Gut-healing peptide (CHEMBL3824227)
A lab-made peptide that activates the gut receptor responsible for intestinal repair and growth; experimental, not yet an approved drug.
A researcher, an agent, or an algorithm wrote down the sequence and picked a target to hit.
An AI model like OpenFold3 or AlphaFold built a 3D structure and scored how well it fits the binding site.
A second contributor repeated the computation on their own hardware and the scores matched.
A chemistry service or a researcher ordered the sequence, it was manufactured, and mass spectrometry confirmed the right molecule was produced.
A binding or activity measurement confirmed that it actually does what the computer predicted — or didn't.
Research directions for this peptide, selected from the current sources — hypotheses you can explore and model. None of it is proven yet; tap any one to see the full thinking.
Does the one altered building block in pep-10372 protect it from DPP-4, the enzyme that chops up and inactivates gut signals like GLP-2?
If the peptide survives longer in the body, patients with short bowel syndrome might need fewer or smaller injections to repair their gut lining. The same single change gives the approved drug teduglutide its staying power, so this is well supported rather than a sure thing.
Does pep-10372 shift from a floppy to a structured form once it docks onto the GLP-2 receptor?
Peptides that fold only at their target can be harder for the body to break down in transit, which could make for longer-lasting gut medicines and better treatments for conditions like short bowel syndrome or Crohn's disease.
▸full evidence table1 metrics
| metric | value | tool |
|---|---|---|
| EC50 | 1.1 nM | GPCRDB/ChEMBL |
▸structural qualityopenfold3
| metric | value | note |
|---|---|---|
| gpde | 0.734 | global PDE — lower = better |
| disorder | 0.243 | fraction disordered |
| chain pair ipTM (A, B) | 0.874 | interface quality |
▸3-letter notation
▸recipeopenfold3-mlx 0.3.1
| parameter | value |
|---|---|
| model | openfold3-mlx 0.3.1 |
| weights | aedd8f3eb814e392… |
| hardware | apple_m4_base_16gb |
| mlx version | 0.31.1 |
| python | 3.14.3 |
| random seed | 42 |
| msa strategy | colabfold |
| diffusion samples | 1 |
| runtime | 634s |
| predicted by | mlx@peptide |
| predicted at | 2026-04-22 |
python3 openfold3/run_openfold.py predict --query_json {query.json} --runner_yaml examples/example_runner_yamls/mlx_runner.yml --output_dir {output_dir} --num_diffusion_samples 1 ▸citationbibtex
@peptide{pep10372,
sequence = {HGDGSFSDEMNTILDNLAARDFINWLI},
target = {glp-2r},
author = {peptidemodel},
year = {2026},
status = {bioassayed}
}