FoldKit: A Python library for efficient storage and retrieval of co-folding predictions
Software Engineering
Summary
The authors created FoldKit, a Python tool to help manage and analyze lots of data from AlphaFold 3 when it predicts how multiple molecules come together. AlphaFold 3 can produce large files, especially when testing many variations, so FoldKit makes these results smaller and easier to work with without losing important details. It also provides easy ways for researchers to check confidence scores and other metrics for each prediction or groups of predictions. The authors tested FoldKit on various datasets and found it reduces storage needs by 5 to 15 times while keeping access to all useful data. This helps scientists studying how proteins and other biomolecules interact on a large scale.
Authors
Jonathan A. Levine, Melissa Pathil, Samuel Nitz, Olga Lyudovyk, Benjamin D. Greenbaum
Abstract
AlphaFold 3 (AF3) enables structure prediction of biomolecular complexes through co-folding multiple interacting molecules, making it increasingly useful for de novo protein design and for large-scale studies of protein-protein, protein-peptide, and other biomolecular interactions. However, systematic co-folding experiments can produce large volumes of output data, particularly when multiple random seeds and samples are generated for each input complex. We introduce FoldKit, a Python package for efficient storage and analysis of large-scale AF3 co-folding results. FoldKit converts raw AF3 outputs into a compact, structured representation while preserving the metadata needed for downstream analysis. The FoldKit Python library provides convenient programmatic access to global, single chain, and interface confidence metrics such as pLDDT, pTM, ipTM, ipAE, and ipSAE, as well as an ensemble-level interface for accessing and aggregating these metrics for a single input across multiple seeds and samples. We benchmark FoldKit on three types of AF3 co-folding datasets: (i) a protein design campaign with 2 chains per input, (ii) a TCR-pMHC dataset with 4 chains per input, and (iii) a pooled-AF3 protein-protein interaction dataset with up to 22 chains per input. We find that FoldKit reduces storage requirements by approximately 5-15-fold compared to native AF3 outputs, depending on dataset composition, while maintaining direct programmatic access to individual predictions, ensembles, and confidence metrics. By reducing storage requirements and facilitating programmatic access to relevant outputs, FoldKit facilitates large-scale computational studies of biomolecular interactions. FoldKit is available from PyPI and can be installed using pip.