A novel gene required for male fertility and functional CATSPER channel formation in spermatozoa

Abstract

Calcium signalling is critical for successful fertilization. In spermatozoa, capacitation, hyperactivation of motility and the acrosome reaction are all mediated by increases in intracellular Ca(2+). Cation channels of sperm proteins (CATSPERS1-4) form an alkalinization-activated Ca(2+)-selective channel required for the hyperactivated motility of spermatozoa and male fertility. Each of the CatSper1-4 genes encodes a subunit of a tetramer surrounding a Ca(2+)-selective pore, in analogy with other six-transmembrane ion channel α subunits. In addition to the pore-forming proteins, the sperm Ca(2+) channel contains auxiliary subunits, CATSPERβ and CATSPERγ. Here, we identify the Tmem146 gene product as a novel subunit, CATSPERδ, required for CATSPER channel function. We find that mice lacking the sperm tail-specific CATSPERδ are infertile and their spermatozoa lack both Ca(2+) current and hyperactivated motility. We show that CATSPERδ is an essential element of the CATSPER channel complex and propose that CATSPERδ is required for proper CATSPER channel assembly and/or transport.

Figure 1. Identification of CATSPERδ encoded by Tmem146 as an auxiliary subunit of native CATSPER channels

(a) Purified CATSPER1 complex (α-CATSPER1) separated by SDS-PAGE and stained with Coomassie blue. Rabbit IgG column eluate serves as control (IgG). Numbered protein bands in the purified CATSPER1 complex were subjected to mass spectrometry identification. Confirmed CATSPER1 interactors are listed (blue). The CATSPER channel in the testis is comprised of a macromolecular complex of all four α subunits (CATSPERS1-4), two previously identified auxiliary subunits (CATSPERβ and γ) and a novel auxiliary subunit, TMEM146 (CATSPERδ). (b and c) Two transmembrane proteins that did not express specifically in testes, SLC39A7 (band 5) and SLC39A6 (band 12), were tested for potential interaction with CATSPER1. Anti-SLC39A7 antibody recognized protein in spermatozoa, but its expression was not CATSPER1-dependent. Interaction with CATSPER1 was not found in testis (b). SLC39A6 antibody detected recombinant protein expressed in HEK293T cells ((+) CTL), but no protein was detected in sperm cells or in the CATSPER1 complex (c). (d and e) Two novel testis-specific proteins from band 12 were tested for potential interaction with CATSPER1. LOC75721 was expressed in testis but not in the CATSPER1 immune complex or sperm cells (d). Another protein identified from band12, TMEM146/CATSPERδ co-immunoprecipitates with CATSPER1 (e).

Figure 2. Molecular cloning of two alternative splice variants of CatSperδ

(a) Tissue distribution of CatSperδ mRNA by reverse-transcription PCR. CatSperδ (upper) and Glyceraldehyde-3-Phosphate Dehydrogenase (control; lower) from 12 mouse cDNAs; negative control (lane “−”). CatSperδ was detected only in testis. (b and c) Molecular cloning of CatSperδ cDNAs. Two bands differing by 118 bp were amplified by mouse testis first-strand cDNAs by PCR with primers corresponding to the most upstream 5′ sequence identified by 5′-RACE and 2 different gene-specific primers (GSP) nested at the 5′-UTR of Tmem146-s. RT, reverse transcriptase (b). Whole open reading frames (ORFs) of Tmem146 were amplified from testis cDNA (c). (d) Schematic diagram of CatSperδ splice variants. Two alternatively spliced mRNA variants are transcribed from the Tmem146 gene. Tmem146-s has a start site in exon 7 (blue). Tmem146-l contains a new start site in exon 1 (green) due to a change in the ORF by the additional 118 bp exon 5 (orange). The locations of probes for in situ hybridization are illustrated above the transcripts. Probe 1 is complementary to both Tmem146-s and –l. Probe 2 was amplified from Tmem146-s cDNA and corresponds to the splicing region (spanning exon 4 and 6). (e) Heterologous expression of CATSPERδ isoforms. V5-tagged Tmem146-s or Tmem146-l, cDNAs were transfected into HEK293T cells. After immunoprecipitation with anti-V5, immune complexes were probed with anti-V5. (f) Spatial localization of Tmem146 splice variants. Representative fields of in situ hybridization in mouse testis using antisense 1 (upper left) and antisense 2 (lower left). Sense probes served as background controls (right panels). Scale bar, 100 μm. (g) Temporal Tmem146-s and Tmem146-l mRNA levels (real time RT-PCR) during testis postnatal development. mRNAs are normalized to TATA binding protein (TBP) at each time point and expressed as ratios relative to adult (80-day) mouse testis (± SEM compared to each prior time point *P < 0.05, **P < 0.005). Tmem146-s mRNA was detected at 17 days (unpaired two-tailed t-test, P = 0.0017) while Tmem146-l appeared at 20 days (P = 0.047 at 20 days, P = 0.042 at 23 days), consistent with the in situ hybridization experiments. Results are from 3 independent experiments.

Figure 3. Characterization of the CATSPERδ protein

(a) Predicted mouse CATSPERδ protein sequences. Predicted signal peptide (SP) and transmembrane (TM) domain are boxed. The two peptides identified by mass spectrometry are in bold (amino acids 436–450 and 781–787). Two peptide epitopes used to generate antibodies are underlined (amino acids 446–470 and 786–805). The first methionines of two potential TMEM146 isoforms are shadowed in grey. (b) Hydrophilicity plots (window size, 11) of mouse (upper) and human (lower) CATSPERδ. The predicted signal peptide and the single transmembrane domain (TM) are marked by arrows. The alternative start site of Tmem146-s is marked by the arrowhead. (c) Immunostaining of mouse sperm by α-CATSPERδ (α-δ446). Left, phase contrast image. The head (H), midpiece (MP), and principal piece (PP) of the sperm are indicated. Middle, immunofluorescence; right, merged signal. Scale bar, 10 μm. (d) Interaction of CATSPER1, CATSPERβ, and CATSPERδ in wt testes (wt). CATSPERδ is associated with CATSPERβ regardless of CATSPER1 expression (1−/−). α-tubulin; input control. (e) Absence of CATSPERδ protein in CatSper1-null spermatozoa. (f) Expression of CATSPER1 and CATSPERβ in the testis of homozygous null CatSper1 (1−/−), CatSper3 (3−/−), and CatSper4 (4−/−) and wild type (wt) mice.

Figure 4. Targeted disruption of Tmem146 gene inactivates CatSperδ

(a) Whole genomic structure of mouse Tmem146 gene, targeting construct, and predicted mutant allele generated by homologous recombination and Cre excision; Filled boxes, exons; thin lines, introns. Neomycin (Neo) and thymidine kinase (TK) selection cassettes are shown. The locations of primers used for genotyping are shown with arrowheads. Primers located outside targeting region, 5F and 3R; inside targeting region, 5R2; within Neo, 5R1 and 3F. (b and c) PCR genotyping of genomic DNA. Tmem146 Neo mutant ES clone (97) is identified by the presence of PCR products at both the 3′- (3F/3R) and 5′- (5F/5R2) of the expected locus (b). Excision of genomic sequence flanked by two loxP sites by PCR with 5F/5R2 (c). (d) RT-PCR of CatSperδ with testis mRNA from CatSperδ–null mice showing the expected products. Combination of two primers with one spanning exon 7/8 and the other in exon 12 demonstrates absence of exon 9 in the CatSperδ transcript (left). RT-PCR of GAPDH is the control (right), CatSperδ null–(−/−), CatSperδ–heterozygotes (+/−) and wildtype (+/+). (e) Immunostaining of mouse epididymal sperm with anti-CATSPERδ antibody (α-δ446). CATSPERδ specifically labels only the principal piece of the tail of wt spermatozoa (left) and is not observed in the CatSperδ-null sperm cells (right). Scale bar, 10 μm. (f) Absence of CATSPER1, β and δ proteins in spermatozoa of CatSperδ homozygous null mice.

Figure 5. CatSperδ-null male mice are infertile and their sperm fail to hyperactivate

(a) Hematoxylin and eosin staining of the testes (top) and epididymis (bottom) of wt (left) and CatSperδ-null (right) mice. Testis morphology is normal. Scale bar, 50 μm. (b) CatSperδ-null males are infertile. (c) Epididymal sperm count (mean ± SEM) from littermates at ages of 2–3 or 7–8 months of age (6 pairs each). Het (open)-versus null (filled): *P < 0.05, paired two-tailed t-test. (d) Flagellar beat frequency of CatSperδ-het (open) and null sperm (filled). Basal beat frequency immediately after isolation (time 0), beat frequencies of activated (10 min) and hyperactivated (90 min) sperm cells incubated in capacitating media; n = 15–54 tethered sperm cells in 4 independent experiments (unpaired two-tailed t-test, ***P < 0.001, **P < 0.005). (e) Aligned flagellar waveform traces. Sperm cells were examined 90 min after incubation in capacitating conditions to induce hyperactivation. Representative traces of single spermatozoa of CatSperδ-het and CatSperδ-null are shown. CatSperδ-het full beat cycle lasted ~230 ms, during which CatSperδ-null sperm completed two beat cycles. (f) Measurement of bending angle. Capacitated het spermatozoa exhibit larger ranges of motion than CatSperδ-null spermatozoa as indicated by the maximum bending angle (inset, α; unpaired two-tailed t-test, **P < 0.005). n=6.

Figure 6. CatSperδ-null mice lack CatSper current

(a) CatSperδ-het and (b) CatSperδ-null I_CatSper. The upper traces show representative time courses of I_CatSper measured in control solutions (1), nominally divalent-free (DVF) solutions (2), and high-K⁺ solutions (3) at −100 mV (open cicrles) and + 100 mV (closed circles). Bottom panels show the current-voltage relations of monovalent I_CatSper in response to voltage ramps at the time points indicated. I_CatSper is absent in CatSperδ-null sperm cells. A small inward I_KSper was seen in both phenotypes when the bath solution was switched to 160 mM K-MeSO₃. CatSperδ-het currents are indistinguishable from previously published wt currents.

Figure 7. Inactivation of CatSperδ decreases the stability of CATSPER1 during spermatogenesis

(a) Reduction of CATSPER1 protein by CatSperδ deletion. Proteins solubilized from testis are immunoprecipitated with specific anti-CATSPERδ antibodies (α-δ786, IP, left) or anti-CATSPER1 (IP, right). CATSPERδ was pulled down from CatSperδ-het (δ+/−) and wt (+/+) testes but not from homozygous mutant testes (δ−/−) (IP, left, middle). CATSPERβ and CATSPER1 proteins are found in the same protein complex from CatSperδ-het and wt testes (IP, left, top, and bottom). Reciprocally, anti-CATSPER1 antibodies also co-immunoprecipitated CATSPERβ and CATSPERδ (IP, right, top and middle) from CatSperδ-het and wt testes. The amount of CATSPER1 was greatly reduced in the CatSperδ homozygous mutants (input, right) while input control (α tubulin) was unchanged (input, left). A small amount of CATSPER1 was recovered by anti-CATSPER1 immunoprecipitation from homozygous mutant testes (IP, right, bottom left lane). (b) In CatSperδ homozygous null mice, CATSPERβ was associated with CATSPERγ. (c) Absence of expression of CATSPER3 and CATSPER4 subunits in the sperm cells of CatSperδ homozygous null mice.