Partitioning of One-Carbon Units in Folate and Methionine Metabolism Is Essential for Neural Tube Closure

Abstract

Abnormal folate one-carbon metabolism (FOCM) is implicated in neural tube defects (NTDs), severe malformations of the nervous system. MTHFR mediates unidirectional transfer of methyl groups from the folate cycle to the methionine cycle and, therefore, represents a key nexus in partitioning one-carbon units between FOCM functional outputs. Methionine cycle inhibitors prevent neural tube closure in mouse embryos. Similarly, the inability to use glycine as a one-carbon donor to the folate cycle causes NTDs in glycine decarboxylase (Gldc)-deficient embryos. However, analysis of Mthfr-null mouse embryos shows that neither S-adenosylmethionine abundance nor neural tube closure depend on one-carbon units derived from embryonic or maternal folate cycles. Mthfr deletion or methionine treatment prevents NTDs in Gldc-null embryos by retention of one-carbon units within the folate cycle. Overall, neural tube closure depends on the activity of both the methionine and folate cycles, but transfer of one-carbon units between the cycles is not necessary.

Keywords: Gldc; Mthfr; eye; folic acid; glycine cleavage system; neural tube defects; non-ketotic hyperglycinemia; one-carbon metabolism; spina bifida.

Graphical abstract

Figure 1

Altered Abundance of Folates in Mthfr-Null Embryos (A) Summary diagram of folate 1C metabolism (enzymes are indicated in purple text). (B–E) LC-MS/MS profiling of folates in (B) post-natal brain, (C) post-natal liver, and embryos at E10.5 (D) and E12.5 (E) shows that the relative abundance of 5-methyl THF (CH₃THF) is significantly reduced in Mthfr^−/− (^∗p < 0.0001 compared with Mthfr^+/+). Conversely, the abundance of other folates was increased (^∗p < 0.01, ^∗∗p < 0.05; significant difference from wild-type, p < 0.05). Note that CH₂-THF may be under-represented because of conversion to THF during analysis (maximal 20% of CH₂-THF at pH 7 used). Number of samples, n = 3 per genotype for brain, liver, and E12.5. At E10.5, n = 4 Mthfr^+/+, 7 Mthfr^+/−, and 5 Mthfr^−/−. See also Figure S1 and Table S1.

Figure 2

Methionine Cycle Intermediates Are Differentially Affected by Mthfr Genotype in Post-natal Tissue and Embryos (A) The abundance of S-adenosylmethionine (SAM) was significantly lower in livers of Mthfr^−/− mice than in wild-types (^∗p < 0.05), and SAM showed a non-significant trend toward lower abundance in brains of Mthfr^−/− (p = 0.07). SAM abundance was not altered in Mthfr^−/− E12.5 embryos compared with littermates of other genotypes. (B and C) In contrast, S-adensylhomocysteine concentration (B, SAH) was elevated, and the SAM/SAH ratio (C) was reduced in Mthfr^−/− tissue and embryos compared with Mthfr^+/+ (^∗p < 0.01, significantly differs from Mthfr^+/+). n = 3 samples per genotype for each tissue. (D–F) The proportion of (D) 2-deoxycytosine, (E) 5-methyldeoxycytosine, and (F) 5-hydroxy-2-deoxycytosine did not differ with Mthfr genotype among embryos at E12.5 (individual samples and mean ± SEM are shown). See also Table S2.

Figure 3

Methionine Cycle Inhibitors Cause NTDs without Imposition of a Methyl Trap (A–C) Treatment in whole-embryo culture with ethionine (5 mM) or cycloleucine (15 mM) caused NTDs among embryos of all Mthfr genotypes (A). NTDs affected the cranial region (open midbrain-forebrain neural folds in cycloleucine-treated embryo; arrow in B), whereas closure was completed during the culture period in vehicle-treated controls (C). Scale bar represents 1 mm. (D) In Mthfr^+/+ embryos, ethionine treatment resulted in a significant increase in relative abundance of THF. Both ethionine and cycloleucine caused a decrease in relative abundance of 5-methyl THF compared with controls (^∗p < 0.01, ANOVA). (E) In cultured Mthfr^−/−embryos, abundance of folate intermediates was not significantly affected by ethionine or cycloleucine, and, as in non-cultured embryos, the relative abundance of THF and 5-methyl THF differed from Mthfr^+/+ embryos (compare with D, p < 0.001, two-way ANOVA). In (D) and (E), n = 3–5 samples per genotype for each treatment

Figure 4

Loss of Function of the GCS Causes Neural Tube Defects (A–E) Cranial neural tube closure is complete in a Gldc^+/+ embryo at E10.5 (A), whereas, in Gldc^GT2/GT2 embryos (B–E), the neural folds remain open (region between arrows) in the mid-hindbrain (B), fore-hindbrain (C), or throughout the entire mid-hindbrain and spinal region (craniorachischisis [Crn], D and E). (F–H) At later stages (F–H, E15.5), failed closure in the brain, low spine, or entire brain and spine leads to the typical appearance of exencephaly (Ex, F and G), spina bifida (SB, G), and Crn (H), respectively (scale bars represent 1 mm). (I–K) Among litters examined at E16.5–18.5, unilateral (J and J’) or bilateral (K and K’) eye defects were frequently observed among Gldc mutant fetuses but not in the wild-type (I and I’). (L) Maternal formate supplementation prevents NTDs in Gldc^GT2/GT2 embryos (n = 10 untreated, 9 formate-treated; ^∗p < 0.02, Fisher’s exact test). (M) Frequency of NTDs among litters from Gldc^GT2/+ intercrosses (n = 38 litters analyzed). Data for eye defects are included for a subset of litters analyzed at E14.5–16.5. See also Table S3.

Figure 5

Glycine Is a 1C Donor in Neurulation-Stage Embryos (A) Labeling with [1,2-¹³C] glycine was performed in whole-embryo culture with the yolk sac intact until E10.5 (typical stage of embryos after culture is shown; the arrow indicates cranial NTD in a Gldc^GT1/GT2 embryo). (B) The ion abundance of labeled glycine was elevated in Gldc-null embryos compared with wild-types (n = 5 embryos per genotype). (C–E) Fractional incorporation of labeled glycine was approximately 10% of total (C). Glycine was incorporated intact into serine (C) and purines (D and E), in which it contributes C4 and C5. In wild-type embryos, M+1 labeling of serine and purines (at C2 or C8) was also detected, implying GCS-mediated cleavage of glycine to generate 5,10-methylene THF and transfer of the 1C unit (indicated in red) via formate to formyl-THF in the cytoplasm (E). No M+1 or M+3 labeling of serine or purines was detected in Gldc-null embryos.

Figure 6

Prevention of Gldc-Associated NTDs by Mthfr Loss of Function (A) The frequency of NTDs among Gldc homozygous mutants is significantly affected by Mthfr genotype (different from Mthfr^+/+, ^∗p < 0.05 Fisher’s exact test). (B) Among embryos carrying loss-of-function alleles of Gldc and Mthfr (n = 4–7 samples per genotype at E11.5), we observed significant variation between genotypes in the relative abundance of each folate (p < 0001, ANOVA; Holm-Sidak pairwise comparison: ^∗∗ indicates difference to all other genotypes, ^∗ bars do not differ from each other but significantly differ from all other genotypes; # indicates significant difference with Gldc genotype in Mthfr^+/+ embryos). (C) Abundance of SAH was significantly increased and the SAM/SAH ratio decreased in all Mthfr^−/−embryos compared with other Mthfr genotypes, irrespective of Gldc genotype (^∗p < 0.01, ANOVA).

Figure 7

Methionine Supplementation of Gldc-Deficient Embryos Is Associated with Normalization of the Folate Profile and Prevention of NTDs (A) Compared with controls (n = 20 litters), maternal supplementation with methionine from E7.5 (n = 12 litters) resulted in a lower frequency of NTDs among homozygous mutant embryos (significant difference from controls; ^∗p < 0.05, Fisher’s exact test). (B) Folate profile of embryos collected at E10.5 following maternal methionine treatment (n = 3–6 embryos per group). Significant differences in relative abundance between genotypes and/or treatment were noted for THF, 5-methyl THF, and formyl THF (p < 0.001, two-way ANOVA; ^∗, significant difference from other genotypes within treatment group; ^∗∗, significant effect of methionine treatment within the same genotype).