PERC: a suite of software tools for the curation of cryoEM data with application to simulation, modeling and machine learning - Abstract

Aug 5, 2026

Upload by Quinn

PERC is a suite of open-source Python software packages designed to reduce the burden of curating cryoEM data for structural biology research. The tools collate public cryoEM datasets or generate synthetic cryoEM data to support the development of data-processing and interpretation algorithms. profet downloads and prepares sequences or structures from Protein Data Bank and AlphaFold, EMPIARreader enables lazy loading of EMPIAR datasets for ML workflows, and CAKED streamlines ML training with cryoEM-specific augmentation and labeling.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages10

Reading Time25 min

AccessFree to download

Introduction

Data access and reuse for structural biology

CryoEM data characteristics and curation challenges

Overview of PERC software packages

methods communications ISSN 2053-230X Received 7 March 2025 Accepted 24 August 2025 Edited by J. Agirre, University of York, United Kingdom ‡ These authors contributed equally. Keywords: cryoEM; electron cryomicroscopy; Python; PERC. Published under a CC BY 4.0 licence PERC: a suite of software tools for the curation of cryoEM data with application to simulation, modeling and machine learning Beatriz Costa-Gomes,a‡ Joel Greer,b‡ Nikolai Juraschko,a,c,d‡ James Parkhurst,c,e‡ Jola Mirecka,b‡ Marjan Famili,a Camila Rangel-Smith,a Oliver Strickson,a Alan Lowe,a Mark Bashamc* and Tom Burnleyb* aThe Alan Turing Institute, British Library, 96 Euston Road, London NW1 2DB, United Kingdom, bScience and Technology Facilities Council, Research Complex at Harwell, Didcot OX11 0FA, United Kingdom, cRosalind Franklin Institute, Harwell Science and Innovation Campus, Didcot OX11 0QX, United Kingdom, dUniversity of Oxford, Oxford OX1 3QU, United Kingdom, and eDiamond Light Source (United Kingdom), Harwell Science and Innovation Campus, Didcot OX11 0DE, United Kingdom. *Correspondence e-mail: [mark.basham@rfi.ac.uk](mark.basham@rfi.ac.uk), [tom.burnley@stfc.ac.uk](tom.burnley@stfc.ac.uk) Ease of access to data, tools and models expedites scientific research. In structural biology there are now numerous open repositories of experimental and simulated data sets. Being able to easily access and utilize these is crucial to allow researchers to make optimal use of their research effort. The tools presented here are useful for collating existing public cryoEM data sets and/or creating new synthetic cryoEM data sets to aid the development of novel data processing and interpretation algorithms. In recent years, structural biology has seen the development of a multitude of machine-learning-based algorithms to aid numerous steps in the processing and reconstruction of experimental datasets and the use of these approaches has become widespread. Developing such techniques in structural biology requires access to large data sets, which can be cumbersome to curate and unwieldy to make use of. In this paper, we present a suite of Python software packages, which we collectively refer to as PERC (profet, EMPIARreader and CAKED) . These are designed to reduce the burden which data curation places upon structural biology research. The protein structure fetcher (profet) package allows users to conveniently download and cleave sequences or structures from the Protein Data Bank or AlphaFold databases. EMPIARreader allows lazy loading of Electron Microscopy Public Image Archive data sets in a machine-learning-compatible structure. The Class Aggregator for Key Electron-microscopy Data (CAKED) package is designed to seamlessly facilitate the training of machine-learning models on electron microscopy data, including electron-cryo-microscopy-specific data augmentation and labeling. These packages may be utilized independently or as building blocks in workflows. All are available in open-source repositories and designed to be easily extensible to facilitate more advanced workflows if required. 1. Introduction Cryogenic-sample electron microscopy (cryoEM) is an imaging technique used to obtain the structure of biomolecular objects on near-atomic resolution scales experimentally via transmission electron microscopy (TEM) of cryogenically frozen samples. Due to advancements in hardware and software over the last decade, the resolution achievable via cryoEM reconstruction approaches that possible through X-ray crystallography (Cheng et al., 2015), with cryoEM being of particular use for determining the structure of macromolecules that are not amenable to other experimental methods such as X-ray crystallography or nuclear magnetic resonance (NMR) spectroscopy (Nogales, 2016) . The images which make up cryoEM data sets commonly have a very low signal-to-noise ratio (SNR) in order to minimize radiation damage. Consequently, the structures of macromole

FAQs

What problem does PERC address in cryoEM research?

PERC reduces the effort required to curate cryoEM data and models for structural biology, making it easier to access, collate, and use large experimental and synthetic datasets for algorithm development.

What does the profet package do?

profet helps users download and cleave sequences or structures from the Protein Data Bank or AlphaFold databases for downstream workflows.

How does EMPIARreader support machine learning pipelines?

EMPIARreader provides lazy loading for EMPIAR cryoEM image datasets in a machine-learning-compatible structure, enabling efficient use during model training.

Aug 5, 2026

Upload by Quinn