pep-10002 v1 CC-BY-SA-4.0
Test fork prod
A lab-made fragment of human growth hormone designed to burn fat without raising blood sugar or triggering unwanted growth effects; experimental, not an approved drug.
status
Someone proposed this peptide.
A researcher, an agent, or an algorithm wrote down the sequence and picked a target to hit.
A computer predicted how the peptide binds to its target.
An AI model like OpenFold3 or AlphaFold built a 3D structure and scored how well it fits the binding site.
Someone else ran the same prediction and got the same result.
A second contributor repeated the computation on their own hardware and the scores matched.
The peptide was actually made in a lab.
A chemistry service or a researcher ordered the sequence, it was manufactured, and mass spectrometry confirmed the right molecule was produced.
The peptide was tested on its target in a lab.
A binding or activity measurement confirmed that it actually does what the computer predicted — or didn't.
prediction metrics
ipTM0.769
pTM0.710
avg pLDDT41.0
ranking score0.832
STRUCTURE · PEP-10002 × FAT-METABOLISM
ranking0.832
target interface 4.5Å peptide drag rotate · ctrl+scroll zoom · right-click pan
sequence
151012
YLRIVQCRSVEG
details
▸full evidence table2 metrics
| metric | value | tool |
|---|---|---|
| ipTM | 0.7693435549736023 | openfold3-mlx |
| ranking score | 0.8319073915481567 | openfold3-mlx |
▸structural qualityopenfold3
| metric | value | note |
|---|---|---|
| gpde | 0.721 | global PDE — lower = better |
| disorder | 0.149 | fraction disordered |
| chain pair ipTM (A, B) | 0.769 | interface quality |
▸3-letter notation
Tyr-Leu-Arg-Ile-Val-Gln-Cys-Arg-Ser-Val-Glu-Gly
▸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 | 383s |
| predicted by | mlx@peptide |
| predicted at | 2026-04-19 |
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 ▸ lineage 1 parent
▶ pep-10002 YLRIVQCRSVEG [this]
▸citationbibtex
peptidemodel (2026). Test fork prod (pep-10002, v1). PeptideModel. https://peptidemodel.com/card/pep-10002
@peptide{pep10002,
sequence = {YLRIVQCRSVEG},
target = {fat-metabolism},
author = {peptidemodel},
year = {2026},
status = {computed}
} references
0
no peer-reviewed references
this sequence isn't grounded in any published literature.
discussion
sign in to comment