March 2023 - April 2023
Source: https://www.10xgenomics.com/resources/analysis-guides/introduction-batch-effect-correction
With the advancement of single-cell RNA sequencing (scRNA-seq) technology, we can access large-scale, high dimensional and diverse genomics data. Single-cell atlases often include samples that span locations, laboratories and conditions, leading to batch effects in data. Thus, batch effect correction is a crucial step in the analysis of scRNA-seq data, aimed at removing systematic differences between batches of samples that arise due to technical or experimental variability.
Recent work has proven VAE and GAN to be individually good at correcting for batch effects. We propose that harnessing the power of both these models may give better results for a wide range of scRNA-seq data. We will further be utilizing the benchmark dataset and the pipeline provided to assess our integration method on 14 different metrics [1]. By utilizing this well-established benchmark, we can ensure that our results are comparable to other state-of-the-art methods in the field.
Python, sklearn, PyTorch, High performance Computing (Cluster)
Mirudhula Mukundan, Kevin Elaba, Yiqing Wang
[1] Luecken, M. D., Büttner, M., Chaichoompu, K., Danese, A., Interlandi, M., Müller, M. F., ... & Theis, F. J. (2022). Benchmarking atlas-level data integration in single-cell genomics. Nature methods, 19 (1), 41-50.
To check out our complete report, click here <to be updated>.