Systematic variation in mRNA 3'-processing signals during mouse spermatogenesis

Abstract

Gene expression and processing during mouse male germ cell maturation (spermatogenesis) is highly specialized. Previous reports have suggested that there is a high incidence of alternative 3'-processing in male germ cell mRNAs, including reduced usage of the canonical polyadenylation signal, AAUAAA. We used EST libraries generated from mouse testicular cells to identify 3'-processing sites used at various stages of spermatogenesis (spermatogonia, spermatocytes and round spermatids) and testicular somatic Sertoli cells. We assessed differences in 3'-processing characteristics in the testicular samples, compared to control sets of widely used 3'-processing sites. Using a new method for comparison of degenerate regulatory elements between sequence samples, we identified significant changes in the use of putative 3'-processing regulatory sequence elements in all spermatogenic cell types. In addition, we observed a trend towards truncated 3'-untranslated regions (3'-UTRs), with the most significant differences apparent in round spermatids. In contrast, Sertoli cells displayed a much smaller trend towards 3'-UTR truncation and no significant difference in 3'-processing regulatory sequences. Finally, we identified a number of genes encoding mRNAs that were specifically subject to alternative 3'-processing during meiosis and postmeiotic development. Our results highlight developmental differences in polyadenylation site choice and in the elements that likely control them during spermatogenesis.

Figure 1

A representation of the current model for the complete mouse 3′-processing regulatory sequences. The upstream PAS, most commonly AAUAAA or close variants, is the most prevalent feature (1). Recent studies have verified that the downstream U- and UG-rich elements, while degenerate, are distinct in both positioning and sequence content (5,6). The remaining elements are often referred to as auxiliary elements. While upstream U-rich elements have been postulated, no specific positioning requirements have been identified.

Figure 2

Variation in 3′-processing elements in various testis cell types. WSEA characterization of the variation in 3′-processing signals in spermatogenesis related tissues compared to the standard control set of 3′-processing sites. Over- and under-representation are signified by ‘+’ symbols and blue color, or ‘−’ symbols and red color, respectively. Significance values are shown reflecting the probability (P) of equal representation in the test and control sets according to permutation analysis (+/–: P < 0.2, ++/−−: P < 0.1, +++/−−−: P < 0.05, 0: no significant change). The reported P-values represent the probability of obtaining the measured difference when randomly selecting test sets of equivalent size from the standard control set. CS: cleavage site, PAS: canonical polyadenylation, ES: enrichment score (Equation 4).

Figure 3

Variation in 3′-UTR length distribution during spermatogenesis. (A) Cumulative length distribution of the 3′-UTR sequences implied by the EST libraries from various testis-related tissues. For comparison, the length distribution is also shown for the standard control set. (B) Median 3′-UTR length plotted as a function of sites with the canonical PAS hexamer (AAUAAA). Bars show the 95% confidence intervals. The libraries shown are a selection of dbEST (86) libraries with similar transcript sampling, as described previously (60).

Figure 4

Variation in transcript measurements of known 3′-processing factors during spermatogenesis. Microarray-based transcript measurements of known 3′-processing factors extracted from a spermatogenesis timecourse (54). Transcripts with multiple probesets (e.g. Cpsf1) typically are designed to assay different isoforms. Accordingly, changes in the relative signal between such probesets across the timecourse potentially indicate alternative processing of the associated transcript at different stages of spermatogenesis (e.g. Cstf1). All probesets were normalized to the average measured value in the two somatic samples from the original data set (54).