LAUSR

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 4.7% 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. Author summary Metagenome assembly quality is fundamental to all downstream analyses of such data. The number of metagenome assemblies, especially metagenome-assembled genomes (MAGs), is rapidly increasing, but tools to assess the quality of these assemblies lack the accuracy needed for robust quality control. Moreover, existing models have been trained on datasets lacking complexity and realism, which may limit their generalization to novel data. Due to the limitations of existing models, most studies forgo such approaches and instead rely on CheckM to assess assembly quality, an approach that only utilizes a small portion of all genomic information and does not identify specific misassemblies. We harnessed existing large genomic datasets and high-performance computing to produce a training dataset of unprecedented size and complexity and thereby trained a deep learning model for predicting misassemblies that can robustly generalize to novel taxonomy and varying assembly methodologies.