Related Experiment Video
Updated: Sep 22, 2025
A Fluorogenic Peptide Cleavage Assay to Screen for Proteolytic Activity: Applications for coronavirus spike protein activation
Published on: January 9, 2019
Potential drug discovery for COVID-19 treatment targeting Cathepsin L using a deep learning-based strategy
Wei-Li Yang1, Qi Li1, Jing Sun2
1Beijing Key Laboratory of Diabetes Research and Care, Beijing Diabetes Institute, Beijing Tongren Hospital, Capital Medical University, Beijing 100730, China.
Abstract:
Cathepsin L (CTSL), a cysteine protease that can cleave and activate the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) spike protein, could be a promising therapeutic target for coronavirus disease 2019 (COVID-19). However, there is still no clinically available CTSL inhibitor that can be used. Here, we applied Chemprop, a newly trained directed-message passing deep neural network approach, to identify small molecules and FDA-approved drugs that can block CTSL activity to expand the discovery of CTSL inhibitors for drug development and repurposing for COVID-19. We found 5 molecules (Mg-132, Z-FA-FMK, leupeptin hemisulfate, Mg-101 and calpeptin) that were able to significantly inhibit the activity of CTSL in the nanomolar range and inhibit the infection of both pseudotype and live SARS-CoV-2. Notably, we discovered that daptomycin, an FDA-approved antibiotic, has a prominent CTSL inhibitory effect and can inhibit SARS-CoV-2 pseudovirus infection. Further, molecular docking calculation showed stable and robust binding of these compounds with CTSL. In conclusion, this study suggested for the first time that Chemprop is ideally suited to predict additional inhibitors of enzymes and revealed the noteworthy strategy for screening novel molecules and drugs for the treatment of COVID-19 and other diseases with unmet needs.
Insights
Researchers used a deep learning model, Chemprop, to identify potential inhibitors for Cathepsin L (CTSL), an enzyme crucial in SARS-CoV-2 infection. This approach successfully identified existing drugs and novel molecules that could be repurposed for COVID-19 treatment.
Area of Science:
- Biochemistry
- Virology
- Computational Chemistry
Background:
- Cathepsin L (CTSL) is a cysteine protease that activates the SARS-CoV-2 spike protein, making it a potential therapeutic target for COVID-19.
- Currently, no clinically approved CTSL inhibitors are available, necessitating the search for new therapeutic strategies.
Purpose of the Study:
- To identify small molecules and FDA-approved drugs that inhibit CTSL activity using a deep neural network approach (Chemprop).
- To explore drug repurposing opportunities for COVID-19 treatment by identifying CTSL inhibitors.
Main Methods:
- Application of Chemprop, a directed message passing deep neural network, for identifying potential CTSL inhibitors.
- In vitro assays to evaluate the inhibitory activity of identified compounds against CTSL.
- SARS-CoV-2 pseudovirus and live virus infection assays to assess antiviral efficacy.
- Molecular docking to predict the binding interactions of identified inhibitors with CTSL.
Main Results:
- Five molecules (Mg-132, Z-FA-FMK, leupeptin hemisulfate, Mg-101, and calpeptin) demonstrated significant CTSL inhibition in the nanomolar range.
- These compounds effectively inhibited both pseudotype and live SARS-CoV-2 infection.
- Daptomycin, an FDA-approved antibiotic, was identified as a potent CTSL inhibitor with efficacy against SARS-CoV-2 pseudovirus infection.
- Molecular docking confirmed stable binding of the identified compounds with CTSL.
Conclusions:
- Chemprop is a suitable tool for predicting enzyme inhibitors, offering a novel strategy for drug discovery and repurposing.
- This study identified promising CTSL inhibitors, including daptomycin, for potential COVID-19 therapeutic development.
- The findings highlight a valuable approach for screening novel molecules and drugs for various diseases.
