PeopleofSuperintelligence

Researcher

Isidro Hotzel

Also known as Isidro Hötzel

Isidro Hotzel is a Distinguished Scientist (Technology) in Antibody Engineering at Genentech and a coauthor of generative-model papers on antibody design. After starting at Genentech in 2005 as a Scientist, they coauthored a 2015 paper on a dual-host phage display vector and an August 2019 study that sequenced more than 250,000 B cells across rat, mouse and human repertoires. In 2023, Hotzel coauthored AbDiffuser, a diffusion model that generates antibody structures and sequences, and the Discrete Walk-Jump Sampling paper, which received an Outstanding Paper award at ICLR 2024. A February 2025 lab-in-the-loop preprint with Hotzel among its authors reported more than 1,800 designed and tested antibody variants. Their group at Genentech works on phage display, antibody repertoire sequencing and bioinformatics tools for antibody engineering.

Now at
Roche
Badges

Timeline

  1. 2005

    Joining Genentech as a Scientist

    In 2005, Hotzel starts at Genentech as a Scientist to develop technologies for antibody discovery against challenging targets. Collaborations with Genentech groups in molecular biology, oncology, infectious diseases, structural biology and protein engineering apply those technologies to potential therapeutic molecules.

  2. 2015

    A dual-host phage display vector

    Hotzel coauthors a 2015 paper in Protein Engineering, Design and Selection on modular protein expression by RNA trans-splicing. The method allows flexible expression of antibody formats in mammalian cells from a dual-host phage display vector.

  3. August 2019

    Single-cell B-cell receptor sequencing

    In August 2019, they coauthor a Communications Biology paper on massively parallel single-cell B-cell receptor sequencing for discovering antigen-reactive antibodies. The study sequences more than 250,000 B cells from rat, mouse and human repertoires to characterize their lineages and expansion.

  4. June 2023

    Discrete Walk-Jump Sampling

    The preprint Protein Discovery with Discrete Walk-Jump Sampling appears on arXiv in June 2023 with Hotzel among its thirteen authors. The method learns a smoothed energy function, samples it with Langevin MCMC and projects back with one-step denoising; in laboratory tests, 97–100% of generated antibody samples are expressed and purified, and 70% of functional designs match or improve on the binding affinity of known functional antibodies.

  5. 2023

    AbDiffuser at NeurIPS

    At NeurIPS 2023, Hotzel is a coauthor of AbDiffuser, a diffusion model that generates antibody 3D structures and sequences together. Laboratory experiments confirm that all 16 HER2 antibodies discovered are expressed at high levels and that 57.1% of the selected designs are tight binders.

  6. 2024

    An outstanding paper at ICLR

    At ICLR 2024, Protein Discovery with Discrete Walk-Jump Sampling, with Hotzel among its authors, is presented as an oral and receives an Outstanding Paper award.

  7. February 2025

    Lab-in-the-loop antibody design

    In February 2025, the bioRxiv preprint Lab-in-the-loop therapeutic antibody design with deep learning lists Hotzel among its authors. It combines generative models, property predictors, active learning and laboratory experiments in an iterative loop, and over 1,800 unique antibody variants are designed and tested against EGFR, IL-6, HER2 and OSM. Every target gains variants with 3–100x better binding.

  8. As of October 2026

    Distinguished Scientist at Genentech

    Hotzel is a Distinguished Scientist (Technology) in Antibody Engineering, Drug Discovery, at Genentech as of 2026. Their group works on phage display, next-generation sequencing of antibody repertoires and antibody libraries, streamlined protein expression, assays for drug-like properties of antibody candidates, and bioinformatics tools for antibody engineering.

  1. The company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes Roche. We estimate where the people shaping AI worked when their most-cited papers appeared: the company share was 31% in 2020–2024 and 8% in 1970–1974, and Google led all organizations in 2020–2024.
  2. 20% of people at companies who shape AI also hold a university role, led by Google and Stanford UniversityIncludes Roche. We estimate that 539 of the 6,766 people with a known current organization (8%) hold both a university role and a company role, including 20% of people at companies and 13% of people at universities.
  3. Google had the most people shaping AI every year from 2014 to 2025Our estimates of which organizations employed the most people shaping AI each year from 1955 to 2025, tracing the shift from university labs to companies.
  4. The United States employs an estimated 48% of people shaping AIWe estimate where the people shaping AI work today, how universities, companies and research institutes split across countries, and how country shares have changed since the 1960s.

Colleagues

People with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Isidro Hotzel yet. Send us a free-licensed photo.

  1. Genentech: Isidro Hötzel | Distinguished Scientist (Technology), Antibody Engineering, Drug Discovery gene.com. Checked 22 October 2026.
  2. Massively parallel single-cell B-cell receptor sequencing enables rapid discovery of diverse antigen-reactive antibodies nature.com. Checked 22 October 2026.
  3. [2306.12360] Protein Discovery with Discrete Walk-Jump Sampling arxiv.org. Checked 22 October 2026.
  4. AbDiffuser: full-atom generation of in-vitro functioning antibodies proceedings.neurips.cc. Checked 22 October 2026.
  5. ICLR 2024 Awards iclr.cc. Checked 22 October 2026.
  6. Lab-in-the-loop therapeutic antibody design with deep learning twistbioscience.com. Checked 22 October 2026.