Artificial intelligence for small-molecule chemical probe design: why drug-centric models may not transfer cleanly

Autores
Carlucci, Renzo; Porta, Exequiel Oscar Jesús
Año de publicación
2026
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
Artificial intelligence (AI) is increasingly used to design and optimize small molecules. However, most current workflows remain centered on drug-candidate objectives, such as potency, ADMET, and drug-likeness, rather than on the distinct requirements of small-molecule chemical probes. We argue that this distinction matters for drug discovery because chemical probes are essential for target validation and mechanistic interrogation. Their value, however, depends on stringent selectivity, demonstrable target engagement in relevant biological contexts, fit-for-purpose concentration windows, and appropriate control compounds that support causal interpretation. These requirements make probe discovery a fundamentally different optimization problem from conventional drug design. Here, we examine how contemporary AI methods (including property prediction, multi-target modeling, generative optimization, and synthesis-aware design) can contribute to chemical probe discovery while highlighting why drug-centric models may not transfer cleanly. We further discuss emerging applications in fluorescent and covalent probe design, where photophysical behavior, signal detectability under biologically relevant conditions, intrinsic reactivity, and site selectivity introduce modality-specific constraints that are poorly captured by conventional datasets and benchmarks. We propose that meaningful progress will require probe-native datasets, probe-centric evaluation frameworks, and closed-loop experimental validation strategies that treat probe success as a function of the molecule, evidence, and context of use.
Fil: Carlucci, Renzo. Universidad Nacional de La Plata. Facultad de Ciencas Exactas. Laboratorio de Investigación y Desarrollo de Bioactivos; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - La Plata; Argentina
Fil: Porta, Exequiel Oscar Jesús. University College London; Estados Unidos. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
Materia
ARTIFICIAL INTELLIGENCE
CHEMICAL PROBE DESIGN
COVALENT PROBES
FLUORESCENT PROBES
GENERATIVE MOLECULAR DESIGN
MACHINE LEARNING
TARGET VALIDATION
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:11336/289979
Acceder
id CONICETDig_6650c6fbe6e156ab357a7f7fedc91003
oai_identifier_str oai:ri.conicet.gov.ar:11336/289979
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Artificial intelligence for small-molecule chemical probe design: why drug-centric models may not transfer cleanlyCarlucci, RenzoPorta, Exequiel Oscar JesúsARTIFICIAL INTELLIGENCECHEMICAL PROBE DESIGNCOVALENT PROBESFLUORESCENT PROBESGENERATIVE MOLECULAR DESIGNMACHINE LEARNINGTARGET VALIDATIONhttps://purl.org/becyt/ford/1.4https://purl.org/becyt/ford/1Artificial intelligence (AI) is increasingly used to design and optimize small molecules. However, most current workflows remain centered on drug-candidate objectives, such as potency, ADMET, and drug-likeness, rather than on the distinct requirements of small-molecule chemical probes. We argue that this distinction matters for drug discovery because chemical probes are essential for target validation and mechanistic interrogation. Their value, however, depends on stringent selectivity, demonstrable target engagement in relevant biological contexts, fit-for-purpose concentration windows, and appropriate control compounds that support causal interpretation. These requirements make probe discovery a fundamentally different optimization problem from conventional drug design. Here, we examine how contemporary AI methods (including property prediction, multi-target modeling, generative optimization, and synthesis-aware design) can contribute to chemical probe discovery while highlighting why drug-centric models may not transfer cleanly. We further discuss emerging applications in fluorescent and covalent probe design, where photophysical behavior, signal detectability under biologically relevant conditions, intrinsic reactivity, and site selectivity introduce modality-specific constraints that are poorly captured by conventional datasets and benchmarks. We propose that meaningful progress will require probe-native datasets, probe-centric evaluation frameworks, and closed-loop experimental validation strategies that treat probe success as a function of the molecule, evidence, and context of use.Fil: Carlucci, Renzo. Universidad Nacional de La Plata. Facultad de Ciencas Exactas. Laboratorio de Investigación y Desarrollo de Bioactivos; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - La Plata; ArgentinaFil: Porta, Exequiel Oscar Jesús. University College London; Estados Unidos. Consejo Nacional de Investigaciones Científicas y Técnicas; ArgentinaFrontiers Media2026-05info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/289979Carlucci, Renzo; Porta, Exequiel Oscar Jesús; Artificial intelligence for small-molecule chemical probe design: why drug-centric models may not transfer cleanly; Frontiers Media; Frontiers in Drug Discovery; 6; 5-2026; 1-102674-0338CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/https://www.frontiersin.org/articles/10.3389/fddsv.2026.1836983/fullinfo:eu-repo/semantics/altIdentifier/doi/10.3389/fddsv.2026.1836983info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-sa/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2026-08-25T15:04:10Zoai:ri.conicet.gov.ar:11336/289979instacron: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:34982026-08-25 15:04:10.848CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Artificial intelligence for small-molecule chemical probe design: why drug-centric models may not transfer cleanly
title Artificial intelligence for small-molecule chemical probe design: why drug-centric models may not transfer cleanly
spellingShingle Artificial intelligence for small-molecule chemical probe design: why drug-centric models may not transfer cleanly
Carlucci, Renzo
ARTIFICIAL INTELLIGENCE
CHEMICAL PROBE DESIGN
COVALENT PROBES
FLUORESCENT PROBES
GENERATIVE MOLECULAR DESIGN
MACHINE LEARNING
TARGET VALIDATION
title_short Artificial intelligence for small-molecule chemical probe design: why drug-centric models may not transfer cleanly
title_full Artificial intelligence for small-molecule chemical probe design: why drug-centric models may not transfer cleanly
title_fullStr Artificial intelligence for small-molecule chemical probe design: why drug-centric models may not transfer cleanly
title_full_unstemmed Artificial intelligence for small-molecule chemical probe design: why drug-centric models may not transfer cleanly
title_sort Artificial intelligence for small-molecule chemical probe design: why drug-centric models may not transfer cleanly
dc.creator.none.fl_str_mv Carlucci, Renzo
Porta, Exequiel Oscar Jesús
author Carlucci, Renzo
author_facet Carlucci, Renzo
Porta, Exequiel Oscar Jesús
author_role author
author2 Porta, Exequiel Oscar Jesús
author2_role author
dc.subject.none.fl_str_mv ARTIFICIAL INTELLIGENCE
CHEMICAL PROBE DESIGN
COVALENT PROBES
FLUORESCENT PROBES
GENERATIVE MOLECULAR DESIGN
MACHINE LEARNING
TARGET VALIDATION
topic ARTIFICIAL INTELLIGENCE
CHEMICAL PROBE DESIGN
COVALENT PROBES
FLUORESCENT PROBES
GENERATIVE MOLECULAR DESIGN
MACHINE LEARNING
TARGET VALIDATION
purl_subject.fl_str_mv https://purl.org/becyt/ford/1.4
https://purl.org/becyt/ford/1
dc.description.none.fl_txt_mv Artificial intelligence (AI) is increasingly used to design and optimize small molecules. However, most current workflows remain centered on drug-candidate objectives, such as potency, ADMET, and drug-likeness, rather than on the distinct requirements of small-molecule chemical probes. We argue that this distinction matters for drug discovery because chemical probes are essential for target validation and mechanistic interrogation. Their value, however, depends on stringent selectivity, demonstrable target engagement in relevant biological contexts, fit-for-purpose concentration windows, and appropriate control compounds that support causal interpretation. These requirements make probe discovery a fundamentally different optimization problem from conventional drug design. Here, we examine how contemporary AI methods (including property prediction, multi-target modeling, generative optimization, and synthesis-aware design) can contribute to chemical probe discovery while highlighting why drug-centric models may not transfer cleanly. We further discuss emerging applications in fluorescent and covalent probe design, where photophysical behavior, signal detectability under biologically relevant conditions, intrinsic reactivity, and site selectivity introduce modality-specific constraints that are poorly captured by conventional datasets and benchmarks. We propose that meaningful progress will require probe-native datasets, probe-centric evaluation frameworks, and closed-loop experimental validation strategies that treat probe success as a function of the molecule, evidence, and context of use.
Fil: Carlucci, Renzo. Universidad Nacional de La Plata. Facultad de Ciencas Exactas. Laboratorio de Investigación y Desarrollo de Bioactivos; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - La Plata; Argentina
Fil: Porta, Exequiel Oscar Jesús. University College London; Estados Unidos. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
description Artificial intelligence (AI) is increasingly used to design and optimize small molecules. However, most current workflows remain centered on drug-candidate objectives, such as potency, ADMET, and drug-likeness, rather than on the distinct requirements of small-molecule chemical probes. We argue that this distinction matters for drug discovery because chemical probes are essential for target validation and mechanistic interrogation. Their value, however, depends on stringent selectivity, demonstrable target engagement in relevant biological contexts, fit-for-purpose concentration windows, and appropriate control compounds that support causal interpretation. These requirements make probe discovery a fundamentally different optimization problem from conventional drug design. Here, we examine how contemporary AI methods (including property prediction, multi-target modeling, generative optimization, and synthesis-aware design) can contribute to chemical probe discovery while highlighting why drug-centric models may not transfer cleanly. We further discuss emerging applications in fluorescent and covalent probe design, where photophysical behavior, signal detectability under biologically relevant conditions, intrinsic reactivity, and site selectivity introduce modality-specific constraints that are poorly captured by conventional datasets and benchmarks. We propose that meaningful progress will require probe-native datasets, probe-centric evaluation frameworks, and closed-loop experimental validation strategies that treat probe success as a function of the molecule, evidence, and context of use.
publishDate 2026
dc.date.none.fl_str_mv 2026-05
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/11336/289979
Carlucci, Renzo; Porta, Exequiel Oscar Jesús; Artificial intelligence for small-molecule chemical probe design: why drug-centric models may not transfer cleanly; Frontiers Media; Frontiers in Drug Discovery; 6; 5-2026; 1-10
2674-0338
CONICET Digital
CONICET
url http://hdl.handle.net/11336/289979
identifier_str_mv Carlucci, Renzo; Porta, Exequiel Oscar Jesús; Artificial intelligence for small-molecule chemical probe design: why drug-centric models may not transfer cleanly; Frontiers Media; Frontiers in Drug Discovery; 6; 5-2026; 1-10
2674-0338
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://www.frontiersin.org/articles/10.3389/fddsv.2026.1836983/full
info:eu-repo/semantics/altIdentifier/doi/10.3389/fddsv.2026.1836983
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 Frontiers Media
publisher.none.fl_str_mv Frontiers Media
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_ 1874775097756090368
score 13.24418

Publicaciones similares