Home


Research


Publication


Download


Teaching


Links

Machine Learning for Drug Discovery

Drug discovery is usually long and expensive. A lot of compounds are subject to a series of tests, but only one might turn out to be a viable drug. To discover a new drug, scientists need learn about a new biological discovery and examine many compounds to find the right ones for this specific discovery. The basic tests will be then conducted on those candidates for toxicity to determine whether the candidate compounds can be absorbed properly or not. Only those candidates that pass early tests will have chances enter into clinical trials. According to the Study of Drug Development, the average cost for a new drug is around $2.5 billion, and the success rate for drugs emarkably low. If deep learning could help better predict the toxicity before scientists try to take a drug to clinical trials, it would directly reduce remarkly costs and time. Even slightly improving the compound screening process, it will signicantly accelerate the drug discovery. This project will investigate how machine learning can be used to improve drug discovery on 1) finding new compounds as potential drugs; 2) predicting how well potential drugs will be; 3) and discovering the combinations of drug for better treatment.

Publication

  1. Yuwei Miao, Hehuan Ma and Junzhou Huang, "Recent Advances in Toxicity Prediction: Applications of Deep Graph Learning", Chemical Research in Toxicology, Volume 36, pp. 1206-1226, August 2023.
  2. Yuanfeng Ji, Lu Zhang, Jiaxiang Wu, Bingzhe Wu, Lanqing Li, Long-Kai Huang, Tingyang Xu, Yu Rong, Jie Ren, Ding Xue, Houtim Lai, Wei Liu, Junzhou Huang, Shuigeng Zhou, Ping Luo, Peilin Zhao and Yatao Bian,"DrugOOD: Out-of-Distribution Dataset Curator and Benchmark for AI-aided Drug Discovery - A Focus on Affinity Prediction Problems with Noise Annotations", In Proc. of the 37th AAAI Conference on Artificial Intelligence, AAAI’23, Washington, DC, USA, February 2023.
  3. Chaochao Yan, Peilin Zhao, Chan Lu, Yang Yu and Junzhou Huang, "RetroComposer: Composing Templates for Template-based Retrosynthesis Prediction", Biomolecules, Volume 12, September 2022.
  4. Chaochao Yan, Jinyu Yang, Hehuan Ma and Junzhou Huang, "Molecule Sequence Generation with Rebalanced Variational Loss", Journal of Computational Biology, Volume 29, August 2022.
  5. Hehuan Ma, Feng Jiang, Yu Rong, Yuzhi Guo and Junzhou Huang, "Robust Self-training Strategy for Various Molecular Biology Prediction Tasks", In Proc. of the 13th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, ACM BCB’22, Chicago, Illinois, USA, August 2022.
  6. Xiaochu Tong, Dingyan Wang, Xiaoyu Ding, Xiaoqin Tan, Qun Ren, Geng Chen, Yu Rong, Tingyang Xu, Junzhou Huang, Hualiang Jiang, Mingyue Zheng and Xutong Li, “Blood-Brain Barrier Penetration Prediction Enhanced by Uncertainty Estimation”, Journal of Cheminformatics, Volume 14, Number 44, July 2022.
  7. Qifeng Bai, Shuo Liu, Yanan Tian, Tingyang Xu, Antonio Jesús Banegas-Luna, Horacio Pérez-Sánchez, Junzhou Huang, Huanxiang Liu and Xiaojun Yao, "Application Advances of Deep Learning Methods for De Novo Drug Design and Molecular Dynamics Simulation", WIREs Computational Molecular Science, Volume 12, Issue 3, June 2022.
  8. Yuzhi Guo, Jiaxiang Wu, Hehuan Ma, Sheng Wang and Junzhou Huang, "Deep Ensemble Learning with Atrous Spatial Pyramid Networks for Protein Secondary Structure Prediction", Biomolecules, 12, 774, June 2022.
  9. Junchi Yu, Tingyang Xu, Yu Rong, Junzhou Huang and Ran He, "Structure-aware Conditional Variational Auto-encoder for Constrained Molecule Optimization", Pattern Recognition, Volume 126, June 2022.
  10. Hehuan Ma, Yatao Bian, Yu Rong, Wenbing Huang, Tingyang Xu, Weiyang Xie, Geyan Ye and Junzhou Huang, "Cross-Dependent Graph Neural Networks for Molecular Property Prediction", Bioinformatics, Volume 38, Issue 7, pp. 2003-2009, April 2022.
  11. Wenbing Huang, Jiaqi Han, Yu Rong, Tingyang Xu, Fuchun Sun and Junzhou Huang, "Constrained Graph Mechanics Networks", In Proc. of the Tenth International Conference on Learning Representations, ICLR'22, April 2022.
  12. Yuzhi Guo, Jiaxiang Wu, Hehuan Ma and Junzhou Huang, "Self-supervised Pretraining for Protein Embeddings Using Tertiary Structures", In Proc. of the Thirty-Sixth AAAI Conference on Artificial Intelligence, AAAI'22, Vancouver, Canada, February 2022.
  13. Peng Han, Peilin Zhao, Chan Lu, Junzhou Huang, Jiaxiang Wu, Shuo Shang, Bin Yao, Xiangliang Zhang, "GNN-Retro: Retrosynthetic planning with Graph Neural Networks", In Proc. of the Thirty-Sixth AAAI Conference on Artificial Intelligence, AAAI'22, Vancouver, Canada, February 2022.
  14. Tao Shen, Jiaxiang Wu, Haidong Lan, Liangzhen Zheng, Jianguo Pei, Sheng Wang, Wei Liu and Junzhou Huang, "When Homologous Sequences Meet Structural Decoys: Accurate Contact Prediction by tFold in CASP14", PROTEINS: Structure, Function, and Bioinformatics, Volume89, Issue12, pp. 1901-1910, December 2021.
  15. Hehuan Ma, Yu Rong, Boyang Liu, Yuzhi Guo, Chaochao Yan, and Junzhou Huang, "Gradient-Norm Based Attentive Loss for Molecular Property Prediction”, In Proc. of IEEE International Conference on Bioinformatics and Biomedicine, BIBM’21, December 2021.
  16. Huaxiu Yao, Ying Wei, Long-Kai Huang, Ding Xue, Junzhou Huang, Zhenhui Li, "Functionally Regionalized Knowledge Transfer for Low-resource Drug Discovery", In Proc. of the 35th Annual Conference on Neural Information Processing Systems, NeurIPS'21, December 2021.
  17. Kelong Mao, Xi Xiao, Tingyang Xu, Yu Rong, Junzhou Huang and Peilin Zhao, "Molecular Graph Enhanced Transformer for Retrosynthesis Prediction", Neurocomputing, Volume 457, pp. 193-202, October 2021.
  18. Yang Yu, Tingyang Xu, Jiawen Li, Yaping Qiu, Yu Rong, Zhen Gong, Xuemin Cheng, Liming Dong, Wei Liu, Jin Li, Dengfeng Dou and Junzhou Huang, "A Novel Scalarized Scaffold Hopping Algorithm with Graph-based Variational Autoencoder for Discovery of JAK1 Inhibitors", ACS Omega, Volume 6, pp. 22945-22954, August 2021.
  19. Qifeng Bai, Jian Ma, Shuo Liu, Tingyang Xud, Antonio Jess Banegas-Luna, Horacio Prez-Snchez, Yanan Tian, Junzhou Huang, Huanxiang Liu and Xiaojun Yao, "WADDAICA: A Webserver for Aiding Protein Drug Design by Artificial Intelligence and Classical Algorithm", Computational and Structural Biotechnology Journal, Volume 19, pp. 3573-3579, June 2021.
  20. Yuzhi Guo, Jiaxiang Wu, Hehuan Ma, Sheng Wang and Junzhou Huang, "Comprehensive Study of Bagging MSA Learning for Protein Structure Property Prediction", Journal of Computational Biology,Volume 28, Number 4, April 2021. [CODE]
  21. Hehuan Ma, Weizhi An, Yuhong Wang, Hongmao Sun, Ruili Huang and Junzhou Huang, "Deep Graph Learning with Property Augmentation for Predicting Drug-Induced Liver Injury", Chemical Research in Toxicology, Volume 34, Issue 2, pp. 495-506, February 2021.
  22. Qin Wang, Boyuan Wang, Zhenlei Xu, Jiaxiang Wu, Peilin Zhao, Zhen Li, Sheng Wang, Junzhou Huang and Shuguang Cui, “PSSM-Distil: Protein Secondary Structure Prediction (PSSP) on Low-Quality PSSM by Knowledge Distillation with Contrastive Learning”, In Proc. of the Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI’21, Vancouver, Canada, February 2021.
  23. Chaochao Yan, Qianggang Ding, Peilin Zhao, Shuangjia Zheng, Jinyu Yang, Yang Yu and Junzhou Huang, "RetroXpert: Decompose Retrosynthesis Prediction Like A Chemist”, In Proc. of the 34th Annual Conference on Neural Information Processing Systems, NeurIPS'20, Vancouver, Canada, December 2020.
  24. Yu Rong, Yatao Bian, Tingyang Xu, Weiyang Xie, Ying Wei, Wenbing Huang and Junzhou Huang, "GROVER: Self-Supervised Message Passing Transformer on Largescale Molecular Graphs”, In Proc. of the 34th Annual Conference on Neural Information Processing Systems, NeurIPS'20, Vancouver, Canada, December 2020
  25. Chaochao Yan, Sheng Wang, Jinyu Yang, Tingyang Xu and Junzhou Huang, "Re-balancing Variational Autoencoder Loss for Molecule Sequence Generation", In Proc. of the 11th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics, ACM BCB'20, September 2020.
  26. Qifeng Bai, Shuoyan Tan, Tingyang Xu, Huanxiang Liu, Junzhou Huang, Xiaojun Yao, "MolAICal: a Soft Tool for 3D Drug Design of Protein Targets by Artificial Intelligence and Classical Algorithm”, Briefings in Bioinformatics, August 2020.
  27. Yuzhi Guo, Jiaxiang Wu, Hehuan Ma, Sheng Wang and Junzhou Huang, "Bagging MSA Learning: Enhancing Low-quality PSSM with Deep Learning for Accurate Protein Structure Property Prediction", In Proc. of The 24th International Conference on Research in Computational Molecular Biology, RECOMB'20, Padova, Italy, May 2020. [CODE]
  28. Sheng Wang, Yuzhi Guo, Yuhong Wang, Hongmao Sun and Junzhou Huang, "SMILES-BERT: Large Scale Unsupervised Pre-Training for Molecular Property Prediction", In Proc. of The 10th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics, ACM BCB'19, Niagara Falls, NY, USA, September 2019.
  29. Xiaoyu Zhang, Sheng Wang, Feiyun Zhu, Zheng Xu, Yuhong Wang and Junzhou Huang, "Seq3seq Fingerprint: Towards End-to-end Semi-supervised Deep Drug Discovery", In Proc. of The 9th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics, ACM BCB'18, Washington DC, USA, September 2018.
  30. Ruoyu Li, Sheng Wang, Feiyun Zhu and Junzhou Huang, “Adaptive Graph Convolutional Neural Networks”, In Proc. of The Thirty-Second AAAI Conference on Artificial Intelligence, AAAI'18, New Orleans, USA, February 2018. (Oral Presentation) [CODE]
  31. Yuhong Wang, Junzhou Huang, Wei Li, Sheng Wang and Chuanfan Ding, “Specific and Intrinsic Sequence Patterns Extracted by Deep Learning from Intra-Protein Binding and Non-binding Peptide Fragments”, Scientific Reports, November 2017.
  32. Zheng Xu, Sheng Wang, Feiyun Zhu and Junzhou Huang, “Seq2seq Fingerprint: An Unsupervised Deep Molecular Embedding for Drug Discovery”, In Proc. of the 8th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics, ACM BCB'17, Boston, MA, August 2017. [CODE]