FoldKit: A Python library for efficient storage and retrieval of co-folding predictions
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.
Related
- A novel one-step multiplex PCR method (OS-MPCR) for efficient NGS library preparation in cancer
- Storage-Centric System Designs for Enabling Fast, Efficient, and Low-Cost Genomic and Metagenomic Analyses
- VOC·BIO Library: An Integrated Platform for Published Aphid GC-MS Evidence, Biological Contexts, Cheminformatics and Exploratory OBP Docking
- 777 High-throughput discovery of rare, functionally potent antigen-reactive TCRs via polyclonal library screening
- SEEKER: A genome-scale library-on-library screening platform for deciphering T cell recognition of antigen
BibTeX
@misc{levine2026foldkit,
title = {{FoldKit: A Python library for efficient storage and retrieval of co-folding predictions}},
author = {Jonathan A. Levine and Melissa Pathil and Samuel Nitz and Olga Lyudovyk and Benjamin D. Greenbaum},
howpublished = {arXiv},
year = {2026},
month = aug,
doi = {10.48550/arxiv.2608.28788},
eprint = {2608.28788},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.28788},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - FoldKit: A Python library for efficient storage and retrieval of co-folding predictions
AU - Jonathan A. Levine
AU - Melissa Pathil
AU - Samuel Nitz
AU - Olga Lyudovyk
AU - Benjamin D. Greenbaum
PY - 2026
DA - 2026/08/28
PB - arXiv
DO - 10.48550/arxiv.2608.28788
UR - https://arxiv.org/abs/2608.28788
AB - 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.
ER -