Enhanced protein secretion in reduced genome strains of Streptomyces lividans

Abstract

Background: S. lividans TK24 is a popular host for the production of small molecules and the secretion of heterologous protein. Within its large genome, twenty-nine non-essential clusters direct the biosynthesis of secondary metabolites. We had previously constructed ten chassis strains, carrying deletions in various combinations of specialized metabolites biosynthetic clusters, such as those of the blue actinorhodin (act), the calcium-dependent antibiotic (cda), the undecylprodigiosin (red), the coelimycin A (cpk) and the melanin (mel) clusters, as well as the genes hrdD, encoding a non-essential sigma factor, and matAB, a locus affecting mycelial aggregation. Genome reduction was aimed at reducing carbon flow toward specialized metabolite biosynthesis to optimize the production of secreted heterologous protein.

Results: Two of these S. lividans TK24 derived chassis strains showed ~ 15% reduction in biomass yield, 2-fold increase of their total native secretome mass yield and enhanced abundance of several secreted proteins compared to the parental strain. RNAseq and proteomic analysis of the secretome suggested that genome reduction led to cell wall and oxidative stresses and was accompanied by the up-regulation of secretory chaperones and of secDF, a Sec-pathway component. Interestingly, the amount of the secreted heterologous proteins mRFP and mTNFα, by one of these strains, was 12 and 70% higher, respectively, than that secreted by the parental strain.

Conclusion: The current study described a strategy to construct chassis strains with enhanced secretory abilities and proposed a model linking the deletion of specialized metabolite biosynthetic clusters to improved production of secreted heterologous proteins.

Keywords: Heterologous secretion; Proteomics; Reduced genome strains; Secretome; Transcriptomics.

Fig. 1

Physical maps of the chromosomal regions deleted in S. lividans TK24 The regions corresponding to the actinorhodin (26.7 kb), undecylprodigiosine (39.3 kb), calcium dependent antibiotic (26.7 kb), coelimycin P1 (59.1 kb) and melanin (8.9 kb) biosynthetic clusters as well as those encoding for the transcription factor HrdD (1.3 kb) and aggregation genes matAB (4.5 kb) were deleted in various combinations

Fig. 2

Total biomass and native secretome yield in S. lividans TK24 and reduced genome derivative strains. (A) Dry cell weight (DCW; g/L; black bars) and total secretome yield (mg secreted protein/ g DCW; grey bars) following growth of the indicated strains in nutrient broth (NB) until late exponential phase. n = 3; values represent the mean ± SD; (B) Equal amount of secreted polypeptides (3 µg/lane) from the indicated strains, grown as in A, were analyzed by SDS-PAGE and silver stained. Lane 1: molecular weight marker. Proteins with major (arrows)/ little (asterisks) change among strains are indicated

Fig. 3

Comparative secretome analysis of S. lividans TK24 and RG1.9 strains. (A) Proteins secreted by the parental and by the RG1.9 strains were differentially abundant. Blue: more abundant in the parental strain; red: more abundant in the RG1.9 strain. The secretome amount that was produced by a fixed amount of cell biomass was loaded for both strains for proteomics analysis. (B) The summary of proteins that were differentially abundant in the secretome of the parental and the RG1.9 strains is shown as volcano plots (for detailed description see panel C and Table S1). Each dot represents one protein. Blue: more abundant in the parental strain; Red: more abundant in the RG1.9 strain. Plotted on the x axis is the fold difference (in log₂ scale) of the mean protein abundance in the parental strain over that in RG1.9, and on the y axis the p-value derived from a t-test between the two strains (–log₁₀, adjusted from [64]. (C) Classification of the differentially abundant proteins based on their biological function, as described [52]. The ratio ‘number of differentially abundant proteins that belong to the indicated functional group/ total number of differentially abundant proteins in the same strain’ is plotted. The dataset was filtered in order to retain secreted proteins and eliminate contaminating cytoplasmic proteins. Functional groups are coded with latin numbers as indicated. (D) Clustering of iBAQ values for proteins that showed differential abundance in the secretome of the parental and of the RG1.9 strains. Proteins have been annotated with both S. lividans TK24 (SLIV) and S. coelicolor (SCO) gene IDs. Latin numbers next to gene IDs indicate protein functions as these were grouped in panel C

Fig. 4

Differential expression of genes between S. lividans TK24 and RG1.9 strains. (A) MA-plot for RNA-Seq datasets comparing S. lividans TK24 and RG1.9 strains. Genes similarly regulated in both strains (grey) and up- (red) or down- (blue) regulated in RG1.9 are indicated (M > 1 or M <-1 respectively; adjusted p-value < 0.05). M and A values were calculated as indicated (Material and Methods). For the 10 most prominently up- / down- regulated genes their SLIV/SCO gene IDs are indicated. (B) Differential expression of genes encoding proteins with the indicated biological function (as described, [52]) in S. lividans TK24 (grey) and RG1.9 (black) strains. For each strain and each functional group, the ratio ‘number of differentially expressed genes / total number of genes’ was plotted. (C) Heatmap of genes related to oxidoreductase (left) or cell wall (right) functions that were upregulated in RG1.9, classified as in panel B. Annotations with SLIV/ SCO gene IDs are indicated. Asterisks: genes that belong to the Sig^R or Sig^E regulons

Fig. 5

Effect of cluster/gene deletions on heterologous protein secretion. (A) Strains carrying pIJ486/sp^Secv-mRFP, as indicated, were grown in NB for 24 h. Secreted proteins were TCA precipitated, analyzed by SDS-PAGE and silver stained. Lanes were loaded with 5–10 µL of collected polypeptides, a volume corresponding to 0.1 mg DCW. Lane 1: Molecular weight marker; Arrow; mRFP, as indicated. (B) Immunostaining of the samples presented in Panel A (same sample loading) using mRFP specific antibodies. Lane 1: purified his-mRFP; Lane 2: molecular weight marker. (C) The amounts of mRFP secreted by the S. lividans TK24 and RG strains (as indicated), grown in NB medium, for 24 (grey) or 48 h (black bars), were expressed either in mg/L (left panel) or in mg/gram of DCW (right panel). n = 3, values represent the mean ± SD

Fig. 6

Proposed model for the effect of specialized metabolite clusters/ matAB deletion on protein secretion. Combined deletions of specialized metabolite clusters and matAB locus in S. lividans TK24 resulted in cells overexpressing and oversecreting proteins related to cell wall remodeling and oxidative stress. (+) indicates positive regulation