Class Data Sciences in Biotechnology

This Course Unit aims to understand concepts associated with Data Science oriented to biotechnology and similar areas. The student is introduced to the mathematical formulation of tools in the domains of Statistics and Probability, which enable the implementation, development and interpretation of scripts in Python language. In this sense, through supervised and unsupervised learning mechanisms, the student is able to generate solutions that comprise processing, analysis and visualization of relevant data sets, which can be extensive (big data) or not.   The relevance of this Curricular Unit is also completed with the study and modeling of applications in the biotechnological domain, such as the prediction of diseases in living beings to effects in genetically modified crops, in order to support decision-making either in academic research or in biobusiness.  

Not applicable

Introduction to Data Science in Biotechnology Mathematical Preliminaries for Data Science Data Munging. Scores and Rankings Statistical Analysis Data Visualization Mathematical Models in Data Science Linear Algebra Linear and Logistic Regression Machine Learning Big Data

In theoretical classes, the contents of the program are presented, using presentations and simulations, stimulating discussion between students and teacher. In theoretical-practical classes, students solve exercises with a progressive transition of complexity.   Assessment can be continuous or non-continuous.   Continuous assessment comprises a written test (theoretical component, TC) and delivery of two exercises solved during the semester (theoretical-practical component, TPC). TC consists of two frequencies or one exam. TCP consists of delivering two exercises solved via Moodle. The final grade for the Curricular Unit results from the calculation: Final Grade = 50% TC + 50% TCP, where TC and TCP are respectively the averages of the tests given in the scope of each component.   Alternatively, at the beginning of the semester, the student can select the non-continuous assessment mode. Thus, the student is submitted to an exam, which must have a minimum grade of 9.5 for approval.  

Trevor Hastie, Robert Tibshirani, Jerome Friedman (2009) The  Elements  of  Statistical  Learning:  Data  Mining,  Inference,  and  Prediction. 2nd edition. Springer (ISBN-13: 978-0387848570) Laura Igual, Santi Segui (2017) Introduction  to  Data  Science:  A  Python  Approach  to  Concepts,  Techniques,  and  Applications. 1st edition. Springer (ISBN-13: 978-3319500164)