Titulo Estágio
Prediction of Molecular Properties using Spiking Neural Networks for Drug Discovery
Áreas de especialidade
Sistemas Inteligentes
Sistemas Inteligentes
Local do Estágio
Laboratory of Artificial Neural Networks (LARN-CISUC)
Enquadramento
Spiking Neural Networks (SNNs) are biologically inspired machine learning algorithms that have been gaining the attention of researchers for their potential in more energy-efficient computing compared to traditional systems. This type of artificial neural network (ANN) can be used for quantitative structure-activity relationship (QSAR) analysis, which is useful for predicting molecular properties relevant to the drug discovery and development process. Therefore, this research proposal aims to explore SNN architectures for the evaluation of important molecular properties for the selection of new drug candidate compounds. Hence, we aim to explore alternative SNN architectures and establish a new paradigm capable of addressing the challenge of predicting the molecular properties of new chemical compounds.
Objetivo
Improvement in the Prediction of Molecular Properties: Develop SNN models that achieve competitive results compared to state-of-the-art methods used in this task.
More Efficient Computing: Demonstrate the efficiency of SNNs for operating on chemical data when compared with more conventional models, highlighting this methodology as a sustainable tool for predicting molecular properties.
Contributions to Future Research: Provide insights into the practical implementation of SNNs in bioinformatics and inspire the exploration of bio-inspired computing paradigms.
Plano de Trabalhos - Semestre 1
1.Study the state-of-the-art SNN methodologies and chemical data representations used in bioinformatics;
2.Analyze the requirements of the SNN architecture to be developed, considering existing methodologies;
3.Design the architecture of the proposed framework and create a prototype;
4.Write an intermediate internship report.
Plano de Trabalhos - Semestre 2
1.Gather diverse datasets of chemical compounds with labels for toxicity, adverse effects, and other molecular properties from databases such as MoleculeNet, ChemBL, etc;
2.Implement preprocessing steps to convert molecular structures into appropriate input formats for SNNs (SMILES, fingerprints, molecular graphs);
3.Design and train SNN architectures using frameworks like PyTorch or TensorFlow. Explore different neural network configurations and learning strategies;
4.Evaluate the performance of SNN models in molecular property prediction using appropriate metrics and discuss model efficiency;
5.Submit an article to a journal or conference (to be determined);
6.Write and submit the thesis.
Condições
The internship will take place at the Laboratory of Artificial Neural Networks (LARN-CISUC) with regular meetings with the supervision team. The candidate should be strongly motivated to conduct research in the areas of artificial intelligence, machine learning and data science. Experience in Python and artificial neural networks is essential, as well as in related machine learning algorithms and software/programming tools. The selected candidate will be integrated within the research team currently working on the ongoing project NextGenAI – Centre For Responsible AI, supported by the National Recovery and Resilience Plan (PRR) and the Next Generation EU Funds.
Observações
A research grant opportunity, supported by the abovementioned project, will become available during the internship.
Orientador
Bernardete Ribeiro (Prof.) / Luis Torres (Prof. Convidado)
luistorres@dei.uc.pt 📩