Back to home

Michael Swift, PhD

Professional Summary

I am a scientist at the intersection of biological experimentation and computational biology. Over 10 years I've designed high-throughput experiments — from massively parallel reporter assays to single-cell multi-omics — and built the computational tools to analyze them. I did my PhD at Stanford in systems biology and have worked across biotech startups and venture capital.

Skills

Computational Biology & Statistical Modeling

  • NGS & Sequence Analysis — custom high-throughput assay design and analysis (MPRAs, immune-repertoire sequencing, scRNA-seq); sequence databases (NCBI, UniProt); all NGS platforms
  • Modeling & ML — dimensionality reduction, clustering, and feature selection on single-cell and high-throughput biological data; model interpretation; sequence optimization
  • Tools — Python, scikit-learn, Jupyter, HuggingFace, Snakemake, PyTorch-based tools
  • Cloud Computing — cloud-scale data pipeline deployment (AWS, SLURM), experiment tracking, version control and code collaboration (GitHub), containerization (Docker)

Communication & Leadership

  • Scientific Communication — 5+ publications (Science, PNAS); conference speaker; strategic reports for non-technical audiences
  • Customer or Stakeholder Engagement — technical expert for Longitude Capital; managed research partnerships with CROs and other biotech startups at Kerna
  • Leadership — research program lead across academic, VC, and startup settings; hiring manager for multiple roles at Kerna

Experimental Biology

  • Techniques — high-throughput functional measurements, sequencing assay development, molecular cloning, gene synthesis, lab automation, biomolecular engineering & mRNA therapeutic design
  • Domains — immunology, systems biology, therapeutic discovery and development

Professional Experience

Kerna Labs — Research Scientist, Platform Development

San Francisco, CA · 2024–present

  • Applied RNA foundation models for biological sequence optimization, achieving 3–8X expression improvements on mRNA targets; evaluated model predictions against laboratory measurements to diagnose failure modes, developing guard rails, and guiding future iteration.
  • Designed and executed high-throughput mRNA UTR and coding sequence optimization campaigns using massively parallel reporter assays (MPRAs), spanning sequence design, gene synthesis, mRNA production, in vitro and in vivo evaluation, and downstream sequencing interpretation.
  • Built the team and coordinated cross-organizational research partnerships (Twist, TriLink, Aragen, Elegen, GenScript) across the mRNA therapeutic production stack.

Longitude Capital Management — Consultant

Menlo Park, CA · 2020–2024

  • Evaluated AI/ML focused biology startups; built investment frameworks for next-generation therapeutics and data-driven R&D.
  • Sourced and evaluated 200+ deal pitches, investor decks, data rooms, and KOL interviews.
  • Created investment memos and gave presentations that built internal consensus for 3 term-sheet submissions.
  • Produced strategic reports translating technical capabilities and opportunities in genomics and ML for general venture capital audiences.

miRagen Therapeutics — Research Associate

Boulder, CO · 2016–2017

  • Developed high-throughput screening assays for RNA therapeutic candidate prioritization; conducted preclinical studies supporting IND-enabling programs.

Education

Stanford University — PhD, Chemical and Systems Biology

2017–2023

  • Dissertation: The Generation and Maintenance of Diversity in the Human B Cell System
  • Built experimental and computational pipelines integrating multi-omic datasets (RNA-seq, repertoire sequencing, flow cytometry) for systems immunology projects.
  • Trained and applied deep learning and traditional models (including scVI, celltypist, cellbender) for feature selection, data filtering, automated data labeling, and gathering biological insights; evaluated protein language model representations of immune repertoires.
  • Collaborated with wet-lab scientists, computational biologists, and clinical researchers to deliver insights and publications from complex datasets.
  • NSF Graduate Research Fellowship; presented research at academic and industry conferences.

Claremont McKenna College — BA, Biochemistry (cum laude)

2012–2016

  • Thesis: Mechanisms of H19 Translation Avoidance
  • Awards: Dean's List (2014–2016)

Selected Research Projects

  • RNA Foundation Models (2024–present) — Applied and evaluated RNA foundation models for mRNA therapeutic design, including validating predictions against laboratory measurements to diagnose failure modes.
  • Protein Language Models (2023–2024) — Extracted and analyzed ESM-2 and AbLang embeddings of antibody sequences to evaluate what these models encode about immune biology. Used PCA and UMAP to examine how V gene families cluster in embedding space, quantified whether embedding distances reflect the biochemical magnitude of amino acid substitutions, and tested whether embeddings contain sufficient information to resolve clonal relationships (they did not).
  • Human B Cell Systems (2020–2023) — Co-led integrative modeling of immune repertoires and memory formation using multi-omic single-cell data.
  • In Vitro Immune Cell Reprogramming (2019–2022) — Designed perturbation experiments and applied ML to identify gene expression signatures driving lineage fate.
  • Tabula Sapiens Consortium (2018–2021) — Contributed to development of a human single-cell transcriptomic atlas; published in Science.