Researchprotbertplastic degradationhidden markov modelsxgboost
PlasticEnz Integrates Homology And Machine Learning
7.7
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.
Key Points
- 1Combines HMMs, DIAMOND alignments, and ProtBERT-based ML classifiers to detect plastizymes across datasets
- 2Achieves PET and PHB classifier F1 scores >0.7, improving detection beyond homology-only approaches
- 3Enables fast, scalable screening of contigs and metagenomes to prioritize candidate depolymerases for validation
Scoring Rationale
Peer-reviewed, practical ML–HMM integration provides usable plastizyme screening; scope limited to 11 polymers and PET/PHB classifiers.
Sources
Public references used for this report.
Practice with real Ad Tech data
90 SQL & Python problems · 15 industry datasets
Used by DS/ML engineers at top companies
Active Search Campaigns by BudgetEasyHigh CPC Clicks & Poor Landing PagesMediumCampaign ROAS by Attribution ModelHard
250 free problems · No credit card
See all Ad Tech problems