damianosmel/dom2vec
dom2vec: Protein domain embeddings
This project helps bioinformaticians and computational biologists understand protein function and relationships by converting protein domain architectures into numerical representations called 'embeddings'. You provide protein domain data (e.g., from InterPro), and it generates these embeddings, which can then be used for tasks like classifying proteins or predicting their properties. This is useful for researchers studying protein evolution, disease mechanisms, or drug discovery.
No commits in the last 6 months.
Use this if you need to transform complex protein domain sequences into a format suitable for machine learning models to analyze protein function or evolutionary relationships.
Not ideal if you're looking for a simple tool to visualize protein structures or perform basic sequence alignment, as this focuses on generating numerical representations of domain architectures.
Stars
7
Forks
—
Language
Python
License
MIT
Category
Last pushed
Jan 27, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/damianosmel/dom2vec"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
DeepChainBio/bio-transformers
bio-transformers is a wrapper on top of the ESM/Protbert model, trained on millions on proteins...
Rostlab/bindPredict
Prediction of binding residues for metal ions, nucleic acids, and small molecules.
bio-ontology-research-group/predCAN
Ontology-based prediction of cancer driver genes
MI2DataLab/memr
R package for Multisource Embeddings for Medical Records
KCLabMTU/LMSuccSite
Improving Protein Succinylation Sites Prediction Using Features Extracted from Protein Language Model