Tn-seq: high-throughput parallel sequencing for fitness and genetic interaction studies in microorganisms

Abstract

Biological pathways are structured in complex networks of interacting genes. Solving the architecture of such networks may provide valuable information, such as how microorganisms cause disease. Here we present a method (Tn-seq) for accurately determining quantitative genetic interactions on a genome-wide scale in microorganisms. Tn-seq is based on the assembly of a saturated Mariner transposon insertion library. After library selection, changes in frequency of each insertion mutant are determined by sequencing the flanking regions en masse. These changes are used to calculate each mutant's fitness. Using this approach, we determined fitness for each gene of Streptococcus pneumoniae, a causative agent of pneumonia and meningitis. A genome-wide screen for genetic interactions of five query genes identified both alleviating and aggravating interactions that could be divided into seven distinct categories. Owing to the wide activity of the Mariner transposon, Tn-seq has the potential to contribute to the exploration of complex pathways across many different species.

Figure 1

Schematic depiction of Tn-seq. (a) A gene disruption library is constructed by first transposing the mini-transposon magellan6 into bacterial genomic DNA in vitro and subsequently transforming a bacterial population with the transposed DNA. The result is a bacterial pool where each bacterium contains a single transposon insertion in its genome. (b) DNA is isolated from a portion of the bacterial pool (t₁), another portion is used to seed a culture on which selection is performed, then DNA is isolated again from recovered bacteria (t₂). (c) DNA from both time points is digested with Mme I; the Mme I restriction site was introduced into the transposon’s inverted repeats. (d) A PCR amplification is performed to obtain a 160 bp sequence with 20 bp of bacterial specific DNA flanked by Illumina specific sequences, which enable sequencing. After sequencing, different samples are identified based on barcode sequence, the 20 bp reads are mapped to the genome and are counted for each insertion, thus allowing fitness to be calculated.

Figure 2

Fitness determination and classification. (a) Independent insertions and their fitness effects in the genomic region from gene SP_0022 to SP_0025 are plotted. The black jagged line depicts the average fitness for each gene. (b) A pie chart categorizing every gene’s fitness in the S. pneumoniae genome into four categories.

Figure 3

Validation of Tn-seq fitness measurements. (a) A technical replicate of the same library comparing the effect of sample preparation and sequencing. Pearson correlation coefficient = 0.97. (b) A biological replicate comparing two independently generated, selected upon and sequenced libraries. Pearson correlation coefficients between biological replicates ranged between 0.70 – 0.90. A representative example is shown. (c) Comparison of fitness (± s.e.m.) obtained with Tn-seq (yellow) and the classical 1×1 competition method (blue) for 30 random transposon insertions and 16 marked gene deletions (*). Numbers underneath the graph refer to Streptococcus pneumoniae TIGR4 gene numbers (SP_number). (d) Three representative growth curves; the wild type strain, a strain with an advantageous deletion (SP_1697, W=1.22) and a strain with a disadvantageous deletion (SP_0841, W=0.71).

Figure 4

Genetic interaction network of five query genes. Interactions between two genes (i and j) are depicted as a line (edge) between two genes (nodes) and were determined by Tn-seq and supplemented with interactions from the STRING database (confidence >0.5; only edges were added and no nodes). Genetic interactions are divided into seven categories depicted underneath the network. W_i, fitness of mutant in gene i; W_j, fitness of mutant in gene j; W_ij, fitness of double mutant. In the top section, genes i and j confer different fitness; in the bottom section, genes i and j have an equal fitness effect. This scheme results in seven color coded genetic interaction categories: synergistic (W_i=W_j<W_ij), partial masking (W_i<W_j<W_ij), masking (W_i<W_j=W_ij), partial suppression (W_i<W_ij<W_j), suppression (W_i=W_ij<W_j), antagonistic (W_ij<W_i≤W_j) and co-equal (W_i=W_j=W_ij) (see Methods for further details). Arrows depict the hypothesized direction of the interaction. Nodes are color coded according to their involvement in a biological process or molecular function. Numbers in nodes refer to Streptococcus pneumoniae TIGR4 gene numbers (SP_number).

Figure 5

Validation of genetic interactions. (a) Fitness (± s.e.m.) of seven genes either knocked out singly or in combination with ccpA are compared between the 1×1 method (blue) and Tn-seq (yellow). The expected multiplicative fitness for each double gene knockout is depicted in green (expected fitness was determined by multiplying ccpA fitness [0.84±0.04 s.e.m.] with fitness measured for the other gene). Numbers underneath the graph refer to Streptococcus pneumoniae TIGR4 gene numbers (SP_number). (b) A detail of the genetic interaction network showing five of the validated genetic interactions and their specific interactions. (c) A sub-network from the larger genetic interaction network showing four PTS genes including two of the validated genetic interactions (SP_0476 and SP_1185), β-galactosidase (SP_0648) and a gene with unknown function (SP_0475). Interaction colors, node colors and numbers are as in Figure 4.