# Positive-unlabeled convolutional neural networks for particle picking in cryo-electron micrographs

arXiv: https://arxiv.org/abs/1803.08207 · HTML: https://mlsanity.com/paper/1803.08207/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Mar 2018.

## Built on by (most cited first, 24 of 24)

- [Multiscale Positive-Unlabeled Detection of AI-Generated Texts](https://mlsanity.com/paper/2305.18149/) (2023)
- [Dist-PU: Positive-Unlabeled Learning from a Label Distribution Perspective](https://mlsanity.com/paper/2212.02801/) (2022)
- [Sparse Object-level Supervision for Instance Segmentation with Pixel Embeddings](https://mlsanity.com/paper/2103.14572/) (2021)
- [Unsupervised Object Representation Learning using Translation and Rotation Group Equivariant VAE](https://mlsanity.com/paper/2210.12918/) (2022)
- [Semi-Supervised Disease Classification based on Limited Medical Image Data](https://mlsanity.com/paper/2405.04295/) (2024)
- [CryoGEM: Physics-Informed Generative Cryo-Electron Microscopy](https://mlsanity.com/paper/2312.02235/) (2023)
- [DRACO: A Denoising-Reconstruction Autoencoder for Cryo-EM](https://mlsanity.com/paper/2410.11373/) (2024)
- [Evaluating multiple models using labeled and unlabeled data](https://mlsanity.com/paper/2501.11866/) (2025)
- [Adapting Segment Anything Model (SAM) through Prompt-based Learning for Enhanced Protein Identification in Cryo-EM Micrographs](https://mlsanity.com/paper/2311.16140/) (2023)
- [CryoMAE: Few-Shot Cryo-EM Particle Picking with Masked Autoencoders](https://mlsanity.com/paper/2404.10178/) (2024)
- [Artificial Intelligence Advances for De Novo Molecular Structure Modeling in Cryo-EM](https://mlsanity.com/paper/2102.06125/) (2021)
- [Affinity-VAE: incorporating prior knowledge in representation learning from scientific images](https://mlsanity.com/paper/2209.04517/) (2022)
- [Robust single-particle cryo-EM image denoising and restoration](https://mlsanity.com/paper/2401.01097/) (2024)
- [Tensorial template matching for fast cross-correlation with rotations and its application for tomography](https://mlsanity.com/paper/2408.02398/) (2024)
- [CRISP: A Framework for Cryo-EM Image Segmentation and Processing with Conditional Random Field](https://mlsanity.com/paper/2502.08287/) (2025)
- [CryoCCD: Conditional Cycle-consistent Diffusion with Biophysical Modeling for Cryo-EM Synthesis](https://mlsanity.com/paper/2505.23444/) (2025)
- [Cryo-forum: A framework for orientation recovery with uncertainty measure with the application in cryo-EM image analysis](https://mlsanity.com/paper/2307.09847/) (2023)
- [Advanced POD-Based Performance Evaluation of Classifiers Applied to Human Driver Lane Changing Prediction](https://mlsanity.com/paper/2408.15722/) (2024)
- [Application of Deep Learning in Biological Data Compression](https://mlsanity.com/paper/2512.12975/) (2025)
- [Score-Based Matching with Target Guidance for Cryo-EM Denoising](https://mlsanity.com/paper/2604.17734/) (2026)
- [ARCHER: Amortized cross-specimen pose estimation for cryo-electron microscopy](https://mlsanity.com/paper/2608.22029/) (2026)
- [Reconstruction-Aware Cryo-EM Particle Picking](https://mlsanity.com/paper/2608.28838/) (2026)
- [FPicker: Topology-Guided Evolution for Filament Tracing in Low-SNR Microscopy](https://mlsanity.com/paper/2609.08305/) (2026)
- [CryoTracer: A Synthetic-to-Real System for Filament Instance Tracing in Cryo-EM](https://mlsanity.com/paper/2610.18696/) (2026)

## Abstract (arXiv)

Cryo-electron microscopy (cryoEM) is an increasingly popular method for protein structure determination. However, identifying a sufficient number of particles for analysis (often >100,000) can take months of manual effort. Current computational approaches are limited by high false positive rates and require significant ad-hoc post-processing, especially for unusually shaped particles. To address this shortcoming, we develop Topaz, an efficient and accurate particle picking pipeline using neural networks trained with few labeled particles by newly leveraging the remaining unlabeled particles through the framework of positive-unlabeled (PU) learning. Remarkably, despite using minimal labeled particles, Topaz allows us to improve reconstruction resolution by up to 0.15 AA over published particles on three public cryoEM datasets without any post-processing. Furthermore, we show that our novel generalized-expectation criteria approach to PU learning outperforms existing general PU learning approaches when applied to particle detection, especially for challenging datasets of non-globular proteins. We expect Topaz to be an essential component of cryoEM analysis.