Data Scientist/Postdoctoral Researcher - Zhou & Gao Labs

Buck Institute•Novato, CA

29d•$80,000 - $130,000•Hybrid

About The Position

The Zhou Lab at the Buck Institute for Research on Aging and the Gao Lab at Stanford University are seeking a Data Scientist or Postdoctoral Researcher to lead computational analysis for a multidisciplinary research program focused on intrinsically disordered proteins and regions (IDPs/IDRs). Unlike many folded proteins with a single stable structure that can be predicted by AlphaFold, IDPs exist as dynamic ensembles of conformations. IDRs/IDPs exist in 50-70% of the human proteome and are particularly important in regulatory proteins and proteins implicated in aging and age-related diseases. This project will generate large-scale complementary experimental measurements of IDR conformational ensembles and interactions. The successful candidate will develop computational approaches to integrate these measurements and determine how mutations, post-translational modifications, binding partners, and environmental conditions alter IDR states and behaviors. This candidate will work in close collaboration with experimental scientists and with structural biology, proteomics, and computational modeling groups. A central feature of the position is an iterative feedback loop between computation and experiment: computational analyses will help guide experimental design, and new experimental data will inform the development and refinement of computational models. The position is jointly mentored by the Zhou and Gao labs and will involve close interaction with both research groups, through a combination of in-person and remote collaboration as appropriate.

Requirements

Ph.D. in computational biology, bioinformatics, biophysics, structural biology, computer science, statistics, applied mathematics, machine learning, or a related field
Strong programming skills in Python and experience with modern scientific computing tools.
Familiarity with modern computational protein modeling, including protein language/foundation models, generative protein modeling, and conformational-ensemble representations.
Experience analyzing large, high-dimensional biological or biophysical datasets.
Strong statistical and quantitative reasoning.
Experience developing reproducible computational pipelines rather than relying exclusively on existing analysis packages.
Ability to communicate closely with experimental scientists and translate biological questions into quantitative analyses.

Nice To Haves

Experience with intrinsically disordered proteins, conformational ensembles, structural bioinformatics, or molecular simulation.
Familiarity with MD trajectories and structural representations of proteins.
Experience with HDX-MS, cryo-EM, single-molecule measurements, proteomics, interactomics, or related structural/biophysical datasets.
Experience applying machine learning approaches applicable to protein structure or heterogeneous biological data, including representation learning, clustering, dimensionality reduction, probabilistic modeling, or deep learning.
Experience integrating multiple experimental modalities.
Experience working with very large datasets and high-performance/GPU computing.
Understanding of the experimental challenges associated with IDR protein purification and handling is highly desirable, as close interaction between computational and experimental researchers will be central to the project.
The ideal candidate will do more than analyze datasets after they are generated. They will help shape experimental design, build new analytical methods, and lead the integration of experimental measurements with computational models of IDR structure and behavior.

Responsibilities

Develop computational methods and pipelines to extract sequence-function relationships in IDRs.
Integrate complementary datasets including HDX-MS, interactomics, Cryo-EM structural measurements, and molecular-dynamics simulations.
Develop reproducible, version-controlled analysis pipelines and structured data products for modeling.
Perform statistical analysis, dimensionality reduction, clustering, representation learning, and other computational analyses of high-dimensional experimental datasets.
Develop visualization and reporting tools for large-scale IDR structural datasets.
Participate in experimental design and determine data/QC requirements needed for robust downstream analysis.
Contribute to publications, technical reports, milestone documentation, and open computational resources arising from the project.