SH3 domain recognition of a proline-independent tyrosine-based RKxxYxxY motif in immune cell adaptor SKAP55

Abstract

Src-homology 3 (SH3) domains recognize PXXP core motif preceded or followed by positively charged residue(s). Whether SH3 domains recognize motifs other than proline-based sequences is unclear. In this study, we report SH3 domain binding to a novel proline-independent motif in immune cell adaptor SKAP55, which is comprised of two N-terminal lysine and arginine residues followed by two tyrosines (i.e. RKxxYxxY). Domains capable of binding to class I proline motifs bound to the motif, while the class II domains failed to bind. Peptide precipitation, alanine scanning and in vivo co-expression studies demonstrated a requirement for the arginine, lysine and tandem tyrosines of the motif. Two-dimensional NMR analysis of the peptide bound FYN-SH3 domain showed overlap with the binding site of a proline-rich peptide on the charged surface of the SH3 domain, while resonance signals for other residues (W119, W120, Y137) were not perturbed by the RKGDYASY based peptide. Expression of the RKGDYASY peptide potently inhibited TcRzeta/CD3-mediated NF-AT transcription in T cells. Our findings extend the repertoire of SH3 domain binding motifs to include a tyrosine-based motif and demonstrate a regulatory role for this motif in receptor signaling.

Fig. 1. FYB SH3 domain binding to the SK4 region of SKAP55. (A) The scheme shows mouse full-length FYB, sub-regions and GST–SH3 domain constructs. (Upper panel of gel) FYB SH3 domain binds full-length SKAP55 in COS-1 cells. COS-1 cells were transfected with full-length SKAP55 alone, or with the GRB-2 or various FYB SH3 domain(s) and assessed for complex formation. Glutathione beads were used to precipitate the GST fusion proteins. Lane 1, pEBG; lane 2, pEBG and SKAP55-HA; lane 3, SKAP55-HA; lane 4, GRB-2 N-terminal SH3 domain; lane 5, GRB-2 C-terminal SH3 domain; lane 6, FYB SH3(695–762); lane 7, FYB SH3(695–770); lane 8; FYB SH3(695–775); lane 9, GRB-2 N-terminal SH3 domain and SKAP55-HA; lane 10, GRB-2 C-terminal SH3 domain and SKAP55-HA; lane 11, FYB SH3(695–762) and SKAP55-HA; lane 12, FYB SH3(695–770) and SKAP55-HA; lane 13, FYB SH3(695–775) and SKAP55-HA. The precipitates were separated on a 10% SDS–polyacrylamide gel followed by anti-HA blotting. (Middle panel) Levels of SKAP55 protein expression. As in upper panel, except cell lysate was blotted with anti-HA. (Lower panel) Levels of GST fusion protein expression. As in upper panel, except that precipitates were blotted with anti-GST. (B) Schematic representation of SKAP55 and various sub-regions. Various DNA fragments encoding the SKAP55 were generated by PCR and inserted into the pSRα at the BamHI and KpnI sites with an in-frame HA tag. (Upper panel of gel) In vivo association of FYB SH3 and SKAP55 at SK4 region. COS-1 cells were co-transfected with different GST–SKAP55 subdomains and FYB SH3 domain and assessed for complex formation. Glutathione–Sepharose beads were used to precipitate the GST fusion proteins. Lane 1, pSRαHa plus FYB SH3; lane 2, pSRαHa-SKAP55(1–106) plus FYB SH3; lane 3, pSRαHa SKAP55(105–208) plus FYB SH3; lane 4, pSRαHa-SKAP55(204–299) plus FYB SH3; lane 5, pSRα Ha-SKAP55(300–369) plus FYB SH3. The precipitates were separated on a 10% SDS–polyacrylamide gel and immunoblotted with anti-HA monoclonal antibody. (Middle panel) Levels of FYB protein expression. As in upper panel except that the cell lysate was blotted with anti-HA. (Lower panel) Levels of GST fusion protein expression. As in upper panel except that precipitates were blotted with anti-GST. (C) (Above) In vitro association of FYB SH3 and SKAP55 at SK4 region. The different truncated GST–SKAP55 fusion proteins used in the far-western assay. Lane 1, pGEX-SKAP55(1–106); lane 2, pGEX-SKAP55(105–208); lane 3, pGEX-SKAP55(204–299); lane 4, pGEX-SKAP55(300–369); lane 5, pGEX-SK1(204–238); lane 6, pGEX-SK2(239–255); lane 7, pGEX-SK3(256–276); lane 8, pGEX-SK4(277–298). The different truncated GST–SKAP55 fusion proteins were separated on a 10% SDS–polyacrylamide gel, transferred to nitrocellulose membranes and probed with Flag-tagged FYB SH3 protein and immunoblotted with anti-Flag monoclonal antibody. The sequence of the motifs contained within the GST fusion proteins is as follows: SK1, ²⁰⁴QISFLLKDLSSLTIPYEEDEEEEEKEETYDDIDGF²³⁸; SK2, ²³⁹DSPSCGSQCRPTILPGS²⁵⁵; SK3, ²⁵⁶VGIKEPTEEKEEEDIYEVLPD²⁷⁶; SK4, ²⁷⁷EEHDLEEDESGTRRKGDYASYY²⁹⁸. (Lower panel) FYB SH3 domain recognizes the SK4 region of SKAP55. The various GST–SH2 and –SH3 fusion proteins used in the far-western assay. Lane 1, pGEX-SK4; lane 2, CRKL SH3; lane 3, LCK SH3; lane 4, p85 SH3; lane 5, Src SH3; lane 6, ABL SH2; lane 7, GRB-2 N SH2; lane 8, FYN, SH2; lane 9, LCK SH2; lane 10, PLCγ SH2-N.

Fig. 1. FYB SH3 domain binding to the SK4 region of SKAP55. (A) The scheme shows mouse full-length FYB, sub-regions and GST–SH3 domain constructs. (Upper panel of gel) FYB SH3 domain binds full-length SKAP55 in COS-1 cells. COS-1 cells were transfected with full-length SKAP55 alone, or with the GRB-2 or various FYB SH3 domain(s) and assessed for complex formation. Glutathione beads were used to precipitate the GST fusion proteins. Lane 1, pEBG; lane 2, pEBG and SKAP55-HA; lane 3, SKAP55-HA; lane 4, GRB-2 N-terminal SH3 domain; lane 5, GRB-2 C-terminal SH3 domain; lane 6, FYB SH3(695–762); lane 7, FYB SH3(695–770); lane 8; FYB SH3(695–775); lane 9, GRB-2 N-terminal SH3 domain and SKAP55-HA; lane 10, GRB-2 C-terminal SH3 domain and SKAP55-HA; lane 11, FYB SH3(695–762) and SKAP55-HA; lane 12, FYB SH3(695–770) and SKAP55-HA; lane 13, FYB SH3(695–775) and SKAP55-HA. The precipitates were separated on a 10% SDS–polyacrylamide gel followed by anti-HA blotting. (Middle panel) Levels of SKAP55 protein expression. As in upper panel, except cell lysate was blotted with anti-HA. (Lower panel) Levels of GST fusion protein expression. As in upper panel, except that precipitates were blotted with anti-GST. (B) Schematic representation of SKAP55 and various sub-regions. Various DNA fragments encoding the SKAP55 were generated by PCR and inserted into the pSRα at the BamHI and KpnI sites with an in-frame HA tag. (Upper panel of gel) In vivo association of FYB SH3 and SKAP55 at SK4 region. COS-1 cells were co-transfected with different GST–SKAP55 subdomains and FYB SH3 domain and assessed for complex formation. Glutathione–Sepharose beads were used to precipitate the GST fusion proteins. Lane 1, pSRαHa plus FYB SH3; lane 2, pSRαHa-SKAP55(1–106) plus FYB SH3; lane 3, pSRαHa SKAP55(105–208) plus FYB SH3; lane 4, pSRαHa-SKAP55(204–299) plus FYB SH3; lane 5, pSRα Ha-SKAP55(300–369) plus FYB SH3. The precipitates were separated on a 10% SDS–polyacrylamide gel and immunoblotted with anti-HA monoclonal antibody. (Middle panel) Levels of FYB protein expression. As in upper panel except that the cell lysate was blotted with anti-HA. (Lower panel) Levels of GST fusion protein expression. As in upper panel except that precipitates were blotted with anti-GST. (C) (Above) In vitro association of FYB SH3 and SKAP55 at SK4 region. The different truncated GST–SKAP55 fusion proteins used in the far-western assay. Lane 1, pGEX-SKAP55(1–106); lane 2, pGEX-SKAP55(105–208); lane 3, pGEX-SKAP55(204–299); lane 4, pGEX-SKAP55(300–369); lane 5, pGEX-SK1(204–238); lane 6, pGEX-SK2(239–255); lane 7, pGEX-SK3(256–276); lane 8, pGEX-SK4(277–298). The different truncated GST–SKAP55 fusion proteins were separated on a 10% SDS–polyacrylamide gel, transferred to nitrocellulose membranes and probed with Flag-tagged FYB SH3 protein and immunoblotted with anti-Flag monoclonal antibody. The sequence of the motifs contained within the GST fusion proteins is as follows: SK1, ²⁰⁴QISFLLKDLSSLTIPYEEDEEEEEKEETYDDIDGF²³⁸; SK2, ²³⁹DSPSCGSQCRPTILPGS²⁵⁵; SK3, ²⁵⁶VGIKEPTEEKEEEDIYEVLPD²⁷⁶; SK4, ²⁷⁷EEHDLEEDESGTRRKGDYASYY²⁹⁸. (Lower panel) FYB SH3 domain recognizes the SK4 region of SKAP55. The various GST–SH2 and –SH3 fusion proteins used in the far-western assay. Lane 1, pGEX-SK4; lane 2, CRKL SH3; lane 3, LCK SH3; lane 4, p85 SH3; lane 5, Src SH3; lane 6, ABL SH2; lane 7, GRB-2 N SH2; lane 8, FYN, SH2; lane 9, LCK SH2; lane 10, PLCγ SH2-N.

Fig. 2. Key residues are required for RKGDTASYY motif binding to the FYB SH3 domain. (A) Amino acid sequence of peptides corresponding to SK1–SK4. The SK4 region, carrying the RKGDYASY motif, is compared with a classic class I RxxPxxP. (B, upper panel) The SKAP55 peptide (TRRKGDYASYYQG; residues 288–300) used in precipitation studies. Various sequential mutants were synthesized in which alanine was used to substitute for amino acids. (Middle panel) AminoLink-Plus coupled to various peptides was used to precipitate the GST-tagged FYB SH3 domain from lysates from COS-1 cells. GST–FYB SH3 domain was detected by anti-GST immunoblotting. Lane 1, bovine serum albumin; lane 2, wild-type TRAKGDYASYYQG peptide; lane 3, TARKGDYASYYQG A-1 peptide; lane 4, TRAKGDYASYYQG A-2 peptide; lane 5, TRRAGDYASYYQG A-3 peptide;; lane 6, TRRKADYASYYQG A-4 peptide; lane 7, TRRKGDAASYYQG A-5 peptide; lane 8, TRRKGDYAAYYQG A-6 peptide; lane 9, TRRKGDYASAYQG A-7 peptide; lane 10, TRRKGDYASYAQG A-8 peptide; lane 11, TRRKGDYASYYAG A-9 peptide; lane 12, TRRKGDYASYYQA A-10 peptide. (Lower panel) Densitometric profile of SKAP55 in GST–FYB SH3 precipitates using a Scantjet laser scanner (Hewlett-Packard). (C) (Upper panel) Mutation of tyrosine residues Y294F/Y297F attenuates in vivo SKAP55 binding to the FYB SH3 domain. COS-1 cells were transfected with SKAP55, SKAP55(Y294F), SKAP55(Y297F) and FYB SH3 domain and assessed for complex formation. Glutathione–Sepharose beads were used to precipitate the GST-tagged FYB SH3 domain. Co-precipitated HA-tagged SKAP55 was detected by anti-HA immunoblotting. Lane 1, pEBG; lane 2, pEBG plus SKAP55; lane 3, SKAP55 plus FYB SH3; lane 4, SKAP55 (Y294F) plus FYB SH3; lane 5, SKAP55 (Y294F) plus FYB SH3 domain. The precipitates were separated on a 10% SDS–polyacrylamide gel and subjected to anti-HA blotting. (Middle panel) Levels of SKAP-HA protein expression. Cell lysates were separated by SDS–PAGE, transferred to nitrocellulose and subjected to blotting with anti-HA. (Lower panel) Levels of GST fusion protein expression. As in middle panel, except that lysates were blotted with anti-GST.

Fig. 3. Other SH3 domains capable of recognizing proline-based class I motifs also recognize tyrosine-based motifs. (A; upper panel) Co-expressed FYN and LCK SH3 domains also interact with HA-tagged SKAP55. COS-1 cells were transfected with SKAP55, GRB-2 SH3, FYB SH3, FYN SH3 and LCK SH3 in pEBG and assessed for complex formation. Glutathione beads were used to precipitate the GST fusion proteins, while co-precipitated HA-tagged SKAP55 was detected by anti-HA blotting. Lane 1, pEBG; lane 2, GRB-2 N-terminal SH3; lane 3, GRB-2 C-terminal SH3; lane 4, FYB SH3; lane 5, FYN SH3; lane 6, LCK SH3; lane 7, SKAP55-HA; lane 8, GRB-2 N-terminal SH3 and SKAP55-HA; lane 9, GRB-2 C-terminal SH3 and SKAP55-HA; lane 10, FYB SH3 and SKAP55-HA; lane 11, FYN SH3 and SKAP55-HA; lane 12, LCK SH3 and SKAP55-HA. The precipitates were separated on a 10% SDS–polyacrylamide gel, transferred to nitrocellulose and subjected to anti-HA blotting. (Lower panel) Expression of SKAP55. As in upper panel except that cell lysate was run on gel and subjected to anti-HA blotting. (B) In vitro binding of FYN SH3 and LCK SH3 with the SK and SK4 regions of SKAP55. SKAP55 constructs were expressed in T cells and subjected to protein–protein blotting with FYN SH3 (lanes 1–8) and LCK SH3 (lanes 9–16). Detection was conducted using anti-Flag antibody coupled to alkaline phosphatase. Lane 1, pGEX-SKAP55(1–106); lane 2, pGEX-SKAP55(105–208); lane 3, pGEX-SKAP55(204–299); lane 4, pGEX-SKAP55(300–369); lane 5, pGEX-SK1(204–238); lane 6, pGEX-SK2(239–255); lane 7, pGEX-SK3(256–276); lane 8, pGEX-SK4(277–298); lane 9, pGEX-SKAP55(1–106); lane 10, pGEX-SKAP55(105–208); lane 11, pGEX-SKAP55(204–299); lane 12, pGEX-SKAP55(300–369); lane 13, pGEX-SK1(204–238); lane 14, pGEX-SK2(239–255); lane 15, pGEX-SK3(256–276); lane 16, pGEX-SK4(277–298).

Fig. 4. Surface plasmon resonance confirms FYB and FYN SH3 domain binding to TRAKGDYASYYQG peptide. Binding of the TRAKGDYASYYQG peptide to immobilized FYB SH3 domain (upper panel), FYN SH3 domain (middle panel) and GRB2 N-terminal SH3 domain (lower panel). Surface plasmon resonance was conducted as described in Materials and methods. Peptide TTGVFVKMPPTE was used as an irrelevant control. Peptides were injected at 35, 70, 175 or 350 µM. Binding was measured in resonance units (RU), where 1 RU corresponds to the binding of 1 ng/mm² of flow cell surface.

Fig. 5. Two-dimensional NMR spectra of TRAKGDYASYYQG peptide binding to the FYN SH3 domain. (A) ¹⁵N–¹H NMR correlation spectra of the isolated and complexed FYN SH3 domain. ¹⁵N–¹H resonances that become significantly shifted upon addition of equimolar amounts of the SK4 peptide ligand are denoted by amino acid type and number within the full-length FYN kinase. The 10 residues that display the largest chemical shift changes upon peptide binding are located in the RT loop (Y93, R96, T97, E98, D100 and L101), the n-Src loop (S114, S115 and E116) and the β-strand (Y132). (B) GRASP (Nicholls et al., 1991) surface representations of the FYN SH3 domain (Morton, 1996). The 10 residues with the largest combined chemical shift index [as in (A)] are depicted in green and are labeled according to residue type and amino acid number within the full-length kinase. (C and D) Combined chemical shift change indices for individual backbone NH groups of the FYN SH3 domain at 0.3 mM upon addition of equimolar amounts of the peptide TRRKGDYASYYQG (C) or PPRPLPVAPGSSKT (D).

Fig. 5. Two-dimensional NMR spectra of TRAKGDYASYYQG peptide binding to the FYN SH3 domain. (A) ¹⁵N–¹H NMR correlation spectra of the isolated and complexed FYN SH3 domain. ¹⁵N–¹H resonances that become significantly shifted upon addition of equimolar amounts of the SK4 peptide ligand are denoted by amino acid type and number within the full-length FYN kinase. The 10 residues that display the largest chemical shift changes upon peptide binding are located in the RT loop (Y93, R96, T97, E98, D100 and L101), the n-Src loop (S114, S115 and E116) and the β-strand (Y132). (B) GRASP (Nicholls et al., 1991) surface representations of the FYN SH3 domain (Morton, 1996). The 10 residues with the largest combined chemical shift index [as in (A)] are depicted in green and are labeled according to residue type and amino acid number within the full-length kinase. (C and D) Combined chemical shift change indices for individual backbone NH groups of the FYN SH3 domain at 0.3 mM upon addition of equimolar amounts of the peptide TRRKGDYASYYQG (C) or PPRPLPVAPGSSKT (D).

Fig. 5. Two-dimensional NMR spectra of TRAKGDYASYYQG peptide binding to the FYN SH3 domain. (A) ¹⁵N–¹H NMR correlation spectra of the isolated and complexed FYN SH3 domain. ¹⁵N–¹H resonances that become significantly shifted upon addition of equimolar amounts of the SK4 peptide ligand are denoted by amino acid type and number within the full-length FYN kinase. The 10 residues that display the largest chemical shift changes upon peptide binding are located in the RT loop (Y93, R96, T97, E98, D100 and L101), the n-Src loop (S114, S115 and E116) and the β-strand (Y132). (B) GRASP (Nicholls et al., 1991) surface representations of the FYN SH3 domain (Morton, 1996). The 10 residues with the largest combined chemical shift index [as in (A)] are depicted in green and are labeled according to residue type and amino acid number within the full-length kinase. (C and D) Combined chemical shift change indices for individual backbone NH groups of the FYN SH3 domain at 0.3 mM upon addition of equimolar amounts of the peptide TRRKGDYASYYQG (C) or PPRPLPVAPGSSKT (D).

Fig. 6. SK4 peptide attentuates TcR up-regulation of IL-2 transcription. (A, left panel) Jurkat T cells were subjected to electroporation using 5 µg NF-AT of the IL-2 promoter luciferase reporter plasmid and 0.2 µg pRL-TK plasmid together with either 20 µg pEBG vector, pEBG-SK3 or pEBG-SK4 constructs. Cells were unstimulated (black bars) or exposed to rabbit anti-mouse (hatched bars), anti-CD3 (OKT3, 2 µg/ml, grey bars) or anti-CD3 (OKT3, 5 µg/ml, open white bars) for 6 h and assayed for luciferase activity. Luciferase units of the experimental vector were normalized to the level of the control vector in each sample. The data are representative of seven independent experiments. Results are the means and standard errors from three replicate experiments. (Right panel) Levels of GST fusion protein expression. Cell lysates from Jurkat T cells that had been transfected with GST–SK4 were subjected to immunoblotting with an anti-GST antibody. Lane 1, pEBG; lane 2, pEBG-SK3; lane 3, pEBG-SK4. (B, left panel) ConA-activated splenocytes 48 h after activation were subjected to electroporation using 5 µg NF-AT of the IL-2 promoter luciferase reporter plasmid and 0.2 µg pRL-TK plasmid together with either 20 µg pEBG vector, pEBG-SK1, pEBG-SK3 or pEBG-SK4 constructs. Cells were exposed to rabbit anti-mouse (black bars) or anti-CD3 (2C11, 2 µg/ml, hatched bars) for 6 h and assayed for luciferase activity. Luciferase activity was measured in spleen cells treated as described in Materials and methods. (Right panel) Levels of GST fusion protein expression. Cell lysates from spleen cells that had been transfected with GST–SK4 were subjected to immunoblotting with an anti-GST antibody. Lane 1, pEBG; lane 2, pEBG-SK1; lane 3, pEBG-SK3; lane 4, pEBG-SK4.