A machine-learning study identified drug-repurposing candidates for ALS
Original source
Identifying candidate therapeutic targets in amyotrophic lateral sclerosis through a transcriptome-wide machine-learning consensus approach for drug repurposing. (opens in a new tab)Compass summarised this from the study's abstract.
Study details
- Studied in
- Human
Population inferred from the title and abstract by Compass.
Researchers analyzed gene-activity data from motor-cortex tissue and blood to identify recurring ALS-associated patterns. Pathway analysis highlighted glial and immune regulation, proteostasis, vesicle trafficking, stress signaling and RNA-related processes. Deferoxamine and disulfiram had the clearest reversal-compatible profiles in motor cortex, while other compounds showed signals in blood or across both datasets.
Why this matters
The results offer testable ideas for laboratory research and future drug-repurposing studies. They do not show that any of the compounds treat ALS, work in people, or are clinically suitable, so they do not currently change treatment.
Limitations and context
This was a computational analysis of two publicly available transcriptomic datasets, not a clinical trial. The findings are hypothesis-generating and require validation in independent patient groups and experimental ALS models. The study explicitly did not establish biomarkers, treatment efficacy or clinical suitability.