| 项目编号 | PRJCA031439 | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| 项目标题 | Pacbio CCS datasets for training and testing Z-Calling | ||||||||
| 涉及领域 | Medical | ||||||||
| 数据类型 | Raw sequence reads | ||||||||
| 物种名称 |
Arabidopsis thaliana
Oryza sativa Acinetobacter phage SH-Ab 15497 Escherichia coli Danio rerio Drosophila melanogaster Saccharomyces cerevisiae |
||||||||
| 描述信息 | Z-Calling is a machine-learning based tool for (1) distinguishing dZ-DNA molecules from ordinary DNAs and (2) calling Z bases in A/Z-coexisting DNAs. Z-Calling also has implemented a pipeline for detecting taxonomic or sequence sources of dZ-DNAs in mixed datasets. In multiple tested datasets, Z-Calling has faithfully identified souces of dZ-DNAs without false positive discory. And its Z base calling module has achieved AUCs ranging from 0.9422 to 0.9550 and F1 scores ranging from 0.85-0.92 across all tested datasets. | ||||||||
| 样品范围 | Multispecies | ||||||||
| 发布日期 | 2024-11-11 | ||||||||
| 项目资金来源 |
|
||||||||
| 提交者 | Bo Wu (aragornwubo@163.com) | ||||||||
| 提交单位 | Zhongshan Ophthalmic Center, Sun Yat-sen University | ||||||||
| 提交日期 | 2024-10-21 |