PeopleofSuperintelligence

Researcher

Alex Derry

Also known as Alexander Derry

Alex Derry is a Biohub research scientist who applies machine learning to protein structure and function and is interested in mechanistic interpretability and scientific discovery with biological foundation models. At MIT, he earned a BS in materials science and engineering, researched bioelectronics and molecular dynamics, and coauthored a 2017 paper on nanowire probes. In 2020, he coauthored a biomedical knowledge-graph method, and ATOM3D received the 2021 NeurIPS Datasets and Benchmarks Best Paper Award. His 2022–2025 work spanned protein-data studies, local-site representations, feature attribution, and residue-level function prediction.

Now at
Biohub
Links
Google Scholar, X and GitHub

Timeline

  1. 2017

    MIT materials science and neural probes

    Before his PhD work, he earns a BS in materials science and engineering at MIT and researches bioelectronics and molecular dynamics. In 2017, he coauthors a Science Advances paper on flexible, stretchable nanowire probes for spinal cord circuits.

  2. 2020

    Knowledge graphs for drug repurposing

    In 2020, he coauthors a knowledge-graph method that uses biomedical literature to propose drug-repurposing hypotheses for rare diseases. The model accounts for uncertainty in literature-derived relationships and explains its predictions.

  3. 2021

    ATOM3D molecule benchmarks

    In 2021, he coauthors ATOM3D, a collection of benchmark datasets and tools for machine learning on three-dimensional molecules. NeurIPS recognizes the paper with its Datasets and Benchmarks Best Paper Award.

  4. 2022

    Training data for protein analysis

    In 2022, he coauthors a study of how training-set composition affects algorithms that analyze three-dimensional protein structures.

  5. 2023

    COLLAPSE and a Stanford dissertation

    He coauthors COLLAPSE in 2023, a framework that learns deep representations from the atoms surrounding protein sites and evolutionary relationships between homologous proteins. In December 2023, he presents a Stanford dissertation on deep learning for protein structure and function using local sites.

  6. 2024

    Prospector Heads feature attribution

    In 2024, he co-leads a Stanford team that publishes Prospector Heads, an efficient and interpretable method for identifying class-specific features across sequences, images, and graphs.

  7. 2025

    PARSE annotates protein function

    In 2025, he coauthors PARSE, a method that combines pretrained local structural embeddings and statistical techniques to predict protein function and provide residue-level annotations.

  8. As of October 2026

    Research scientist at Biohub

    He is a research scientist at Biohub, with interests in mechanistic interpretability and scientific discovery using biological foundation models. In July 2026, he speaks at a Biohub webinar on ESMC interpretability and the ESM Atlas.

Career

  1. NowBiohubResearch scientist

Education

  1. 2023Stanford UniversityPhD
  2. Massachusetts Institute of TechnologyBS

From the biography.

  1. 84% of people shaping AI with recorded undergraduate and doctoral schools changed institutions for their doctorateIncludes Alex Derry. 84% of people shaping AI with recorded undergraduate and doctoral schools changed institutions for their doctorate. Across 2,116 people with both an undergraduate degree and a doctorate recorded, we trace which undergraduate schools feed which doctoral programs, how often students stay at the same school, and how paths differ by birth-country region.
  2. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes Massachusetts Institute of Technology. We estimate where the people shaping AI studied and where their careers led. Massachusetts Institute of Technology leads with 467 former students, including 291 recorded doctorates.
  3. 20% of people at companies who shape AI also hold a university role, led by Google and Stanford UniversityIncludes Stanford University. 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.
  4. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other universityIncludes Massachusetts Institute of Technology. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other university. We compare doctorate and 5+ year employment links, career timing and current workplaces for 187 major-prize and 1,111 best-paper winners.

Sources and credits

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

  1. Alexander Derry awfderry.github.io. Checked 20 October 2026.
  2. Flexible and stretchable nanowire-coated fibers for optoelectronic probing of spinal cord circuits pmc.ncbi.nlm.nih.gov. Checked 20 October 2026.
  3. A Literature-Based Knowledge Graph Embedding Method for Identifying Drug Repurposing Opportunities in Rare Diseases pmc.ncbi.nlm.nih.gov. Checked 20 October 2026.
  4. Announcing the NeurIPS 2021 Award Recipients blog.neurips.cc. Checked 20 October 2026.
  5. ATOM3D: Tasks on Molecules in Three Dimensions datasets-benchmarks-proceedings.neurips.cc. Checked 20 October 2026.
  6. Training data composition affects performance of protein structure analysis algorithms pmc.ncbi.nlm.nih.gov. Checked 20 October 2026.
  7. COLLAPSE: A representation learning framework for identification and characterization of protein structural sites pmc.ncbi.nlm.nih.gov. Checked 20 October 2026.
  8. Alex Derry’s Dissertation Defense dbds.stanford.edu. Checked 20 October 2026.
  9. Gautam Machiraju and Alex Derry lead team for paper accepted for publication in the 2024 International Conference on Machine Learning in Vienna, Austria dbds.stanford.edu. Checked 20 October 2026.
  10. Prospector Heads: Generalized Feature Attribution for Large Models & Data proceedings.mlr.press. Checked 20 October 2026.
  11. Protein functional site annotation using local structure embeddings pmc.ncbi.nlm.nih.gov. Checked 20 October 2026.
  12. ESMC Interpretability and the ESM Atlas Webinar biohub.org. Checked 20 October 2026.