data-datum/GCNN_resources

Lista de Materiales para estudio de Graph Convolutional Neural Networks (GCNN) y Graph Neural Networks (GNN)

Graph Convolutional Neural Networks and Graph Neural Networks - Resources

CS224W: Machine Learning with Graphs - Stanford Course Resources

Papers with code

---

* DeepChemStable: Chemical Stability Prediction with an Attention-Based Graph Convolution Network (Li, 2019)

• Link del paper
• Repositorio

Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals (2019)

• Paper
• Repositorio

Pushing the Boundaries of Molecular Representation for Drug Discovery with the Graph Attention Mechanism (Xiong, 2019)

• Paper
• Repositorio

Drug–target affinity prediction using graph neural network and contact maps (Jiang, 2020)

• Paper
• Repositorio

A Bayesian graph convolutional network for reliable prediction of molecular properties with uncertainty quantification (2019)

• Paper
• Repositorio

Molecule Attention Transformer (Maziarka, 2020)

• arXiv preprint
• Repositorio

Youtube Videos

• Graph Representation Learning (Stanford university
• Jure Leskovec | Advancements in Graph Neural Networks
• Generalizing Convolutions for Deep Learning
• Lista de Reproduccion - Representation Learning
• Xavier Bresson: "Convolutional Neural Networks on Graphs"
• BMVA Symposium: Deep Learning in 3D: Michael Edward Graph Convolutional Neural Networks
• Learning Equivariant and Hybrid Message Passing on Graphs | Max Welling
• [IPAM2019] Thomas Kipf "Unsupervised Learning with Graph Neural Networks"
• A Literature Review on Graph Neural Networks
• Learning the Structure of Graph Neural Networks | Mathias Niepert | heidelberg.ai
• CS224W Classes Playlist

RIIAA materiales

Tutorial: Graph Neural Networks

• Repo: https://github.com/beangoben/gnn_workshop_riiaa

Material Previo

• Un review paper de GNNs: https://arxiv.org/abs/1806.01261
• Usaremos el codigo de deepmind: https://github.com/deepmind/graph_nets
• Usaremos dos datasets del Open Graph Database: https://ogb.stanford.edu/

Tutorial: Atribución en Grafos

• Repo: https://github.com/beangoben/gnn_workshop_riiaa

Material Previo

• Un buen review de attribution: https://arxiv.org/abs/1711.06104
• Un review paper de GNNs: https://arxiv.org/abs/1806.01261
• Usaremos el codigo de deepmind: https://github.com/deepmind/graph_nets
• Distill post sobre attribucion: https://distill.pub/2020/attribution-baselines/

Link de google colab: https://colab.research.google.com/github/beangoben/gnn_workshop_riiaa/blob/master/Prediccion_de_Grafos_y_attribucion.ipynb?authuser=1#scrollTo=5DA0QH4Tovux

Tutorial: Machine Learning y Moléculas

• Repo: https://github.com/beangoben/ML_DL_con_moleculas

Maeterial Previo

• Usaremos rdkit para manipular moleculas: https://www.rdkit.org/
• Usaremos scikit-learn para modelos de ML: https://scikit-learn.org/stable/
• Usaremos tensorflow/sonnet/graphnets para deep learning con molecules: https://www.tensorflow.org/, https://github.com/deepmind/sonnet, https://github.com/deepmind/graph_nets
• Para reducción de dimensionalidad usaremos UMAP: https://pair-code.github.io/understanding-umap/supplement.html
• Para descriptores quimo-informáticos usaremos mordred: https://github.com/mordred-descriptor/mordred https://jcheminf.biomedcentral.com/articles/10.1186/s13321-018-0258-y (paper de modred)
• Un review de deep learning e inverse design: https://science.sciencemag.org/content/361/6400/360.abstract

Tutorial: Deep Learning con JAX

• Repo: https://github.com/beangoben/intro_dl

Material Previo

• La parte 1 de "Deep Learning de Ian Goodfellow" (https://github.com/janishar/mit-deep-learning-book-pdf/tree/master/chapter-wise-pdf), en particular capitulo 3,4 y 5.
• El github de Jax: https://github.com/google/jax
• El github de Flax: https://github.com/google/flax
• Video introductorio a Jax: https://www.youtube.com/watch?v=0mVmRHMaOJ4
• Video introductorio a diferenciación automática: https://www.youtube.com/watch?v=NG21KWZSiok