PhD candidate in Molecular Biology working at the intersection of computational biology, regulatory genomics, RNA splicing, and machine learning.
I build sequence-to-function models, RNA-seq / splicing analysis pipelines, and interpretable ML workflows to study how genomic sequence encodes splicing regulation and immune-cell-specific transcript variation.
I am currently seeking roles in:
- Computational Biology
- Machine Learning for Genomics / Biology
- Bioinformatics
- Scientific ML / Research Engineering
- Alternative splicing regulation in immune systems
- Fine-tuning genomic foundation models for splicing prediction
- RNA-seq and splicing label generation pipelines
- Attribution, motif discovery, and model interpretation
- Reproducible analysis and training workflows for large genomics datasets
- Personal website — portfolio, project summaries, publications, and CV
sequence_to_function_model_tools— tooling for sequence-based regulatory genomics modeling- Selected RNA-seq / splicing analysis repositories — pipelines and analysis workflows from transcriptomics projects
ML / Engineering PyTorch · PyTorch Lightning · foundation model fine-tuning · interpretability · HPC / SLURM · reproducible workflows
Computational Biology RNA-seq · scRNA-seq · alternative splicing · STAR · StringTie · rMATS · regulatory genomics
- Website: jsdearbo.github.io
- GitHub: @jsdearbo
- LinkedIn: Jake Dearborn
- Email: jakedearborn@gmail.com
Most of my current work centers on RNA splicing regulation, immune transcriptomics, and interpretable deep learning for genomics.
If you're hiring in computational biology or ML for biology, feel free to reach out.

