AI Insight
PhySeqNet is a physics-informed deep learning framework that detects fluorescent foci in BARseq spatial transcriptomics without requiring manual annotations. The method trains neural networks on synthetic images generated from optical models and real experimental noise, then applies them to actual tissue samples. In brain tissue analysis, PhySeqNet detected more gene transcripts per cell (median 51 vs 47 counts) compared to existing methods while maintaining biological consistency with reference datasets.
Why it matters
This approach addresses a critical bottleneck in spatial transcriptomics by improving detection sensitivity in dense, overlapping fluorescent signals without needing labor-intensive manual labeling. The improved transcript detection could enhance the resolution and accuracy of gene expression mapping in intact tissues, benefiting neuroscience research and disease studies.
Understand the Science
⚠️ Preprint – Noch nicht peer-reviewed
Dieser Artikel wurde noch nicht von unabhängigen Experten begutachtet. Die Ergebnisse sind vorläufig und sollten mit Vorsicht interpretiert werden.
Abstract: BARseq enables spatially resolved gene-expression profiling across intact tissue, but its sensitivity depends on accurate detection and decoding of dense fluorescent rolonies. Existing spot-calling approaches can be conservative where signals overlap, while supervised deep learning is limited by the lack of reliable manual ground truth in real tissue images. Here we present PhySeqNet, a physics-informed deep learning framework for annotation-free fluorescent foci detection in BARseq. PhySeqNet trains U-Net detectors entirely on semi-synthetic images generated from an instrument-matched optical model combined with real sample-free experimental noise, and is integrated into pyBARseq, a modular Python pipeline for BARseq analysis. PhySeqNet achieved high detection performance on held-out simulated data across wavelength bands. On real tissue images, where ground truth is unavailable, we evaluated detections by forward-model reconstruction: PhySeqNet with conservative barcode-aware non-maxima suppression (NMSB) achieved higher reconstruction fidelity (NCC and MS-SSIM) than the BarDensr single-shot estimator, tuned classical spot detectors, and a pretrained deep-learning detector. In the analyzed brain section, PhySeqNet with NMSB yielded a median of 51 counts per cell versus 47 for BarDensr, with a similar number of genes detected per cell. The recovered transcripts produced spatial expression patterns qualitatively consistent with Allen MERFISH reference data and preserved cell-type composition after scANVI label transfer. These results show that physics-informed simulation can train practical, annotation-free detectors that improve BARseq sensitivity without disrupting downstream biological interpretation.
Source: PhySeqNet: physics-informed fluorescent foci detection for BARseq spatial transcriptomics