alibaba/LucaProt
LucaProt: A novel deep learning framework that incorporates protein amino acid sequence and structural information to predict protein function.
Combines sequence tokenization with structural encoding modules to enable binary, multi-class, and multi-label protein function classification tasks. The five-module architecture (Input, Tokenizer, Encoder, Pooling, Output) processes amino acid sequences up to 4096 residues and outputs predictions as single or multiple functional labels. Includes a deployable Flask web application, GPU-optimized inference for memory-constrained hardware (A10 GPUs), and post-processing workflows for classifying viral RdRPs into 180+ supergroups.
223 stars.
Stars
223
Forks
40
Language
Python
License
Apache-2.0
Category
Last pushed
Jan 29, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/alibaba/LucaProt"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
NygenAnalytics/CyteType
Multi-agent LLM driven cell type annotation for single-cell RNA-Seq data
cafferychen777/mLLMCelltype
Cell type annotation for single-cell RNA-seq using multi-LLM consensus
LucaOne/LucaOne
The resources of LucaOne, including: the model code, training scripts, embedding inference code,...
monarch-initiative/curategpt
LLM-driven curation assist tool
LucaOne/LucaPCycle
We developed a dual-channel model named LucaPCycle, based on the raw sequence and protein...