One of the authors here. Ask us anything!<p>This paper is just a first step - what we'd really like to use this for is designing recipes for synthesizing new molecules.<p>I would also be remiss if I didn't link to a closely-related paper from another group that came out at the same time:
<a href="http://pubs.acs.org/doi/abs/10.1021/ci5006614" rel="nofollow">http://pubs.acs.org/doi/abs/10.1021/ci5006614</a>
I skimmed through the paper (through my university's subscription) and found out that the source code & data is (or will be) available on GitHub (yay): <a href="https://github.com/jnwei/neural_reaction_fingerprint" rel="nofollow">https://github.com/jnwei/neural_reaction_fingerprint</a>
Abstract:<p>"Reaction prediction remains one of the major challenges for organic chemistry and is a prerequisite for efficient synthetic planning. It is desirable to develop algorithms that, like humans, “learn” from being exposed to examples of the application of the rules of organic chemistry. We explore the use of neural networks for predicting reaction types, using a new reaction fingerprinting method. We combine this predictor with SMARTS transformations to build a system which, given a set of reagents and reactants, predicts the likely products. We test this method on problems from a popular organic chemistry textbook."
Very interesting, great concept! The paper is on
my to-read list!<p>I am only afraid that the datasets you have used might not be of sufficiently quality for a neural network application. There are old recipes when the state of art in chemistry was at an earlier stage e.g. before the discovery of specific mechanisms, molecule classes, analytics and general concepts. Also, as mentioned in this thread, there are aspects of the synthetic chemists work and experience that might not be taken into consideration in this approach.
I'm not a chemist, and didn't read the paper, but would it be helpful if the neural network had additional inputs coming from e.g. a (simplified) Schrodinger equation solver?