The human A33 antigen is a transmembrane glycoprotein and a novel member of the immunoglobulin superfamily

Abstract

The mAb A33 detects a membrane antigen that is expressed in normal human colonic and small bowel epithelium and > 95% of human colon cancers. It is absent from most other human tissues and tumor types. The murine A33 mAb has been shown to target colon cancer in clinical trials, and the therapeutic potential of a humanized antibody is currently being evaluated. Using detergent extracts of the human colon carcinoma cell lines LIM1215 and SW1222, in which the antigen is highly expressed, the molecule was purified, yielding a 43-kDa protein. The N-terminal sequence was determined and further internal peptide sequence obtained following enzymatic cleavage. Degenerate primers were used in PCRs to produce a probe to screen a LIM1215 cDNA library, yielding clones that enabled us to deduce the complete amino acid sequence of the A33 antigen and express the protein. The available data bases have been searched and reveal no overall sequence similarities with known proteins. Based on a hydrophilicity plot, the A33 protein has three distinct structural domains: an extracellular region of 213 amino acids (which, by sequence alignment of conserved residues, contains two putative immunoglobulin-like domains), a single hydrophobic transmembrane domain, and a highly polar intracellular tail containing four consecutive cysteine residues. These data indicate that the A33 antigen is a novel cell surface receptor or cell adhesion molecule in the immunoglobulin superfamily.

Figure 1

cDNA sequence and deduced amino acid sequence of the longest cDNA clone (clone 18; 2.8 kb) encoding the human A33 antigen. The longest open reading frame, encompassing nucleotides 345-1301, contains the known N-terminal sequence of the native A33 antigen and predicts a protein of 319 amino acids. The stop codon at 1302–1304 is boxed, and the amino acid sequences of the internal peptides identified by digestion of the native molecule are shown (shaded areas). A putative signal sequence (bold underline), three potential N-linked glycosylation sites (overline), and a transmembrane domain (second bold underline) are indicated. Adjacent to the transmembrane domain, four consecutive cysteine residues are observed. The spans of the two putative Ig-like domains are enclosed by square brackets with the specific residues conserved in Ig superfamily members shown in circles. Other features of the DNA sequence include a tandem repeat of 25 bp in the 5′ untranslated region (bold overline) and a polyadenylylation signal (AATAAA) 11 bp upstream from the poly(A) tail. The asterisk above the C at position 294 denotes the fact that a C was found in this position in 2 out of 5 independent clones sequenced (including clone 18) and an A in the 3 other clones.

Figure 2

Kyte–Doolittle hydrophilicity plot of the deduced amino acid sequence of the A33 antigen. Several structural features are indicated: the presence of an N-terminal hydrophobic region likely to correspond to a signal sequence, a more distal highly hydrophobic sequence consistent with the presence of a single-span transmembrane domain, and a highly polar C-terminal region consistent with an intracellular location for this part of the molecule.

Figure 3

Expression of recombinant A33 antigen by transfected Cos cells. Cos cells were transfected either with the parental vector, pcDNA3, or with pcDNA3 into which a 2.6-kb A33 antigen cDNA had been subcloned. Cells were harvested in this experiment 5 days after transfection and subjected to Western blot analysis (A) and flow cytometry (B). (A) Transfected cells were solubilized in Triton X-100 and electrophoresed into SDS/polyacrylamide gels without reduction and processed for Western blot analysis as described. The signal obtained with Cos cells transfected with pcDNA3 containing A33 antigen cDNA (lane 1) corresponds to approximately the same M_r (43,000) as the signal obtained with LIM1215 cells expressing high endogenous levels of A33 antigen (lane 3). Cells transfected with the parental vector gave no signal (lane 2). The positions of blue prestained standards (lane M) (NOVEX, San Diego) are indicated on the right. (B) FACScan profiles of control and A33 antigen-expressing Cos cells. The profile obtained with A33 antigen-expressing Cos cells (shown in bold) has been superimposed on the profile obtained with Cos cells transfected with pcDNA3 alone to show the shift to the right in fluorescence intensity of cells expressing A33 antigen.

Figure 4

Northern blot analysis of A33 antigen mRNA, indicated by arrows on the left, in (A) cell lines derived from human colorectal carcinoma and (B) normal and diseased human colonic tissue. (A) The six colorectal carcinoma cell lines had been previously analyzed for A33 antigen expression using immunocytochemistry and flow cytometry (unpublished data), and half (LIM1215, LIM1863, and LIM1899) were found to be positive. The remaining half (LIM2099, LIM2405, and LIM2537) were negative. The pattern of A33 antigen mRNA expression shown is consistent with the protein expression data. (B) A33 antigen mRNA expression in samples of normal and diseased human colorectal tissue obtained from patients during surgical resection. The samples are in pairs except for lanes 1–3, which contain RNA extracted from the normal colon, adenomatous polyp, and tumor of the same patient, respectively. Thus, lanes 1, 4, 6, and 8 contain RNA extracted from the crypts of normal colonic mucosa, and the strong hybridization signals correspond to relatively high expression of A33 antigen compared with that in the corresponding tumor preparations (lanes 3, 5, and 7) and the RNA extracted from the large polyp (lane 2), which all produced weaker A33 antigen mRNA signals. Lane 9 contains RNA extracted from the inflamed colonic crypts of a patient with Crohn disease, which produces an A33 antigen signal similar to that of its normal counterpart (lane 8). Lane 10 contains RNA from human peripheral blood buffy coat cells, and lane 11, RNA from LIM1215 cells (positive control). For both blots, the lower panel shows the pattern obtained with a γ-³²P-labeled oligonucleotide probe designed to hybridize to 18 S rRNA. Arrows on the right indicate the positions of RNA markers.