DeCure's autonomous Rare AI scientist is researching a drug-repurposing hypothesis for intestinal disease — screening already-approved drugs against its 38-gene Open Targets disease module to publish open-access research. Research is fast; the path to publication is funded in milestone stages.
Disease moduleIntestinal disease maps to a 38-gene Open Targets module — the target space DeCure's AI scientist screens approved drugs against.
DeCure.ai methodSignature reversal (LINCS) plus network proximity (STRING) rank already-approved drugs likely to perturb this module — the same engine that produces DeCure.ai's repurposing hypotheses.
Repurposing thesisScreening approved medicines against this disease module, then publishing the evidence for the strongest candidate. Known pharmacology and human exposure data make the first question sharper — they do not establish safety or efficacy in a new indication.
Research record
01
ResearchComing soon
Candidate research + dossier — target rationale, drug-repurposing thesis and evidence pack.proof: Published dossier + on-chain hash
02
ValidationComing soon
In-vitro biological validation at a contract research org (CRO).proof: CRO contract + in-vitro report
03
Peer review & paperComing soon
Peer-reviewed paper published open-access (preprint + journal).proof: DOI + open-access link + on-chain hash
Current lead
No approved-drug candidate for intestinal disease is corroborated in the literature DeepSearch retrieved. Some conditions are managed with non-pharmacological care — a device, surgery or physical therapy — rather than a medicine; that may be the case here, or the literature we found may simply be too sparse yet to support a drug-repurposing angle.
Molecular view
ABO, alpha 1-3-N-acetylgalactosaminyltransferase and alpha 1-3-galactosyltransferase (ABO) — ABO is one of the genes genetically linked to this disease in Open Targets — shown as context, not as a drug target we're pursuing: no approved-drug candidate for this disease is yet corroborated in the literature we found.
Loading structure…
helix sheet 6-deoxy-alpha-l-galactopyranosyldrag to rotate · scroll to zoom
RCSB Protein Data Bank · entry 4Y63 · 1.3 Å · ligand octyl 2-O-(6-deoxy-alpha-L-galactopyranosyl)-beta-D-galactopyranoside (BHE). Experimental structure, not a prediction.
What the evidence adds up to
In a 2020 database study, 20 protein-coding genes were identified as having the highest probability of overlap across ulcerative colitis, Crohn’s disease, and their extra-intestinal manifestations (uveitis, arthritis, primary sclerosing cholangitis, pyoderma gangrenosum). The analysis drew on 3783 genes linked to ulcerative colitis and 3980 linked to Crohn’s disease from four genetic databases. Among the shared genes, interleukin-25 and monensin-resistant homolog 2 appeared only in ulcerative colitis, Crohn’s disease, pyoderma gangrenosum, and arthritis; arachidonate 5-lipoxygenase was involved in ulcerative colitis, Crohn’s disease, and arthritis; and SLCO1B3 was exclusive to pyoderma gangrenosum, ulcerative colitis, and Crohn’s disease. TNF involvement was noted in Crohn’s disease, ulcerative colitis, primary sclerosing cholangitis, and arthritis. The authors proposed these genes and their effectors as potential therapeutic targets, but no drug was tested, no patient outcomes were measured, and no clinical validation was performed.
A 2012 case report from Bangladesh described one patient with immunoproliferative small intestinal disease who was treated with unspecified medications and reported a “comparatively good smooth course.” No drug name, response duration, or objective outcome measure was given. The report provides no controlled data and no basis for generalising to other patients.
A 2016 gene expression dataset (GSE40292) provided a comprehensive scan of expression quantitative trait loci in intestinal tissue, noting that up to 50% of such loci are tissue-specific. The dataset is a resource for studying how genetic variation may alter gene expression in the gut, but it does not test any drug or link any specific gene to a therapeutic intervention.
What is missing: no clinical trial has tested any of the 20 proposed gene targets in patients; no drug has been repurposed or validated for intestinal disease based on these genetic findings; the single case report offers no reproducible evidence; and the gene expression dataset remains a reference tool, not a treatment. Funding for translational studies, a properly designed clinical trial, and patient stratification by genetic or molecular subtype are all absent.
Evidence
Retrieved by DeepSearch across 234,678,978 indexed works and resolved on OpenAlex — ranked by citations, including the results that did not work.
Clinical and Experimental Gastroenterology · 2020 · 11 citations · open access
<p>Identification of Novel Therapeutic Molecular Targets in Inflammatory Bowel Disease by Using Genetic Databases</p>
AbstractPURPOSE: Utilization of genetic databases to identify genes involved in ulcerative colitis (UC), Crohn's disease (CD), and their extra-intestinal manifestations. METHODS: Protein coding genes involved in ulcerative colitis (3783 genes), Crohn's disease (3980 genes), uveitis (1043 genes), arthritis (5583 genes), primary sclerosing cholangitis (PSC) (1313 genes), and pyoderma gangrenosum (119 genes) were categorized using four genetic databases. These include Genecards: The Human Gene Database (www.genecards.org), DisGeNET (https://www.disgenet.org/), The Comparative Toxicogenomics Database (http://ctdbase.org/) and the Universal Protein Resource (https://www.uniprot.org/). NDex, Network Data Exchange (http://www.ndexbio.org/), was then utilized for mapping a unique signal pathway from the identified shared genes involved in the above disease processes. RESULTS: We have detected a unique array of 20 genes with the highest probability of overlay in UC, CD, uveitis, arthritis, pyoderma gangrenosum, and PSC. Figure 1 represents the interactome of these 20 protein coding genes. Of note, unique immune modulators in different disease processes are also noted. Interleukin-25 (IL-25) and monensin-resistant homolog 2 (MON-2) are only noted in UC, CD, pyoderma gangrenosum, and arthritis. Arachidonate 5-lipoxygenase (ALOX5) is involved in UC, CD, and arthritis. SLCO1B3 is exclusively involved with pyoderma gangrenosum, UC, and CD. As expected, TNF involvement is noted in CD, UC, PSC, and arthritis. Table 1 depicts the detailed result. CONCLUSION: Our work has identified a distinctive set of genes involved in IBD and its associated extra-intestinal disease processes. These genes play crucial roles in mechanisms of immune response, inflammation, and apoptosis and further our understanding of this complex disease process. We postulate that these genes play a critical role at intersecting pathways involved in inflammatory bowel disease, and these novel molecules, their upstream and downstream effectors, are potential targets for future therapeutic agents.
Euroasian Journal of Hepato-Gastroenterology · 2012 · 1 citations · open access
Immunoproliferative Small Intestinal Disease:First Case Report from Bangladesh
AbstractA case of immunoproliferative small intestinal disease (IPSID) was diagnosed and treated at Bangabandhu Sheikh Mujib Medical University, Dhaka, Bangladesh. Although this rare disease entity has been reported from different countries, there are paucity of information about IPSID from Indian subcontinent. Careful assessment of patient and supportive laboratory investigations are required for its diagnosis. The patient is passing a comparatively good smooth course after getting medications.
Gene expression data from Gene Expression Omnibus - GSE40292
Abstract"Genome-wide association studies (GWAS) have been pivotal to increasing our understanding of intestinal disease. However, the mode by which genetic variation results in phenotypic change remains largely unknown, with many associated polymorphisms likely to modulate gene expression. Analyses of expression quantitative trait loci (eQTL) to date indicate that as many as 50% of these are tissue specific. Here we report a comprehensive eQTL scan of intestinal tissue."<br>http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE40292
Disease module: DeepOracle (Open Targets). Structures: RDKit from PubChem SMILES. Literature: retrieved by DeepSearch across 234,678,978 indexed works (targeted per-candidate search), resolved on OpenAlex.
DeCure is a research and publication project, not medical advice and not a treatment. "DeCure for X" describes a research goal, not a claim that a cure exists. Backing a cure is a contribution to fund the research — it is not an investment, and confers no yield, royalty, equity or IP ownership. Papers are published open-access by the DeCure.ai DAO.
