Barnabas Gall
@barnabas-gall.bsky.social
PhD student at the Jackson Lab, Australian National University
Reposted by Barnabas Gall
www.nature.com/articles/s42...
Paper on ASR protein ML published (congrats @danasmatthews.bsky.social and everyone else not on Bluesky). Some interesting bits - ASR can generate quality synthetic data, local sequence density important, and evo relationships can yield smoother fitness landscapes
Paper on ASR protein ML published (congrats @danasmatthews.bsky.social and everyone else not on Bluesky). Some interesting bits - ASR can generate quality synthetic data, local sequence density important, and evo relationships can yield smoother fitness landscapes
Leveraging ancestral sequence reconstruction for protein representation learning - Nature Machine Intelligence
Matthews et al. present a protein sequence embedding based on data from ancestral sequences that allows machine learning to be used for tasks where training data are scarce or expensive.
www.nature.com
December 19, 2024 at 4:54 AM
www.nature.com/articles/s42...
Paper on ASR protein ML published (congrats @danasmatthews.bsky.social and everyone else not on Bluesky). Some interesting bits - ASR can generate quality synthetic data, local sequence density important, and evo relationships can yield smoother fitness landscapes
Paper on ASR protein ML published (congrats @danasmatthews.bsky.social and everyone else not on Bluesky). Some interesting bits - ASR can generate quality synthetic data, local sequence density important, and evo relationships can yield smoother fitness landscapes
Reposted by Barnabas Gall
arxiv.org/abs/2412.06115
The emergence of order from disorder, sensitivity to initial conductions, epistasis, the fractal geometry of phylo trees, etc., are all traits protein evolution has in common with other “complex systems”.
The emergence of order from disorder, sensitivity to initial conductions, epistasis, the fractal geometry of phylo trees, etc., are all traits protein evolution has in common with other “complex systems”.
Protein Evolution as a Complex System
Protein evolution underpins life, and understanding its behavior as a system is of great importance. However, our current models of protein evolution are arguably too simplistic to allow quantitative ...
arxiv.org
December 10, 2024 at 3:38 AM
arxiv.org/abs/2412.06115
The emergence of order from disorder, sensitivity to initial conductions, epistasis, the fractal geometry of phylo trees, etc., are all traits protein evolution has in common with other “complex systems”.
The emergence of order from disorder, sensitivity to initial conductions, epistasis, the fractal geometry of phylo trees, etc., are all traits protein evolution has in common with other “complex systems”.