Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
awesome-AI4Drug-papers
A collection of AI for Drug Design related papers and corresponding code sources (in progress).
https://github.com/Beastlyprime/awesome-AI4Drug-papers
Last synced: 5 days ago
JSON representation
-
Molecule
-
Representation Learning
- Motif-based Graph Self-Supervised Learning for Molecular Property Prediction - supervised pretraining frameworks for GNNs only focus on node-level or graph-level tasks. These approaches cannot capture the rich information in subgraphs or graph motifs.
- Directional Message Passing on Molecular Graphs via Synthetic Coordinates
- GemNet: Universal Directional Graph Neural Networks for Molecules - hop message passing are indeed universal approximators for predictions that are invariant to translation, and equivariant to permutation and rotation.
- Learning 3D Representations of Molecular Chirality with Invariance to Bond Rotations
- A Program to Build E(N)-Equivariant Steerable CNNs - steerable kernel spaces for equivariant steerable CNNs.
- Geometric and Physical Quantities improve E(3) Equivariant Message Passing
- Spherical Message Passing for 3D Molecular Graphs
- Deep Molecular Representation Learning via Fusing Physical and Chemical Information
- MoReL: Multi-omics Relational Learning - omics data analysis has the potential to discover hidden molecular interactions, revealing potential regulatory and/or signal transduction pathways for cellular processes of interest when studying life and disease systems.
- Graph Neural Networks with Learnable Structural and Positional Representations
- Pre-training Molecular Graph Representation with 3D Geometry
- Chemical-Reaction-Aware Molecule Representation Learning
-
Molecule Generation
- Hit and Lead Discovery with Explorative RL and Fragment-based Molecule Generation
- A 3D Generative Model for Structure-Based Drug Design
- Data-Efficient Graph Grammar Learning for Molecular Generation - efficient generative model that can be learned from datasets with orders of magnitude smaller sizes than common benchmarks.
- Spanning Tree-based Graph Generation for Molecules
- Amortized Tree Generation for Bottom-up Synthesis Planning and Synthesizable Molecular Design
- Learning to Extend Molecular Scaffolds with Structural Motifs - based generative model of molecules that can be constrained to include an arbitrary subgraph (scaffold).
- Differentiable Scaffolding Tree for Molecule Optimization
- Top-N: Equivariant Set and Graph Generation without Exchangeability - n can replace i.i.d. generation in any VAE or GAN -- it is easier to train and better captures complex dependencies in the data.
- Multi-objective Optimization by Learning Space Partition - world MOO tasks, by up to 225% in sample efficiency for neural architecture search on Nasbench201, and up to 10% for molecular design.
- Spatial Graph Attention and Curiosity-driven Policy for Antiviral Drug Discovery - 19 using machine learning.
- An Autoregressive Flow Model for 3D Molecular Geometry Generation from Scratch
-
Ensembles Generation
-
Property Prediction
- Property-Aware Relation Networks for Few-Shot Molecular Property Prediction - shot problem which makes it hard to use regular machine learning models.
- Functionally Regionalized Knowledge Transfer for Low-resource Drug Discovery - learning algorithm FRML for transferring the knowledge from previous assays, namely in-vivo experiments, by different laboratories and against various target proteins.
- Meta-Learning with Fewer Tasks through Task Interpolation - learning algorithms is the requirement of a large number of meta-training tasks, which may not be accessible in real-world scenarios.
- Constrained Graph Mechanics Networks
- SE(3)-equivariant prediction of molecular wavefunctions and electronic densities - equivariant operations and building blocks for constructing deep learning architectures for geometric point cloud data and apply them to reconstruct wavefunctions of atomistic systems with unprecedented accuracy.
- Equivariant Transformers for Neural Network based Molecular Potentials - equilibrium conformations for the evaluation of molecular potentials.
- Ab-Initio Potential Energy Surfaces by Pairing GNNs with Neural Wave Functions
- Simple GNN Regularisation for 3D Molecular Property Prediction and Beyond - label noise to a GNN. There is little technical novelty. The proposed applications of the approach are interesting.
-
-
Gene
-
Representation Learning
- GeneDisco: A Benchmark for Experimental Design in Drug Discovery - source implementations of state-of-the-art active learning policies for experimental design and exploration.
-
-
Protein
-
Design
-
Representation Learning
- Multi-Scale Representation Learning on Proteins - scale graph construction of a protein.
- OntoProtein: Protein Pretraining With Gene Ontology Embedding - training.
-
Function Prediction
-
Contact Prediction / Docking
- Co-evolution Transformer for Protein Contact Prediction
- Geometric Transformers for Protein Interface Contact Prediction - evolving graph transformer for 3D protein structures.
- Independent SE(3)-Equivariant Models for End-to-End Rigid Protein Docking
-