Graph neural networks and molecular docking as two complementary approaches for virtual screening: a case study on Cruzain

Autores
Luchi, Adriano Martín; Gómez Chávez, José Leonardo; Villafañe, Roxana Noelia; Conti, German Andrés; Perez, Ernesto Rafael; Angelina, Emilio Luis; Peruchena, Nelida Maria
Año de publicación
2022
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
The idea behind virtual screening is to first test compounds computationally in order to reduce the number of compounds that need to be screened experimentally, thus reducing the time and cost of physical experiments. Molecular docking is the most popular virtual screening technique, it predicts the binding of candidate compounds to the protein target by modeling the interactions at the binding pocket. Despite being widely used, docking accuracy is often low due to the difficulty of modeling inherently complex biological systems. On the other hand, state of the art deep neural networks, like Graph Convolutional Networks (GCNs) are able to capture the complex non-linear relationships between structural and biological data, but they lack the interpretability of structure-based modeling. In this work we took advantage of the activity data from a quantitative High Throughput Screen (HTS) of ~200K compounds against Cruzain (Cz) to retrospectively evaluate the ability of a docking algorithm and a Graph Convolutional Network for prioritizing the active compounds from the dataset. We then propose strategies to combine both techniques in a single virtual screening pipeline in order to exploit their orthogonal benefits. By plugging in the atomic embeddings learned by the GCN into the docking algorithm by means of pharmacophoric restraints, docking ability to retrieve the active ligands was enhanced. Moreover, by applying the GCN as a pre-docking filter, the compound’s library was enriched in active molecules and subsequent docking of the filtered library achieved significantly higher hit rates. This work aims to be a proof of concept of the usefulness of combination strategies involving deep learning and classical molecular docking techniques, in the context of drug discovery.
Fil: Luchi, Adriano Martín. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Nordeste. Instituto de Química Básica y Aplicada del Nordeste Argentino. Universidad Nacional del Nordeste. Facultad de Ciencias Exactas Naturales y Agrimensura. Instituto de Química Básica y Aplicada del Nordeste Argentino; Argentina
Fil: Gómez Chávez, José Leonardo. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Nordeste. Instituto de Química Básica y Aplicada del Nordeste Argentino. Universidad Nacional del Nordeste. Facultad de Ciencias Exactas Naturales y Agrimensura. Instituto de Química Básica y Aplicada del Nordeste Argentino; Argentina
Fil: Villafañe, Roxana Noelia. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Nordeste. Instituto de Química Básica y Aplicada del Nordeste Argentino. Universidad Nacional del Nordeste. Facultad de Ciencias Exactas Naturales y Agrimensura. Instituto de Química Básica y Aplicada del Nordeste Argentino; Argentina
Fil: Conti, German Andrés. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Nordeste. Instituto de Química Básica y Aplicada del Nordeste Argentino. Universidad Nacional del Nordeste. Facultad de Ciencias Exactas Naturales y Agrimensura. Instituto de Química Básica y Aplicada del Nordeste Argentino; Argentina
Fil: Perez, Ernesto Rafael. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Nordeste. Instituto de Química Básica y Aplicada del Nordeste Argentino. Universidad Nacional del Nordeste. Facultad de Ciencias Exactas Naturales y Agrimensura. Instituto de Química Básica y Aplicada del Nordeste Argentino; Argentina
Fil: Angelina, Emilio Luis. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Nordeste. Instituto de Química Básica y Aplicada del Nordeste Argentino. Universidad Nacional del Nordeste. Facultad de Ciencias Exactas Naturales y Agrimensura. Instituto de Química Básica y Aplicada del Nordeste Argentino; Argentina
Fil: Peruchena, Nelida Maria. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Nordeste. Instituto de Química Básica y Aplicada del Nordeste Argentino. Universidad Nacional del Nordeste. Facultad de Ciencias Exactas Naturales y Agrimensura. Instituto de Química Básica y Aplicada del Nordeste Argentino; Argentina
Materia
GRAPH NEURAL NETWORK
DOCKING
CHAGAS DISEASE-CRUZAIN
STRUCTURE /LIGAND BASED VIRTUAL SCREANING
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/257076
Acceder
id CONICETDig_3013184bc27847b82c67f860f04ea612
oai_identifier_str oai:ri.conicet.gov.ar:11336/257076
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Graph neural networks and molecular docking as two complementary approaches for virtual screening: a case study on CruzainLuchi, Adriano MartínGómez Chávez, José LeonardoVillafañe, Roxana NoeliaConti, German AndrésPerez, Ernesto RafaelAngelina, Emilio LuisPeruchena, Nelida MariaGRAPH NEURAL NETWORKDOCKINGCHAGAS DISEASE-CRUZAINSTRUCTURE /LIGAND BASED VIRTUAL SCREANINGhttps://purl.org/becyt/ford/1.6https://purl.org/becyt/ford/1The idea behind virtual screening is to first test compounds computationally in order to reduce the number of compounds that need to be screened experimentally, thus reducing the time and cost of physical experiments. Molecular docking is the most popular virtual screening technique, it predicts the binding of candidate compounds to the protein target by modeling the interactions at the binding pocket. Despite being widely used, docking accuracy is often low due to the difficulty of modeling inherently complex biological systems. On the other hand, state of the art deep neural networks, like Graph Convolutional Networks (GCNs) are able to capture the complex non-linear relationships between structural and biological data, but they lack the interpretability of structure-based modeling. In this work we took advantage of the activity data from a quantitative High Throughput Screen (HTS) of ~200K compounds against Cruzain (Cz) to retrospectively evaluate the ability of a docking algorithm and a Graph Convolutional Network for prioritizing the active compounds from the dataset. We then propose strategies to combine both techniques in a single virtual screening pipeline in order to exploit their orthogonal benefits. By plugging in the atomic embeddings learned by the GCN into the docking algorithm by means of pharmacophoric restraints, docking ability to retrieve the active ligands was enhanced. Moreover, by applying the GCN as a pre-docking filter, the compound’s library was enriched in active molecules and subsequent docking of the filtered library achieved significantly higher hit rates. This work aims to be a proof of concept of the usefulness of combination strategies involving deep learning and classical molecular docking techniques, in the context of drug discovery.Fil: Luchi, Adriano Martín. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Nordeste. Instituto de Química Básica y Aplicada del Nordeste Argentino. Universidad Nacional del Nordeste. Facultad de Ciencias Exactas Naturales y Agrimensura. Instituto de Química Básica y Aplicada del Nordeste Argentino; ArgentinaFil: Gómez Chávez, José Leonardo. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Nordeste. Instituto de Química Básica y Aplicada del Nordeste Argentino. Universidad Nacional del Nordeste. Facultad de Ciencias Exactas Naturales y Agrimensura. Instituto de Química Básica y Aplicada del Nordeste Argentino; ArgentinaFil: Villafañe, Roxana Noelia. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Nordeste. Instituto de Química Básica y Aplicada del Nordeste Argentino. Universidad Nacional del Nordeste. Facultad de Ciencias Exactas Naturales y Agrimensura. Instituto de Química Básica y Aplicada del Nordeste Argentino; ArgentinaFil: Conti, German Andrés. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Nordeste. Instituto de Química Básica y Aplicada del Nordeste Argentino. Universidad Nacional del Nordeste. Facultad de Ciencias Exactas Naturales y Agrimensura. Instituto de Química Básica y Aplicada del Nordeste Argentino; ArgentinaFil: Perez, Ernesto Rafael. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Nordeste. Instituto de Química Básica y Aplicada del Nordeste Argentino. Universidad Nacional del Nordeste. Facultad de Ciencias Exactas Naturales y Agrimensura. Instituto de Química Básica y Aplicada del Nordeste Argentino; ArgentinaFil: Angelina, Emilio Luis. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Nordeste. Instituto de Química Básica y Aplicada del Nordeste Argentino. Universidad Nacional del Nordeste. Facultad de Ciencias Exactas Naturales y Agrimensura. Instituto de Química Básica y Aplicada del Nordeste Argentino; ArgentinaFil: Peruchena, Nelida Maria. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Nordeste. Instituto de Química Básica y Aplicada del Nordeste Argentino. Universidad Nacional del Nordeste. Facultad de Ciencias Exactas Naturales y Agrimensura. Instituto de Química Básica y Aplicada del Nordeste Argentino; ArgentinaCHEMRxiv2022-12info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/257076Luchi, Adriano Martín; Gómez Chávez, José Leonardo; Villafañe, Roxana Noelia; Conti, German Andrés; Perez, Ernesto Rafael; et al.; Graph neural networks and molecular docking as two complementary approaches for virtual screening: a case study on Cruzain; CHEMRxiv; ChemRxiv; 12-2022; 1-392573-2293CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/https://chemrxiv.org/engage/chemrxiv/article-details/63a216b2dadddcb60195aecfinfo:eu-repo/semantics/altIdentifier/doi/10.26434/chemrxiv-2022-btz77info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-sa/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-10-15T15:10:51Zoai:ri.conicet.gov.ar:11336/257076instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982025-10-15 15:10:51.325CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Graph neural networks and molecular docking as two complementary approaches for virtual screening: a case study on Cruzain
title Graph neural networks and molecular docking as two complementary approaches for virtual screening: a case study on Cruzain
spellingShingle Graph neural networks and molecular docking as two complementary approaches for virtual screening: a case study on Cruzain
Luchi, Adriano Martín
GRAPH NEURAL NETWORK
DOCKING
CHAGAS DISEASE-CRUZAIN
STRUCTURE /LIGAND BASED VIRTUAL SCREANING
title_short Graph neural networks and molecular docking as two complementary approaches for virtual screening: a case study on Cruzain
title_full Graph neural networks and molecular docking as two complementary approaches for virtual screening: a case study on Cruzain
title_fullStr Graph neural networks and molecular docking as two complementary approaches for virtual screening: a case study on Cruzain
title_full_unstemmed Graph neural networks and molecular docking as two complementary approaches for virtual screening: a case study on Cruzain
title_sort Graph neural networks and molecular docking as two complementary approaches for virtual screening: a case study on Cruzain
dc.creator.none.fl_str_mv Luchi, Adriano Martín
Gómez Chávez, José Leonardo
Villafañe, Roxana Noelia
Conti, German Andrés
Perez, Ernesto Rafael
Angelina, Emilio Luis
Peruchena, Nelida Maria
author Luchi, Adriano Martín
author_facet Luchi, Adriano Martín
Gómez Chávez, José Leonardo
Villafañe, Roxana Noelia
Conti, German Andrés
Perez, Ernesto Rafael
Angelina, Emilio Luis
Peruchena, Nelida Maria
author_role author
author2 Gómez Chávez, José Leonardo
Villafañe, Roxana Noelia
Conti, German Andrés
Perez, Ernesto Rafael
Angelina, Emilio Luis
Peruchena, Nelida Maria
author2_role author
author
author
author
author
author
dc.subject.none.fl_str_mv GRAPH NEURAL NETWORK
DOCKING
CHAGAS DISEASE-CRUZAIN
STRUCTURE /LIGAND BASED VIRTUAL SCREANING
topic GRAPH NEURAL NETWORK
DOCKING
CHAGAS DISEASE-CRUZAIN
STRUCTURE /LIGAND BASED VIRTUAL SCREANING
purl_subject.fl_str_mv https://purl.org/becyt/ford/1.6
https://purl.org/becyt/ford/1
dc.description.none.fl_txt_mv The idea behind virtual screening is to first test compounds computationally in order to reduce the number of compounds that need to be screened experimentally, thus reducing the time and cost of physical experiments. Molecular docking is the most popular virtual screening technique, it predicts the binding of candidate compounds to the protein target by modeling the interactions at the binding pocket. Despite being widely used, docking accuracy is often low due to the difficulty of modeling inherently complex biological systems. On the other hand, state of the art deep neural networks, like Graph Convolutional Networks (GCNs) are able to capture the complex non-linear relationships between structural and biological data, but they lack the interpretability of structure-based modeling. In this work we took advantage of the activity data from a quantitative High Throughput Screen (HTS) of ~200K compounds against Cruzain (Cz) to retrospectively evaluate the ability of a docking algorithm and a Graph Convolutional Network for prioritizing the active compounds from the dataset. We then propose strategies to combine both techniques in a single virtual screening pipeline in order to exploit their orthogonal benefits. By plugging in the atomic embeddings learned by the GCN into the docking algorithm by means of pharmacophoric restraints, docking ability to retrieve the active ligands was enhanced. Moreover, by applying the GCN as a pre-docking filter, the compound’s library was enriched in active molecules and subsequent docking of the filtered library achieved significantly higher hit rates. This work aims to be a proof of concept of the usefulness of combination strategies involving deep learning and classical molecular docking techniques, in the context of drug discovery.
Fil: Luchi, Adriano Martín. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Nordeste. Instituto de Química Básica y Aplicada del Nordeste Argentino. Universidad Nacional del Nordeste. Facultad de Ciencias Exactas Naturales y Agrimensura. Instituto de Química Básica y Aplicada del Nordeste Argentino; Argentina
Fil: Gómez Chávez, José Leonardo. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Nordeste. Instituto de Química Básica y Aplicada del Nordeste Argentino. Universidad Nacional del Nordeste. Facultad de Ciencias Exactas Naturales y Agrimensura. Instituto de Química Básica y Aplicada del Nordeste Argentino; Argentina
Fil: Villafañe, Roxana Noelia. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Nordeste. Instituto de Química Básica y Aplicada del Nordeste Argentino. Universidad Nacional del Nordeste. Facultad de Ciencias Exactas Naturales y Agrimensura. Instituto de Química Básica y Aplicada del Nordeste Argentino; Argentina
Fil: Conti, German Andrés. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Nordeste. Instituto de Química Básica y Aplicada del Nordeste Argentino. Universidad Nacional del Nordeste. Facultad de Ciencias Exactas Naturales y Agrimensura. Instituto de Química Básica y Aplicada del Nordeste Argentino; Argentina
Fil: Perez, Ernesto Rafael. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Nordeste. Instituto de Química Básica y Aplicada del Nordeste Argentino. Universidad Nacional del Nordeste. Facultad de Ciencias Exactas Naturales y Agrimensura. Instituto de Química Básica y Aplicada del Nordeste Argentino; Argentina
Fil: Angelina, Emilio Luis. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Nordeste. Instituto de Química Básica y Aplicada del Nordeste Argentino. Universidad Nacional del Nordeste. Facultad de Ciencias Exactas Naturales y Agrimensura. Instituto de Química Básica y Aplicada del Nordeste Argentino; Argentina
Fil: Peruchena, Nelida Maria. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Nordeste. Instituto de Química Básica y Aplicada del Nordeste Argentino. Universidad Nacional del Nordeste. Facultad de Ciencias Exactas Naturales y Agrimensura. Instituto de Química Básica y Aplicada del Nordeste Argentino; Argentina
description The idea behind virtual screening is to first test compounds computationally in order to reduce the number of compounds that need to be screened experimentally, thus reducing the time and cost of physical experiments. Molecular docking is the most popular virtual screening technique, it predicts the binding of candidate compounds to the protein target by modeling the interactions at the binding pocket. Despite being widely used, docking accuracy is often low due to the difficulty of modeling inherently complex biological systems. On the other hand, state of the art deep neural networks, like Graph Convolutional Networks (GCNs) are able to capture the complex non-linear relationships between structural and biological data, but they lack the interpretability of structure-based modeling. In this work we took advantage of the activity data from a quantitative High Throughput Screen (HTS) of ~200K compounds against Cruzain (Cz) to retrospectively evaluate the ability of a docking algorithm and a Graph Convolutional Network for prioritizing the active compounds from the dataset. We then propose strategies to combine both techniques in a single virtual screening pipeline in order to exploit their orthogonal benefits. By plugging in the atomic embeddings learned by the GCN into the docking algorithm by means of pharmacophoric restraints, docking ability to retrieve the active ligands was enhanced. Moreover, by applying the GCN as a pre-docking filter, the compound’s library was enriched in active molecules and subsequent docking of the filtered library achieved significantly higher hit rates. This work aims to be a proof of concept of the usefulness of combination strategies involving deep learning and classical molecular docking techniques, in the context of drug discovery.
publishDate 2022
dc.date.none.fl_str_mv 2022-12
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/257076
Luchi, Adriano Martín; Gómez Chávez, José Leonardo; Villafañe, Roxana Noelia; Conti, German Andrés; Perez, Ernesto Rafael; et al.; Graph neural networks and molecular docking as two complementary approaches for virtual screening: a case study on Cruzain; CHEMRxiv; ChemRxiv; 12-2022; 1-39
2573-2293
CONICET Digital
CONICET
url http://hdl.handle.net/11336/257076
identifier_str_mv Luchi, Adriano Martín; Gómez Chávez, José Leonardo; Villafañe, Roxana Noelia; Conti, German Andrés; Perez, Ernesto Rafael; et al.; Graph neural networks and molecular docking as two complementary approaches for virtual screening: a case study on Cruzain; CHEMRxiv; ChemRxiv; 12-2022; 1-39
2573-2293
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/https://chemrxiv.org/engage/chemrxiv/article-details/63a216b2dadddcb60195aecf
info:eu-repo/semantics/altIdentifier/doi/10.26434/chemrxiv-2022-btz77
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv CHEMRxiv
publisher.none.fl_str_mv CHEMRxiv
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1846083256827510784
score 13.22299

Publicaciones similares