Hi, I'm Gabriel Navarro, PhD Computational Scientist
I employ cutting-edge computational methods to solve challenging scientific problems. Let's push the boundaries of research together!
Experienced Computational Scientist
-
Cross-Disciplinary ExpertiseOver a decade of experience at the intersection of biology, chemistry, and machine learning—spanning metabolomics, proteomics, genomics, and drug discovery.
-
Industry-Backed InnovationLed high-impact projects at global companies and startups, including Datacca, Triplebar, Brightseed, Amyris, Hexagon Bio, and Mondelez, building platforms used by R&D and commercial teams.
-
Scientific Rigor & Engineering PrecisionCombines deep scientific knowledge with advanced software and cloud engineering to turn raw biological data into scalable, actionable systems.
Machine Learning in Biosciences
-
Genome Language ModelsTrained and fine-tuned fungal genome language models to optimize protein expression and secretion, accelerating synthetic biology applications.
-
Protein Language ModelsFine-tuned antibody-specific PLMs to enhance sequence design with demonstrably improved functional outcomes
-
Molecule Fingerprints from Mass SpectrometryDeveloped machine learning models that mapped 20,000+ plant compounds to human health outcomes, driving a 1000x increase in phytonutrient discovery throughput.
-
Fungal Compound DiscoveryDesigned and deployed scalable workflows on Google Cloud Vertex AI using GATK, samtools, Dragen-OS, and other bioinformatics tools to streamline genomic analysis at scale.
Omics Infrastructure & Pipelines
🧫 Genomics
-
Scalable DNA ProcessingDesigned and deployed scalable workflows on Google Cloud Vertex AI using GATK, samtools, Dragen-OS, and other bioinformatics tools to streamline genomic analysis at scale.
🧪 Proteomics
-
End-to-End Proteomics PlatformBuilt a comprehensive proteomics pipeline supporting the entire research workflow—from benchside experimentation to insights-driven decision-making by scientists.
🧉 Metabolomics
-
Scalable DNA ProcessingDeveloped high-throughput metabolomics pipelines capable of processing terabyte-scale LC-MS/MS datasets for accelerated discovery.
Data Science & Visualization
-
Multi-Omics Platform for R&DBuilt interactive Python Dash and FastHTML dashboards to empower scientists to explore complex datasets and extract actionable insights across multi-omics domains.
Infrastructure & Scalability
-
Cloud BioinformaticsArchitected and deployed scalable, production-ready infrastructure to support AI/ML-driven genome and antibody design workflows in cloud environments.