Consistent annotation transfer from reference dataset to query dataset is fundamental to the development and reproducibility of single-cell research. Compared with traditional annotation methods, deep learning based methods are faster and more automated. A series of useful single cell analysis tools based on autoencoder architecture have been developed but these struggle to strike a balance between depth and interpretability. Here, we present TOSICA, a multi-head self-attention deep learning model based on Transformer that enables interpretable cell type annotation using biologically understandable entities, such as pathways or regulons. We show that TOSICA achieves fast and accurate one-stop annotation and batch-insensitive integration while providing biologically interpretable insights for understanding cellular behavior during development and disease progressions. We demonstrate TOSICA’s advantages by applying it to scRNA-seq data of tumor-infiltrating immune cells, and CD14+ monocytes in COVID-19 to reveal rare cell types, heterogeneity and dynamic trajectories associated with disease progression and severity.
Pharmacogenetics research on leukotriene modifiers (LTMs) for asthma has been developing rapidly, although pharmacogenetic testing for LTMs is not yet used in clinical practice. We performed a systematic review and meta-analysis on the impact of pharmacogenomics on LTMs response. Studies published until May 2022 were searched using PubMed, EMBASE, and Cochrane databases. Pharmacogenomics/genetics studies of patients with asthma using LTMs with or without other anti-asthmatic drugs were included. Statistical tests of the meta-analysis were performed with Review Manager (Revman, version 5.4, The Cochrane Collaboration, Copenhagen, Denmark) and R language and environment for statistical computing (version 4.1.0 for Windows, R Core Team, Vienna, Austria) software. In total, 31 studies with 8084 participants were included in the systematic review and five studies were also used to perform the meta-analysis. Two included studies were genome-wide association studies (GWAS), which showed different results. Furthermore, none of the SNPs investigated in candidate gene studies were identified in GWAS. In candidate gene studies, the most widely studied SNPs were ALOX5 (tandem repeats of the Sp1-binding domain and rs2115819), LTC4S-444A/C (rs730012), and SLCO2B1 (rs12422149), with relatively inconsistent conclusions. LTC4S-444A/C polymorphism did not show a significant effect in our meta-analysis (AA vs. AC (or AC + CC): −0.06, 95%CI: −0.16 to 0.05, p = 0.31). AA homozygotes had smaller improvements in parameters pertaining to lung functions (−0.14, 95%CI: −0.23 to −0.05, p = 0.002) in a subgroup of patients with non-selective CysLT receptor antagonists and patients without inhaled corticosteroids (ICS) (−0.11, 95%CI: −0.14 to −0.08, p < 0.00001), but not in other subgroups. Variability exists in the pharmacogenomics of LTMs treatment response. Our meta-analysis and systematic review found that LTC4S-444A/C may influence the treatment response of patients taking non-selective CysLT receptor antagonists for asthma, and patients taking LTMs not in combination with ICS for asthma. Future studies are needed to validate the pharmacogenomic influence on LTMs response.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.