Phytopathogen Effector Biology in the Burgeoning AI Era
Gespeichert in:
| Titel: | Phytopathogen Effector Biology in the Burgeoning AI Era |
|---|---|
| Autoren: | Bain, Darcy, Raffaele, Sylvain |
| Weitere Verfasser: | SEGUIN, Nathalie |
| Quelle: | Annual Review of Phytopathology. 63:63-88 |
| Verlagsinformationen: | Annual Reviews, 2025. |
| Publikationsjahr: | 2025 |
| Schlagwörter: | [SDV] Life Sciences [q-bio], machine learning, effector, DeepBlast, learnMSA, FoldMason Effector structure, evolution, bioinformatics, PLM embeddings, [SDV.BV.PEP] Life Sciences [q-bio]/Vegetal Biology/Phytopathology and phytopharmacy, evolution Effector families and taxonomic distributions FoldSeek, machine learning bioinformatics effector evolution Effector families and taxonomic distributions FoldSeek DeepBlast PLM embeddings learnMSA FoldMason Effector structure, [SDV.BV.BOT] Life Sciences [q-bio]/Vegetal Biology/Botanics |
| Beschreibung: | Plant pathogens secrete effectors to facilitate infection and manipulate host physiological and immune responses. Effector proteins are challenging to characterize because of their sequence and functional diversity, rapid evolution, and host-specific interactions. Recent advances in artificial intelligence (AI), particularly in protein biology, offer new opportunities for identifying and characterizing effector proteins and understanding their evolutionary processes. This review discusses recent progress in applying AI to effector biology, focusing on identification, functional characterization, and evolution. Key areas include subcellular localization prediction, protein structural modeling with tools like AlphaFold, and the use of pretrained protein language models. AI promises to complement existing experimental and computational approaches and further accelerate the investigation of effector protein functions and their evolutionary histories, even in the absence of clear sequence similarity or known functional domains. |
| Publikationsart: | Article |
| Dateibeschreibung: | application/pdf |
| Sprache: | English |
| ISSN: | 1545-2107 0066-4286 |
| DOI: | 10.1146/annurev-phyto-121823-081033 |
| Zugangs-URL: | https://hal.inrae.fr/hal-05284207v1 https://doi.org/10.1146/annurev-phyto-121823-081033 https://hal.inrae.fr/hal-05284207v1/document |
| Rights: | CC BY |
| Dokumentencode: | edsair.doi.dedup.....4c55cc0573ca4e599cbf4396f5057776 |
| Datenbank: | OpenAIRE |
Nájsť tento článok vo Web of Science | Abstract: | Plant pathogens secrete effectors to facilitate infection and manipulate host physiological and immune responses. Effector proteins are challenging to characterize because of their sequence and functional diversity, rapid evolution, and host-specific interactions. Recent advances in artificial intelligence (AI), particularly in protein biology, offer new opportunities for identifying and characterizing effector proteins and understanding their evolutionary processes. This review discusses recent progress in applying AI to effector biology, focusing on identification, functional characterization, and evolution. Key areas include subcellular localization prediction, protein structural modeling with tools like AlphaFold, and the use of pretrained protein language models. AI promises to complement existing experimental and computational approaches and further accelerate the investigation of effector protein functions and their evolutionary histories, even in the absence of clear sequence similarity or known functional domains. |
|---|---|
| ISSN: | 15452107 00664286 |
| DOI: | 10.1146/annurev-phyto-121823-081033 |