scRNA-seq Bias Detector: An Integrated Unsupervised Anomaly Recognition and Multi-Track Quality Control Framework for Single-Cell Transcriptomics

Single-cell RNA sequencing (scRNA-seq) has emerged as a transformative technology for profiling cellular heterogeneity and identifying cell-type-specific gene expression signatures at genome-wide resolution. However, the integration of scRNA-seq datasets across experimental batches, sequencing runs, and protocols introduces systematic technical biases and batch effects that can mask true biological signals and confound downstream analyses. We present the scRNA-seq Bias Detector , a comprehensive, open-source Python framework designed to bridge the gap between wet-lab biological intuition and the algorithmic foundations of quality control in single-cell genomics. The platform integrates seven complementary computational modules: (1) differential expression analysis for identifying batch-biased genes, (2) principal component analysis for quantifying batch-induced separation, (3) isolation forest-based unsupervised anomaly detection for contaminating cell identification, (4) comprehensive gene expression quality metrics including zero-inflation and variance distribution profiling, (5) UMAP and t-SNE nonlinear dimensionality reduction for batch mixing assessment, (6) Harmony batch correction with quantitative separation scoring, and (7) graph neural network (GNN)-based cell similarity analysis for neighbourhood-aware anomaly detection. Deployed via a lightweight Streamlit interface, the framework provides researchers with interactive visualizations, statistical reports, and directly actionable outputs compatible with batch correction workflows such as ComBat, Harmony, and Scanorama. We validated our approach using synthetic datasets with known batch effects and a biologically realistic semi-synthetic PBMC dataset modelled after established IFN-β stimulation experimental designs [1], demonstrating robust performance across both controlled and biologically meaningful batch-effect scenarios. The scRNA-seq Bias Detector serves as both a scalable prototyping environment for automated quality control pipelines and a translational tool to render computational batch assessment interpretable and actionable in immunometabolism and host-pathogen interaction studies.