Search for: All records

Abstract Particle picking in cryo-electron tomograms (cryo-ET) is crucial for in situ structure detection of macro-molecules and protein complexes. The traditional template-matching-based approaches for particle picking suffer from template-specific biases and have low throughput. Given these problems, learning-based solutions are necessary for particle picking. However, the paucity of annotated data for training poses substantial challenges for such learning-based approaches. Moreover, preparing extensively annotated cryo-ET tomograms for particle picking is extremely time-consuming and burdensome. Addressing these challenges, we present TomoPicker, an annotation-efficient particle-picking approach that can effectively pick particles when only a minuscule portion (∼ 0.3 − 0.5%) of the total particles in a cellular cryo-ET dataset is provided for training. TomoPicker regards particle picking as a voxel classification problem and solves it with two different positive-unlabeled learning approaches. We evaluated our method on a benchmark cryo-ET dataset of eukaryotic cells, where we observed about 30% improvement by TomoPicker against the most recent state-of-the-art annotation efficient learning-based picking approaches. 

In this work, we address the problem of detecting anomalies in a certain laboratory automation setting. At first, we collect video images of liquid transfer in automated laboratory experiments. We mimic the real-world challenges of developing an anomaly detection model by considering two points. First, the size of the collected dataset is set to be relatively small compared to large-scale video datasets. Second, the dataset has a class imbalance problem where the majority of the collected videos are from abnormal events. Consequently, the existing learning-based video anomaly detection methods do not perform well. To this end, we develop a practical human-engineered feature extraction method to detect anomalies from the liquid transfer video images. Our simple yet effective method outperforms state-of-the-art anomaly detection methods with a notable margin. In particular, the proposed method provides 19% and 76% average improvement in AUC and Equal Error Rate, respectively. Our method also quantifies the anomalies and provides significant benefits for deployment in the real-world experimental setting. 

Macromolecular structure classification from cryo-electron tomography (cryo-ET) data is important for understanding macro-molecular dynamics. It has a wide range of applications and is essential in enhancing our knowledge of the sub-cellular environment. However, a major limitation has been insufficient labelled cryo-ET data. In this work, we use Contrastive Self-supervised Learning (CSSL) to improve the previous approaches for macromolecular structure classification from cryo-ET data with limited labels. We first pretrain an encoder with unlabelled data using CSSL and then fine-tune the pretrained weights on the downstream classification task. To this end, we design a cryo-ET domain-specific data-augmentation pipeline. The benefit of augmenting cryo-ET datasets is most prominent when the original dataset is limited in size. Overall, extensive experiments performed on real and simulated cryo-ET data in the semi-supervised learning setting demonstrate the effectiveness of our approach in macromolecular labeling and classification.