Serval: A modular framework for decoding imaging based spatial transcriptomics data

Imaging-based spatial transcriptomics technologies have opened new avenues for studying cellular organization and gene expression within intact tissues. However, the accuracy of downstream analyses depends critically on the decoding step that reconstructs barcodes from fluorescence patterns and maps them to gene identities. Despite a growing number of decoding methods, systematic benchmarking has been limited.

Here, we introduce Serval, a modular framework for developing and benchmarking decoding methods across diverse spatial transcriptomics platforms. Serval separates key decoding stages into independently configurable modules, enabling flexible integration of alternative algorithms. Using this framework, we develop CoSiD (Cosine Similarity Decoder), a novel method that improves transcript recovery by optimizing cosine similarity to known barcodes. We evaluate CoSiD and baseline methods on synthetic and real MERFISH datasets, showing that CoSiD achieves higher transcript recovery and superior correlation with expression references compared to existing methods. Furthermore, we demonstrate that the Serval framework generalizes beyond MERFISH. By extending to the DART-FISH platform, we show that CoSiD improves transcript recovery, clustering stability and supports more direct annotation of complex biological structures such as the human primary motor cortex. These results establish that modular decoding frameworks facilitate robust, platform-agnostic benchmarking, ultimately supporting more accurate spatial transcriptomics analysis across diverse biological samples.

Serval and CoSiD are open source and publicly available at https://github.com/Roth-Lab/serval. Code for the simulation and analysis pipelines is available from the repositories described in the Data Availability section.

Supplementary data are available at Bioinformatics online.