Difference between revisions of "Team:Heidelberg/Software"
| Line 16: | Line 16: | ||
https://static.igem.org/mediawiki/2017/e/e6/T--Heidelberg--2017_Background_board.jpg|turk| | https://static.igem.org/mediawiki/2017/e/e6/T--Heidelberg--2017_Background_board.jpg|turk| | ||
{{Heidelberg/abstract|https://static.igem.org/mediawiki/2017/b/ba/T--Heidelberg--2017_AiGEM_GA.jpg| | {{Heidelberg/abstract|https://static.igem.org/mediawiki/2017/b/ba/T--Heidelberg--2017_AiGEM_GA.jpg| | ||
| + | {{Heidelberg/templateus/Contentsection| | ||
{{#tag:html| | {{#tag:html| | ||
To simplify the generation desired functionalities <i>de novo</i> and enable evolutionary leaps, we created AiGEM, our Artificial Intelligence for Genetic Evolution Mimicking software suite. The heart of our software is DeeProtein, a deep neuronal network trained on ~10 million protein sequences and able to infer sequence-function relationships from raw sequence data with high accuracy. By interfacing DeeProtein with our genetic algorithm GAIA, we – for the first time - established a fully closed, <i>in silico</i> evolution cycle driven by an intelligent network. We used AiGEM to successfully modulate the catalytic efficiency of \(\beta\)-lactamases, thereby even producing variants which highly outperform the wild type enzyme. To demonstrate AiGEM’s ability for generating functionality de novo, we created a novel, highly efficient \(\beta\)-galactosidase purely by <i>in silico</i> evolution of a \(\beta\) -glucuronidase parental sequence. Finally, as part of our integrated human practices project, we implemented SafetyNet, a DeeProtein-based web application safeguarding directed evolution experiments. | To simplify the generation desired functionalities <i>de novo</i> and enable evolutionary leaps, we created AiGEM, our Artificial Intelligence for Genetic Evolution Mimicking software suite. The heart of our software is DeeProtein, a deep neuronal network trained on ~10 million protein sequences and able to infer sequence-function relationships from raw sequence data with high accuracy. By interfacing DeeProtein with our genetic algorithm GAIA, we – for the first time - established a fully closed, <i>in silico</i> evolution cycle driven by an intelligent network. We used AiGEM to successfully modulate the catalytic efficiency of \(\beta\)-lactamases, thereby even producing variants which highly outperform the wild type enzyme. To demonstrate AiGEM’s ability for generating functionality de novo, we created a novel, highly efficient \(\beta\)-galactosidase purely by <i>in silico</i> evolution of a \(\beta\) -glucuronidase parental sequence. Finally, as part of our integrated human practices project, we implemented SafetyNet, a DeeProtein-based web application safeguarding directed evolution experiments. | ||
| − | }}}} | + | }}}}}} |
{{Heidelberg/templateus/Contentsection| | {{Heidelberg/templateus/Contentsection| | ||
{{#tag:html| | {{#tag:html| | ||
Revision as of 19:38, 1 November 2017
AiGEM
Artificial intelligence for Genetic Evolution Mimicking
To simplify the generation desired functionalities de novo and enable evolutionary leaps, we created AiGEM, our Artificial Intelligence for Genetic Evolution Mimicking software suite. The heart of our software is DeeProtein, a deep neuronal network trained on ~10 million protein sequences and able to infer sequence-function relationships from raw sequence data with high accuracy. By interfacing DeeProtein with our genetic algorithm GAIA, we – for the first time - established a fully closed, in silico evolution cycle driven by an intelligent network. We used AiGEM to successfully modulate the catalytic efficiency of \(\beta\)-lactamases, thereby even producing variants which highly outperform the wild type enzyme. To demonstrate AiGEM’s ability for generating functionality de novo, we created a novel, highly efficient \(\beta\)-galactosidase purely by in silico evolution of a \(\beta\) -glucuronidase parental sequence. Finally, as part of our integrated human practices project, we implemented SafetyNet, a DeeProtein-based web application safeguarding directed evolution experiments.
