Application of data mining and artificial intelligence techniques to mass spectrometry data for knowledege discovery

  1. López Fernández, Hugo
Dirigida por:
  1. Miguel Reboiro Jato Director
  2. Daniel González Peña Director

Universidad de defensa: Universidade de Vigo

Fecha de defensa: 29 de marzo de 2016

Tribunal:
  1. Gilberto Paulo Peixoto Igrejas Presidente/a
  2. Fernando Díaz Gómez Secretario/a
  3. Anália Lourenço Vocal
Departamento:
  1. Informática

Tipo: Tesis

Resumen

Mass spectrometry using matrix assisted laser desorption ionization coupled to time of flight analyzers (MALDI-TOF MS) has become popular during the last decade due to its high speed, sensitivity and robustness for detecting proteins and peptides. This allows quickly analyzing large sets of samples are in one single batch and doing high-throughput proteomics. In this scenario, bioinformatics methods and computational tools play a key role in MALDI-TOF data analysis, as they are able handle the large amounts of raw data generated in order to extract new knowledge and useful conclusions. A typical MALDI-TOF MS data analysis workflow has three main stages: data acquisition, preprocessing and analysis. Although the most popular use of this technology is to identify proteins through their peptides, analyses that make use of artificial intelligence (AI), machine learning (ML), and statistical methods can be also carried out in order to perform biomarker discovery, automatic diagnosis, and knowledge discovery. In this research work, this workflow is deeply explored and new solutions based on the application of AI, ML, and statistical methods are proposed. In addition, an integrated software platform that supports the full MALDI-TOF MS data analysis workflow that facilitate the work of proteomics researchers without advanced bioinformatics skills has been developed and released to the scientific community.