A motif-based analysis of glycan array data to determine the specificities of glycan-binding proteins

Abstract

Glycan arrays have enabled detailed studies of the specificities of glycan-binding proteins. A challenge in the interpretation of glycan array data is to determine the specific features of glycan structures that are critical for binding. To address this challenge, we have developed a systematic method to interpret glycan array data using a motif-based analysis. Each glycan on a glycan array is classified according to its component sub-structures, or motifs. We analyze the binding of a given lectin to each glycan in terms of the motifs in order to identify the motifs that are selectively present in the glycans that are bound by the lectin. We compared two different methods to calculate the identification, termed intensity segregation and motif segregation, for the analysis of three well-characterized lectins with highly divergent behaviors. Both methods accurately identified the primary specificities as well as the weaker, secondary specificities of all three lectins. The complex binding behavior of wheat germ agglutinin was reduced to its simplified, independent specificities. We compiled the motif specificities of a wide variety of plant lectins, human lectins, and glycan-binding antibodies to uncover the relationships among the glycan-binding proteins and to provide a means to search for lectins with particular binding specificities. This approach should be valuable for rapidly analyzing and using glycan array data, for better describing and understanding glycan-binding specificities, and as a means to systematize and compare data from glycan arrays.

Fig. 1

Glycan array data. The plot represents the fluorescence intensities of individual glycans (ordered along the x-axis) on glycan arrays, after incubation with either VVL (top), ConA (middle), or WGA (bottom). Next to each graph, the top-ranking glycans are listed along with the numeric value of the corresponding fluorescence intensities.

Fig. 2

Motif-based analysis of glycan-binding specificities. (A) Classifying glycans by their component motifs. For each glycan, the presence or absence of each of 63 possible motifs was recorded with a “1” or “0”, respectively. (B) The intensity segregation method for identifying motif specificities. For each set of glycan array data, a threshold is set which segregates the glycans with high intensity from those with low intensity. The thresholds were based on the distributions of the fluorescence intensities in order to maximize segregation between low-intensity and high-intensity spots. For each motif, the percent presence is calculated in both the high-intensity glycans and the low-intensity glycans, and the difference between the two fractions is calculated. The example here shows the analysis of glycan-array data from the lectin VVL for three different motifs. (C) The motif segregation method. For each motif, the glycans are segregated according to the presence or absence of that motif. A statistical test compares the intensities or ranks of the glycans containing the motif to the glycans not containing the motif. The example here shows data from VVL, and P-values and z-scores based on the Mann–Whitney test.

Fig. 3

Comparisons of the intensity segregation and motif segregation methods. The scores for each motif derived from the intensity segregation method are plotted with respect to the scores from the motif segregation method for the lectins (A) VVL; (B) ConA; and (C) WGA. Each data point is a separate motif. The intensity segregation scores are the fractional differences calculated as shown in Figure 2B, and the motif segregation scores are the logged (base 10) Mann–Whitney P-values calculated as in Figure 2C. The P-values were multiplied by the sign of the z-score, so that negative values indicate motifs negatively associated with lectin binding.

Fig. 4

Associations between motifs that are enriched in high-intensity glycans. For the lectins VVL (A), ConA (B), and WGA (C), the top glycans were ordered by intensity, and the presence or absence of the top-ranking motifs (by motif segregation) is indicated for each glycan by yellow or black squares, respectively. For VVL, GalNAcα was placed as the second-ranking motif for clarity, although it was not ranked second by motif segregation. All other motifs are ordered from top to bottom by their motif segregation P-value. (D) Groupings among the glycans containing the top-ranking motifs. The data from (C) were clustered by similarity among both the glycans (columns) and the motifs (rows). The glycans group according to the dominant and independent presence of distinct motifs, as labeled above the cluster.

Fig. 5

Comparative analysis of the motif specificities of plant lectins. The data from 113 different glycan array incubations of plant lectins were analyzed using the motif segregation method, and the logged P-values (multiplied by the sign of the z-score) are clustered by similarity among both the motifs (columns) and the rows (lectins). Eighty-four unique lectins are presented, with some lectins run on multiple arrays under varying conditions. The P-values are indicated by the color bar. Clusters of motifs and lectins with high-significance scores are highlighted.