Explainable drug side effect prediction via biologically informed graph neural network
Huang, T.; Lin, K.-H.; Vieira, R. M.; Soares, J. C.; Jiang, X.; Kim, Y.
Show abstract
Early detection of potential side effects (SE) is a critical and challenging task for drug discovery and patient care. In-vitro or in-vivo approach to detect potential SEs is not scalable for many drug candidates during the preclinical stage. Recent advances in explainable machine learning may facilitate detecting potential SEs of new drugs before market release and elucidating the critical mechanism of biological actions. Here, we leverage multi-modal interactions among molecules to develop a biologically informed graph-based SE prediction model, called HHAN-DSI. HHAN-DSI predicted frequent and even uncommon SEs of the unseen drug with higher or comparable accuracy against benchmark methods. When applying HHAN-DSI to the central nervous system, the organs with the largest number of SEs, the model revealed diverse psychiatric medications previously unknown but probable SEs, together with the potential mechanisms of actions through a network of genes, biological functions, drugs, and SEs.
Matching journals
The top 9 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Interpretable Deep Learning for Improving Cancer Patient Survival Based on Personal Transcriptomes 95%
- Interpretable deep recommender system model for prediction of kinase inhibitor efficacy across cancer cell lines 94%
- Repurposing Non-pharmacological Interventions for Alzheimer’s Diseases through Link Prediction on Biomedical Literature 94%
Similar papers in this journal
Similar papers in this journal
- Genome-scale annotation of protein binding sites via language model and geometric deep learning 93%
- Pathway activation model for personalized prediction of drug synergy 93%
- MCGA: a multi-strategy conditional gene-based association framework integrating with isoform-level expression profiles reveals new susceptible and druggable candidate genes of schizophrenia 92%
Similar papers in this journal
Similar papers in this journal
- Algorithmic identification of treatment-emergent adverse events from clinical notes using large language models: a pilot study in inflammatory bowel disease 90%
- DrugWAS: Leveraging drug-wide association studies to facilitate drug repurposing for COVID-19 90%
- Pharmacogenetics at scale: An analysis of the UK Biobank 89%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.