EffectorP: predicting fungal effector proteins from secretomes using machine learning. Issue 2 (17th December 2015)

• Record Type: Journal Article
• Authors: Sperschneider, Jana; Gardiner, Donald M.; Dodds, Peter N.; Tini, Francesco; Covarelli, Lorenzo; Singh, Karam B.; Manners, John M.; Taylor, Jennifer M.
• Is Part Of: New phytologist. Volume 210:Issue 2(2016)
• Page Start: 743
• Page End: 761
• Publication Date: 2015-12-17
• Subjects: effector -- EffectorP -- fungal effector prediction -- fungal pathogen -- machine learning -- secretomes; Botany -- Periodicals; 580
• DOI: 10.1111/nph.13794
• Languages: English
• ISSNs: 0028-646X

Abstract

Summary: Eukaryotic filamentous plant pathogens secrete effector proteins that modulate the host cell to facilitate infection. Computational effector candidate identification and subsequent functional characterization delivers valuable insights into plant–pathogen interactions. However, effector prediction in fungi has been challenging due to a lack of unifying sequence features such as conserved N‐terminal sequence motifs. Fungal effectors are commonly predicted from secretomes based on criteria such as small size and cysteine‐rich, which suffers from poor accuracy. We present Effector P which pioneers the application of machine learning to fungal effector prediction. Effector P improves fungal effector prediction from secretomes based on a robust signal of sequence‐derived properties, achieving sensitivity and specificity of over 80%. Features that discriminate fungal effectors from secreted noneffectors are predominantly sequence length, molecular weight and protein net charge, as well as cysteine, serine and tryptophan content. We demonstrate that Effector P is powerful when combined with in planta expression data for predicting high‐priority effector candidates. Effector P is the first prediction program for fungal effectors based on machine learning. Our findings will facilitate functional fungal effector studies and improve our understanding of effectors in plant–pathogen interactions. Effector P is available at http://effectorp.csiro.au .