Héctor Rodríguez-Pérez

[BIOINFORMATICS] > [DATA_SCIENCE] > [ML_RESEARCH]
about_me.sh
  • I'm Héctor, a PhD bioinformatics scientist with a strong foundation in computer science and specialized expertise in data science and machine learning. My work focuses on developing robust analytical methods for complex datasets, from genomic sequences to large-scale machine learning applications. With a background that bridges computational theory and practical implementation, I approach problems from multiple angles.
  • Beyond biological applications and data science, I'm passionate about computational techniques, programming language design, systems programming, and distributed computing architectures. My experience includes designing statistical models, implementing high-performance algorithms, and developing scalable systems for data processing. In all projects, I emphasize methodological rigor, code quality, and reproducible research practices.
most_relevant_publications.md
  1. Rodríguez-Pérez H, Ciuffreda L, Flores C. NanoRTax, a real-time pipeline for taxonomic and diversity analysis of nanopore 16S rRNA amplicon sequencing data. Computational and Structural Biotechnology Journal. 20, pp. 5350 - 5354. 2022.
  2. Rodríguez H, Ciuffreda L, Flores C. NanoCLUST: a species-level analysis of 16S rRNA nanopore sequencing data. Bioinformatics. 37 - 11, pp. 1600 - 1601. 2021.
  3. Ciuffreda L, Rodríguez Perez H, Flores Infante C. Nanopore sequencing and its application to the study of microbial communities. Computational and Structural Biotechnology Journal. 19, pp. 1497 - 1511. 2021.
  4. Rodríguez-Pérez H, Ciuffreda L. et al. Tracheal aspirate metagenomics reveals association of antibiotic resistance with non-pulmonary sepsis mortality. American Journal of Respiratory Cell and Molecular Biology. (2024).

For a complete list of publications, please visit my Google Scholar profile or PubMed.

SKILLS_AND_COMPETENCIES

BIOINFORMATICS

  • NGS Data Analysis and Pipelines (Nanopore, Illumina)
  • Human Genomics
  • Metagenomics
  • Antibiotic Resistance
  • Single-cell Genomics and Epigenomics

AI_&_MACHINE_LEARNING

  • Advanced Statistical Modeling
  • Deep Learning
  • LLMs and Open Source Language Models
  • Data Mining and Predictive Analysis in general

DEVELOPMENT

  • Python and R environments for data analysis and ML
  • Java, C/C++, Rust, Bash scripting
  • SQL and Database design
  • Linux enthusiast and system administration
  • Docker and HPC/cloud computing

PERSONAL_PROJECTS

KRAKENCLIP

A high-performance Rust utility for processing Kraken2 bioinformatics software reports and log files. Focused on fast and efficient processing of classifier outputs for large datasets or bioinformatics pipelines.

POKEPASSWORDS

A CLI tool built in Zig for secure password generation using Pokémon 2D sprite images as seeds.

2D-PARTICLES

A p5.js visualization playground for 2D particle systems with interactive effects, customizable particle behaviors, and adjustable physics parameters. Includes mouse-based particle interactions and visual effects.

TWITCH BATTLE ROYALE BOT

A Twitch bot that simulates a battle royale game in chat, allowing viewers to participate in an interactive experience.

PERSONA CHATTING BOT

A multiengine AI-powered Twitch bot that brings diverse interactions to chat using advanced GPT and Claude language models. The bot responds to messages based on chosen character personas.

LLM TRAINING MONITOR

A Rust-based CLI tool for monitoring LLM training processes. It provides real-time information about system resources used during LLM training, including CPU and GPU usage, memory consumption, and process-specific metrics.