MetaTransformer: deep metagenomic sequencing read classification using self-attention models.

Deep learning has emerged as a paradigm that revolutionizes numerous domains of scientific research. Transformers have been utilized in language modeling outperforming previous approaches. Therefore, the utilization of deep learning as a tool for analyzing the genomic sequences is promising, yielding convincing results in fields such as motif identification and variant calling. DeepMicrobes, a machine learning-based classifier, has recently been introduced for taxonomic prediction at species and genus level. However, it relies on complex models based on bidirectional long short-term memory cells resulting in slow runtimes and excessive memory requirements, hampering its effective usability. We present MetaTransformer, a self-attention-based deep learning metagenomic analysis tool. Our transformer-encoder-based models enable efficient parallelization while outperforming DeepMicrobes in terms of species and genus classification abilities. Furthermore, we investigate approaches to reduce memory consumption and boost performance using different embedding schemes. As a result, we are able to achieve 2× to 5× speedup for inference compared to DeepMicrobes while keeping a significantly smaller memory footprint. MetaTransformer can be trained in 9 hours for genus and 16 hours for species prediction. Our results demonstrate performance improvements due to self-attention models and the impact of embedding schemes in deep learning on metagenomic sequencing data.

Modeling the initial phase of SARS-CoV-2 deposition in the respiratory tract mimicked by the 11C radionuclide.

The knowledge on the deposition and retention of the viral particle of SARS-CoV-2 in the respiratory tract during the very initial intake from the ambient air is of prime importance to understand the infectious process and COVID-19 initial symptoms. We propose to use a modified version of a widely tested lung deposition model developed by the ICRP, in the context of the ICRP Publication 66, that provides deposition patterns of microparticles in different lung compartments. In the model, we mimicked the "environmental decay" of the virus, determined by controlled experiments related to normal speeches, by the radionuclide 11C that presents comparable decay rates. Our results confirm clinical observations on the high virus retentions observed in the extrathoracic region and the lesser fraction on the alveolar section (in the order of 5), which may shed light on physiopathology of clinical events as well on the minimal inoculum required to establish infection.