PETase ANnotation and Triage System

Methods and limitations

Spec section 7 calls this page non-negotiable "given how easily this kind of tool is over-read". This project has more to disclose than most.

Trained on the measured set alone, the activity head reaches AUC 0.976 (± 0.021) across 45 independent sequence clusters, with average precision 0.987 and a Brier score of 0.052, against 0.829 for a classifier using amino-acid composition and length only. That is the first defensible activity signal in this project: experimental labels, a split by cluster rather than by sequence, and a real margin over the composition baseline instead of a tie.

Until PAZy was loaded the measured positives numbered 17 across 5 clusters, too few for the protocol below to run. The head was not scoring badly; it could not be scored.

Positives by evidence tier

Training runs

The composition baseline uses amino-acid fractions and length only. Any model claim must clear it as well as the retrieval baseline.

Pipeline runs

Data sources

Limitations

1. Positives number in the low hundreds and most carry family annotation rather than measured PET activity.
2. Published activity data is not harmonised across assay formats. Absolute rate predictions should not be trusted.
3. Crystalline PET degradation at 37 °C by any known enzyme is slow. PANTS ranks relative promise, not therapeutic viability.
4. Predicted structures are predictions. Cleft geometry on a metagenomic sequence with no close homologue carries real uncertainty, and a brittle version of that measurement scored IsPETase's own prediction at half its crystal value before being fixed.
5. AUC 0.976 is measured against hard negatives from other α/β-hydrolase families. Tested against the near misses instead it reaches 1.000, which is a warning rather than a result: every near miss is a single ESTHER family (Cutinase), and one homogeneous family separates as a block (composition alone scores 0.910). Neither contrast shows that the head ranks PET activity within the polyesterase family.
6. The within-family question has no dataset. It needs PET-inactive polyesterases, measured and published, and databases record what works: nobody systematically publishes a failed assay. That is publication bias, not a curation gap, and more database mining will not fix it.
7. Nothing here addresses delivery, immunogenicity, biodistribution, or what happens to liberated TPA and EG in vivo.
8. Metagenomic candidates may come from unculturable organisms, may not express in a standard host, and may be fragments or misassemblies.
9. Cleft width currently separates a fungal cutinase from the polyesterase family, but does not order that family by PET activity. Family-level separation is a much easier task than the one that matters.

Recent manifests