From transcriptomics to proteomics: Unraveling biological knowledge via Machine Learning

• Autores: Guillermo Serrano Sanz
• Directores de la Tesis: Mikel Hernáez (dir. tes.), Elizabeth Guruceaga (dir. tes.)
• Lectura: En la Universidad de Navarra ( España ) en 2022
• Idioma: inglés
• Número de páginas: 146
• Tribunal Calificador de la Tesis: Antonio Pineda Lucena (presid.), Silvestre Vicent Cambra (secret.), Ian Michael Traniello (voc.), David Gómez-Cabrero López (voc.), Enrique Santamaría Martínez (voc.)
• Programa de doctorado: Programa de Doctorado en Medicina Aplicada y Biomedicina por la Universidad de Navarra
• Materias:
  • Ciencias de la vida
    • Genética
    • Biología molecular
  • Ciencias tecnológicas
    • Tecnología bioquímica
• Enlaces
  • Tesis en acceso abierto en: Dadun
• Resumen

  • We start by highlighting basic concepts of both molecular biology and machine learning. This overview focuses on the key ideas that are required to comprehend the rest of the work, and thus, it does not attempt at providing a comprehensive review. We start with the basis of DNA and RNA, the genetic building bricks, until the formation of the proteins, the final actors of the genetic machinery. We also explore state-of-the-art technologies to measure those processes along with their limitations. After introducing the basic biological concepts, we will discuss the basics of machine learning methodologies and some of the most important models used in recent years to solve many biological problems.