Background The amyloid precursor protein (APP) is a transmembrane glycoprotein that undergoes alternative proteolytic processing. Its processing through the amyloidogenic pathway originates a large sAPP beta ectodomain fragment and the beta-amyloid peptide, while non-amyloidogenic processing generates sAPP alpha and shorter non-fibrillar fragments. Hence, measuring sAPP alpha and sAPP beta has been proposed as a means to identify imbalances between the amyloidogenic/non-amyloidogenic pathways in the brain of Alzheimer's disease (AD) patients. However, to date, no consistent changes in these proteolytic fragments have been identified in either the brain or cerebrospinal fluid of AD individuals. Methods In frontal cortex homogenates from AD patients (n = 7) and non-demented controls (NDC;n = 7), the expression of total APP mRNA and that of the APP isoforms generated by alternative splicing, APP695 and APP containing the Kunitz protease inhibitor (KPI), was analyzed byqRT-PCR using TaqMan and SYBR Green probes. The balance between the amyloidogenic/non-amyloidogenic pathways was examined in western blots estimating the sAPP alpha and sAPP beta fragments and their membrane-tethered C-terminal fragments CTF alpha and CTF beta. CHO-PS70 cells, stably over-expressing wild-type human APP, served to evaluate whether A beta 42 peptide treatment results in altered APP glycosylation. We determined the glycosylation pattern of sAPP alpha and sAPP beta in brain extracts and CHO-PS70 culture media by lectin-binding assays. Results In the cortex of AD patients, we detected an increase in total APP mRNA relative to the controls, due to an increase in both the APP695 and APP-KPI variants. However, the sAPP alpha or sAPP beta protein levels remained unchanged, as did those of CTF alpha and CTF beta. We studied the glycosylation of the brain sAPP alpha and sAPP beta using lectins and pan-specific antibodies to discriminate between the fragments originated from neuronal APP695 and glial/KPI variants. Lectin binding identified differences in the glycosylation of sAPP beta species derived from the APP695 and APP-KPI variants, probably reflecting their distinct cellular origin. Moreover, the lectin-binding pattern differed in the sAPP alpha and sAPP beta originated from all the variants. Finally, when the lectin-binding pattern was compared between AD and NDC groups, significant differences were evident in sAPP alpha glycosylation. Lectin binding of the soluble sAPP alpha and sAPP beta from CHO-PS70 cells were also altered in cells treated with the A beta peptide. Conclusion Our analysis of the lectin binding to sAPP alpha and sAPP beta suggests that glycosylation dictates the proteolytic pathway for APP processing. Differences between the demented and controls indicate that changes in glycosylation may influence the generation of the different APP fragments and, consequently, the pathological progression of AD.