Interesting paper. Nevertheless, natural designs are still less symmetric than engineered ones. (I think!) Any thoughts on why?
https://www.pnas.org/doi/10.1073/pnas.2113883119
Symmetry and simplicity spontaneously emerge from the algorithmic nature of evolution
https://www.nytimes.com/2022/03/24/science/symmetry-biology-evolution.html
https://www.nature.com/articles/s41586-021-03922-4
https://twitter.com/SEHanlon/status/1513548800949989377
At #AACR22, @VanAllenLab gives a nice overview of his paper using an interpretable NN model to get insights into determining cancer severity (https://nature.com/articles/s41586-021-03922-4)
Biologically informed deep neural network for prostate cancer discovery
Liked the way he hard-coded specific genes & pathways into the model & looked in detail where the model misclassified specific patients #AACR22 #AACR2022
Also, thought the hard-coding of genes into the model was similar to that in another interpretable AI approach (for brain disease, https://science.org/doi/10.1126/science.aat8464) Could have used the “rank projection trees” from this to highlight important genes #AACR22 #AACR2022
https://www.science.org/doi/10.1126/science.abj6987
Congratulations. Looking forward to mapping trillions of reads against CHM13!
Neural Distance Embeddings for Biological Sequences
Gabriele Corso, Rex Ying, Michal Pándy, Petar Veličković, Jure Leskovec, Pietro Liò
abs: https://arxiv.org/abs/2109.09740
github: https://github.com/gcorso/NeuroSE
https://arxiv.org/pdf/2109.09740.pdf
https://proceedings.neurips.cc/paper/2021/file/9a1de01f893e0d2551ecbb7ce4dc963e-Paper.pdf
Liked the extensive scATAC-seq analysis. We discussed this in a journal club.
https://www.nature.com/articles/s41586-021-03209-8
Single-cell epigenomics reveals mechanisms of human cortical development
Ryan S. Ziffra, Chang N. Kim, Jayden M. Ross, Amy Wilfert, Tychele N. Turner, Maximilian Haeussler, Alex M. Casella, Pawel F. Przytycki, Kathleen C. Keough, David Shin, Derek Bogdanoff, Anat Kreimer, Katherine S. Pollard, Seth A. Ament, Evan E. Eichler, Nadav Ahituv & Tomasz J. Nowakowski
Nature volume 598, pages 205–213 (2021)
eQTLs paper is out in Nature Genetics:
Zeng, B., Bendl, J., Kosoy, R. et al. [Panos R] Multi-ancestry eQTL meta-analysis of human brain identifies candidate causal variants for brain-related traits. Nat Genet (2022).
https://doi.org/10.1038/s41588-021-00987-9
linkstream2 microblog 