ProFET: Feature engineering captures high-level protein functions

By Dan Ofer, Michal Linial. 2015

104 citations recorded by the source corpus.

Subfields: Biophysics, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biophysics

1. Tristan Bepler
2. Bonnie Berger
3. Frances H. Arnold
4. Kevin Kaichuang Yang
5. Zachary Wu
6. Nadav Brandes
7. Hannah Currant
8. David T. Jones

In Molecular Biology

1. Kevin Kaichuang Yang
2. Bonnie Berger
3. David T. Jones
4. Zachary Wu
5. Tristan Bepler
6. Nadav Brandes
7. Frances H. Arnold
8. Dan Ofer

Citations in the corpus

• Learning protein sequence embeddings using information from structure (2019, methodology): “Other methods have focused on manual feature engineering based on biophysical and sequence attributes [14].”
• Machine-learning-guided directed evolution for protein engineering (2018, background): “AAIndex 65 and ProFET 66 have large collections of physical descriptors for protein sequences.”
• GOLabeler: Improving Sequence-based Large-scale Protein Function Prediction by Learning to Rank (2017, methodology): “5 LR-ProFET: sequence features including biophysical properties We run ProFET3 [23] over a sequence in D to extract features including elementary biophysical properties, etc.”
• Extensive complementarity between gene function prediction methods (2016, background): “Features were extracted using ProFET (Ofer and Linial, 2015).”
• The language of proteins: NLP, machine learning & protein sequences (2021, methodology): “BoW has been used in many bioinformatics studies on proteins [66,18,64,11,62,103,51].”
• Learned protein embeddings for machine learning (2018, methodology): “Table 2 compares the GP regression results on the test set for each task using embeddings, physical properties from AAIndex, ProFET, a mismatch kernel with k¼5 and m¼1, and one-hot encodings.”
• FFPred 3: feature-based function prediction for all Gene Ontology domains (2016, methodology): “A more recent study has confirmed the effectiveness of this feature-based approach with the use of random forests for supervised learning 18 .”
• Machine learning in protein engineering (2018, background): “ProFET is another encoding system that considers physical properties of the bulk protein, the individual residues, and sub-sequences of residues (Ofer & Linial, 2015).”