Ceratobasidium sp. is associated with cassava witches' broom disease, a re-emerging threat to cassava cultivation in Southeast Asia

Abstract

Cassava witches' broom disease (CWBD) is a devastating disease of cassava in Southeast Asia (SEA), of unknown etiology. Affected plants show reduced internodal length, proliferation of leaves and weakening of stems. This results in poor germination of infected stem cuttings (i.e., planting material) and significant reductions in fresh root yields and starch content, causing economic losses for farmers and processors. Using a metagenomic approach, we identified a fungus belonging to the Ceratobasidium genus, sharing more than 98.3-99.7% nucleotide identity at the Internal Transcribed Spacer (ITS), with Ceratobasidium theobromae a pathogen causing similar symptoms in cacao. Microscopy analysis confirmed the identity of the fungus and specific designed PCR tests readily showed (1) Ceratobasidium sp. of cassava is strongly associated with CWBD symptoms, (2) the fungus is present in diseased samples collected since the first recorded CWBD outbreaks in SEA and (3) the fungus is transmissible by grafting. No phytoplasma sequences were detected in diseased plants. Current disease management efforts include adjustment of quarantine protocols and guarantee the production and distribution of Ceratobasidium-free planting material. Implications of related Ceratobasidium fungi, infecting cassava, and cacao in SEA and in other potential risk areas are discussed.

Figure 1

Metagenomic analysis of cassava plants with and without CWBD. (A) Alpha diversity indexes of healthy (blue) and diseased plants (yellow), including observed richness, Shannon and Simpson indexes. Box plots show significant differences (p < 0.05) according to the Wilcoxon non-parametric test. (B) Principal coordinate analysis (PCoA) with Bray–Curtis distance using OTUs abundance. (C) Relative abundance of different taxa identified in healthy (S1-S3) and diseased (S4-S6) cassava plants. Bar plots show the top 8 abundant classifieds within family and genus taxa. normalized by sequencing depth of microbial communities detected in diseased (yellow) and healthy (blue) plants. (D) Log-transformed ratio of the relative abundance of 8 genera of OTUs found in diseased (yellow) and healthy (blue) plants estimated by DESeq2.

Figure 2

Symptoms associated with Ceratobasidium sp. and microscopy observations of the fungus isolated from cassava. Symptoms observed in cassava KU50 with CWBD, both in the field on 12-month-old plants and after graft transmission. Similar symptoms have been reported for VSD caused by C. theobromae in cacao. (A) Cotton like mycelium growing around the base of petioles. (B) Detail of the CWBD symptoms coming out from buds showing fungal-like growth. (C) When slicing the petiole base, discoloration (dark central part) is observed exclusively in plants infected with CWBD. (D) An enlarged view of the basal bud in (A), showing stem splitting symptoms, which are also associated with C. theobromae. (E) At a magnification of 1000x, the presence of a septa in every branching structure is visible, emerging at a near right angle. (F) The bi-nucleate cells hallmark, of members of the genus Ceratobasidium.

Figure 3

Relationship of Ceratobasidium from cassava with isolates causing vascular necrosis in cacao and honeysuckle. Ceratobasidium sp. ITS sequences isolated from M. esculenta of Cambodia (OR145521), Vietnam (OR145522) and Lao PDR (OR145523) (yellow shading) grouped between ITS sequences isolates from T. cacao and L. japonica. The tree was constructed using maximum-likelihood method base on GTR + G model (1000 replicates) with related sequences available in GenBank. The bootstrap value for the branch is displayed only when it exceeds 90%. The average nucleotide identity in the compared regions (ITS) of Ceratobasidium sequences isolated from cassava and cacao is above 98.3–99.7%. The evolutionary distances were computed using the Maximum Likelihood method. All positions containing gaps and missing data were eliminated (there were 556 positions in the final dataset).

Figure 4

Changes in disease incidence in Southeast Asia. (A) CWBD field-incidence intervals observed in SEA during surveys performed in 2020 (white bars) and in 2022 (gray bars). The surveys were organized following a finite population sampling approach with 60 observations per hectare (see materials and methods) on the same locations in both years. (B) Box plots showing significant differences (p < 0.05), according to the Wilcoxon non-parametric test. We used upper limits incidence values for 2020 and 2022 as calculated per field (hectare) surveyed. An interactive map of CWBD reports is available at https://pestdisplace.org/embed/news/map/disease/3.

Figure 5

Induction of CWBD symptoms by grafting in cassava. (A) CWBD symptoms were induced after graft transmission of Ceratobasidum sp. to two cassava genotypes, KU50 and Rayong11. Left: an infected cassava plant; center: a healthy cassava plant grafted with an infected plant; right: a healthy cassava plant grafted with another healthy cassava plant. (B) Petiole length in healthy (blue) and diseased (yellow) plants during the experiment in both varieties. Box plots show significant differences (p < 0.05) according to the Wilcoxon non-parametric test.