End-to-end differentiable learning of protein structure
1–10 of 28 posts
Re: End-to-end differentiable learning of protein structure
#2I work on protein structure, albeit not from a computational standpoint, and it struck me as odd that none of the work from the Baker group (Univ Washington) e.g. Rosetta (https://www.rosettacommons.org/) was mentioned. Rosetta can be used to predict tertiary structure from amino acid sequence. Does anyone familiar with the field know how the methods used by software like ROSETTA differ from those presented in this paper?
Re: End-to-end differentiable learning of protein structure
#3I work on protein structure, albeit not from a computational standpoint, and it struck me as odd that none of the work from the Baker group (Univ Washington) e.g. Rosetta ( https://www.rosettacommons.org/ ) was mentioned. Rosetta can be used to predict tertiary structure from amino acid sequence. Does anyone familiar with the field know how the methods used by software like ROSETTA differ from those presented in this…
Hi! I’m the author of the paper. Not sure why you say Rosetta isn’t mentioned? It’s extensively referenced throughout the paper, discussed in the discussion section, and is one of the top 5 CASP servers compared to in the results section.
Also as for how it’s different from what’s described in the paper, that’s the topic of the introduction of the paper. Rosetta uses both fragment assembly and co-evolution methods.
Re: End-to-end differentiable learning of protein structure
#4I work on protein structure, albeit not from a computational standpoint, and it struck me as odd that none of the work from the Baker group (Univ Washington) e.g. Rosetta ( https://www.rosettacommons.org/ ) was mentioned. Rosetta can be used to predict tertiary structure from amino acid sequence. Does anyone familiar with the field know how the methods used by software like ROSETTA differ from those presented in this…
Hi! I’m the author of the paper. Not sure why you say Rosetta isn’t mentioned? It’s extensively referenced throughout the paper, discussed in the discussion section, and is one of the top 5 CASP servers compared to in the results section. Also as for how it’s different from what’s described in the paper, that’s the topic of the introduction of the paper. Rosetta uses both fragment assembly and co-evolution methods.
Oops I seemed to have skimmed it a bit too quickly. Thank you for the kind reply.
Re: End-to-end differentiable learning of protein structure
#5It would be cool if machine learning researchers would start participating CASP and CAPRI. If you crack Go, you get fame, but if you crack protein prediction, you get Nobel price and completely revolutionize biochemistry and medicine.
http://www.ebi.ac.uk/msd-srv/capri/
edit: Why there is no XPRICE for protein folding?
Re: End-to-end differentiable learning of protein structure
#6It would be cool if machine learning researchers would start participating CASP and CAPRI. If you crack Go, you get fame, but if you crack protein prediction, you get Nobel price and completely revolutionize biochemistry and medicine. http://predictioncenter.org/ http://www.ebi.ac.uk/msd-srv/capri/ edit: Why there is no XPRICE for protein folding?
DeepMind and others are trying. "Hassabis said the company is now planning to apply an algorithm based on AlphaGo Zero to other domains with real-world applications, starting with protein folding."
[1] https://www.bloomberg.com/news/articles/2017-10-18/deepmind-...
Re: End-to-end differentiable learning of protein structure
#7It would be cool if machine learning researchers would start participating CASP and CAPRI. If you crack Go, you get fame, but if you crack protein prediction, you get Nobel price and completely revolutionize biochemistry and medicine. http://predictioncenter.org/ http://www.ebi.ac.uk/msd-srv/capri/ edit: Why there is no XPRICE for protein folding?
lol what-I was looking at this list of people who do this-in fact a lot of them ARE machine learning researchers...including some in my department!
Re: End-to-end differentiable learning of protein structure
#8It would be cool if machine learning researchers would start participating CASP and CAPRI. If you crack Go, you get fame, but if you crack protein prediction, you get Nobel price and completely revolutionize biochemistry and medicine. http://predictioncenter.org/ http://www.ebi.ac.uk/msd-srv/capri/ edit: Why there is no XPRICE for protein folding?
lol what-I was looking at this list of people who do this-in fact a lot of them ARE machine learning researchers...including some in my department!
I do think however that protein folding is very much understudied in the ML community, relative to say the big three of vision, NLP, and speech. The lack of standardized data sets and benchmarks, not to mention the need for domain knowledge, have made it difficult to get into the field
Re: End-to-end differentiable learning of protein structure
#9This is a very interesting approach. Clearly a lot more work to do but the robust prediction of protein structure from sequence would be an absolute game changer for biomedical science so I hope that this opens up new strategies.
Re: End-to-end differentiable learning of protein structure
#10Earlier quoted context omitted.
lol what-I was looking at this list of people who do this-in fact a lot of them ARE machine learning researchers...including some in my department!
I do think however that protein folding is very much understudied in the ML community, relative to say the big three of vision, NLP, and speech. The lack of standardized data sets and benchmarks, not to mention the need for domain knowledge, have made it difficult to get into the field
CASP is a pretty nice dataset, so is all of the PDB.