Accurate somatic variant detection using weakly supervised deep learning.
Ontology highlight
ABSTRACT:
SUBMITTER: Krishnamachari K
PROVIDER: S-EPMC9307817 | biostudies-literature | 2022 Jul
REPOSITORIES: biostudies-literature
Publications
Accurate somatic variant detection using weakly supervised deep learning.
Krishnamachari Kiran K Lu Dylan D Swift-Scott Alexander A Yeraliyev Anuar A Lee Kayla K Huang Weitai W Leng Sim Ngak SN Skanderup Anders Jacobsen AJ
Nature communications 20220722 1
Identification of somatic mutations in tumor samples is commonly based on statistical methods in combination with heuristic filters. Here we develop VarNet, an end-to-end deep learning approach for identification of somatic variants from aligned tumor and matched normal DNA reads. VarNet is trained using image representations of 4.6 million high-confidence somatic variants annotated in 356 tumor whole genomes. We benchmark VarNet across a range of publicly available datasets, demonstrating perfo ...[more]
Similar Datasets
Project description:Image-based spatial transcriptomics methods enable transcriptome-scale gene expression measurements with spatial information but require complex, manually-tuned analysis pipelines. We present Polaris, an analysis pipeline for image-based spatial transcriptomics that combines deep learning models for cell segmentation and spot detection with a probabilistic gene decoder to quantify single-cell gene expression accurately. Polaris offers a unifying, turnkey solution for analyzing spatial transcriptomics data from MERFSIH, seqFISH, or ISS experiments. Polaris is available through the DeepCell software library (https://github.com/vanvalenlab/deepcell-spots) and https://www.deepcell.org.
| S-EPMC10508757 | biostudies-literature
Project description:Beat-by-beat arrhythmia detection in ambulatory electrocardiogram (ECG) monitoring is critical for the evaluation and prognosis of cardiac arrhythmias, however, it is a highly professional demanding and time-consuming task. Current methods for automatic beat-by-beat arrhythmia detection suffer from poor generalization ability due to the lack of large-sample and finely-annotated (labels are given to each beat) ECG data for model training. In this work, we propose a weakly supervised deep learning framework for arrhythmia detection (WSDL-AD), which permits training a fine-grained (beat-by-beat) arrhythmia detector with the use of large amounts of coarsely annotated ECG data (labels are given to each recording) to improve the generalization ability. In this framework, heartbeat classification and recording classification are integrated into a deep neural network for end-to-end training with only recording labels. Several techniques, including knowledge-based features, masked aggregation, and supervised pre-training, are proposed to improve the accuracy and stability of the heartbeat classification under weak supervision. The developed WSDL-AD model is trained for the detection of ventricular ectopic beats (VEB) and supraventricular ectopic beats (SVEB) on five large-sample and coarsely-annotated datasets and the model performance is evaluated on three independent benchmarks according to the recommendations from the Association for the Advancement of Medical Instrumentation (AAMI). The experimental results show that our method improves the F 1 score of supraventricular ectopic beats detection by 8%-290% and the F1 of ventricular ectopic beats detection by 4%-11% on the benchmarks compared with the state-of-the-art methods of supervised learning. It demonstrates that the WSDL-AD framework can leverage the abundant coarsely-labeled data to achieve a better generalization ability than previous methods while retaining fine detection granularity. Therefore, this framework has a great potential to be used in clinical and telehealth applications. The source code is available at https://github.com/sdnjly/WSDL-AD.
| S-EPMC9037749 | biostudies-literature
Project description:To solve three-dimensional structures of biological macromolecules in situ, large numbers of particles often need to be picked from cryo-electron tomograms. However, adoption of automated particle-picking methods remains limited because of their technical limitations. To overcome the limitations, we develop DeepETPicker, a deep learning model for fast and accurate picking of particles from cryo-electron tomograms. Training of DeepETPicker requires only weak supervision with low numbers of simplified labels, reducing the burden of manual annotation. The simplified labels combined with the customized and lightweight model architecture of DeepETPicker and accelerated pooling enable substantial performance improvement. When tested on simulated and real tomograms, DeepETPicker outperforms the competing state-of-the-art methods by achieving the highest overall accuracy and speed, which translate into higher authenticity and coordinates accuracy of picked particles and higher resolutions of final reconstruction maps. DeepETPicker is provided in open source with a user-friendly interface to support cryo-electron tomography in situ.
| S-EPMC11258139 | biostudies-literature
Project description:Mapping chromatin insulator loops is crucial to investigating genome evolution, elucidating critical biological functions, and ultimately quantifying variant impact in diseases. However, chromatin conformation profiling assays are usually expensive, time-consuming, and may report fuzzy insulator annotations with low resolution. Therefore, we propose a weakly supervised deep learning method, InsuLock, to address these challenges. Specifically, InsuLock first utilizes a Siamese neural network to predict the existence of insulators within a given region (up to 2000 bp). Then, it uses an object detection module for precise insulator boundary localization via gradient-weighted class activation mapping (~40 bp resolution). Finally, it quantifies variant impacts by comparing the insulator score differences between the wild-type and mutant alleles. We applied InsuLock on various bulk and single-cell datasets for performance testing and benchmarking. We showed that it outperformed existing methods with an AUROC of ~0.96 and condensed insulator annotations to ~2.5% of their original size while still demonstrating higher conservation scores and better motif enrichments. Finally, we utilized InsuLock to make cell-type-specific variant impacts from brain scATAC-seq data and identified a schizophrenia GWAS variant disrupting an insulator loop proximal to a known risk gene, indicating a possible new mechanism of action for the disease.
| S-EPMC9026820 | biostudies-literature
Project description:Deep learning and computer vision have become emerging tools for diseased plant phenotyping. Most previous studies focused on image-level disease classification. In this paper, pixel-level phenotypic feature (the distribution of spot) was analyzed by deep learning. Primarily, a diseased leaf dataset was collected and the corresponding pixel-level annotation was contributed. A dataset of apple leaves samples was used for training and optimization. Another set of grape and strawberry leaf samples was used as an extra testing dataset. Then, supervised convolutional neural networks were adopted for semantic segmentation. Moreover, the possibility of weakly supervised models for disease spot segmentation was also explored. Grad-CAM combined with ResNet-50 (ResNet-CAM), and that combined with a few-shot pretrained U-Net classifier for weakly supervised leaf spot segmentation (WSLSS), was designed. They were trained using image-level annotations (healthy versus diseased) to reduce the cost of annotation work. Results showed that the supervised DeepLab achieved the best performance (IoU = 0.829) on the apple leaf dataset. The weakly supervised WSLSS achieved an IoU of 0.434. When processing the extra testing dataset, WSLSS realized the best IoU of 0.511, which was even higher than fully supervised DeepLab (IoU = 0.458). Although there was a certain gap in IoU between the supervised models and weakly supervised ones, WSLSS showed stronger generalization ability than supervised models when processing the disease types not involved in the training procedure. Furthermore, the contributed dataset in this paper could help researchers get a quick start on designing their new segmentation methods in future studies.
| S-EPMC10076051 | biostudies-literature
Project description:The yield of cereal crops such as sorghum (Sorghum bicolor L. Moench) depends on the distribution of crop-heads in varying branching arrangements. Therefore, counting the head number per unit area is critical for plant breeders to correlate with the genotypic variation in a specific breeding field. However, measuring such phenotypic traits manually is an extremely labor-intensive process and suffers from low efficiency and human errors. Moreover, the process is almost infeasible for large-scale breeding plantations or experiments. Machine learning-based approaches like deep convolutional neural network (CNN) based object detectors are promising tools for efficient object detection and counting. However, a significant limitation of such deep learning-based approaches is that they typically require a massive amount of hand-labeled images for training, which is still a tedious process. Here, we propose an active learning inspired weakly supervised deep learning framework for sorghum head detection and counting from UAV-based images. We demonstrate that it is possible to significantly reduce human labeling effort without compromising final model performance (R 2 between human count and machine count is 0.88) by using a semitrained CNN model (i.e., trained with limited labeled data) to perform synthetic annotation. In addition, we also visualize key features that the network learns. This improves trustworthiness by enabling users to better understand and trust the decisions that the trained deep learning model makes.
| S-EPMC7706102 | biostudies-literature
Project description:PurposeThe purpose of this study was to design an automated algorithm that can detect fluorescence leakage accurately and quickly without the use of a large amount of labeled data.MethodsA weakly supervised learning-based method was proposed to detect fluorescein leakage without the need for manual annotation of leakage areas. To enhance the representation of the network, a residual attention module (RAM) was designed as the core component of the proposed generator. Moreover, class activation maps (CAMs) were used to define a novel anomaly mask loss to facilitate more accurate learning of leakage areas. In addition, sensitivity, specificity, accuracy, area under the curve (AUC), and dice coefficient (DC) were used to evaluate the performance of the methods.ResultsThe proposed method reached a sensitivity of 0.73 ± 0.04, a specificity of 0.97 ± 0.03, an accuracy of 0.95 ± 0.05, an AUC of 0.86 ± 0.04, and a DC of 0.87 ± 0.01 on the HRA data set; a sensitivity of 0.91 ± 0.02, a specificity of 0.97 ± 0.02, an accuracy of 0.96 ± 0.03, an AUC of 0.94 ± 0.02, and a DC of 0.85 ± 0.03 on Zhao's publicly available data set; and a sensitivity of 0.71 ± 0.04, a specificity of 0.99 ± 0.06, an accuracy of 0.87 ± 0.06, an AUC of 0.85 ± 0.02, and a DC of 0.78 ± 0.04 on Rabbani's publicly available data set.ConclusionsThe experimental results showed that the proposed method achieves better performance on fluorescence leakage detection and can detect one image within 1 second and thus has great potential value for clinical diagnosis and treatment of retina-related diseases, such as diabetic retinopathy and malarial retinopathy.Translational relevanceThe proposed weakly supervised learning-based method that automates the detection of fluorescence leakage can facilitate the assessment of retinal-related diseases.
| S-EPMC8934548 | biostudies-literature
Project description:IntroductionEarly detection of pancreatic cancer continues to be a challenge due to the difficulty in accurately identifying specific signs or symptoms that might correlate with the onset of pancreatic cancer. Unlike breast or colon or prostate cancer where screening tests are often useful in identifying cancerous development, there are no tests to diagnose pancreatic cancers. As a result, most pancreatic cancers are diagnosed at an advanced stage, where treatment options, whether systemic therapy, radiation, or surgical interventions, offer limited efficacy.MethodsA two-stage weakly supervised deep learning-based model has been proposed to identify pancreatic tumors using computed tomography (CT) images from Henry Ford Health (HFH) and publicly available Memorial Sloan Kettering Cancer Center (MSKCC) data sets. In the first stage, the nnU-Net supervised segmentation model was used to crop an area in the location of the pancreas, which was trained on the MSKCC repository of 281 patient image sets with established pancreatic tumors. In the second stage, a multi-instance learning-based weakly supervised classification model was applied on the cropped pancreas region to segregate pancreatic tumors from normal appearing pancreas. The model was trained, tested, and validated on images obtained from an HFH repository with 463 cases and 2,882 controls.ResultsThe proposed deep learning model, the two-stage architecture, offers an accuracy of 0.907 ± 0.01, sensitivity of 0.905 ± 0.01, specificity of 0.908 ± 0.02, and AUC (ROC) 0.903 ± 0.01. The two-stage framework can automatically differentiate pancreatic tumor from non-tumor pancreas with improved accuracy on the HFH dataset.DiscussionThe proposed two-stage deep learning architecture shows significantly enhanced performance for predicting the presence of a tumor in the pancreas using CT images compared with other reported studies in the literature.
| S-EPMC11390448 | biostudies-literature
Project description:The development of decision support systems for pathology and their deployment in clinical practice have been hindered by the need for large manually annotated datasets. To overcome this problem, we present a multiple instance learning-based deep learning system that uses only the reported diagnoses as labels for training, thereby avoiding expensive and time-consuming pixel-wise manual annotations. We evaluated this framework at scale on a dataset of 44,732 whole slide images from 15,187 patients without any form of data curation. Tests on prostate cancer, basal cell carcinoma and breast cancer metastases to axillary lymph nodes resulted in areas under the curve above 0.98 for all cancer types. Its clinical application would allow pathologists to exclude 65-75% of slides while retaining 100% sensitivity. Our results show that this system has the ability to train accurate classification models at unprecedented scale, laying the foundation for the deployment of computational decision support systems in clinical practice.
| S-EPMC7418463 | biostudies-literature
Project description:Background & aimsThe diagnosis of primary liver cancers (PLCs) can be challenging, especially on biopsies and for combined hepatocellular-cholangiocarcinoma (cHCC-CCA). We automatically classified PLCs on routine-stained biopsies using a weakly supervised learning method.MethodWe selected 166 PLC biopsies divided into training, internal and external validation sets: 90, 29 and 47 samples, respectively. Two liver pathologists reviewed each whole-slide hematein eosin saffron (HES)-stained image (WSI). After annotating the tumour/non-tumour areas, tiles of 256x256 pixels were extracted from the WSIs and used to train a ResNet18 neural network. The tumour/non-tumour annotations served as labels during training, and the network's last convolutional layer was used to extract new tumour tile features. Without knowledge of the precise labels of the malignancies, we then applied an unsupervised clustering algorithm.ResultsPathological review classified the training and validation sets into hepatocellular carcinoma (HCC, 33/90, 11/29 and 26/47), intrahepatic cholangiocarcinoma (iCCA, 28/90, 9/29 and 15/47), and cHCC-CCA (29/90, 9/29 and 6/47). In the two-cluster model, Clusters 0 and 1 contained mainly HCC and iCCA histological features. The diagnostic agreement between the pathological diagnosis and the two-cluster model predictions (major contingent) in the internal and external validation sets was 100% (11/11) and 96% (25/26) for HCC and 78% (7/9) and 87% (13/15) for iCCA, respectively. For cHCC-CCA, we observed a highly variable proportion of tiles from each cluster (cluster 0: 5-97%; cluster 1: 2-94%).ConclusionOur method applied to PLC HES biopsy could identify specific morphological features of HCC and iCCA. Although no specific features of cHCC-CCA were recognized, assessing the proportion of HCC and iCCA tiles within a slide could facilitate the identification of cHCC-CCA.Impact and implicationsThe diagnosis of primary liver cancers can be challenging, especially on biopsies and for combined hepatocellular-cholangiocarcinoma (cHCC-CCA). We automatically classified primary liver cancers on routine-stained biopsies using a weakly supervised learning method. Our model identified specific features of hepatocellular carcinoma and intrahepatic cholangiocarcinoma. Despite no specific features of cHCC-CCA being recognized, the identification of hepatocellular carcinoma and intrahepatic cholangiocarcinoma tiles within a slide could facilitate the diagnosis of primary liver cancers, and particularly cHCC-CCA.
| S-EPMC10877109 | biostudies-literature