D4 - Deep Drug Discovery and Deployment (PI: Bernardete Ribeiro; co-PI: Joel P. Arrais)
Scope
National
Research Group
coordinator
Synopsis
The traditional drug discovery process may take up to 15 years from conceptualization to market with a cost that can reach one thousand million, without any warranties that the identified compounds will reach the market. The first three stages, namely target identification, lead discovery, and lead optimization, may take 4 to 7 years alone. This is mainly a data-driven process that starts with all human proteins that can be used as putative targets, the millions of lead compounds that need to be evaluated and, for the final candidates, a massive number of structural variants to be tested. D4 is a joint venture to address the challenge of using computational methods to improve the pipeline for drug discovery and deployment. D4 proposes the use of state-of-the-art Deep Learning methods to tackle the challenges identified on each of the initial stages of the drug discovery pipeline. Deep networks were proven to be more effective than shallow architectures to face complex problems like speech or image recognition. In addition, deep architectures are able to amplify key discriminative aspects from the input data while suppressing irrelevant information, thus attaining improved accuracy. D4 will explore these advantages. For instance, target identification can benefit from the improved use of methods for representation learning instead of relying on manual feature engineering. Restricted Boltzmann Machines rely on the correct evaluation of features that better represent the small variations in protein structure, which can be potentially used in the lead identification stage. The lead optimization stage can capitalize from the iterative refinement of methodologies that comply with low starting data such as Zero-Shot Learning. The project team brings together researchers from University of Coimbra (UC) and University of Aveiro (UA). These researchers combine a unique set of expertise in Machine Learning, with focus on Pattern Recognition, Deep Learning and Differential Geometry, and on Computational Biology with emphasis on the prediction of protein and drug interactions. This project also includes one industrial partner, BSIM2, which will contribute to shape the project requirements, in addition to help explore the market viability of research results. BSIM2 is particularly interested on a drug discovery programme that targets transthyretin-related amyloid diseases. This will be used as case study to validate the proposed methodologies. The main contribution of this project is the creation of an improved computational pipeline that uses Deep Learning architectures to support the drug discovery process. The pipeline will be implemented within a framework that will be available to the community. Both the final platform and the computational methods will be validated with the close collaboration of the industrial partner, which will apply it to develop novel therapeutics for neurodegenerative amyloid diseases.
Funding
FCT
Total budget
€ 239 796.00
Keywords
Deep Learning, Drug Discovery; Bioinformatics
Start Date
2018-07-01
Partners
Universidade de Aveiro, BSIM2
CISUC budget
€ 175 746.00
End Date
2021-06-30
Publications
2024
L. H. M. Torres and B. Ribeiro and J. P. Arrais, "Multi-scale cross-attention transformer via graph embeddings for few-shot molecular property prediction", in Applied Soft Computing, vol. 153, no. 111268, 2024
2023
L. H. M. Torres and J. P. Arrais and B. Ribeiro, "Few-shot learning via graph embeddings with convolutional networks for low-data molecular property prediction", Neural Computing and Applications, in Neural Computing and Applications, 2023
L. H. M. Torres and B. Ribeiro and J. P. Arrais, "Few-shot learning with transformers via graph embeddings for molecular property prediction", Expert Systems with Applications, in Expert Systems with Applications, pp. 120005-120005, 2023
L. H. M. Torres and B. Ribeiro and J. P. Arrais, "Convolutional Transformer via Graph Embeddings for Few-shot Toxicity and Side Effect Prediction", in ESANN 2023 proceedings, 2023
2022
J. P. Arrais and J. L. Oliveira and M. Abbasi and H. V. Ávila and C. J. V. Simões and N. R. C. Monteiro, "Explainable deep drug–target representations for binding affinity prediction", BMC Bioinformatics, in BMC Bioinformatics, vol. 23, 2022
2021
T. Pereira and M. Abbasi and J. P. Arrais and B. Ribeiro and J. L. Oliveira, "Optimizing blood–brain barrier permeation through deep reinforcement learning for de novo drug design", Bioinformatics, vol. 37, no. Supplement_1, pp. i84-i92, 2021
T. Pereira and M. Abbasi and B. Ribeiro and J. P. Arrais, "Diversity oriented Deep Reinforcement Learning for targeted molecule generation", Journal of cheminformatics, vol. 13, no. 1, 2021
M. Abbasi and T. Pereira and B. Ribeiro and J. P. Arrais and B. P. Santos, "Optimizing Recurrent Neural Network Architectures for De Novo Drug Design", 2021
M. Abbasi and B. Ribeiro and J. P. Arrais and T. Pereira and B. P. Santos, "Improvement on Generative Adversarial Network for Targeted Drug Design", in The 29th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2021), 2021
M. Abbasi and T. Pereira and B. Ribeiro and J. P. Arrais and B. P. Santos, "Multiobjective Reinforcement Learning in Optimized Drug Design", in The 29th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2021), 2021
2020
N. R. C. Monteiro and B. Ribeiro and J. P. Arrais, "Drug-Target Interaction Prediction: End-to-End Deep Learning Approach", IEEE/ACM Transactions on Computational Biology and Bioinformatics, pp. 1-1, 2020
T. Pereira and M. Abbasi and B. Ribeiro and J. P. Arrais, "Deep Reinforcement Learning for Optimized Drug Design", in Bioinformatics Open Days, 2020
L. H. M. Torres and N. R. C. Monteiro and B. Ribeiro and J. P. Arrais, "Siamese Neural Networks for One-Shot Drug Discovery", in Bioinformatics Open Days (BOD) 2020, 2020
J. P. Arrais and C. Pereira and L. Silva, "Using a Novel Unbiased Dataset and Deep Learning Architectures to Predict Protein-Protein Interactions", in International Conference on Bioinformatics and Biomedicine (BIBM), 2020
M. Abbasi and B. Ribeiro and T. Pereira and J. P. Arrais, "End-to-end Deep Reinforcement Learning for Targeted Drug Generation", 2020
L. H. M. Torres and N. R. C. Monteiro and J. P. Arrais and B. Ribeiro, "Exploring a Siamese Neural Network Architecture for One-Shot Drug Discovery", in Exploring a Siamese Neural Network Architecture for One-Shot Drug Discovery, 2020
2019
N. R. C. Monteiro and B. Ribeiro and J. P. Arrais, "Deep Neural Network Architecture for Drug-Target Interaction Prediction", in Artificial Neural Networks and Machine Learning – ICANN 2019, 2019
N. R. C. Monteiro and B. Ribeiro and J. P. Arrais, "Drug-Target Interaction Prediction: End-to-End Deep Learning Approach", in Bioinformatics Open Days (BOD) 2019, 2019
N. R. C. Monteiro and B. Ribeiro and J. P. Arrais, "End-to-End Deep Learning Approach for Drug-Target Interaction Prediction", in Ciência2019, 2019
2018
J. Albuquerque and C. Pereira and J. P. Arrais, "Analysis of Auto-encoders for Feature Representation of Protein Sequences", in 24th Portuguese Conference on Pattern Recognition, 2018
N. R. C. Monteiro and B. Ribeiro and J. P. Arrais, "Drug-Target Interaction Prediction: End-to-End Deep Learning Approach", in EJIBCE2018, 2018