EC General
OracleSuggests broad enzyme-class hypotheses from protein sequence.
- enzyme
- annotation
EC General
EC General gives a broad Enzyme Commission signal from amino acid sequence. It is designed for early enzyme-function triage, not final functional assignment.
What It Does
The oracle ranks whether a sequence may belong to major enzyme-function classes. It helps users decide which candidates deserve deeper annotation, active-site review, substrate screening, or pathway analysis.
Why It Matters
Broad enzyme hypotheses are useful early in a workflow. They can organize unknown proteins, guide literature review, and help teams decide where more expensive evidence should be collected.
Intended Use
Use EC General when you need a quick enzyme-class readout before running stricter annotation tools or biochemical assays.
Limitations
EC General does not prove catalytic activity or substrate specificity. Confirm important assignments with homology, active-site conservation, cofactors, structural context, curated databases, and biochemical validation.
Try EC General
Run predictions with this model through the Synthyra platform.
Related Models
Translator
OracleTurns protein sequences into structured functional annotation hypotheses.
EC Rigor
OracleProvides stricter enzyme-function hypotheses when higher-confidence EC assignment is needed.
kcat
OracleEstimates enzyme turnover potential from protein sequence.
Related News
July 30, 2024
Annotation Vocabulary: Teaching Protein Models the Language of Function
Replace free-text protein descriptions with a vocabulary of ontology terms, and a model trained for three dollars in compute produces better functional embeddings than models a thousand times its cost.
August 21, 2025
Protify: Model Choice As An Experiment
Across 32 protein tasks, 13 different models won at least once and none of the wins were statistically significant. Picking a protein language model is an experiment, not a preference.
September 15, 2023
cdsBERT: Why Codons Still Matter for Protein AI
Two genes can encode an identical protein and still differ. cdsBERT extends a protein language model's vocabulary from 20 amino acids to 64 codons to find out how much that difference is worth.