Self-distillation contrastive learning enables clustering-free signature extraction and mapping to multimodal single-cell atlas of multimillion scale (preprint)

Massively generated single-cell multi-omics datasets are revolutionizing biological studies of heterogenous tissues and organisms, which necessitate powerful computational methods to unleash the full potential of these tremendous data. Here, we present Concerto, stands for self-distillation contrastive learning of cell representations, a self-supervised representation learning framework optimized with asymmetric teacher-student configuration to analyze single-cell multi-omics datasets with scalability up to building 10 million-cell reference within 1.5 hour and querying 10k cells within 8 seconds. Concerto leverages dropout layer as minimal data augmentation to learn meaningful cell representations in a contrastive manner. The teacher module uses attention mechanism to aggregate contextualized gene embeddings within cellular context, while the student module uses simpler dense structure with discreate input. The learned task-agnostic representations can be adapted to a broad range of single-cell computation tasks. 1) Via supervised fine-tuning, Concerto enables automatic cell classification as well as novel cell-type discovery; 2) Attention weights provide model interpretability via automatically extracting specific molecular signatures at single-cell resolution without the needs of clustering; 3) Via source-aware training, Concerto supports efficient data integration by projecting all cells across multiple batches into a joint embedding space. 4) Via batch-aware inference or unsupervised fine-tuning, Concerto enables mapping query cells onto reference and accurately transferring annotations. Concerto can flexibly extend to multi-omics datasets simply through cross-modality summation operation to obtain unified cell embeddings. Using examples from human peripheral blood, human thymus, human pancreas, and mouse tissue atlas, Concerto shows superior performance benchmarking against other top-performing methods. We also demonstrate Concerto recapitulates detailed COVID-19 disease variation through query-to-reference mapping. Concerto can operate on all genes and represents a fully data-driven approach with minimum prior distribution assumptions, eliminating the needs of PCA-like or autoencoder-like dimensionality reduction, which significantly reforms the current best practice. Concerto is a simple, straightforward, robust, and scalable framework, offering a brand new perspective to derive cell representations and can effectively satisfy the emerging paradigm of query-to-reference mapping in the era of atlas-level single-cell multimodal analysis.

The expression of PDCD1 and CD274 in T cells and macrophages correlated positively with COVID-19 severity (preprint)

The immune responses underlying the infection of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) remain unclear. To help understand the pathology of coronavirus disease 2019 (COVID-19) pandemics, public data were analyzed and the expression of PDCD1 (encoding PD-1) and CD274 (encoding PD-L1) in T cells and macrophages were identified to correlate positively with COVID-19 severity.

Effect of large-scale testing platform in prevention and control of the COVID-19 pandemic: an empirical study with a novel numerical model (preprint)

Background: China adopted an unprecedented province-scale quarantine since January 23rd 2020, after the novel coronavirus (COVID-19) broke out in Wuhan in December 2019. Responding to the challenge of limited testing capacity, large-scale standardized and fully-automated laboratory (Huo-Yan) was built as an ad-hoc measure. There was so far no empirical data or mathematical model to reveal the impact of the testing capacity improvement since the quarantine. Methods: We integrated public data released by the Health Commission of Hubei Province and Huo-Yan Laboratory testing data into a novel differential model with non-linear transfer coefficients and competitive compartments, to evaluate the trends of suspected cases under different nucleic acid testing capacities. Results: Without the establishment of Huo-Yan, the suspected cases would increased by 47% to 33,700, the corresponding cost of the quarantine would be doubled, and the turning point of the increment of suspected cases and the achievement of "daily settlement" (all daily new discovered suspected cases were diagnosed according to the nucleic acid testing results) would be delayed for a whole week and 11 days. If the Huo-Yan Laboratory could ran at its full capacity, the number of suspected cases could started to decrease at least a week earlier, the peak of suspected cases would be reduced by at least 44% and the quarantine cost could be reduced by more than 72%. Ideally, if a daily testing capacity of 10,500 could achieved immediately after the Hubei lockdown, "daily settlement" for all suspected cases would be achieved immediately. Conclusions: Large-scale and standardized clinical testing platform with nucleic acid testing, high-throughput sequencing and immunoprotein assessment capabilities need to be implemented simultaneously in order to maximize the effect of quarantine and minimize the duration and cost. Such infrastructure like Huo-Yan, is of great significance for the early prevention and control of infectious diseases for both common times and emergencies.