RESUMO
The number of published metagenome assemblies is rapidly growing due to advances in sequencing technologies. However, sequencing errors, variable coverage, repetitive genomic regions, and other factors can produce misassemblies, which are challenging to detect for taxonomically novel genomic data. Assembly errors can affect all downstream analyses of the assemblies. Accuracy for the state of the art in reference-free misassembly prediction does not exceed an AUPRC of 0.57, and it is not clear how well these models generalize to real-world data. Here, we present the Residual neural network for Misassembled Contig identification (ResMiCo), a deep learning approach for reference-free identification of misassembled contigs. To develop ResMiCo, we first generated a training dataset of unprecedented size and complexity that can be used for further benchmarking and developments in the field. Through rigorous validation, we show that ResMiCo is substantially more accurate than the state of the art, and the model is robust to novel taxonomic diversity and varying assembly methods. ResMiCo estimated 7% misassembled contigs per metagenome across multiple real-world datasets. We demonstrate how ResMiCo can be used to optimize metagenome assembly hyperparameters to improve accuracy, instead of optimizing solely for contiguity. The accuracy, robustness, and ease-of-use of ResMiCo make the tool suitable for general quality control of metagenome assemblies and assembly methodology optimization.
Assuntos
Aprendizado Profundo , Metagenoma , Metagenoma/genética , Genômica/métodos , Análise de Sequência de DNA/métodos , Metagenômica , SoftwareRESUMO
MOTIVATION: Methodological advances in metagenome assembly are rapidly increasing in the number of published metagenome assemblies. However, identifying misassemblies is challenging due to a lack of closely related reference genomes that can act as pseudo ground truth. Existing reference-free methods are no longer maintained, can make strong assumptions that may not hold across a diversity of research projects, and have not been validated on large-scale metagenome assemblies. RESULTS: We present DeepMAsED, a deep learning approach for identifying misassembled contigs without the need for reference genomes. Moreover, we provide an in silico pipeline for generating large-scale, realistic metagenome assemblies for comprehensive model training and testing. DeepMAsED accuracy substantially exceeds the state-of-the-art when applied to large and complex metagenome assemblies. Our model estimates a 1% contig misassembly rate in two recent large-scale metagenome assembly publications. CONCLUSIONS: DeepMAsED accurately identifies misassemblies in metagenome-assembled contigs from a broad diversity of bacteria and archaea without the need for reference genomes or strong modeling assumptions. Running DeepMAsED is straight-forward, as well as is model re-training with our dataset generation pipeline. Therefore, DeepMAsED is a flexible misassembly classifier that can be applied to a wide range of metagenome assembly projects. AVAILABILITY AND IMPLEMENTATION: DeepMAsED is available from GitHub at https://github.com/leylabmpi/DeepMAsED. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
Assuntos
Metagenoma , Software , Bactérias , Simulação por Computador , Metagenômica , Análise de Sequência de DNARESUMO
Fracture prediction is essential in managing patients with osteoporosis, and is an integral component of many fracture prevention guidelines. We aimed to identify the most relevant clinical fracture risk factors in contemporary populations by training and validating short- and long-term fracture risk prediction models in two cohorts. We used traditional and machine learning survival models to predict risks of vertebral, hip and any fractures on the basis of clinical risk factors, T-scores and treatment history among participants in a nationwide Swiss osteoporosis registry (N = 5944 postmenopausal women, median follow-up of 4.1 years between January 2015 and October 2022; a total of 1190 fractures during follow-up). The independent validation cohort comprised 5474 postmenopausal women from the UK Biobank with 290 incident fractures during follow-up. Uno's C-index and the time-dependent area under the receiver operating characteristics curve were calculated to evaluate the performance of different machine learning models (Random survival forests and eXtreme Gradient Boosting). In the independent validation set, the C-index was 0.74 [0.58, 0.86] for vertebral fractures, 0.83 [0.7, 0.94] for hip fractures and 0.63 [0.58, 0.69] for any fractures at year 2, and these values further increased for longer estimations of up to 7 years. In comparison, the 10-year fracture probability calculated with FRAX® Switzerland was 0.60 [0.55, 0.64] for major osteoporotic fractures and 0.62 [0.49, 0.74] for hip fractures. The most important variables identified with Shapley additive explanations (SHAP) values were age, T-scores and prior fractures, while number of falls was an important predictor of hip fractures. Performances of both traditional and machine learning models showed similar C-indices. We conclude that fracture risk can be improved by including the lumbar spine T-score, trabecular bone score, numbers of falls and recent fractures, and treatment information has a significant impact on fracture prediction.
Fracture prediction is essential in managing patients with osteoporosis. We developed and validated traditional and machine learning models to predict short- and long-term fracture risk and identify the most relevant clinical fracture risk factors for vertebral, hip, and any fractures in contemporary populations. We used data from 5944 postmenopausal women in a Swiss osteoporosis registry and validated our findings with 5474 women from the UK Biobank. Our machine learning models performed well, with C-index values of 0.74 [0.58, 0.86] for vertebral fractures, 0.83 [0.7, 0.94] for hip fractures and 0.63 [0.58, 0.69] for any fractures at year 2, and these values further increased for longer estimations of up to 7 years. In contrast, FRAX® Switzerland had lower C-index values (0.60 [0.55, 0.64] for major fractures and 0.62 [0.49, 0.74] for hip fracture probabilities over 10 years). Key predictors identified included age, T-scores, prior fractures, and number of falls. We conclude that incorporating a broader range of clinical factors, as well as lumbar spine T-scores, fall history, recent fractures, and treatment information, can improve fracture risk assessments in osteoporosis management. Both traditional and machine learning models showed similar effectiveness in predicting fractures.