Accurate single-molecule spot detection for image-based spatial transcriptomics with weakly supervised deep learning

Copyright and License

Acknowledgement

We thank Lior Pachter, Barbara Englehardt, Sami Farhi, Ross Barnowski, and the other members of the Van Valen lab for useful feedback and interesting discussions. We thank Nico Pierson and Jonathan White for contributing data and providing early annotations. The HeLa cell line was used in this research. Henrietta Lacks and the HeLa cell line established from her tumor cells without her knowledge or consent in 1951 have made significant contributions to scientific progress and advances in human health. We are grateful to Henrietta Lacks, now deceased, and her surviving family members for their contributions to biomedical research. This work was supported by awards from the Shurl and Kay Curci Foundation (to D.V.V.), the Rita Allen Foundation (to D.V.V.), the Susan E Riley Foundation (to D.V.V.), the Pew-Stewart Cancer Scholars program (to D.V.V.), the Gordon and Betty Moore Foundation (to D.V.V.), the Schmidt Academy for Software Engineering (to T.D.), the Michael J. Fox Foundation through the Aligning Science Across Parkinsons consortium (to D.V.V.), the Heritage Medical Research Institute (to D.V.V.), the NIH New Innovator program (DP2-GM149556) (to D.V.V.), and an HHMI Freeman Hrabowski Scholar award (to D.V.V.).

Contributions

E.L., N.R., and D.V.V. conceived the project. E.L., N.R., and D.V.V. conceived the weakly supervised deep-learning method for spot detection. E.L. and E.P. created the seqFISH training data for the spot detection model. L.O. contributed to the seqFISH protocol used to create training data. E.L. developed software for training data annotation. E.L. curated and annotated the training data for the spot detection model. N.R. and E.L. developed the spot detection model training software. E.L. trained the models. E.L. and N.R. developed the metrics software for the spot detection model. X.W., E.L., Y.Y., and D.V.V. conceived the combinatorial barcode assignment method. E.L. and X.W. developed the barcode assignment software, with input from Y.Y. and D.V.V. E.L. developed the multiplex image analysis pipeline. E.L. and X.W. benchmarked the multiplex image analysis pipeline. E.L. and T.D. developed the cloud deployment. R.J.X. and J.R.M. collected and analyzed MERFISH data. E.L. and E.P. created the macrophage seqFISH dataset. W.G. and D.V.V. oversaw software engineering for Polaris. Y.Y. and D.V.V. oversaw the algorithm development for the project. E.L. and D.V.V. wrote the manuscript, with input from all authors. D.V.V. supervised the project.

Conflict of Interest

D.V.V. is a co-founder of Barrier Biosciences and holds equity in the company. D.V.V., E.L., and N.R. filed a patent for weakly supervised deep learning for spot detection. J.R.M. is co-founder and scientific advisor to Vizgen and holds equity in the company. J.R.M. is an inventor of patents related to MERFISH filed on his behalf by Harvard University and Boston Children’s Hospital.