I'm a computational biologist and software-focused researcher who builds reproducible tools for genomics, structural biology, and machine learning. My background combines biochemistry, computer science, and high-performance computing, which allows me to move comfortably between biological questions, scalable data workflows, and production-quality scientific software.
I am currently completing an M.S. in Computer Science at the University of Illinois Urbana-Champaign and have completed an M.S degree in Biochemistry. I have about three years of experience in research and industry work where I have enjoyed building tools that help scientists analyze complex biological data, interpret results, and make research workflows easier to reproduce and scale.
flowchart LR
A[Biological Question] --> B[Data Processing]
B --> C[Reproducible Pipeline]
C --> D[Machine Learning / Statistical Analysis]
D --> E[Biological Interpretation]
E --> F[Documentation + Usable Tools]
I am especially interested in roles where I can contribute to:
- Bioinformatics and computational biology software
- Genomics, transcriptomics, and spatial omics workflows
- Machine learning for biological or healthcare data
- Research software engineering and reproducible scientific computing
- Cloud/HPC-based analysis pipelines
Bioinformatics & Scientific Computing: NGS analysis, RNA-seq, ChIP-seq, genome assembly, spatial transcriptomics, AlphaFold 2/3, PyMOL, VMD, Nextflow, SLURM, HPC workflows
Built reproducible cloud-based bioinformatics and machine learning workflows for spatial transcriptomics analysis, using Docker, AWS EC2, S3, Python, Scanpy, and Squidpy. Designed the workflow to move from local development to cloud execution while preserving reproducibility, organized outputs, trained models, logs, and processed data.
Highlights
- Dockerized an end-to-end 10x Visium breast cancer spatial transcriptomics workflow
- Ran the pipeline on AWS EC2 with S3-backed input/output storage and IAM-based access
- Built supervised ML workflows to classify biologically annotated spatial tumor microenvironment niches
- Compared five ML models across expression-derived, marker-signature, QC, spatial-coordinate, and neighbor-context features
- Implemented spatial holdout validation using a 3 × 3 tissue grid to test model robustness beyond random train/test splits
- Documented cloud execution with an EC2/S3 runbook for reproducible deployment
Tech: AWS EC2 AWS S3 IAM Docker Python Scanpy Squidpy spatial transcriptomics machine learning data engineering bioinformatics pipelines
Developed Python-based workflows for structural and functional protein-ligand analysis, including conserved binding residue identification and large-scale experimentation on HPC systems.
Highlights
- Used AlphaFold, PyMOL, VMD, and Python-based analysis tools
- Ran and validated compute-intensive workflows on HPC clusters with SLURM
- Improved code maintainability and usability for scientists
Tech: Python AlphaFold PyMOL VMD SLURM HPC structural biology
Built machine learning workflows for biomedical data, including multi-label ECG classification and healthcare-focused model development.
Highlights
- Developed task structure for multi-label ECG classification
- Worked with physiological waveform-style data
- Emphasized clean APIs, testing, and documentation
Tech: Python PyTorch machine learning healthcare data time series testing
Re-implemented and validated comparative single-cell RNA-seq workflows with an emphasis on reproducibility, modular design, and fair method comparison.
Highlights
- Built modular workflows for comparing analysis methods
- Focused on reproducibility and validation of published results
- Connected computational outputs back to biological interpretation
Tech: R Python single-cell RNA-seq benchmarking reproducible research
I bring a combination that is especially useful for bioinformatics, computational biology, and scientific software roles:
- Biology fluency: I understand the experimental context behind genomics, transcriptomics, structural biology, and molecular biology data.
- Software engineering mindset: I care about maintainable code, documentation, testing, and tools that other scientists can actually use.
- Scalable computing experience: I have worked with HPC, SLURM, Docker, AWS, and large biological datasets.
- Communication strength: I have written tutorials, taught technical concepts, collaborated across disciplines, and presented research clearly.
I am most excited about roles in bioinformatics, computational biology, machine learning for biology/healthcare, and research software engineering.
- GitHub: github.com/misaell2
- LinkedIn: linkedin.com/in/misael-lazaro
- Email: lazaromisael95@gmail.com
Thanks for visiting my profile! I am always interested in projects at the intersection of biology, software, and machine learning.