EternaBrain: Automated RNA design through move sets and strategies from an Internet-scale RNA videogame.
Emerging RNA-based approaches to disease detection and gene therapy require RNA sequences that fold into specific base-pairing patterns, but computational algorithms generally remain inadequate for these secondary structure design tasks. The Eterna project has crowdsourced RNA design to human video...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2019-06-01
|
| Series: | PLoS Computational Biology |
| Online Access: | https://doi.org/10.1371/journal.pcbi.1007059 |
| _version_ | 1797660715112202240 |
|---|---|
| author | Rohan V Koodli Benjamin Keep Katherine R Coppess Fernando Portela Eterna participants Rhiju Das |
| author_facet | Rohan V Koodli Benjamin Keep Katherine R Coppess Fernando Portela Eterna participants Rhiju Das |
| author_sort | Rohan V Koodli |
| collection | DOAJ |
| description | Emerging RNA-based approaches to disease detection and gene therapy require RNA sequences that fold into specific base-pairing patterns, but computational algorithms generally remain inadequate for these secondary structure design tasks. The Eterna project has crowdsourced RNA design to human video game players in the form of puzzles that reach extraordinary difficulty. Here, we demonstrate that Eterna participants' moves and strategies can be leveraged to improve automated computational RNA design. We present an eternamoves-large repository consisting of 1.8 million of player moves on 12 of the most-played Eterna puzzles as well as an eternamoves-select repository of 30,477 moves from the top 72 players on a select set of more advanced puzzles. On eternamoves-select, we present a multilayer convolutional neural network (CNN) EternaBrain that achieves test accuracies of 51% and 34% in base prediction and location prediction, respectively, suggesting that top players' moves are partially stereotyped. Pipelining this CNN's move predictions with single-action-playout (SAP) of six strategies compiled by human players solves 61 out of 100 independent puzzles in the Eterna100 benchmark. EternaBrain-SAP outperforms previously published RNA design algorithms and achieves similar or better performance than a newer generation of deep learning methods, while being largely orthogonal to these other methods. Our study provides useful lessons for future efforts to achieve human-competitive performance with automated RNA design algorithms. |
| first_indexed | 2024-03-11T18:34:59Z |
| format | Article |
| id | doaj.art-745e3db877f44745a278b34d058b3b67 |
| institution | Directory Open Access Journal |
| issn | 1553-734X 1553-7358 |
| language | English |
| last_indexed | 2024-03-11T18:34:59Z |
| publishDate | 2019-06-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS Computational Biology |
| spelling | doaj.art-745e3db877f44745a278b34d058b3b672023-10-13T05:31:03ZengPublic Library of Science (PLoS)PLoS Computational Biology1553-734X1553-73582019-06-01156e100705910.1371/journal.pcbi.1007059EternaBrain: Automated RNA design through move sets and strategies from an Internet-scale RNA videogame.Rohan V KoodliBenjamin KeepKatherine R CoppessFernando PortelaEterna participantsRhiju DasEmerging RNA-based approaches to disease detection and gene therapy require RNA sequences that fold into specific base-pairing patterns, but computational algorithms generally remain inadequate for these secondary structure design tasks. The Eterna project has crowdsourced RNA design to human video game players in the form of puzzles that reach extraordinary difficulty. Here, we demonstrate that Eterna participants' moves and strategies can be leveraged to improve automated computational RNA design. We present an eternamoves-large repository consisting of 1.8 million of player moves on 12 of the most-played Eterna puzzles as well as an eternamoves-select repository of 30,477 moves from the top 72 players on a select set of more advanced puzzles. On eternamoves-select, we present a multilayer convolutional neural network (CNN) EternaBrain that achieves test accuracies of 51% and 34% in base prediction and location prediction, respectively, suggesting that top players' moves are partially stereotyped. Pipelining this CNN's move predictions with single-action-playout (SAP) of six strategies compiled by human players solves 61 out of 100 independent puzzles in the Eterna100 benchmark. EternaBrain-SAP outperforms previously published RNA design algorithms and achieves similar or better performance than a newer generation of deep learning methods, while being largely orthogonal to these other methods. Our study provides useful lessons for future efforts to achieve human-competitive performance with automated RNA design algorithms.https://doi.org/10.1371/journal.pcbi.1007059 |
| spellingShingle | Rohan V Koodli Benjamin Keep Katherine R Coppess Fernando Portela Eterna participants Rhiju Das EternaBrain: Automated RNA design through move sets and strategies from an Internet-scale RNA videogame. PLoS Computational Biology |
| title | EternaBrain: Automated RNA design through move sets and strategies from an Internet-scale RNA videogame. |
| title_full | EternaBrain: Automated RNA design through move sets and strategies from an Internet-scale RNA videogame. |
| title_fullStr | EternaBrain: Automated RNA design through move sets and strategies from an Internet-scale RNA videogame. |
| title_full_unstemmed | EternaBrain: Automated RNA design through move sets and strategies from an Internet-scale RNA videogame. |
| title_short | EternaBrain: Automated RNA design through move sets and strategies from an Internet-scale RNA videogame. |
| title_sort | eternabrain automated rna design through move sets and strategies from an internet scale rna videogame |
| url | https://doi.org/10.1371/journal.pcbi.1007059 |
| work_keys_str_mv | AT rohanvkoodli eternabrainautomatedrnadesignthroughmovesetsandstrategiesfromaninternetscalernavideogame AT benjaminkeep eternabrainautomatedrnadesignthroughmovesetsandstrategiesfromaninternetscalernavideogame AT katherinercoppess eternabrainautomatedrnadesignthroughmovesetsandstrategiesfromaninternetscalernavideogame AT fernandoportela eternabrainautomatedrnadesignthroughmovesetsandstrategiesfromaninternetscalernavideogame AT eternaparticipants eternabrainautomatedrnadesignthroughmovesetsandstrategiesfromaninternetscalernavideogame AT rhijudas eternabrainautomatedrnadesignthroughmovesetsandstrategiesfromaninternetscalernavideogame |