Resume
Last updated November 2023.
General Information
| Full Name | Santiago Manuel Castro Dau |
| Date of Birth | 24th of May 1995 |
| Languages | Spanish (native), English (fluent), German (B1) |
| Nationalities | Mexico and United States of America |
Education
-
2020 - 2023 Master of Science in Computational Biology and Bioinformatics
ETH Zürich, Zürich, Switzerland - Final average, 5.6/6
- Master's thesis grade 6/6
-
2014 - 2019 Bachelor of Engineering in Chemical Engineering
Universidad Nacional Autónoma de México, Mexico City, Mexico - Admission rate for 2014 was 10% of applicants
- Graduated with honors, top 7% of cohort
- Final average, 9.6/10
-
2018 Visiting Student
University of Tokyo, Tokyo, Japan
Experience
-
2023 - Today Software Engineer
Food Systems Biotechnology group, ETH Zürich - Developing microbiome analysis software tools for Qiime2, a package collection with reproducibility at its core.
- Supervisor: Michal Ziemski
-
2022-2023 Research Assistant
Artificial Intelligence for Single Cell Research group, IBM Research Zürich - Designed and implemented an innovative machine learning framework, enabling interpretable predictions of tumor tissue images through concept and geometric-deep learning.
- Supervisors at IBM: Marianna Rapsomaniki, Pushpak Pati and Adriano Martinelli
- Supervisor at UZH: Mark Robinson
-
2022 Research Assistant
Cortical Computation group, Institute of Neuroinformatics ETH/UZH - Modeled the learning process in biological neurons by representing the system with an artificial neural network and describing its dynamics through mixture model parameter inference.
- Supervisor: Matthew Cook
-
2021 Research Assistant
Computational Evolution group, ETH Zürich - Conducted a statistical analysis of epidemiological data to investigate the potential applicability of a COVID-19 effective reproductive number estimator to data from countries outside the EU.
- Supervisor: Jana Sanne Huisman
-
2019 - 2020 Research Assistant
Computational Genomics group, Instituto Nacional de Medicina Genomica, Mexico City - Conducted a statistical analysis of copy number mutations in breast cancer to explore their impact on the structure of the transcriptional network.
- Supervisor: Enrique Hernández Lemus
Achievements
-
2023 Contributed Talk
- Selected for an oral presentation at Basel Computational Biology Conference, Switzerland’s main event in the domain of Computational Biology and one of the major events of its kind in Europe.
-
2021 Winner of ETH Week 2021
- I was part of the winning team of 'ETH Week 2021: Health for Tomorrow', an interdisciplinary, innovative, problem-solving challenge that required us to come up with an attractive solution for a real-world health related problem.
-
2020 Scholarship Awardee
- Recipient of Jóvenes de Excelencia Citibanamex scholarship for promising graduates looking to continue their studies at a recognized international institution.
-
2019 Contributed Talk
- Selected for an oral presentation at Instituto Nacional de Medicina Genomica’s 5th Student Encounter.
-
2018 Scholarship Awardee
- Recipient of Beca de Movilidad Internacional scholarship to study abroad at the University of Tokyo in Japan, one of the world’s top academic institutions.
Academic Interests
-
Artificial Intelligence
- Probabilistic AI
- Interpretability and Explainability
- Bayesian Learning
-
Biology
- Tissue structure and functioning
- Computing in bimolecular systems
- Computation and memory in the brain
- Stochastisity in biological systems
-
Others
- Philosophy of Science
- Causality
- Experimental Design
- Information Theory
- Dynamical Systems
Programming Skills
-
- Programming lenguages; Python, R, git/GitHub, C++, SQL, Matlab, Bash, LATEX.
- Fluency in popular libraries and command line tools, e.g. PyTorch, scikit-learn, MLFlow, Snakemake, NetworkX, Qiime2, Tidyverse.
- Experience developing software in Python adhering to various standard technologies and best practices including CI/CD tools.
- First-hand experience with bash scripting, workflow management systems and high-performance computing environments.
- Experience with a variety of machine learning approaches, e.g. bayesian, concept, reinforcement and active learning, geometric deep-learning, and vision transformers.
- Familiarity with proteomic, genomic, transcriptomic, and spatial datasets.