A Literature-Derived Knowledge Graph Augments the Interpretation of Single Cell RNA-seq Datasets.

Technology to generate single cell RNA-sequencing (scRNA-seq) datasets and tools to annotate them have advanced rapidly in the past several years. Such tools generally rely on existing transcriptomic datasets or curated databases of cell type defining genes, while the application of scalable natural language processing (NLP) methods to enhance analysis workflows has not been adequately explored. Here we deployed an NLP framework to objectively quantify associations between a comprehensive set of over 20,000 human protein-coding genes and over 500 cell type terms across over 26 million biomedical documents. The resultant gene-cell type associations (GCAs) are significantly stronger between a curated set of matched cell type-marker pairs than the complementary set of mismatched pairs (Mann Whitney p = 6.15 × 10-76, r = 0.24; cohen's D = 2.6). Building on this, we developed an augmented annotation algorithm (single cell Annotation via Literature Encoding, or scALE) that leverages GCAs to categorize cell clusters identified in scRNA-seq datasets, and we tested its ability to predict the cellular identity of 133 clusters from nine datasets of human breast, colon, heart, joint, ovary, prostate, skin, and small intestine tissues. With the optimized settings, the true cellular identity matched the top prediction in 59% of tested clusters and was present among the top five predictions for 91% of clusters. scALE slightly outperformed an existing method for reference data driven automated cluster annotation, and we demonstrate that integration of scALE can meaningfully improve the annotations derived from such methods. Further, contextualization of differential expression analyses with these GCAs highlights poorly characterized markers of well-studied cell types, such as CLIC6 and DNASE1L3 in retinal pigment epithelial cells and endothelial cells, respectively. Taken together, this study illustrates for the first time how the systematic application of a literature-derived knowledge graph can expedite and enhance the annotation and interpretation of scRNA-seq data.

Real-time analysis of a mass vaccination effort confirms the safety of FDA-authorized mRNA COVID-19 vaccines.

BACKGROUND: As the coronavirus disease 2019 (COVID-19) vaccination campaign unfolds, it is important to continuously assess the real-world safety of Food and Drug Administration (FDA)-authorized vaccines. Curation of large-scale electronic health records (EHRs) enables near-real-time safety evaluations that were not previously possible. METHODS: In this retrospective study, we deployed deep neural networks over a large EHR system to automatically curate the adverse effects mentioned by physicians in over 1.2 million clinical notes between December 1, 2020 and April 20, 2021. We compared notes from 68,266 individuals who received at least one dose of BNT162b2 (n = 51,795) or mRNA-1273 (n = 16,471) to notes from 68,266 unvaccinated individuals who were matched by demographic, geographic, and clinical features. FINDINGS: Individuals vaccinated with BNT162b2 or mRNA-1273 had a higher rate of return to the clinic, but not the emergency department, after both doses compared to unvaccinated controls. The most frequently documented adverse effects within 7 days of each vaccine dose included myalgia, headache, and fatigue, but the rates of EHR documentation for each side effect were remarkably low compared to those derived from active solicitation during clinical trials. Severe events, including anaphylaxis, facial paralysis, and cerebral venous sinus thrombosis, were rare and occurred at similar frequencies in vaccinated and unvaccinated individuals. CONCLUSIONS: This analysis of vaccine-related adverse effects from over 1.2 million EHR notes of more than 130,000 individuals reaffirms the safety and tolerability of the FDA-authorized mRNA COVID-19 vaccines in practice. FUNDING: This study was funded by nference.