Cargando…
Structure-based virtual screening for PDL1 dimerizers: Evaluating generic scoring functions
The interaction between PD1 and its ligand PDL1 has been shown to render tumor cells resistant to apoptosis and promote tumor progression. An innovative mechanism to inhibit the PD1/PDL1 interaction is PDL1 dimerization induced by small-molecule PDL1 binders. Structure-based virtual screening is a p...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Elsevier
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9234010/ https://www.ncbi.nlm.nih.gov/pubmed/35769111 http://dx.doi.org/10.1016/j.crstbi.2022.06.002 |
_version_ | 1784735951663136768 |
---|---|
author | Tran-Nguyen, Viet-Khoa Simeon, Saw Junaid, Muhammad Ballester, Pedro J. |
author_facet | Tran-Nguyen, Viet-Khoa Simeon, Saw Junaid, Muhammad Ballester, Pedro J. |
author_sort | Tran-Nguyen, Viet-Khoa |
collection | PubMed |
description | The interaction between PD1 and its ligand PDL1 has been shown to render tumor cells resistant to apoptosis and promote tumor progression. An innovative mechanism to inhibit the PD1/PDL1 interaction is PDL1 dimerization induced by small-molecule PDL1 binders. Structure-based virtual screening is a promising approach to discovering such small-molecule PD1/PDL1 inhibitors. Here we investigate which type of generic scoring functions is most suitable to tackle this problem. We consider CNN-Score, an ensemble of convolutional neural networks, as the representative of machine-learning scoring functions. We also evaluate Smina, a commonly used classical scoring function, and IFP, a top structural fingerprint similarity scoring function. These three types of scoring functions were evaluated on two test sets sharing the same set of small-molecule PD1/PDL1 inhibitors, but using different types of inactives: either true inactives (molecules with no in vitro PD1/PDL1 inhibition activity) or assumed inactives (property-matched decoy molecules generated from each active). On both test sets, CNN-Score performed much better than Smina, which in turn strongly outperformed IFP. The fact that the latter was the case, despite precluding any possibility of exploiting decoy bias, demonstrates the predictive value of CNN-Score for PDL1. These results suggest that re-scoring Smina-docked molecules with CNN-Score is a promising structure-based virtual screening method to discover new small-molecule inhibitors of this therapeutic target. |
format | Online Article Text |
id | pubmed-9234010 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Elsevier |
record_format | MEDLINE/PubMed |
spelling | pubmed-92340102022-06-28 Structure-based virtual screening for PDL1 dimerizers: Evaluating generic scoring functions Tran-Nguyen, Viet-Khoa Simeon, Saw Junaid, Muhammad Ballester, Pedro J. Curr Res Struct Biol Graphical Review The interaction between PD1 and its ligand PDL1 has been shown to render tumor cells resistant to apoptosis and promote tumor progression. An innovative mechanism to inhibit the PD1/PDL1 interaction is PDL1 dimerization induced by small-molecule PDL1 binders. Structure-based virtual screening is a promising approach to discovering such small-molecule PD1/PDL1 inhibitors. Here we investigate which type of generic scoring functions is most suitable to tackle this problem. We consider CNN-Score, an ensemble of convolutional neural networks, as the representative of machine-learning scoring functions. We also evaluate Smina, a commonly used classical scoring function, and IFP, a top structural fingerprint similarity scoring function. These three types of scoring functions were evaluated on two test sets sharing the same set of small-molecule PD1/PDL1 inhibitors, but using different types of inactives: either true inactives (molecules with no in vitro PD1/PDL1 inhibition activity) or assumed inactives (property-matched decoy molecules generated from each active). On both test sets, CNN-Score performed much better than Smina, which in turn strongly outperformed IFP. The fact that the latter was the case, despite precluding any possibility of exploiting decoy bias, demonstrates the predictive value of CNN-Score for PDL1. These results suggest that re-scoring Smina-docked molecules with CNN-Score is a promising structure-based virtual screening method to discover new small-molecule inhibitors of this therapeutic target. Elsevier 2022-06-09 /pmc/articles/PMC9234010/ /pubmed/35769111 http://dx.doi.org/10.1016/j.crstbi.2022.06.002 Text en © 2022 The Authors https://creativecommons.org/licenses/by/4.0/This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Graphical Review Tran-Nguyen, Viet-Khoa Simeon, Saw Junaid, Muhammad Ballester, Pedro J. Structure-based virtual screening for PDL1 dimerizers: Evaluating generic scoring functions |
title | Structure-based virtual screening for PDL1 dimerizers: Evaluating generic scoring functions |
title_full | Structure-based virtual screening for PDL1 dimerizers: Evaluating generic scoring functions |
title_fullStr | Structure-based virtual screening for PDL1 dimerizers: Evaluating generic scoring functions |
title_full_unstemmed | Structure-based virtual screening for PDL1 dimerizers: Evaluating generic scoring functions |
title_short | Structure-based virtual screening for PDL1 dimerizers: Evaluating generic scoring functions |
title_sort | structure-based virtual screening for pdl1 dimerizers: evaluating generic scoring functions |
topic | Graphical Review |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9234010/ https://www.ncbi.nlm.nih.gov/pubmed/35769111 http://dx.doi.org/10.1016/j.crstbi.2022.06.002 |
work_keys_str_mv | AT trannguyenvietkhoa structurebasedvirtualscreeningforpdl1dimerizersevaluatinggenericscoringfunctions AT simeonsaw structurebasedvirtualscreeningforpdl1dimerizersevaluatinggenericscoringfunctions AT junaidmuhammad structurebasedvirtualscreeningforpdl1dimerizersevaluatinggenericscoringfunctions AT ballesterpedroj structurebasedvirtualscreeningforpdl1dimerizersevaluatinggenericscoringfunctions |