AI reveals insights into link between CD33 and cognitive impairment in Alzheimer's Disease

Abstract

Modeling biological mechanisms is a key for disease understanding and drug-target identification. However, formulating quantitative models in the field of Alzheimer's Disease is challenged by a lack of detailed knowledge of relevant biochemical processes. Additionally, fitting differential equation systems usually requires time resolved data and the possibility to perform intervention experiments, which is difficult in neurological disorders. This work addresses these challenges by employing the recently published Variational Autoencoder Modular Bayesian Networks (VAMBN) method, which we here trained on combined clinical and patient level gene expression data while incorporating a disease focused knowledge graph. Our approach, called iVAMBN, resulted in a quantitative model that allowed us to simulate a down-expression of the putative drug target CD33, including potential impact on cognitive impairment and brain pathophysiology. Experimental validation demonstrated a high overlap of molecular mechanism predicted to be altered by CD33 perturbation with cell line data. Altogether, our modeling approach may help to select promising drug targets.

Fig 1. The Integrative VAMBN (iVAMBN) approach.

The iVAMBN approach integrates gene expression data, clinical and patho-physiological (phenotype) measures (bottom left) into a joint quantitative, probabilistic graphical model. The method initially uses a knowledge graph (top left) for defining modules and for informing about potential connections between them. In a second step, a representation of each module using a Heterogeneous Incomplete Variational Autoencoder (HI-VAE) is learned. In a third step a modular Bayesian Network between autoencoded modules is learned while taking into account the information derived from the knowledge graph. Finally, the iVAMBN model is used to simulate gene perturbation (top right).

Fig 2. Network representation of iVAMBN model for ROSMAP data.

Shown are the learned (grey) and knowledge-derived (green) edges between gene modules (purple nodes), single gene modules (green) and CD33 and phenotype module (red). All these edges appeared with bootstrap frequency > 0.4. The newly inferred shortest path between CD33 and phenotype is displayed in orange. Other edges with bootstrap frequency > 0.4 have been removed for visualization purposes, except for those six edges which were trained with a bootstrap confidence of 1.

Fig 3. Quantitative relationships learned by iVAMBN.

Each correlation (R) is shown along with its confidence interval (CI) and multiple testing adjusted p-value. Left: Correlation of NAV3 with TGF-Beta subgraph module member MAVS. Right: Correlation of Low density lipoprotein subgraph module member SRSF10 with CREB1, a member of the Calpastatin-calpain subgraph module. Further plots can be found in S2 and S3 Figs.

Fig 4. External model validation.

Statistical significance −log₁₀(p) value of the marginal log-likelihood of the model when evaluated on the training data (ROSMAP) and external validation data (Mayo).

Fig 5. Module distributions in original and simulated CD33 down-expression.

The blue curve describes the original distribution, while the red one describes the CD33 down-expression scenario. CD33 down-expression simulation (left) results in lower scores of the prostaglandin pathway module (right).

Fig 6. Predicted changes on phenotype (MMSE and Braak stages) as a consequence of CD33 down-expression.

Distribution of MMSE and Braak stages in CD33 original (blue) and down-expressed (red) patients shows a significant improvement of scores and thus cognition as well as brain pathophysiology.