Back

GitHub Projects

7 open-source repositories spanning large language models for mRNA, active learning, molecular property prediction, and lipid nanoparticle design.

2024
[1]
CodonBERT: Large Language Models for mRNA Design and Optimization

github.com/Sanofi-Public/CodonBERT · 2024

A transformer-based model for predicting and optimizing mRNA sequences, enabling improved therapeutic mRNA design through deep learning.

View on GitHub
2024
[2]
LMR-SurfaceID: Language Model for Antibody Surface Identification

github.com/Sanofi-Public/LMR-SurfaceID · 2024

A protein language model for identifying and characterizing antibody surface residues critical for antigen binding and therapeutic development.

View on GitHub
2024
[3]
MolQuery: Molecular Property Prediction and Query System

github.com/Sanofi-Public/MolQuery · 2024

A machine learning framework for querying and predicting molecular properties to accelerate drug discovery and molecular design.

View on GitHub
2024
[4]
ALIEN: Active Learning for Intelligent Experimental Design

github.com/Sanofi-Public/Alien · 2024

An active learning framework for optimizing experimental design in biological and chemical spaces, reducing experimental costs while maximizing information gain.

View on GitHub
2024
[5]
mRNA-LM: Language Models for mRNA Therapeutics

github.com/Sanofi-Public/mRNA-LM · 2024

A suite of language models specifically designed for mRNA sequence analysis, property prediction, and therapeutic optimization.

View on GitHub
2024
[6]
Dewdrop: Deep Learning for Drug Property Optimization

github.com/Sanofi-Public/dewdrop · 2024

A deep learning toolkit for predicting and optimizing physicochemical properties of small molecule therapeutics.

View on GitHub
2024
[7]
LipoBART: BART-based Model for Lipid Nanoparticle Design

github.com/Sanofi-Public/LipoBART · 2024

A transformer architecture for designing and optimizing lipid nanoparticles for mRNA delivery systems.

View on GitHub