Related Experiment Video
Updated: Mar 27, 2026
05:47
Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
Published on: June 13, 2025
1.8K
Explainable drug side effect prediction in central neural system via biologically informed graph neural network
Tongtong Huang1, Ko-Hong Lin1, Rodrigo Machado-Vieira2
1McWilliams School of Biomedical Informatics, UTHealth, Houston, TX, US.
Translational Psychiatry
|March 25, 2026
Summary
Early detection of drug side effects (SEs) is crucial. A new AI model, HHAN-DSI, uses molecular interactions to predict SEs and their biological causes for novel therapeutics.
Area of Science:
- Pharmacology and Toxicology
- Computational Biology
- Artificial Intelligence in Medicine
Background:
- Early detection of drug side effects (SEs) is a significant challenge in drug development and patient care.
- Traditional in-vitro and in-vivo methods for SE detection are often impractical for scaling during preclinical drug development.
- Explainable artificial intelligence (XAI) presents opportunities for early SE detection and understanding underlying biological mechanisms of novel therapeutics.
Purpose of the Study:
- To introduce HHAN-DSI, a novel biologically informed graph-based model for early detection of potential SEs.
- To apply the model to the central nervous system (CNS) domain, which has the highest incidence of SEs.
- To demonstrate the model's capability in identifying novel SEs and elucidating their biological mechanisms.
Main Methods:
- Development of a biologically informed graph-based model named HHAN-DSI.
- Leveraging multimodal interactions among molecular entities within the model.
- Application of the model to analyze central nervous system (CNS) drug-induced SEs.
Main Results:
- HHAN-DSI successfully identified previously unrecognized SEs for various psychiatric drugs.
- The model elucidated the biological mechanisms underlying these SEs.
- A complex network of genes, biological functions, drugs, and SEs was delineated.
Conclusions:
- HHAN-DSI offers a promising approach for the early detection of potential drug side effects.
- The model provides insights into the biological mechanisms driving SEs, particularly within the CNS.
- This biologically informed AI model aids in understanding drug-induced SEs and their associated pathways.
Related Concept Videos
01:09Pharmacodynamic Models: Additive and Proportional Drug Effect Model
61
Drug response models describe how pharmacological agents interact with biological systems to produce measurable effects. Baseline responses are inherent physiological activities without a drug significantly influencing the observed pharmacological outcomes. Depending on the drug response model employed, these baseline responses may combine with the drug's effect in either an additive or proportional manner.Additive Drug Response ModelIn the additive model, the drug effect is independent of the...
61
01:26Neurochemical Transmission: Sites of Drug Action
3.9K
Neurochemical transmission, the conduction of electrical impulses between neurons mediated by neurotransmitters, plays a vital role in various physiological processes. Autonomic drugs exert their effects by modulating neurotransmission within the autonomic nervous system. For instance, drugs such as hemicholinium block the precursor uptake necessary for synthesizing acetylcholine, an essential autonomic neurotransmitter. Following synthesis, neurotransmitters are stored in vesicles. Metyrosine...
3.9K
01:29Drugs Affecting Neurotransmitter Synthesis
2.5K
Drugs affecting neurotransmitter synthesis can impact the adrenergic neuron and the synthesis of neurotransmitters. For example, α-methyltyrosine and carbidopa target specific enzymes involved in catecholamine synthesis. α-methyltyrosine inhibits the enzyme tyrosine hydroxylase, which converts tyrosine into dopamine. By blocking this enzyme, α-methyltyrosine reduces dopamine production and other catecholamines. Carbidopa, on the other hand, inhibits the enzyme dopa decarboxylase,...
2.5K
01:30Classification of Neurotransmitters
5.9K
Neurotransmitters play a crucial role in the communication between neurons in the autonomic nervous system. Neurons in the autonomic nervous system can be cholinergic or adrenergic depending on the neurotransmitters synthesized. Cholinergic neurons use acetylcholine as their primary neurotransmitter. This includes all the preganglionic fibers of the sympathetic and pre- and postganglionic fibers of the parasympathetic nervous systems. In addition, neurons of the somatic nervous system also use...
5.9K
01:14Pharmacodynamic Models: Link Model and Systems Pharmacodynamic Model
81
The link model is a fundamental pharmacokinetic-pharmacodynamic (PK–PD) approach to account for delayed drug responses when the observed effect does not immediately correlate with the drug's plasma concentration peak. This delay is mathematically addressed by introducing an effect compartment concentration, Ce, which is kinetically linked to the plasma concentration, Cp, via a first-order rate constant, ke0. The linkage allows for a more accurate prediction of drug effects over time. A...
81
02:26Protein Networks
4.7K
An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
4.7K