Using expected sequence features to improve basecalling accuracy of amplicon pyrosequencing data.
Thomas S. RaskBent PetersenDonald S. ChenKaren P. DayAnders Gorm PedersenPublished in: BMC Bioinform. (2016)
Keyphrases
- database
- data sets
- prior knowledge
- data processing
- training data
- raw data
- data structure
- data analysis
- learning algorithm
- data sources
- data points
- computer systems
- structural information
- data distribution
- experimental data
- synthetic data
- data collection
- training and testing data
- input data
- high accuracy
- small number
- high quality
- knowledge discovery
- classification accuracy
- sensor data
- low level
- feature vectors
- data streams
- data reduction
- feature extraction