Batch effects

Batch effects

Data-Driven Approaches for Detecting and Identifying Anomalous Data Streams

Published in Ervin Sejdić, Tiago H. Falk, Signal Processing and Machine Learning for Biomedical Big Data, 2018

Shaofeng Zou, Yingbin Liang, H. Vincent Poor, Xinghua Shi

More generally, these methods can be used to detect and alleviate batch effects by removing batch biases in many experimental data sets on various platforms. Applied to data generated from sequencing and microarray technologies, these anomaly detection and identification methods can be used to identify and remove sequencing or assay biases from different batches, lanes, and platforms. Such analysis can be imposed at many different layers including DNA, RNA, metabolite, protein, and epignetic factors.

Intelligent framework for brain tumor grading using advanced feature analysis

View Article

Journal Information

Published in Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 2023

Geethu Mohan, Monica Subashini M

A major challenge in collaborative repositories like TCGA is data quality, where data piles up from various establishments. When it comes to quality control, TCGA has two challenges in terms of data quality: (a) Artefacts that come by at the time of image acquisition and (b) Batch effect that comes as an outcome of discrepancy in experimental protocol.

Explore chapters and articles related to this topic

Data-Driven Approaches for Detecting and Identifying Anomalous Data Streams

Intelligent framework for brain tumor grading using advanced feature analysis