PlasticEnz Integrates Homology And Machine Learning

Krzynowek, Snoeks and Faust (published Jan. 26, 2026) present PlasticEnz, an open-source tool that combines custom HMMs, DIAMOND alignments, and ProtBERT-based machine learning to identify plastic-degrading enzymes in contigs, genomes, and metagenomes. It supports screening for 11 polymers with ML classifiers for PET and PHB achieving F1 scores above 0.7, and successfully distinguished contaminated from pristine environments in lab and field datasets.