That is a very strange way to generate molecules. It would be interesting to see if this is any better than other approaches used to generate molecules like those used in drug design. It would be particularly interesting to see how this compares with the approach that was used to generate GDB-17[1] a database of randomly generated molecules or at least see if generated molecules pass through the filters used to make GDB-17. Grammatically correct does not necessarily mean physically reasonable, recall Chomsky's "colorless green ideas sleep furiously."<p>While it would be interesting to model reactions with RNN, I'm not so sure this would offer any advantage over simply searching a database of reactions like the Crossfire Beilstein database[2][3]. I am also curious if you investigated reaction MQL in work with the carbonate project.<p>This work is interesting though. Essentially you are using a neural network to generate graphs. There are a lot of things that can be represented with graphs, IE electric circuits and such. Maybe you could make a RNN for generating neural networks!<p>[1]<a href="http://www.gdb.unibe.ch/gdb/home.html" rel="nofollow">http://www.gdb.unibe.ch/gdb/home.html</a>
[2]<a href="https://en.wikipedia.org/wiki/Beilstein_database" rel="nofollow">https://en.wikipedia.org/wiki/Beilstein_database</a>
[3]<a href="http://www.ncbi.nlm.nih.gov/pubmed/21378798" rel="nofollow">http://www.ncbi.nlm.nih.gov/pubmed/21378798</a>
Haha, interesting, but I thought this was going in a different direction. There's a lot of work going on lately to try to model molecular potentials (for molecular dynamics / quantum chemistry) using neural networks. Accurate potentials are extremely expensive to calculate.