Home

Awesome

👏 A Survey of Artificial Intelligence in Drug Discovery

💡 Artificial intelligence has been widely applied in drug discovery over the past decade and is still gaining popularity. This repository compiles a collection works on related areas, based on the manuscript Artificial Intelligence in Drug Discovery: Applications and Techniques by Jianyuan Deng et al. The preprint version is available in ResearchGate. Hope you will find it useful for your research (citation is provided below).

🔔 This repository is updated regularly.

<p align="center"> <img width="820" height="360" src="/images/github21.png"> </p>
@article{deng2022artificial,
  title={Artificial intelligence in drug discovery: applications and techniques},
  author={Deng, Jianyuan and Yang, Zhibo and Ojima, Iwao and Samaras, Dimitris and Wang, Fusheng},
  journal={Briefings in Bioinformatics},
  volume={23},
  number={1},
  pages={bbab430},
  year={2022},
  publisher={Oxford University Press}
}

Contents


<a name="review" />

1. Reviews and Perspectives

<a name="general" /> <b>1.1 General Drug Discovery</b> <a name="aidd" /> <b>1.2 Drug Discovery in the AI Era</b>

<i>Side Notes: Successful Applications </i>

<a name="caveats" /> <b>1.3 AI-Driven Drug Discovery: Hope or Hype</b>
<a name="data" />

2. Data, Representation & Benchmarks

<a name="databases"/>

<b>2.1 Large-Scale Databases</b>

<a name="pubchem" /> <b>PubChem</b> <a name="chembl" /> <b>ChEMBL</b> <a name="zinc" /> <b>ZINC</b> <a name="others" /> <b>Others</b> <a name="molRep" />

<b>2.2 Small Molecule Representations</b>

<a name="benchmark" />

<b>2.3 Benchmark Platforms</b>

<a name="moleculenet" /> <b>MoleculeNet</b> <a name="molmapnet" /> <b>MolMapNet</b> <a name="chemprop" /> <b>ChemProp</b> <a name="reinvent" /> <b>REINVENT</b> <a name="graphinvent" /> <b>GraphINVENT</b> <a name="guacamol" /> <b>Guacamol</b> <a name="moses" /> <b>MOSES</b> <a name="atom3d" /> <b>ATOM3D</b>
<a name="architec" />

3. Model Architectures

<a name="cnn" />

<b>3.1 Convolutional Neural Networks</b>

<i>Task*: Molecular Property Prediction; Representation*: Images</i>

<i>Task*: Molecular Property Prediction; Representation*: Fingerprints</i>

<i>Side Note: Molecular Structure Extraction and Recognition</i>

<a name="rnn" />

<b>3.2 Recurrent Neural Networks</b>

<i>Task*: Molecular Property Prediction; Representation*: SMILES Strings</i>

<i>Task*: Molecule Generation; Representation*: SMILES Strings</i>

<i>Task*: Molecule Generation; Representation*: Molecular Graphs</i>

<a name="gnn" />

<b>3.3 Graph Neural Networks</b>

<i>Task*: Molecular Property Prediction; Representation*: Molecular Graphs</i>

<i>Task*: Molecule Generation; Representation*: Molecular Graphs</i>

<i>Side Note: Common GNN Models</i>

<a name="vae" />

<b>3.4 Variational Autoencoders</b>

<i>Task*: Molecule Generation; Representation*: SMILES Strings</i>

<i>VAE Variant: AAE</i>

<i>Task*: Molecule Generation; Representation*: Molecular Graphs</i>

<i>Side Note: Reaction & Retrosynthesis Prediction; Representation*: Molecular Graphs</i>

<a name="gan" />

<b>3.5 Generative Adversarial Networks</b>

<i>Task*: Molecule Generation; Representation*: SMILES Strings</i>

<i>Task*: Molecule Generation; Representation*: Molecular Graphs</i>

<a name="flow" />

<b>3.6 Normalizing Flow Models</b>

<i>Task*: Molecule Generation; Representation*: Molecular Graphs</i>

<a name="transformer" />

<b>3.7 Transformers</b>

<i>Task*: Molecular Property Prediction; Representation*: SMILES Strings</i>

<i>Task*: Molecular Property Prediction; Representation*: Molecular Graphs</i>

<i>Task*: Molecule Generation; Representation*: SMILES Strings</i>

<i>Task*: Molecule Generation; Representation*: Molecular Graphs</i>


<a name="learning" />

4. Learning Paradigms

<a name="selfsuper" />

<b>4.1 Self-Supervised Learning in Molecular Property Prediction</b>

<a name="gl" />

<i>Generative Learning</i>

<a name="cl" />

<i>Contrastive Learning</i>

<a name="rl" />

<b>4.2 Reinforcement Learning in Molecule Generation</b>

<i>Side Note: Common RL Algorithms</i>

<i>Side Note: Pareto Optimality</i>

<i>Side Note: Reaction & Retrosynthesis Optimization</i>

<a name="otherlearning" />

<b>4.4 Other Learning Paradigms</b>

<a name="mel" />

<i>Metric Learning</i>

<a name="fsl" />

<i>Few-Shot Learning</i>

<a name="metal" />

<i>Meta Learning</i>

<a name="al" />

<i>Active Learning</i>


<a name="challenges" />

5. Addressing Existing Challenges

<i>Model Interpretation</i>

<i>Dataset Concerns</i>

<i>Uncertainty Estimation</i>

<i>Representation Capacity</i>

<i>Out-of-Distribution Generalization</i>

<i>Threshold Adjustment</i>

<i>Model Comparison</i>

<i>Model Adoption</i>

<i>Molecular Docking</i>

<i>Molecular Fragmentation & Assembly</i>