PeopleofSuperintelligence

Researcher

Andrew J. Ballard

Andrew Ballard is a researcher whose work connects machine learning with molecular simulation and protein structure prediction. In 2017, he applied energy-landscape ideas to machine learning and coauthored a neural-network method for free-energy estimation in 2020. At DeepMind, he contributed to AlphaFold's CASP14 team and later work on the AlphaFold Database. In 2024, he served as a Core Contributor on AlphaFold 3, which predicts structures of complexes across proteins, nucleic acids, small molecules and ions.

Works
30
Badges

Publication numbers from OpenAlex, as of 18 October 2026. Citations and h-index are hidden because this OpenAlex record may be incomplete or mix in other authors.

Timeline

  1. 2017

    Energy landscapes for machine learning

    In 2017, he and six coauthors apply molecular potential-energy landscape methods to machine-learning training and predictions.

  2. 2020

    Learning free-energy mappings

    In 2020, he and colleagues recast targeted free-energy perturbation as a machine-learning problem, using a neural network to increase overlap between sampled distributions.

  3. 2020

    AlphaFold at CASP14

    At CASP14 in 2020, he contributes to DeepMind's AlphaFold team as its model reaches a median GDT score of 92.4.

  4. 2021

    Protein structures at atomic accuracy

    In 2021, he receives equal authorship credit on the Nature paper that presents a neural-network model for protein-structure prediction with atomic accuracy.

  5. 2021

    AlphaFold at proteome scale

    In 2021, he coauthors DeepMind's account of the AlphaFold DB, which makes predictions for reference proteomes freely available.

  6. 2024

    Core contributor to AlphaFold 3

    In 2024, he serves as a Core Contributor at Google DeepMind on AlphaFold 3, which predicts structures of complexes containing proteins, nucleic acids, small molecules, ions and modified residues.

  1. The median h-index is 54 at universities and 20 at frontier AI labsIncludes Andrew J. Ballard. The median h-index is 54 at universities and 20 at frontier AI labs. We compare publishing careers, citations and moves to estimate how universities and frontier labs contribute to AI research.
  2. 14% of AI career moves in the 2020s went from a university to a companyIncludes Andrew J. Ballard. Our estimates of how university-to-company career transitions changed by decade, including roles added alongside an earlier job.
  3. Google has the highest combined h-index among AI organizationsIncludes Google. Our estimates of combined and median h-index at AI organizations, using current affiliations and OpenAlex records.
  4. Google alumni founded or led 82 other organizations, the most among the labs we compareIncludes Google. We trace 189 organizations founded or led by AI lab alumni, and 196 career moves between the labs.

Colleagues

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

Sources and credits

Photo: We have no published photo of Andrew J. Ballard yet. Send us a free-licensed photo.

  1. Perspective: Energy Landscapes for Machine Learning arxiv.org. Checked 18 October 2026.
  2. Targeted free energy estimation via learned mappings arxiv.org. Checked 18 October 2026.
  3. AlphaFold: a solution to a 50-year-old grand challenge in biology deepmind.google. Checked 18 October 2026.
  4. Highly accurate protein structure prediction with AlphaFold nature.com. Checked 18 October 2026.
  5. Enabling high-accuracy protein structure prediction at the proteome scale deepmind.google. Checked 18 October 2026.
  6. Accurate structure prediction of biomolecular interactions with AlphaFold 3 nature.com. Checked 18 October 2026.