BiomedSciAI / biomed-multi-view
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.
☆16Updated 3 weeks ago
Related projects ⓘ
Alternatives and complementary repositories for biomed-multi-view
- We introduce ibm/biomed.omics.bl.sm.ma-ted-458m. A biomedical foundation model trained over 2 billion biological samples across multiple …☆22Updated this week
- FuseMedML based molecular biochemistry library for drug discovery/repurposing☆14Updated this week
- ☆32Updated last month
- Fine-tuning of ChemBERTA LLMs to predict molecules' HIV inhibition replication.☆18Updated last year
- Knowledge-enhanced learned representation enriches protein sequence and SMILES drug databases with a large Knowledge Graph fused from dif…☆51Updated last week
- Automated QSAR based on multiple small molecule descriptors☆30Updated this week
- Official implementation of DrugGEN☆51Updated 3 months ago
- Generative Pre-Training from Molecules☆17Updated last year
- SELFormer: Molecular Representation Learning via SELFIES Language Models☆84Updated 2 months ago
- Uncover meaningful structures of latent spaces learned by generative models with flows!☆37Updated 6 months ago
- Machine Learning dataset splitting for life sciences.☆26Updated 4 months ago
- Code for the paper Context-Guided Diffusion for Out-of-Distribution Molecular and Protein Design☆34Updated 4 months ago
- A foundational package for molecular predictive modelling☆86Updated last month
- Generative modeling of molecular dynamics trajectories☆106Updated last week
- ☆35Updated 5 months ago
- ☆57Updated 7 months ago
- This is a curated list of research papers, resources and tools related to using Graph Neural Networks (GNNs) for drug discovery.☆43Updated 7 months ago
- Foster the development of impactful AI models in drug discovery.☆97Updated this week
- ☆21Updated last year
- Code for generation and benchmarks of the Multimodal Spectroscopic Dataset☆24Updated last month
- A geometry-complete diffusion generative model (GCDM) for 3D molecule generation and optimization (Nature CommsChem)☆181Updated 2 months ago
- A single model for all your molecular design tasks☆86Updated 2 months ago
- A concise and easy-to-customize reimplementation of "ChemProp" (Yang et al, 2019) in PyTorch Geometric.☆20Updated 2 years ago
- Graph neural networks for molecular machine learning. Implemented and compatible with TensorFlow and Keras.☆48Updated this week
- Visualizing the space of chemical reactions with the parametric (learnable) t-SNE.☆10Updated 2 years ago
- Code for our Nature Scientific Reports paper "A universal framework for accurate and efficient geometric deep learning of molecular syste…☆53Updated 3 weeks ago
- DeepDrugDomain: A versatile Python toolkit for streamlined preprocessing and accurate prediction of drug-target interactions and binding …☆21Updated last month
- AutoML system for building trustworthy peptide bioactivity predictors☆20Updated this week
- Molecule Graph Generation using Graph Convolutional Networks-based Variational Graph AutoEncoders (VGAE) in PyTorch☆21Updated 2 weeks ago
- Working collection of papers, repos and models of transformer based language models trained or tuned for the Chemical domain, from natura…☆50Updated last year