BiomedSciAI / biomed-multi-viewLinks
This repository contains the implementation of the Multi-view Molecular Embedding with Late Fusion (MMELON) architecture. MMELON combines molecular representations from three views — image, graph, and text —to learn a joint embedding that can be finetuned for downstream tasks in chemical and biological property prediction.
☆40Updated 5 months ago
Alternatives and similar repositories for biomed-multi-view
Users that are interested in biomed-multi-view are comparing it to the libraries listed below
Sorting:
- Reagent prediction with Molecular Transformer. Improvement of data for reaction product prediction in a self-supervised fashion.☆28Updated last year
- Downloads USPTO patents and finds molecules related to keyword queries☆66Updated last year
- ☆29Updated 4 months ago
- Source code accompanying the 'Transfer learning with graph neural networks for improved molecular property prediction in the multi-fideli…☆31Updated 5 months ago
- Useful functions for working with small molecules☆55Updated 2 months ago
- ☆29Updated 2 years ago
- Recursion's molecular foundation model☆64Updated 5 months ago
- Diffusion-based molecule conformer generation☆43Updated last year
- ☆28Updated last year
- Sample-efficient Generative Molecular Design using Memory Manipulation☆66Updated 5 months ago
- SELFormer: Molecular Representation Learning via SELFIES Language Models☆103Updated 11 months ago
- ☆24Updated last year
- ☆31Updated 3 years ago
- ☆42Updated last week
- Atom-in-SMILES tokenizer for SMILES strings.☆42Updated last year
- A concise and easy-to-customize reimplementation of "ChemProp" (Yang et al, 2019) in PyTorch Geometric.☆23Updated 3 years ago
- Semi-supervised Junction Tree Variational Autoencoder for jointly trained property prediction and molecule structure generation. (AAAI 23…☆12Updated 2 years ago
- Machine Learning dataset splitting for life sciences.☆36Updated last year
- Chemical representation learning paper in Digital Discovery☆63Updated last year
- ChemSpaceAL: An Efficient Active Learning Methodology Applied to Protein-Specific Molecular Generation☆16Updated last year
- Message Passing Neural Networks for Molecule Property Prediction☆47Updated 3 years ago
- ☆16Updated last year
- Chemprop benchmarking scripts and data for v1☆28Updated last year
- Synthetic Bayesian Classification☆47Updated 4 years ago
- A simple molecule fragmentation method.☆40Updated 2 years ago
- Chemical reaction data cleaning☆30Updated 3 years ago
- Extract structure-functions from data using XAI and LLMs☆26Updated 10 months ago
- Jupyter Notebook Tutorials for Creating Chemical Space Networks☆37Updated last year
- A Benchmarking Platform for Realistic And Practical Inverse Molecular Design☆78Updated 6 months ago
- IBM Molecule Generation Experience (MolGX) is a tool to accelerate an AI-driven design of new materials.☆15Updated 3 years ago