Few-Shot Graph Learning for Molecular Property Prediction

The recent success of graph neural networks has significantly boosted molecular property prediction, advancing activities such as drug discovery. The existing deep neural network methods usually require large training dataset for each property, impairing their performance in cases (especially for new molecular properties) with a limited amount of experimental data, which are common in real situations. To this end, we propose Meta-MGNN, a novel model for few-shot molecular property prediction. Meta-MGNN applies molecular graph neural network to learn molecular representations and builds a meta-learning framework for model optimization. To exploit unlabeled molecular information and address task heterogeneity of different molecular properties, Meta-MGNN further incorporates molecular structures, attribute based self-supervised modules and self-attentive task weights into the former framework, strengthening the whole learning model. Extensive experiments on two public multi-property datasets demonstrate that Meta-MGNN outperforms a variety of state-of-the-art methods.

[1]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[2]  Xianfeng Tang,et al.  Learning from Multiple Cities: A Meta-Learning Approach for Spatial-Temporal Prediction , 2019, WWW.

[3]  Edward W. Lowe,et al.  Computational Methods in Drug Discovery , 2014, Pharmacological Reviews.

[4]  Jure Leskovec,et al.  Inductive Representation Learning on Large Graphs , 2017, NIPS.

[5]  Pietro Liò,et al.  Graph Attention Networks , 2017, ICLR.

[6]  Junzhou Huang,et al.  Seq2seq Fingerprint: An Unsupervised Deep Molecular Embedding for Drug Discovery , 2017, BCB.

[7]  Junzhou Huang,et al.  SMILES-BERT: Large Scale Unsupervised Pre-Training for Molecular Property Prediction , 2019, BCB.

[8]  Vijay S. Pande,et al.  Low Data Drug Discovery with One-Shot Learning , 2016, ACS central science.

[9]  Lei Jia,et al.  Chemi-Net: A Molecular Graph Convolutional Network for Accurate Drug Property Prediction , 2018, International journal of molecular sciences.

[10]  Tao Xiang,et al.  Learning to Compare: Relation Network for Few-Shot Learning , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[11]  Xiaoyu Zhang,et al.  Seq3seq Fingerprint: Towards End-to-end Semi-supervised Deep Drug Discovery , 2018, SIGB.

[12]  Bowen Zhou,et al.  A Structured Self-attentive Sentence Embedding , 2017, ICLR.

[13]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[14]  Sereina Riniker,et al.  Similarity maps - a visualization strategy for molecular fingerprints and machine-learning methods , 2013, Journal of Cheminformatics.

[15]  Yuan He,et al.  Graph Neural Networks for Social Recommendation , 2019, WWW.

[16]  Sergey Levine,et al.  Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks , 2017, ICML.

[17]  Nitesh V. Chawla,et al.  Few-Shot Knowledge Graph Completion , 2019, AAAI.

[18]  Nitesh Chawla,et al.  Few-Shot Multi-Hop Relation Reasoning over Knowledge Bases , 2020, FINDINGS.

[19]  Bin Li,et al.  Applications of machine learning in drug discovery and development , 2019, Nature Reviews Drug Discovery.

[20]  Wenhao Yu,et al.  Early Anomaly Detection by Learning and Forecasting Behavior , 2020, ArXiv.

[21]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[22]  Nitesh V. Chawla,et al.  Heterogeneous Graph Neural Network , 2019, KDD.

[23]  Jure Leskovec,et al.  How Powerful are Graph Neural Networks? , 2018, ICLR.

[24]  Elman Mansimov,et al.  Molecular Geometry Prediction using a Deep Generative Graph Neural Network , 2019, Scientific Reports.

[25]  Philip S. Yu,et al.  A Comprehensive Survey on Graph Neural Networks , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[26]  Joan Bruna,et al.  Few-Shot Learning with Graph Neural Networks , 2017, ICLR.

[27]  R. M. Owen,et al.  An analysis of the attrition of drug candidates from four major pharmaceutical companies , 2015, Nature Reviews Drug Discovery.

[28]  Jian Tang,et al.  Session-Based Social Recommendation via Dynamic Graph Attention Networks , 2019, WSDM.

[29]  Wenhao Yu,et al.  Identifying Referential Intention with Heterogeneous Contexts , 2020, WWW.

[30]  Jure Leskovec,et al.  Strategies for Pre-training Graph Neural Networks , 2020, ICLR.

[31]  Peer Bork,et al.  The SIDER database of drugs and side effects , 2015, Nucleic Acids Res..

[32]  Nitesh V. Chawla,et al.  Graph Few-shot Learning via Knowledge Transfer , 2020, AAAI.

[33]  Yoshua Bengio,et al.  MetaGAN: An Adversarial Approach to Few-Shot Learning , 2018, NeurIPS.

[34]  Oriol Vinyals,et al.  Matching Networks for One Shot Learning , 2016, NIPS.

[35]  Luca Bertinetto,et al.  Meta-learning with differentiable closed-form solvers , 2018, ICLR.

[36]  Ji Geng,et al.  Meta-GNN: On Few-shot Node Classification in Graph Meta-learning , 2019, CIKM.

[37]  Yuedong Yang,et al.  Identifying Structure-Property Relationships through SMILES Syntax Analysis with Self-Attention Mechanism , 2018, J. Chem. Inf. Model..

[38]  Qi Liu,et al.  Molecular Property Prediction: A Multilevel Quantum Interactions Modeling Perspective , 2019, AAAI.

[39]  David Weininger,et al.  SMILES. 2. Algorithm for generation of unique SMILES notation , 1989, J. Chem. Inf. Comput. Sci..

[40]  Nitesh Chawla,et al.  GraSeq: Graph and Sequence Fusion Learning for Molecular Property Prediction , 2020, CIKM.

[41]  Samuel S. Schoenholz,et al.  Neural Message Passing for Quantum Chemistry , 2017, ICML.

[42]  Vijay S. Pande,et al.  MoleculeNet: a benchmark for molecular machine learning , 2017, Chemical science.

[43]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[44]  Seungjin Choi,et al.  Gradient-Based Meta-Learning with Learned Layerwise Metric and Subspace , 2018, ICML.