A trade-off between proliferation and defense in the fungal pathogen Cryptococcus at alkaline pH is controlled by the transcription factor GAT201

Abstract

Cryptococcus is a fungal pathogen whose virulence relies on proliferation in and dissemination to host sites, and on synthesis of a defensive yet metabolically costly polysaccharide capsule. Regulatory pathways required for Cryptococcus virulence include a GATA-like transcription factor, Gat201, that regulates Cryptococcal virulence in both capsule-dependent and capsule-independent ways. Here we show that Gat201 is part of a negative regulatory pathway that limits fungal survival at alkaline pH. RNA-seq analysis found strong induction of GAT201 expression within minutes of transfer to RPMI media at alkaline pH. Microscopy, growth curves, and colony forming unit assays show that in RPMI at alkaline pH wild-type Cryptococcus neoformans yeast cells produce capsule but do not bud or maintain viability, while gat201Δ cells make buds and maintain viability, yet fail to produce capsule. GAT201 is required for transcriptional upregulation of a specific set of genes, the majority of which are direct Gat201 targets. Evolutionary analysis shows that Gat201 is in a subfamily of GATA-like transcription factors that is conserved within pathogenic fungi but absent in model yeasts. This work identifies the Gat201 pathway as controlling a trade-off between proliferation and production of defensive capsule. The assays established here will allow characterisation of the mechanisms of action of the Gat201 pathway. Together, our findings urge improved understanding of the regulation of proliferation as a driver of fungal pathogenesis.

Fig 1:. Cryptococcus neoformans rapidly induces media-specific growth programs upon reactivation from stationary phase.

A, Design of time-course experiment to measure the contribution of media and temperature on reactivation of stationary phase cells. B, Budding (yellow-green arrow) is seen in YPD at both temperatures (top row) while capsule (light red arrow) is primarily seen in RPMI + serum at 37°C (bottom right). Micrograph shows India Ink staining of cells taken from one replicate of cells used for the RNA-seq experiment, 150 minutes after inoculation. C, Time from inoculation and media dominate the overall variance in gene expression, shown by principal component analysis on the regularized log-counts per gene in every replicate. Each replicate is plotted and labeled by the timepoint, with colours as in Fig. 1A (grey - 0 min, yellow - YPD 25°C, orange - YPD 37°C, light purple - RPMI 25°C, dark purple - RPMI 37°C), additionally with dark green for exponential phase rich media 30°C. D, Distinct clusters of co-regulated genes respond to reactivation in different media, shown by clustered heatmap of log2 fold-change per gene calculated by DESeq2. Each row represents an individual gene and rows are clustered by co-expression patterns (see methods), while each column represents the regularised log2 fold-change estimate across both replicates in a single condition. E, Representative genes from different clusters show distinct expression patterns, again in regularised log2 fold-change per gene. Colours of growth conditions are as in Fig. 1A.

Fig 2:. GAT201 represses the proliferation and viability of Cryptococcus neoformans during reactivation in RPMI medium.

A, GAT201 promotes capsule biosynthesis and represses budding in RPMI-1640 medium (without serum) at 37°C 2 hours after inoculation. Micrographs show GAT201 (H99), gat201Δm, and complemented GAT201-C1 strains, stained with India Ink, capsule highlighted with red arrow and buds highlighted with green arrows. GAT201-C1 complements the budding phenotype but does not clearly complement the capsule phenotype. B, Quantification of budding index at 2 hrs (% budded cells) shows that gat201Δm cells reactivate to produce buds in RPMI, (n= >100 cells per replicate, with 3 biological replicates per condition). Figs 2A and 2B are taken from the same experiment, and larger sets of representative cells are shown in Fig S3. C, GAT201 (H99) cell populations reactivating in RPMI show a fall in density after 10 hours growth, which is absent in gat201Δ strains and absent during growth in rich YPD media. Growth curves of optical density at 595 nm (OD₅₉₅) were collected via plate reader from 7 biological replicates, 3 technical replicates each, at 37°C. Note the different y-axis limits in the subpanels, reflecting higher final OD in rich media. D. GAT201 (H99) cells reactivating in RPMI or RPMI + serum show a decline in viability after 12–24 hours, which is absent in gat201Δ and partially restored by complementing GAT201. The decline in viability is more severe in RPMI without serum than it is in RPMI with serum. Colony forming units per ml of culture were measured by serial dilution on plates, in 3 biological replicates; individual replicates are plotted as dots with a dotted line connecting the medians.

Fig 3:. Serum is not the dominant driver of GAT201-dependent phenotypes in RPMI 1640 media.

A, GAT201 promotes capsule biosynthesis and represses budding in RPMI medium both with and without serum at 37°C, 2 hours after inoculation. Strains are GAT201 (KN99alpha) and gat201Δm. B, Time from inoculation dominates the overall variance in gene expression regardless of serum addition or GAT201 allele, shown by principal component analysis on the regularized log-counts per gene in every replicate. C, Only a small set of genes are differentially regulated by serum or by GAT201, shown by clustered heatmap of log2 fold-change per gene calculated by DESeq2. D, Representative genes show distinct expression patterns, again in log2 fold-change per gene.

Fig 4.. GAT201 specifically affects gene expression as cells reactivate, acting via its direct targets.

A. There is more GAT201-dependent differential gene expression at later time points in activation. Fig 4A shows the number of 2-fold differentially expressed (DE) genes at 5% FDR at each combination of growth condition and time point. Differential expression is calculated by DESeq2 using the Wald test as the average over 4 samples: 2 wild-type and 2 deletion strains, each strain measured in biological duplicate. B. GAT201 promotes upregulation of specific genes more than downregulation. Volcano plot of log2 fold-change and p-value, with differential expressed genes calculated and coloured as in panel A. Genes with extreme p-values or fold-changes are plotted at the edge of the panel area. C. GAT201-dependent differential gene expression is more extreme at later timepoints. The panel shows all the genes that are at least 8x differentially expressed in any combination of condition and time, ordered by their average fold-change at 4 hours. D. Over half of the upregulated differentially expressed genes are direct targets of GAT201. Venn diagram shows the number DEGs in RPMI at 4 hours (as in panel B) compared to Gat201 targets measured by ChIP-seq from Homer et al. 2016. This is approximately a 3-fold enrichment. E. GAT204, as well as GAT201, is required to repress growth of cells in RPMI.

Fig 5.. The effect of GAT201 on growth depends on sodium bicarbonate (NaHCO₃).

Starting with an RPMI formulation lacking NaHCO₃, we added either 0mM, 1.5mM, 6mM, or 24mM NaHCO₃ and grew Cryptococcus for 24 hours. Wild-type GAT201 cells grow in 0mM NaHCO₃ but do not grow in 24 mM NaHCO₃, while gat201Δ have opposite phenotypes of no growth in 0mM and growth at 24 mM. These cells have intermediate phenotypes at intermediate concentrations of NaHCO₃, while complemented strains have growth phenotypes resembling wild-type. This figure shows the median of 3 technical replicates from a single biological replicate, and 2 further biological replicates are shown in Fig S13.

Fig 6.. C. neoformans Gat201 is homologous to other GATA-family zinc finger proteins that regulate fungal growth and environmental responses.

A, Domain structure of Gat201 and 4 close homologs, with GATA-like zinc finger domain shown in red (Interpro IPR013088) and predicted unstructured regions in blue (MobiDB Lite consensus disorder), taken from Interpro (Blum et al. 2021). B, Multiple sequence alignment of the GATA-like zinc finger domains of homologs made with MUSCLE (Edgar 2004). Conserved cysteine residues typical of GATA-like zinc fingers are indicated with asterisks. An extended phylogeny and homology analysis is shown in Fig S15.

Fig 7.. The Gat201 pathway promotes Cryptococcus virulence and represses proliferation.

Gat201 acts in parallel to serum-responsive cAMP/Pka pathway and the major pH-responsive Rim101 pathway. Gat201 requires mutual activators, Gat204 and Liv3, to suppress proliferation.