Jesus Gonzalez Ferrer

PhD candidate at UC Santa Cruz

Graduate Researcher · Braingeneers, UC Santa Cruz

I work in the Braingeneers group with David Haussler and Mohammed Mostajo-Radji, and part-time at Genentech in the AIBT group. Previously M.Sc. in Computational Biology (Universidad Politécnica de Madrid) and B.Sc. in Biotechnology (Universidad Miguel Hernández).

Jesus Gonzalez Ferrer

I am a PhD candidate in Bioinformatics & Bioengineering at UC Santa Cruz, working in the Braingeneers group with David Haussler and Mohammed Mostajo-Radji. Before Santa Cruz, I completed an M.Sc. in Computational Biology at the Universidad Politécnica de Madrid and a B.Sc. in Biotechnology at the Universidad Miguel Hernández.

My work sits at the intersection of genomics, neuroscience and deep learning. I build computational tools for single-cell data, including SIMS, a deep-learning label-transfer method for scRNA-seq. I also develop models for neural electrophysiology, including HIPPIE, a generative model that classifies and translates extracellular recordings across species, technologies and modalities. Alongside that, I work on protosequences and cell-fate plasticity in human cortical organoids. Broadly, I want to use machine learning to understand how the brain develops and computes.

Next: A Virtual Brain Organoid

The direction I care about most is a virtual brain organoid: a model you could give a genotype and a perturbation, and ask what the tissue is going to do next. Which cell types appear, how they mature, and how the network ends up firing.

Most of the individual pieces are moving quickly. We can perturb organoids at scale, measure transcriptomics and electrical activity from the same tissue, and train models that transfer across species and recording technologies. The harder problem is putting them together in a way that works across labs, cell lines, and experimental systems.

That may be less of an algorithm problem than a coordination problem. There is still no agreed way to evaluate whether a model really predicts organoid dynamics, which makes any claim that one does hard to interpret. That is the part I am most interested in helping build: not only models that make predictions, but the datasets and benchmarks that let us find out whether those predictions hold up.

What would a virtual brain organoid actually be? →

Selected News

  1. Aug 2026

    Paper HIPPIE, our generative model for electrophysiological analysis across species, technologies and modalities, is out in Nature Communications.

    Nature CommunicationsGitHub
  2. Jul 2026

    Paper Our cloud-connected pluripotent stem cell platform, which lets students run and observe live stem cell experiments remotely, is out in Stem Cell Reports.

    Stem Cell Reports
  3. 2026

    Award Awarded a Dissertation-Year Fellowship by UC Santa Cruz for 2026–27.

  4. Jan 2026

    Paper Our work on preconfigured neuronal firing sequences in human brain organoids is out in Nature Neuroscience.

    Nature Neuroscience
  5. Jan 2026

    Preprint New preprint: CytoVerse runs single-cell AI foundation models entirely in the browser, searching 20M+ reference cells while keeping data private.

    bioRxivGitHub
  6. Jun 2025

    Paper A step-by-step protocol for deep-learning-driven cell type label transfer with SIMS is out in STAR Protocols.

    STAR ProtocolsGitHub
  7. Apr 2025

    Paper A perspective on automated, explainable high-throughput perturbation analysis in single cells is out in Patterns.

    Patterns
  8. Apr 2025

    Paper Our study of the fate plasticity of interneuron specification was published in iScience.

    iScience
  9. Mar 2025

    Preprint Released the HIPPIE preprint, a multimodal deep-learning model for the electrophysiological classification of neurons.

    bioRxivGitHub
  10. Jun 2024

    Paper SIMS, our deep-learning label-transfer tool for single-cell RNA-seq, was published in Cell Genomics.

    Cell GenomicsGitHub

Selected Publications

Full list on Google Scholar, or see the CV. (*) denotes co-first authorship.

  1. NeuroscienceDeep Learning

    HIPPIE: a generative model for electrophysiological analysis across species, technologies, and modalities

    Gonzalez-Ferrer, J., Lehrer, J., Alvarez-Esteban, B., Moreno-Ochando, A., Schweiger, H. E., … & Mostajo-Radji, M. A.

    Nature Communications, 2026.

    PaperGitHub
  2. Neuroscience

    Preconfigured neuronal firing sequences in human brain organoids

    van der Molen, T., Spaeth, A., Chini, M., Hernandez, S., Kaurala, G. A., Gonzalez-Ferrer, J., et al.

    Nature Neuroscience, 29(1), 123–135, 2026.

    Paper
  3. GenomicsDeep Learning

    SIMS: A deep-learning label transfer tool for single-cell RNA sequencing analysis

    Gonzalez-Ferrer, J., Lehrer, J., O'Farrell, A., Paten, B., Teodorescu, M., Haussler, D., … & Mostajo-Radji, M. A.

    Cell Genomics, 4(6), 2024.

    PaperGitHub
  4. GenomicsDeep Learning

    Toward automated and explainable high-throughput perturbation analysis in single cells

    Gonzalez-Ferrer, J. & Mostajo-Radji, M. A.

    Patterns, 6(4), 2025.

    Paper
  5. NeuroscienceGenomics

    Fate plasticity of interneuron specification

    Mostajo-Radji, M. A., Leon, W. R. M., Breevoort, A., Gonzalez-Ferrer, J., … & Pollen, A. A.

    iScience, 28(4), 2025.

    Paper
  6. GenomicsTools

    CytoVerse: Single-cell AI foundation models in the browser

    Currie, R.*, Gonzalez-Ferrer, J.*, Mostajo-Radji, M. A. & Haussler, D.

    bioRxiv, 2026.

    PreprintGitHub
  7. Tools

    Internet-enabled lab-on-a-chip technology for education

    Sano, T., Sampad, M. J. N., Gonzalez-Ferrer, J., et al.

    Scientific Reports, 14, 14364, 2024.

    Paper

Writing

Notes on neuroscience, genomics and ML on The Brainformatician.

All posts →