Disruption of the kringle 1 domain of prothrombin leads to late onset mortality in zebrafish

Abstract

The ability to prevent blood loss in response to injury is a conserved function of all vertebrates. Complete deficiency of the central clotting enzyme prothrombin has never been observed in humans and is incompatible with postnatal life in mice, thus limiting the ability to study its role in vivo. Zebrafish are able to tolerate severe hemostatic deficiencies that are lethal in mammals. We have generated a targeted genetic deletion in the kringle 1 domain of zebrafish prothrombin. Homozygous mutant embryos develop normally into the mid-juvenile stage but demonstrate complete mortality by 2 months of age primarily due to internal hemorrhage. Mutants are unable to form occlusive venous and arterial thrombi in response to endothelial injury, a defect that was phenocopied using direct oral anticoagulants. Human prothrombin engineered with the equivalent mutation exhibits a severe reduction in secretion, thrombin generation, and fibrinogen cleavage. Together, these data demonstrate the conserved function of thrombin in zebrafish and provide insight into the role of kringle 1 in prothrombin maturation and activity. Understanding how zebrafish are able to develop normally and survive into early adulthood without thrombin activity will provide important insight into its pleiotropic functions as well as the management of patients with bleeding disorders.

Figure 1

Peptide sequence alignment shows strong conservation of prothrombin across a broad range of species. Sequences shown include the conserved domains. Numbering begins at the first residue after the propetide according to the prothrombin numbering scheme. Sequences are shaded to indicate degree of conservation. Green colored residues indicate conserved cysteines. Red colored residues represent amino acids altered by mutagenesis (Δ15; C138A) with the affected paired cysteines highlighted in yellow. Numbers above alignment indicate paired cysteines in human prothrombin.

Figure 2

Direct oral anticoagulants prevent occlusive thrombus formation in zebrafish. 5 dpf larvae were exposed to chemical inhibitors of thrombin (dabigatran) and FXa (apixaban, rivaroxaban) for 24 hours. This resulted in the inability to form occlusive venous thrombi at 6 dpf in wild-type larvae following laser-mediated endothelial injury.

Figure 3

Genome editing creates a 14 bp genomic deletion with a resulting decrease in mRNA expression. (A) Alignment of Sanger sequencing with the chromosome 7 genomic region showed an overall 17 bp genomic deletion replaced with a 3 bp insertion; outlined in red, resulting in a net 14 bp deletion. (B) in situ hybridization demonstrated reduction of transcript at 72 and 120 hours post fertilization in homozygous mutants compared to control siblings. Spatial regulation remained intact with expression restricted primarily to the liver. (C) qPCR data of f2 expression reveals significant decrease of 45% in the homozygous mutant embryos. (D) Semi-quantitative RT-PCR of embryos shows a mutant band ~30 bp smaller than expected (later shown to be a 45 bp deletion, Fig. 4). Quantitation of the bands reveal that the mutant band is only 26% of the total in heterozygotes.

Figure 4

Single molecule real time sequencing of f2^+/Δ14 mRNA demonstrates altered splicing in f2 following a deletion in exon 6. (top) Sanger sequencing of f2^+/+ and f2 ^Δ14/Δ14 cDNA reveals a canonical splice donor but alternative splice acceptor (red dashed lines indicate splice junctions). Allelic SNPs in exon 7 allowed the sorting of transcripts by their genomic allele in mRNA extracted from heterozygotes. Wild-type transcripts (middle) solely demonstrated canonical splicing. Mutant transcripts (bottom) primarily exhibited alternative splicing to a cryptic splice site with a resulting 45 bp inframe deletion, as well as low frequency canonical splicing with a resulting 14 bp out of frame deletion. gDNA, genomic DNA.

Figure 5

Loss of prothrombin results in early lethality due to hemorrhage. (A) Survival curve demonstrating significant mortality by 2 months of age in f2^−/− siblings, log-rank (Mantel-Cox) analysis. (B) Examples of grossly visible intracranial, intramuscular, and fin bleeds (arrows). (C) Histological sections of wild-type and f2^−/− siblings demonstrated microscopic bleeds in the brain, jaw, heart, muscle, and fins. Arrows point to pools of erythrocytes and unaffected comparable tissue in the control.

Figure 6

Loss of thrombin activity results in defects in secondary hemostasis. (A) Larvae were immobilized in agarose, subjected to laser-mediated endothelial injury (green arrow) of the venous (PCV, blue) or arterial (dorsal aorta, red) circulation, and followed for 2 minutes by a blinded observer. (B) Genetic ablation of f2 resulted in the inability to form induced PCV thrombi at 3 dpf and was not influenced by inhibiting fibrinolysis (ɛ-aminocaproic acid treatment, blue). (C) Overexpression of human F2 cDNA (blue) rescued the ability to form thrombi in the PCV at 3 dpf. (D) Homozygous mutant larvae demonstrated a significant impairment in arterial thrombus formation at 5 and 6 dpf without any changes in the time to initial thrombocyte attachment (E). (F) The number of thrombocytes attached to the site of injury in 2 minutes was significantly increased at 6 dpf in f2 homozygous mutants. Statistical significance assessed by Mann-Whitney U testing.

Figure 7

Expression and activation of prothrombin variants and resulting activity of thrombin upon activation. (A) Measurement of prothrombin in the cell media by ELISA demonstrated that expression of prothrombin variants in HEK293T cells resulted in reduced secretion levels that were indistinguishable from control and (B) corresponding measurement of prothrombin in the cell lysate demonstrated decreased biosynthesis. (C) Rates of prothrombin activation by prothrombinase measured using DAPA. Once prothrombin variants were fully activated by prothrombinase, their ability to cleave synthetic substrate S-2238 (D) or fibrinogen (E) were monitored, with significant differences in the latter, but not the former. For both S-2238 and fibrinogen, the rate was calculated during the initial reaction phase when the substrate is non-limiting and the conditions are presumed to be steady-state. Rate was then normalized to enzyme concentration. (F) Clotting profile between wild-type and C138A/Δ15 demonstrated delayed clot initiation and altered turbidity. (G) The rates of clot formation were determined from the clotting profile and reduced in the mutant.