Could carbamazepine treat pancreatic cancer?
Robertium found 856 such cross-domain drug repurposing candidates by analyzing 167,145 biomedical papers. None have clinical trials yet. All have evidence chains in published literature.
Open-source. Reproducible. PubMed-validated.
{
"drug": "carbamazepine",
"drug_domain": "epilepsy",
"mediator": "KRAS",
"outcome": "pancreatic ductal adenocarcinoma",
"outcome_domain": "pancreatic_cancer",
"score": 0.300,
"evidence_papers": 4,
"clinical_trial_status": "none",
"literature_status": "novel_signal"
} EXPLORE
Browse three ways
Same 1,618 outreach-quality hypotheses, three different lenses.
- By disease
Hypothesis catalog
The full table grouped by therapeutic domain. Filter by quality tier, literature status, clinical trial status. Best when you already know which indication you are exploring.
Open catalog → - By drug
Drug index
411 unique drugs. Click any drug to see every hypothesis it appears in across all disease domains, plus the registered ClinicalTrials.gov record for each pair.
Open drug index → - By prediction status
Prospective tracking
Live leaderboard of Robertium-surfaced hypotheses, ordered by how much new PubMed evidence has emerged since they were frozen. Where the methodology is being put to the test.
Open leaderboard →
The Problem
Over 4,000 biomedical papers are published every day. Knowledge stays fragmented across journals, disciplines, and languages. The connections that would lead to new treatments often already exist in the published literature, but no human team can find them systematically.
Approach
Robertium reads open biomedical literature, extracts structured claims about drugs, genes, and diseases, and connects them into a knowledge graph. From this graph, it surfaces contradictions, gaps, and reasoning chains that point to new drug repurposing hypotheses.
The pipeline is domain-agnostic. Currently active across ten therapeutic domains: glioblastoma, epilepsy, ALS, Alzheimer's disease, pancreatic cancer, major depressive disorder, multiple sclerosis, type 2 diabetes, rheumatoid arthritis, and inflammatory bowel disease. New domains can be added in days, not months.
Read
Open biomedical literature from OpenAlex, PubMed, bioRxiv
Extract
Structured claims about drugs, genes, diseases via language models
Connect
Knowledge graph reveals contradictions, gaps, and reasoning chains
Open
Robertium is open-source under the MIT license. The code, the extracted claims, and the knowledge graph are all freely available.
This is intentional. Drug discovery infrastructure should belong to the scientific community, not to private platforms.
Audit-grade transparency
Every hypothesis has a full provenance trace
Source papers, extracted claims, scoring code, embedding model, prompt version, and the exact pipeline run that produced the row. Downloadable JSON. No black boxes.
Featured hypotheses
Top cross-domain candidates with no prior direct evidence linking drug to outcome — surfaced through shared molecular mediators. Each card links to the full evidence chain.
Suggests curcumin (an Alzheimer's drug) binds to TDP-43, which is associated with ALS.
Suggests Auranofin (a rheumatoid arthritis drug) inhibits TDP-43, which is associated with ALS.
Suggests metformin (a type 2 diabetes drug) activates AMPK, which prevents metabolic dysfunction.
Suggests erlotinib (a pancreatic cancer drug) inhibits EGFR, which is associated with glioblastoma.
Suggests resveratrol (a heart failure drug) activates SIRT1, which increases proliferation.
Suggests auraptene (a glioblastoma drug) downregulates MMP-9, which is associated with epilepsy.
Get notified when API launches
We'll email you once when the API enters beta. No spam, no marketing.
Or email daniel@robertium.com directly.