No abstract

Cell type identification is a vital step in the analysis of scRNA-seq data. Transcriptome subtype pivotal information such as alternative polyadenylation (APA) obtained from standard scRNA-seq data can also provide valid clues for cell type identification with no alteration of experimental techniques or increased experimental costs. Furthermore, using multimodal analysis techniques and their methods, more confident cell type identification results can be obtained. For that purpose, we constructed a workflow framework: On five different scRNA-seq datasets, 18 methods based on machine learning that have not yet been applied to identify cell types by association APA and single-cell gene expression fusion were compared with three single-cell clustering methods, and compared these method against the advanced method scLAPA based on similarity network fusion (SNF). In our experiments, we used the adjusted Rand index (ARI) as a metric. We found that unsupervised methods like WMSC and supervised methods like MOGONET have more robust and excellent results in associating APA with single-cell gene expression clustering than methods based only on single-cell gene expression clustering and advanced scLAPA methods.

Prime editors (PEs) are promising genome editing tools, but efficiency pre-testing of prime editing guide RNA (pegRNA) design is still laborious and time-consuming due to the lack of accurate and universal approaches. Here, we design a customized attention-based model OPED and train it using transfer learning to improve the accuracy and universality of efficiency prediction and design optimal pegRNAs. We demonstrate its powerful generalization capability across diverse published test datasets. Furthermore, we extend OPED to design optimal pegRNAs and single guide RNAs (sgRNAs) to install various ClinVar human pathogenic variants, and 28 of 30 (93.33%) target sites yield desired variants with few byproducts and practical editing efficiencies of up to 29.30%, 82.84%, and 90.05% for PE2, PE3/PE3b, and ePE systems, respectively. We construct the OPEDVar database of optimal designs from over two billion candidates for all ClinVar variants and provide a user-friendly web application of OPED for any intended edit.

No abstract