language models and multimodal architectures specifically designed for AVP design. AVP-GPT demonstrated exceptional efficiency, generating 10,000 unique peptides and identifying potential AVPs within two days on a GPU system. Pre-trained on a respiratory syncytial virus (RSV) dataset, AVP-GPT successfully adapted to influenza A virus (INFVA) and other respiratory viruses. Compared to state-of-the-art models like LSTM and SVM, AVP-GPT achieved significantly lower perplexity (2.09 vs. 16.13) and higher AUC (0.90 vs. 0.82), indicating superior peptide sequence prediction and AVP classification. AVP-GPT generated a diverse set of peptides with excellent novelty and identified candidates with remarkably higher antiviral success rates than conventional design methods. Notably, AVP-GPT generated novel peptides against RSV and INFVA with exceptional potency, including four peptides exhibiting EC50 values around 0.02 uM—the strongest anti-RSV activity reported to date. These findings highlight AVP-GPT's potential to revolutionize AVP discovery and development, accelerating the creation of novel antiviral drugs. Future studies could explore the application of AVP-GPT to other viral targets and investigate alternative AVP design strategies. [ABSTRACT FROM AUTHOR]

Development of potent and broad‐spectrum drugs against severe acute respiratory syndrome coronavirus 2 (SARS‐CoV‐2) remains one of the top priorities, especially in the cases of the emergence of mutant viruses and inability of current vaccines to prevent viral transmission. In this study, we have generated a novel membrane fusion‐inhibitory lipopeptide IPB29, which is currently under clinical trials; herein, we report its design strategy and preclinical data. First, we surprisingly found that IPB29 with a rigid linker between the peptide sequence and lipid molecule had greatly improved α‐helical structure and antiviral activity. Second, IPB29 potently inhibited a large panel of SARS‐CoV‐2 variants including the previously and currently circulating viruses, such as Omicron XBB.5.1 and EG.5.1. Third, IPB29 could also cross‐neutralize the bat‐ and pangolin‐isolated SARS‐CoV‐2‐related CoVs (RatG13, PCoV‐GD, and PCoV‐GX) and other human CoVs (SARS‐CoV, MERS‐CoV, HCoV‐NL63, and HCoV‐229E). Fourth, IPB29 administrated as an inhalation solution (IPB29‐IS) in Syrian hamsters exhibited high therapeutic and preventive efficacies against SARS‐CoV‐2 Delta or Omicron variant. Fifth, the pharmacokinetic profiles and safety pharmacology of IPB29‐IS were extensively characterized, providing data to support its evaluation in humans. In conclusion, our studies have demonstrated a novel design strategy for viral fusion inhibitors and offered an ideal drug candidate against SARS‐CoV‐2 and other coronaviruses. [ABSTRACT FROM AUTHOR]

Pulsatilla Adans (PSA) herbs (Ranunculaceae) have been widely used in traditional medicine in China and other countries. However, the authentication and quality control of PSA herbs have always been a challenging task due to their similar morphological characteristics and the diversity of the multiple components that exist in the complicated matrix. Herein, a novel integrated strategy combining UHPLC/Q-Orbitrap-MS techniques with chemometrics analysis is proposed for the discrimination of PSA materials. We developed a comprehensive method integrating a nontargeted bidirectionally screened (NTBDS) MS data set and a targeted extraction peak area analysis for the characterization of triterpenoid saponins of PSA from different species. After that, partial least-squares discriminant analysis (PLS-DA) was performed on the obtained MS data set and the parameter variable importance for the projection (VIP) value and P value were employed to screen the valuable MS features to discriminate PSA from different species. In addition, the receiver operating characteristic (ROC) curve is used to verify the reliability of MS features. Finally, heatmap visualization was employed to clarify the distribution of the identified triterpenoid saponins, and four medicinal species of PSA were successfully differentiated. Additionally, 34 constituents were reported in PSAs for the first time, 81 triterpenoid saponins were identified as differential components, and 12 chemical ingredients were characterized as potential chemical markers to differentiate the four officinal PSA herbs. This is the first time that the differences in different PSA herbs have been observed systematically at the chemical level. The results suggested that using the identified characteristic components as chemical markers to identify different PSA herbs was effective and viable. This method provides promising perspectives in the analysis and identification of the ingredients of Chinese herbal medicines, and the identification of similar herbs from the same species. [ABSTRACT FROM AUTHOR]