DeCure's autonomous Metabolic AI scientist is researching a drug-repurposing hypothesis for phenylketonuria — screening already-approved drugs against its 5-gene Open Targets disease module to publish open-access research. Research is fast; the path to publication is funded in milestone stages.
Disease modulePhenylketonuria maps to a 5-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
approvedTetrahydrobiopterinApproved drug
Structures already discussed alongside phenylketonuria in the retrieved literature, rendered from public PubChem SMILES. Which drugs appear here reflects the evidence found, not a ranked prediction.
Molecular view
BOVINE ENDOTHELIAL NITRIC OXIDE SYNTHASE HEME DOMAIN — Tetrahydrobiopterin has a real, experimentally solved structure in complex with this target (PDB 1D1V, 1.93 Å). This is the drug's own deposited structure, not a prediction, and confirms it is a structurally characterised molecule rather than an untested guess.
Loading structure…
helix sheet h4bdrag to rotate · scroll to zoom
RCSB Protein Data Bank · entry 1D1V · 1.93 Å · ligand Tetrahydrobiopterin (H4B). Experimental structure, not a prediction.
What the evidence adds up to
A 1960 review of all published cases of phenylketonuria treated with a low-phenylalanine diet up to 1959 found that among 43 patients treated before three years of age, the mean age at start of treatment was 16.2 months and the mean duration of treatment was 16.8 months. The treated group had 18 times as many individuals with an IQ above 60 and twice as many with a normal electroencephalogram as the untreated group. Those treated before 16 months of age had four times as many with an IQ above 60 and none had seizures, compared with those treated between 16 months and three years. For the whole group, final IQ was negatively correlated with age at start of treatment, with a minimal loss of nearly five IQ points each ten weeks that treatment was delayed. The authors concluded the diet was effective as a preventative of mental deficiency and neurologic abnormalities but less effective in reversing changes already developed.
A 1966 neuropathology study described the brain changes in untreated phenylketonuria but provided no quantitative data on treatment outcomes. A 2018 systematic review of cognitive functioning in early treated adults with phenylketonuria included a data extraction table summarising 76 kilobytes of information on patient numbers, sex, age, IQ, classification, time of diagnosis, onset and duration of treatment, treatment status, measures of metabolic control, and cognitive outcomes. The review did not report any pooled effect sizes or new trial results.
The evidence base rests entirely on observational data from the 1960s, with no randomised controlled trials comparing dietary treatment to no treatment or to any pharmacological intervention. The 2018 review confirms that even early-treated adults have been studied only in small, heterogeneous cohorts without standardised cognitive endpoints. What is still missing is a modern, adequately powered trial that randomises patients to different dietary stringency levels or to adjunctive therapies, with long-term cognitive and neurological outcomes measured prospectively. No drug therapy was mentioned in any of these abstracts.
Evidence
Retrieved by DeepSearch across 234,678,978 indexed works and resolved on OpenAlex — ranked by citations, including the results that did not work.
AbstractJournal Article Neuropathology of Phenylketonuria Get access N. Malamud, M.D. N. Malamud, M.D. San Francisco, Calif. Search for other works by this author on: Oxford Academic PubMed Google Scholar Journal of Neuropathology & Experimental Neurology, Volume 25, Issue 2, April 1966, Pages 254–268, https://doi.org/10.1097/00005072-196604000-00006 Published: 01 July 1980
AN EVALUATION OF THE TREATMENT OF PHENYLKETONURIA WITH DIETS LOW IN PHENYLALANINE
AbstractEssentially all cases of phenylketonuria treated with a low phenylalanine diet and published up to December, 1959, were reviewed and evaluated. All untreated individuals with phenylketonuria with an I.Q. above 60 that have been recorded were tabulated. The number of these (20) verifies as reasonable the incidence of 2.5% of 466 untreated cases of phenylketonuria that have an I.Q. above 60. This figure was used as one basis of evaluation of the treatment. Forty-four patients with phenylketonuria, over 3 years of age, have been treated without impressive change in mental or neurologic status. These were not considered further. Forty-three patients with phenylketonuria, treated before 3 years of age, were tabulated and evaluated in detail. The mean age at start of treatment was 16.2 months, and the mean duration of treatment was 16.8 months. The treated group had 18 times as many with an I.Q. above 60 and twice as many with a normal electroencephalogram as the untreated group. These differences were highly significant. The treated group also had fewer seizures. Those treated before 16 months of age, compared with those treated between 16 months and 3 years of age, had four times as many with an I.Q. above 60 and fewer (none) with seizures. These differences were highly significant. The early treated group also has more with normal electroencephalograms. For the whole group the final I.Q. was negatively correlated with age at the start of treatment in a highly significant manner (r = -0.67, P < .01). Over the 3-year period studied, a minimal loss of nearly 5 points in the I.Q. occurred each 10 weeks that treatment was delayed. The low phenylalanine diet started in the early months of life is therefore effective as a preventative of mental deficiency and neurologic abnormalities. The diet is less effective in reversing changes which have already developed.
Evidence-based Complementary and Alternative Medicine · 2022 · 4 citations · open access
Influencing Factors on the Use of Tetrahydrobiopterin in Patients with Phenylketonuria
AbstractObjective. To explore and analyze the influencing factors of tetrahydrobiopterin therapy in patients with phenylketonuria. Methods. 86 children with phenylketonuria (PKU) diagnosed and treated in our hospital from February 2019 to September 2021 were randomly enrolled. All the children underwent coenzyme hydroxybiopterin and urinary pterin spectrum analysis, and the children with deficiency received gene mutation testing. Results. The results of urine pterin analysis showed that 82 patients had higher urinary N and B contents than the normal reference values, with the N/B slightly higher than the normal B% within the normal range. 4 patients had extremely high urinary N/B and B% <5% and were diagnosed as BH4 deficiency caused by 6-pyruvoyl-tetrahydropterin synthase (PTPS) deficiency, and a combined stress test was performed. The blood Phe level was (720–1200) μmol/L 3 h after Phe loading, and the blood Phe concentration decreased to (120–240) μmol/L 4–6 h after oral administration of 7.5 mg/kg BH4 tablet. After one week of treatment, the blood Phe concentration decreased significantly to 239 ± 173 μmol/L, with a decrease rate of 52.14 ± 25.28%. It shows that the application of tetrahydrobiopterin intervention therapy is effective in patients with PKU. The results of the full-length cDNA analysis of the PTPS gene showed that a total of 4 gene mutations were found. A C ⟶ T substitution occurred at the 259th base, and the 87th proline (Pro) in the coding region was converted to serine (Ser) (P87S). G ⟶ A substitution at base 286 converts aspartic acid (Asp) at position 96 of the coding region to asparagine (Asn) (D96N). A ⟶ G substitution occurs at the 155th base to convert asparagine (Asn) at position 52 of the coding region to serine (Ser) (N52S). G ⟶ C substitution occurs at the 430th base to convert glycine at position 144 (Gly) to arginine (Arg) (G144R). G144R is a new mutation type. The gene mutation types of the 4 patients were P87S/D96N, N52S/G144R, D96N/P87S, and P87S/P87S, all of which were from their parents, which conformed to the law of autosomal recessive inheritance. Conclusion. PKU is caused by the defect of phenylalanine hydroxylase activity in children, which causes phenylalanine metabolism disorder, and tetrahydrobiopterin intervention therapy can affect the activity of phenylalanine hydroxylase, increase the decline rate of blood Phe, significantly reduce the level of phenylalanine in children, and promote intellectual recovery. The dose of tetrahydrobiopterin should be tailored, with small doses for mild phenotypes and long-term treatment using even smaller doses.
Additional file 1: of A systematic review of cognitive functioning in early treated adults with phenylketonuria
AbstractTable S1. Summary of papers included within the systematic review. Data extraction table summarising the main characteristics of each of the papers included in this review. The table provides an overview of all information provided by each publication in regard to: the number of adults with phenylketonuria (PKU) and controls (where applicable), sex, age, IQ, classification of PKU, time of diagnosis, onset of treatment, treatment status, duration of treatment, measures of metabolic control and cognitive measures used and reported outcomes. (XLS 76 kb)
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.
