AIbase
EN
Home
Esm2 T30 150M UR50D
E

Esm2 T30 150M UR50D

Developed by facebook
ESM-2 is a state-of-the-art protein model trained on masked language modeling objectives, suitable for fine-tuning on various protein sequence input tasks.
Protein Model
Transformers
Open Source License:MIT#Protein sequence prediction#Masked language modeling#Biomedical research
Downloads 69.91k
Release Time : 9/27/2022

Model Overview

ESM-2 is a protein language model specifically designed for processing protein sequence data, supporting fine-tuning for multiple protein-related tasks.

Model Features

Masked language modeling
Trains the model by masking parts of protein sequences and predicting the missing portions, suitable for protein sequence analysis.
Multi-scale models
Offers models ranging from 8 million to 15 billion parameters to accommodate different computational resources and accuracy needs.
Fine-tuning support
The model can be fine-tuned for specific protein-related tasks, such as structure prediction and functional annotation.

Model Capabilities

Protein sequence modeling
Masked sequence prediction
Protein structure prediction
Protein function annotation

Use Cases

Bioinformatics
Protein structure prediction
Using the ESM-2 model to predict the three-dimensional structure of proteins.
Protein function annotation
Predicting protein functional properties by fine-tuning the ESM-2 model.
Drug discovery
Protein-drug interaction prediction
Analyzing interactions between proteins and potential drug molecules using the ESM-2 model.
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
English简体中文繁體中文にほんご
© 2025AIbase