About me
João Correia is an Assistant Professor at the Faculty of Engineering of the University of Porto and a co-founder of the spin-off OmniumAI. He holds a Ph.D. in Informatics (2024) and a Master’s degree in Bioinformatics (2018) from the University of Minho, as well as a Bachelor’s degree in Bioengineering (2016) from the University of Trás-os-Montes and Alto Douro. His research focuses on the development of artificial intelligence methods for chemical data analysis.
Publications
- NeuroScaler: Towards energy-optimal autoscaling for container-based services. Chaves, A. O., Moreira, R., Rodrigues Moreira, L. F., Correia, J., et al. IEEE ICC (2026). doi
- DeepMol: o pacote de quimioinformática pioneiro em Portugal. Capela, J., Correia, J., & Rocha, M. Boletim da Sociedade Portuguesa de Química (2026). doi
- DeepMol: an automated machine and deep learning framework for computational chemistry. Correia, J., Capela, J., & Rocha, M. Journal of Cheminformatics (2024). doi
- Combining evolutionary algorithms with reaction rules towards focused molecular design. Correia, J., Pereira, V., & Rocha, M. GECCO (2023). doi
- Evaluating molecular representations in machine learning models for drug response prediction and interpretability. Baptista, D., Correia, J., Pereira, B., & Rocha, M. Journal of Integrative Bioinformatics (2022). doi
- Predicting the number of biochemical transformations needed to synthesize a compound. Correia, J., Carreira, R., Pereira, V., & Rocha, M. IJCNN (2022). doi
- Development of deep learning approaches to predict relationships between chemical structures and sweetness. Capela, J., Correia, J., Pereira, V., & Rocha, M. IJCNN (2022). doi
- A comparison of different compound representations for drug sensitivity prediction. Baptista, D., Correia, J., Pereira, B., & Rocha, M. PACBB (2021). doi
- Generative deep learning for targeted compound design. Sousa, T., Correia, J., Pereira, V., & Rocha, M. Journal of Chemical Information and Modeling (2021). doi
- Combining multi-objective evolutionary algorithms with deep generative models towards focused molecular design. Sousa, T., Correia, J., Pereira, V., & Rocha, M. EvoApplications (2021). doi
- Artificial intelligence in biological activity prediction. Correia, J., Resende, T., Baptista, D., & Rocha, M. PACBB (2019). doi
Supervisions
Supervision
- A reinforcement learning framework for adaptive reaction-driven evolutionary molecular optimization, Lino Vaz, M.Sc. in Informatics and Computing Engineering, University of Porto (2026–2027, ongoing)
- Graph counterfactual explanations for multi-endpoint antimicrobial activity prediction, Daniela Osório, M.Sc. in Artificial Intelligence, University of Porto (2026–2027, ongoing)
- FoodLens: Um sistema multimodal de análise nutricional e recomendação de produtos alimentares, Diogo Silva, M.Sc. in Informatics and Computing Engineering, University of Porto (2026–2027, ongoing)
- Diversity-aware molecular generation with GFlowNets and evolutionary algorithms, Rafael Pacheco, M.Sc. in Artificial Intelligence, University of Porto (2026–2027, ongoing)
- Hybrid large language model and reaction-driven genetic operators for synthesis-aware molecular optimization, Valentina Cadime, M.Sc. in Artificial Intelligence, University of Porto (2026–2027, ongoing)
Co-supervision
- Generative Antimicrobial Peptide Design via Quality-Diversity Optimization, Carina Ferreira, M.Sc. in Bioinformatics, University of Minho (2026–2027, ongoing)
- Multiobjective optimization of chemical compounds with generative artificial intelligence with applications in the food industry, Catarina Gomes, M.Sc. in Bioinformatics, University of Minho (2025–present, ongoing)
- A machine learning-based approach to improving CD4 T-cell epitope immunogenicity prediction, Carolina Madaleno, M.Sc. in Data Science and Engineering, University of Porto (2025–2026)
- Enhancing explainability in machine and deep learning models for molecular activity prediction, Ricardo Oliveira, M.Sc. in Bioinformatics, University of Minho (2024–2025)
- Developing an automated machine and deep learning framework for protein classification, Guilherme Sousa, M.Sc. in Bioinformatics, University of Minho (2023–2024)
- Development of a machine learning-based application to predict the toxicity of chemical compounds, Diogo Rebelo, M.Sc. in Informatics Engineering, University of Minho (2023–2024)
- Development of a software application based on deep learning to predict drug sensitivity of cancer cell lines, Leonardo Marreiros, M.Sc. in Informatics Engineering, University of Minho (2022–2023)
- Development of deep learning-based tools for the design of new compounds with desired biological activities, Tiago Sousa, M.Sc. in Bioinformatics, University of Minho (2019–2020)
Software
- PyHIV: a Python package for local HIV-1 sequence alignment, subtyping and gene splitting.
- DeepMol: an automated machine and deep learning framework for computational chemistry.
- ReactEA: combines evolutionary algorithms with reaction rules for focused molecular design.
- BioCatalyzer: a rule-based tool to predict compound metabolism.