Transcriptome analysis of zebrafish embryogenesis using microarrays

Abstract

Zebrafish (Danio rerio) is a well-recognized model for the study of vertebrate developmental genetics, yet at the same time little is known about the transcriptional events that underlie zebrafish embryogenesis. Here we have employed microarray analysis to study the temporal activity of developmentally regulated genes during zebrafish embryogenesis. Transcriptome analysis at 12 different embryonic time points covering five different developmental stages (maternal, blastula, gastrula, segmentation, and pharyngula) revealed a highly dynamic transcriptional profile. Hierarchical clustering, stage-specific clustering, and algorithms to detect onset and peak of gene expression revealed clearly demarcated transcript clusters with maximum gene activity at distinct developmental stages as well as co-regulated expression of gene groups involved in dedicated functions such as organogenesis. Our study also revealed a previously unidentified cohort of genes that are transcribed prior to the mid-blastula transition, a time point earlier than when the zygotic genome was traditionally thought to become active. Here we provide, for the first time to our knowledge, a comprehensive list of developmentally regulated zebrafish genes and their expression profiles during embryogenesis, including novel information on the temporal expression of several thousand previously uncharacterized genes. The expression data generated from this study are accessible to all interested scientists from our institute resource database (http://giscompute.gis.a-star.edu.sg/~govind/zebrafish/data_download.html).

Figure 1. Hierarchical Clustering Analysis of Differentially Expressed Zebrafish Genes

Of the 16,416 genes in the array, 3,657 genes, which showed a significant level of differential expression at least at one time point, were clustered hierarchically into groups on the basis of similarity of their expression profile, following Eisen's clustering method. The horizontal lines indicate the expression pattern of each gene, and the vertical rows indicate the embryonic developmental stages. For each gene, the ratio of transcript abundance in the developing stages of the embryo to its abundance in the reference RNA is represented by color intensities (red color indicates the higher expression, and green color indicates the lower expression of the gene in the embryos). Coordinated expression of the beta-actin gene (control) is indicated.

Figure 2. Analysis of Expression Patterns of the Zebrafish Embryonic Transcriptome

(A) The onset and peak of transcript accumulation were calculated using an algorithm for each of the differentially expressed genes. An average performance of the gene in each group is presented in the clustergram. Of the set of 1,972 genes commencing at the onset of the blastula stage, subsets of genes displayed peak activity at blastula, gastrula, segmentation, and pharyngula stages. Average performance of these genes in each subset is represented in the clustergram. Similar analysis was made for the genes commencing transcript accumulation at gastrula, segmentation, and pharyngula stages, and the data are presented. (B) Patterns of differential degradation of maternally loaded transcripts. (a) Transcripts level of the genes in this group degraded drastically prior to blastula. Groups of genes whose transcripts persisted till blastula (b) and subsequent stages (c) of development are represented graphically. (C) Cumulative analysis of onset and peak of expression of zygotic genes. A number of zygotic genes commenced their transcript accumulation steadily during early development. About 99% of the genes initiated transcript accumulation by the end of the segmentation stage. The figure inserted in Figure 2C indicates that the percentage of genes showing peak of activity also increased steadily and about 90% of the zygotic genes displayed their peak of expression within 24 hpf (prior to the pharyngula stage). The dynamics of zygotic genome activation during early development is evident from the cumulative expression analysis. (D and E) Frequency distribution of onset of transcript accumulation (D) and peak of expression (E). Of the 3,657 genes analyzed, about 54% (> 2,000 genes) commenced transcript accumulation during the blastula stage. Considering the peak of expression, the majority of genes (> 1,000 genes) displayed a peak of expression during the gastrula stage. (F) Transcriptome analysis during blastula and gastrula stages. Of the total zygotic genes (3,035 genes; 100%; red circle), percentage of genes commencing transcript accumulation (80.5%; yellow circle) and showing peak of expression (53%; light-blue circle) during blastula and gastrula stages are indicated pictorially. (G) Total period of embryonic development of zebrafish (48 h; yellow bar) and the time required for each stage of development is indicated (color-coded for each stage). Considering all the developmentally regulated genes (3,657), the percentage of genes showing peak of activity at the designated developmental stages are indicated in the top bar. The bottom bar indicates the percentage of zygotic genes (3,035 genes) commencing transcript accumulation at the designated developmental stages.

Figure 3. Overview of the Expression Patterns of Genes Peaking at Selected Developmental Stages

(A,B) Differentially expressed genes were clustered based on the peak of expression at the selected developmental stages and presented in the clustergram. Of the total number of 3,657 genes analyzed, 622, 609, 1,006, 688, and 732 genes showed peak expression at maternal, blastula, gastrula, segmentation, and pharyngula stages, respectively. (C) General trend and average performance of the genes at each developmental stage are graphically represented (red, high expression; green, low expression). It is clear from this analysis that different sets of genes displayed their maximum at different stages of development, indicating the temporal/stage-specific maximum activity of the developmentally regulated genes.

Figure 4. Expression of Genes Involved in Specific Functions

(A) Expression patterns of genes involved in the cell cycle. Genes involved in the cell cycle, namely cyclin and cyclin-dependent kinase genes, were identified based on GO and clustered separately. Most of the cyclin genes commenced their expression maternally, and the cyclin-dependent kinase genes showed expression throughout embryogenesis. (B and C) Genes involved in ubiquitin function (proteasomes and ubiquitins) are active during most of the developmental stages, and the peak of activity is between the gastrula and segmentation stages. (D) Gene expression during somitogenesis. Genes involved in somitogenesis were selected based on the GO list. Expression of MSP genes (acta 1, actc1, tpma, ckm, tnnt1, mibp2, myhz1, myhz2, mylz2, mylz3, tnnc, and tnnt3a) are clustered. Most of the MSP genes commenced their expression around 12 hpf and displayed their maximum during the pharyngula stage. (E) Expression pattern of somitogenic (myotome-specific) transcription factors (mespa, mespb, mef2a, mef2c, med2d, myf5, myog, foxc1a, her4, her6, her7, and her9). Most of the transcription factors commenced transcript accumulation from the blastula stage onwards well in advance of commencement of MSP gene transcription. (F) Coordinated expression of RP genes. From the array data, the expression profile of RP genes was clustered. Most of the genes showed an identical pattern of expression.

Figure 5. Analysis of the Zebrafish Transcriptome during Pre-MBT and Post-MBT Stages of Embryonic Development

Transcriptional profiles of the genes during pre-MBT: one- to four-cell, 64-/128-cell, and post-MBT: blastula (4 hpf) and gastrula (6 hpf) stages were analyzed. This analysis revealed four different gene clusters. Clusters 1, 3, and 4 represent gene expression patterns, which have been identified earlier. Cluster 2 represents a novel pattern of gene expression commencing transcript accumulation at the 64-/128-cell stage onwards that represents the pre-MBT stage.

Figure 6. Validation of Zebrafish Transcriptome Pre-MBT and Post-MBT Results

Comparison between RT-PCR and microarray results for selected genes. Real-time PCR was done for 16 clones from Cluster 2 using the same RNA used for array hybridization. The RT-PCR profile closely parallels the microarray data, cross-validating both techniques as quantitative estimates.

Figure 7. WISH Was Performed for Selected Clones

All the clones subjected for in situ analysis showed a lower intensity of hybridization signal at one- to four-cell stages and increased intensity at 64-/128-cell and 256-/512-cell stages. These observations support the data obtained in the real-time PCR and microarray data, indicating the pre-MBT accumulation of transcripts.