Neurology applications

Alzheimer's · ALS · Epilepsy · Depression

Robertium has been applied across four neurological and psychiatric domains: Alzheimer's disease, amyotrophic lateral sclerosis (ALS), epilepsy, and depression. These domains share substantial mechanistic overlap — neuroinflammation, protein aggregation, neurotransmitter imbalance, neuronal excitability — making them rich substrate for cross-domain drug repurposing analysis.

By the numbers

1,143
cross-domain
hypotheses
123
high-confidence
candidates
531
novel candidates
(no existing trial)
69
active clinical
trials reproduced

Counts include hypotheses where any of the four neuro domains is either the drug-source domain or the outcome domain. A single hypothesis may bridge into an oncology domain (e.g. epilepsy drug → mediator → pancreatic cancer).

Featured hypotheses

Selected high-quality candidates surfaced through shared molecular mediators. Each card links to the full evidence chain in the catalog.

osimertinib → EGFR → Alzheimer's disease
glioblastoma → alzheimer via protein

Suggests osimertinib (a Glioblastoma drug) inhibits EGFR, which is associated with Alzheimer's disease.

novel no trial
score 0.312 3 + 1 evidence papers
metformin → α-synuclein → Parkinson's disease
epilepsy → alzheimer via protein

Suggests metformin (an Epilepsy drug) upregulates α-synuclein, which is associated with Parkinson's disease.

known trial active
score 0.416 1 + 7 evidence papers
Riluzole → MMP-9 → epilepsy
als → epilepsy via protein

Suggests Riluzole (an ALS drug) downregulates MMP-9, which is associated with epilepsy.

known no trial
score 0.416 1 + 7 evidence papers
valproic acid → histone deacetylase → amyotrophic lateral sclerosis
epilepsy → als via protein

Suggests valproic acid (an Epilepsy drug) inhibits histone deacetylase, which correlates with amyotrophic lateral sclerosis.

known trial completed
score 0.345 4 + 1 evidence papers
apigenin → GFAP → Alzheimer's disease
glioblastoma → alzheimer via protein

Suggests apigenin (a Glioblastoma drug) upregulates GFAP, which predicts Alzheimer's disease.

known no trial
score 0.312 1 + 3 evidence papers
erlotinib → EGFR → Alzheimer's disease
pancreatic cancer → alzheimer via protein

Suggests erlotinib (a Pancreatic cancer drug) inhibits EGFR, which is associated with Alzheimer's disease.

partial no trial
score 0.396 6 + 1 evidence papers
curcumin → TDP-43 → FTLD
alzheimer → als via protein

Suggests curcumin (an Alzheimer drug) binds to TDP-43, which is associated with FTLD.

partial no trial
score 0.312 1 + 3 evidence papers
Esketamine → NMDA receptor → cell-autonomous excitotoxicity
depression → als via protein

Suggests Esketamine (a Depression drug) inhibits NMDA receptor, which is associated with cell-autonomous excitotoxicity.

novel no trial
score 0.289 8 + 1 evidence papers
gemcitabine → IL-8 → major depressive disorder
pancreatic cancer → depression via protein

Suggests gemcitabine (a Pancreatic cancer drug) upregulates IL-8, which is associated with major depressive disorder.

novel no trial
score 0.271 2 + 4 evidence papers

Alzheimer's → · ALS → · Epilepsy → · Depression →

Methodology note

These hypotheses were surfaced using the same Swanson ABC reasoning applied across all of Robertium's domains: identifying cases where a drug literature and a disease literature share an intermediate mediator but rarely cite each other. Full methodology is described at /method.

Why this matters

Alzheimer's disease affects 55 million people globally with no disease-modifying treatments widely available. ALS has a median survival of 3–5 years from diagnosis with only two FDA-approved drugs (riluzole, edaravone) showing modest effect. Epilepsy remains pharmacologically uncontrolled in approximately one-third of patients. Treatment-resistant depression affects roughly 30% of patients with major depressive disorder. Cross-domain literature analysis can surface candidates that mainstream neurology research has not prioritized.

Open data

  • Full catalog — the complete cross-domain hypothesis set is at /hypotheses, filterable by drug or outcome domain.
  • Archived dataset — the hypothesis catalog is permanently archived on Zenodo: 10.5281/zenodo.20110977.
  • License — source code under MIT, extracted data under CC-BY-4.0.
  • Contact — if you research Alzheimer's, ALS, epilepsy, or depression and want to discuss specific candidates, reach out to daniel@robertium.com.