Eva Cano Gallego

Developed code in R, Python and bash to implement and integrate Docker containerized Machine Learning models. Download and process large datasets stored in PostgresSQL for their transformation into actionable insights for the model training. Statistical analysis to select the most relevant predictive variables. (% of missings, constant features, correlations, and PSI analysis) Evaluated model performance to select the best-performing model for the production deployment (AUC, KS, Gini). Created model result visualization in Power BI, achieving 80% of time savings in report generation.

NGS data analysis (RNA-seq, WES,MinION): copy number variation, SNPs, differential expression analysis. Developed an end-to-end pipeline (R and Python), to diagnose potential genetic mutations through the detection of copy number variants from whole exome sequencing data. Containerized software with Singularity, ensembled pipelines with Snakemake, and created environments using conda. Managed version control with git and remote repositories (Github).

Developed end-to-end control-quality software with R and Python to check the outputs generated by a team-developed RNA-Seq differential expression analysis pipeline. Containerized software with Docker. Managed version control and teamwork with git and remote repositories (Github). Contributed to database design using PostGreSQL.