A substantial number of therapeutic drugs for Alzheimer's disease (AD) have failed in late-stage trials, highlighting the translational disconnect with pathology-based animal models. To bridge the gap between preclinical animal models and clinical outcomes, we implemented a conductance-based computational model of cortical circuitry to simulate working memory as a measure for cognitive function. The model was initially calibrated using preclinical data on receptor pharmacology of catecholamine and cholinergic neurotransmitters. The pathology of AD was subsequently implemented as synaptic and neuronal loss and a decrease in cholinergic tone. The model was then calibrated with clinical ADAS-Cog results on acetylcholinesterase inhibitors and 5-HT6 antagonists to improve the model's prediction of clinical outcomes. As an independent validation, we reproduced clinical data for APOE genotypes showing that the ApoE4 genotype reduces the network performance much more in mild cognitive impairment conditions than at later stages of Alzheimer's disease pathology. We use the model to demonstrate differential effect of memantine, an NMDA subunit selective weak inhibitor, in early and late Alzheimer's disease pathology, and show that inhibition of the NMDA receptor NR2C/NR2D subunits located on inhibitory interneurons compensates for the greater excitatory decline observed with pathology. This quantitative systems pharmacology approach is shown to be complementary to traditional animal models, with the potential to assess potential off-target effects, the consequences of pharmacologically active human metabolites, the effect of comedications, and the impact of a small number of well described genotypes.