Titulo Estágio
Machine learning applied to psychotic diseases diagnosis
Local do Estágio
Life Sciences Mass Spectrometry @ CNC, UC-Biotech
Enquadramento
The diagnosis of psychiatric diseases is based on a clinical interview with many potential confounding factors. The stratification of the patients can be misleading, and a bad diagnosis will not be translated to a good therapeutic approach. The use of proteomics and metabolomics large data screenings can be advantageous to indicate new potential biomarkers that can be of help to a faster and more precise diagnosis. However, the number of variables which are generated can be properly analyzed by a single person and extensive data extraction and integration will only be possible through machine learning approaches.
Objetivo
The main objective of this proposal is to develop a predictive model to improve the diagnosis of psychiatric disorders:
-organize large dataset screening data in a format which can be used by different platforms
-Perform Data Pre-Processing, Normalization and Scaling,
- Select appropriate ML algorithms for building the Predictive Model;
- Perform Sampling and Model Evaluation;
- Validate the overall Model with real data.
Plano de Trabalhos - Semestre 1
•Overview of diagnostic tools and proteomics and metabolomics datasets
Propose initial predictive model
•Prepare the intermediate report.
•Overview of Deep Learning techniques.
•Propose initial predictive model
•Prepare the intermediate report.
Plano de Trabalhos - Semestre 2
•Select, and preprocess a collection of large datasets for experiments;
•Study, and select, machine learning (ML) algorithms and feature selection (FS) algorithms for building the predictive model
•Analyze experimental results: e.g., study parameter values; compare performance of the reduced datasets vs. previous results, etc.;
•Prepare a research paper;
•Prepare the final version of the thesis.
Condições
This work will be carried out in the Laboratory of Neural Networks (LARN) of CISUC, where there will be a regular supervision and feedback on the behalf of the supervisors.
The work will also be performed at UC-Biotech, at the Life Sciences Mass Spectrometry lab
Familiarity with machine learning and data mining algorithms and software tools are essential. Participating students will acquire valuable knowledge and experience with model building and data science by mining massive datasets.
Observações
Orientador
Bruno Manadas
bmanadas@cnc.uc.pt 📩