Track genomics, neuroscience and molecular biology.
Search papers, labs, and topics across Lattice.
This paper introduces PhySeqNet, a physics-informed deep learning framework for annotation-free fluorescent foci detection in BARseq spatial transcriptomics. By training on semi-synthetic data derived from an optical model and experimental noise, PhySeqNet overcomes the limitations of manual ground truth and conservative existing methods. The framework demonstrates superior reconstruction fidelity and improved transcript detection sensitivity on real tissue data compared to established estimators and a pretrained deep learning detector.
Annotation-free fluorescent foci detection for BARseq is now possible with physics-informed deep learning, achieving higher reconstruction fidelity than existing methods on real tissue.
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.