Artificial Intelligence-Powered Molecular Docking and Steered Molecular Dynamics for Accurate scFv Selection of Anti-CD30 Chimeric Antigen Receptors
, Michela Capurro 1, Gizem Mansour 2, Ramina Vossoughi Jahromi 1, Arianna Stella 1, Roberta Rossi 1, Emanuele Longetti 1, Barbara Bigerna 1, Marco Gentili 1, Ariele Rosseto 1, Riccardo Rossi 1, Chiara Cencini 3, Carla Emiliani 3, Sabata Martino 3, Marten Beeg 2, Marco Gobbi 2, Enrico Tiacci 1,†, Brunangelo Falini 1,†, Francesco Morena 3,*,†and Vincenzo Maria Perriello 1,*,†
Round 1
Reviewer 1 Report
Comments and Suggestions for AuthorsDear Authors,
it is an interesting approach for immunotherapy.
ijms-3079466
Artificial Intelligence-powered molecular docking and steered molecular dynamics for accurate scFv selection of anti-CD30 Chimeric Antigen Receptors by artarelli demonstrates the importance of Chimeric Antigen Receptor (CAR) T immunotherapy. The authors aimed to predict the finest scFv binding before CAR-T cell engineering, they performed artificial intelligence (AI)-guided molecular docking and steered molecular dynamics analysis of different anti-CD30 mAb clones. Virtual computational scFv screening showed comparable results to surface plasmon resonance (SPR) and functional CAR-T cell in vitro and in vivo assays, respectively in terms of binding capacity and anti-tumor efficacy. The authors demonstrate the fast and low expensive in silico analysis has the potential to advance development of novel CAR constructs, with a substantial impact on reducing time, costs and the need for laboratory animal use. This manuscript is very interesting will be useful in translational research.
Positive comments:
1. Novel screening and validation of anti-CD30 mAbs.
2. Application of AI-Guided 3D Structure Prediction of Anti-CD30 mAbs/CD30 Antigen Binding Interaction.
3. Predicted the 3D structures of antibody clones and antigen, and predicted paratope and 127 epitope is interesting.
4. Modeling CD30 Antibody-Antigen Complexes by AI-Information-Driven Docking is innovative.
5. Docking model interaction between CD30 and the three different antibody clones is interesting.
6. Application of molecular dynamic is a positive approach.
7.
Minor comments:
1. Please keep the iThenticate less than 15%
2. Minor proof reading needed.
Comments on the Quality of English Language
Minor Edit required
Author Response
Dear Ms. Nantanawut,
Thank you very much for your evaluation of our manuscript entitled “Artificial Intelligence-powered molecular docking and steered molecular dynamics for accurate scFv selection of anti-CD30 Chimeric Antigen Receptors”. We read the reviewers’ comments very carefully and would like to thank them for providing thoughtful and constructive feedbacks.
Below, we provide additional point-by-point response to the reviewer 1 comments.
Reviewer 1
Dear Authors,
it is an interesting approach for immunotherapy.
Artificial Intelligence-powered molecular docking and steered molecular dynamics for accurate scFv selection of anti-CD30 Chimeric Antigen Receptors by artarelli demonstrates the importance of Chimeric Antigen Receptor (CAR) T immunotherapy. The authors aimed to predict the finest scFv binding before CAR-T cell engineering, they performed artificial intelligence (AI)-guided molecular docking and steered molecular dynamics analysis of different anti-CD30 mAb clones. Virtual computational scFv screening showed comparable results to surface plasmon resonance (SPR) and functional CAR-T cell in vitro and in vivo assays, respectively in terms of binding capacity and anti-tumor efficacy. The authors demonstrate the fast and low expensive in silico analysis has the potential to advance development of novel CAR constructs, with a substantial impact on reducing time, costs and the need for laboratory animal use. This manuscript is very interesting will be useful in translational research.
Positive comments:
- Novel screening and validation of anti-CD30 mAbs.
- Application of AI-Guided 3D Structure Prediction of Anti-CD30 mAbs/CD30 Antigen Binding Interaction.
- Predicted the 3D structures of antibody clones and antigen, and predicted paratope and 127 epitope is interesting.
- Modeling CD30 Antibody-Antigen Complexes by AI-Information-Driven Docking is innovative.
- Docking model interaction between CD30 and the three different antibody clones is interesting.
- Application of molecular dynamic is a positive approach.
Minor comments:
- Please keep the iThenticate less than 15%
- Minor proof reading needed.
RE: We thank the reviewer for highlighting all the positive comments of our study. The revised manuscript version has been checked for plagiarism by the Plagiarism Checker X server, reporting an overall similarity of 9% (see report attached).
Author Response File: 
Author Response.pdf
Reviewer 2 Report
Comments and Suggestions for AuthorsImpressive work and very updated by using AI. Very technical (in some paragraph too technical for an average reader).
Good idea and accesible tools (free), but as I said, when authors mentione what algorythm are using, or special lab technique was used, please mentioned in 1 or 2 sentence, why and what is the importance of the item. For example,
'From the SMD trajectories, snapshots were taken to generate the starting configura-513 tions for the umbrella sampling'- what is the purpose?
'Coarse Grained (CG) Sterred Molecular Dynamics (SMD)'- what are the importance of these two in designing and clinical use of the proposed molecule?
Author Response
Impressive work and very updated by using AI. Very technical (in some paragraph too technical for an average reader).
Good idea and accesible tools (free), but as I said, when authors mentione what algorythm are using, or special lab technique was used, please mentioned in 1 or 2 sentence, why and what is the importance of the item. For example, 'From the SMD trajectories, snapshots were taken to generate the starting configura-513 tions for the umbrella sampling'- what is the purpose?
'Coarse Grained (CG) Sterred Molecular Dynamics (SMD)'- what are the importance of these two in designing and clinical use of the proposed molecule?
RE: We thank the reviewer for this concise summary of our work and pointing out this issue. We better explained in brief the tools/techniques exploited in this study:
- AlphaFold2 in predicting the 3D structure (lines 123-124, 438-440 in red)
- ProABC-2 and DiscoTope-3.0 for the identification of antigen/antibody binding regions (lines 139-149, in red)
- Umbrella sampling and Coarse Grained (CG) Sterred Molecular Dynamics (SMD)' (lines 226-229, 492-495 and 526-529 in red).
