A crowdsourcing method for correcting sequencing errors for the third-generation sequencing data.
Yu GengZhongmeng ZhaoZhaofang DuYixuan WangTian ZhengSiyu HeXuanping ZhangJiayin WangPublished in: BIBM (2017)
Keyphrases
- synthetic data
- input data
- data sets
- data processing
- missing data
- information loss
- noisy data
- missing values
- data collection
- raw data
- preprocessing
- data points
- cost function
- high accuracy
- statistical methods
- database
- training data
- dynamic programming
- significant improvement
- neural network
- prior knowledge
- similarity measure
- prior information
- statistical analysis
- computational complexity
- test data
- objective function
- data structure
- statistical significance
- spectral clustering
- original data
- high quality
- segmentation method
- high dimensional data
- detection method
- data analysis
- pairwise
- xml documents
- knowledge discovery
- computational cost