Identification and genetic validation of drug-comorbidity interactions in type 2 diabetes using data-driven disease trajectory analysis
Ichikawa, O.; Glicksberg, B. S.; Minsky, N.; Lee, H.-C.; Li, S. D.; Chen, R.; LI, L.; Dudley, J.
Show abstract
Given various risk profiles, manifestations, comorbidities, and outcomes for individuals with Type 2 diabetes mellitus (T2D), a one-size-fits-all approach towards treatment and management is inadequate, and there is a clear need for personalized medications to reduce rates of complications and comorbidities. Here, we leveraged comprehensive Electronic Medical Records (EMR) to identify associations between T2D comorbidities and medications and evaluated their biological determinants using EMR-linked genetic information. We discovered clinically novel associations supported by the previous laboratory studies; e.g. 5-hydroxytryptamine 3 receptor antagonists, ondansetron and granisetron, are protective against cognitive disorders, and clopidogrel is protective against retinopathy. Furthermore, potentially novel associations were validated by genetic analysis; e.g. association between gabapentin and cognitive disorders was supported via variants of its target genes, GRIN1 and CACNA2D2. These results of the current study open the door for optimizing treatment combinations to mitigate risks and for individualizing therapy based on T2D subtype risk profiles.
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Metabolome-wide Mendelian randomization characterizes heterogeneous and shared causal effects of metabolites on human health 95%
- Identification of plasma proteomic markers underlying polygenic risk of type 2 diabetes and related comorbidities 95%
- Metabolic and proteomic signatures of type 2 diabetes subtypes in an Arab population 95%
Similar papers in this journal
- Complex patterns of multimorbidity associated with severe COVID-19 and Long COVID 95%
- The Interpretable Multimodal Machine Learning (IMML) framework reveals pathological signatures of distal sensorimotor polyneuropathy 94%
- Sex-specific transcriptome similarity networks elucidate comorbidity relationships 94%
Similar papers in this journal
- Multi-ancestry omic Mendelian randomization revealing putative drug targets of COVID-19 severity 94%
- A systematic analysis of the contribution of genetics to multimorbidity and comparisons with primary care data 93%
- Machine learning guided association of adverse drug reactions with in vitro target-based pharmacology 92%
Similar papers in this journal
- Novel protein-altering variants associated with serum apolipoprotein and lipid levels 92%
- Longitudinal analysis of genetic and environmental interplay in human metabolic profiles and the implication for metabolic health 92%
- Type 2 Diabetes risk alleles in Peptidyl-glycine Alpha-amidating Monooxygenase influence GLP-1 levels and response to GLP-1 Receptor Agonists 92%
"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.