SOS1 mutations in Noonan syndrome: molecular spectrum, structural insights on pathogenic effects, and genotype-phenotype correlations

Abstract

Noonan syndrome (NS) is among the most common nonchromosomal disorders affecting development and growth. NS is caused by aberrant RAS-MAPK signaling and is genetically heterogeneous, which explains, in part, the marked clinical variability documented for this Mendelian trait. Recently, we and others identified SOS1 as a major gene underlying NS. Here, we explored further the spectrum of SOS1 mutations and their associated phenotypic features. Mutation scanning of the entire SOS1 coding sequence allowed the identification of 33 different variants deemed to be of pathological significance, including 16 novel missense changes and in-frame indels. Various mutation clusters destabilizing or altering orientation of regions of the protein predicted to contribute structurally to the maintenance of autoinhibition were identified. Two previously unappreciated clusters predicted to enhance SOS1's recruitment to the plasma membrane, thus promoting a spatial reorientation of domains contributing to inhibition, were also recognized. Genotype-phenotype analysis confirmed our previous observations, establishing a high frequency of ectodermal anomalies and a low prevalence of cognitive impairment and reduced growth. Finally, mutation analysis performed on cohorts of individuals with nonsyndromic pulmonic stenosis, atrial septal defects, and ventricular septal defects excluded a major contribution of germline SOS1 lesions to the isolated occurrence of these cardiac anomalies.

Figure 1

SOS1 domain structure and location of residues altered in Noonan syndrome. A: Schematic structure of SOS1 and variants identified in the present study. SOS1 protein domains are indicated (DH, DBL homology domain; PH, pleckstrin homology domain; REM, RAS exchanger motif; CDC25, CDC25 domain). Disease-causing mutations and probably pathogenetic/unclassified variants are shown above and below the cartoon, respectively. Residues affected by class 1 mutations/variants are shown in red, while those affected by class 2 and class 3 changes are shown in yellow and green, respectively. Residues affected by substitutions with unpredictable effect on SOS1 function are shown in black. Novel amino acid substitutions are underlined. B: Location of affected residues in SOS1 represented in its inactive conformation, according to the crystal structure of the protein truncated at the C-terminus (residues 1–1049) (PDB ID: 3KSY) [Guerasko et al., 2010]. Cα ribbon trace of the HF (sky blue), DH (sandy brown), PH (plum), REM (dark green), and CDC25 (blue) domains, and the helical linker connecting the PH and REM domains (gray). Mutated residues are indicated with their side chains as thick lines and colored as reported above. Residue Asp309 (uncharacterized mutation p.Asp309Tyr) is shown in purple. Affected residues are listed in Supp. Table S2.

Figure 2

Detailed analysis of structural perturbations resulting from Noonan syndrome-causing amino acid substitutions. A: Class 1 mutations affecting residues at the distal RAS binding site. The cartoon includes the DH (sandy brown) and REM (dark green) domains only. Affected residues are shown in red. The autoinhibitory binding network includes the hydrophobic interaction between residues Met269 (DH) and Trp729 (REM), both mutated in NS, and between the former and Leu687 (green). Leu690, Val697, Ile718, and Ile736 are hydrophobic residues (cyan) that interact with Ile733 (REM). Mutated residues Thr266 (DH) and Lys728 (REM) face each other. Substitution of Thr266 by lysine would create an electrostatic repulsion with Lys728. The unclassified variant Leu252 contributes to a hydrophobic core with residues Tyr215, Leu219, Ile249, Tyr295, and Tyr298 (purple), whose disruption is expected to perturb considerably the DH domain surface interacting with the REM domain. B: Class 1B mutations. The cartoon includes the HF (sky blue), DH (sandy brown), and PH (magenta) domains and the PH-REM helical linker (gray). Relevant affected residues are shown in red. Met422 and Ile437 (PH) participate in a hydrophobic bonding network with residues Ile425, Phe464, and Leu467 (cyan, see also the inset). Hydrophobic interaction between Tyr337 and Met538 (green) contributes to the binding network stabilizing the interaction between the PH and DH domains. Other interdomain interactions involve Leu550 and residues of the DH and PH domains, Val225, Leu221, Phe226, and Tyr546 (gray), Arg552, and residues of the HF domain, Asp140 and Asp169 (orange), Ser548 and Asp169, and Lys170, and residues of the PH domain, Arg497 and Lys498 (blue). Phe78 participates to the hydrophobic interaction involving residues of the HF domain core located close to the PH domain and PH-REM linker (Leu55, Leu59, Val74, Val133, and Ile137; purple). C: Class 1 mutations affecting the REM domain region (dark green) interacting with the CDC25 domain (blue). The helical hairpin (residues 929–978) implicated in the conformational switch (green) and residues interacting with RAS at the active site (light blue) are shown. Phe623 hydrophobically interact with Ile 601, Leu613, Phe627, Ile956, and Phe958 (cyan). The hydrogen bond between Tyr702 and Ser802 (orange) is also shown. D: Class 2 mutations affecting the HF domain. The left panel shows the HF (light blue), DH (sandy brown), and PH (plum) domains. The HF surface colored according to the electrostatic potential (from red at −3kT/e to blue at +3kT/e) is also shown (right panel). Mutations affect solvent exposed residues (yellow side chains, left panel; yellow circles, right panel) located in a region that has a positive electrostatic potential (right panel), and has been implicated in membrane binding. E: Class 2 mutations affecting the PH domain. The left panel includes the PH domain (plum) only. The PH surface, colored according to the electrostatic potential (from red at −5kT/e to blue at +5kT/e) is also shown (left panel). Affected residues are shown in yellow (side chains, left panel; circles, right panel). Residues that are predicted to bind to PIP₂ [Zheng et al., 1997], Lys456, Arg459, Lys472, and Arg489, are shown in green (circled in the right panel), whereas the PA-interacting region (residues 472–483) [Zhao et al., 2007] is shown in orange (circled in the right panel). F: Class 3 mutations. The cartoon includes the REM (dark green) and CDC25 (blue) domains only (residues 567–1049). Affected residues are shown in green. Residues implicated in RAS binding at the catalytic site are shown (light blue). Glu846 and Pro894 are placed distally from the active site and regions implicated in the conformational rearrangement of the CDC25 domain. Glu846 electrostatically interacts with Arg1026 and Lys 1029 (orange).

Figure 3

Facial dysmorphism and other features of subjects with Noonan syndrome heterozygous for mutations in the SOS1 gene. SOS1 mutation-positive subjects generally exhibit typical facial features, including macrocephaly, hypertelorism, ptosis, downslanting palpebral fissures, sparse eyebrows with keratosis pylaris, a short and broad nose with upturned tip, low-set and posteriorly angulated ears, and high forehead commonly associated with bitemporal narrowing and prominent supraorbital ridges. Curly hair is present in most of the patients. Other common features include pectus anomalies (NS10, NS19, NS37), short and/or webbed neck (NS6, NS10, NS19, NS22, NS38), and cubitus valgus (NS37). Keloid scars (NS16), recurrent hemorrhages (NS18), and deep plantar creases (NS38) also occur in these subjects. In some infants, the face is suggestive of cardiofaciocutaneous syndrome due to the coarseness of features (NS39).