2017

Towards "AlphaChem": Chemical Synthesis Planning with Tree Search and Deep Neural Network Policies

Segler, Marwin, Preuß, Mike, Waller, Mark P.

Understand

Retrosynthesis is a technique to plan the chemical synthesis of organic molecules, for example drugs, agro- and fine chemicals.

  • In retrosynthesis, a search tree is built by analysing molecules recursively and dissecting them into simpler molecular building blocks until one obtains a set of known building blocks.
  • The search space is intractably large, and it is difficult to determine the value of retrosynthetic positions.
  • Here, we propose to model retrosynthesis as a Markov Decision Process.

Built on

  • The Logic of Chemical Synthesis

    EJ Corey and XM Cheng · 1989

    Earlier work this paper cites.

  • Computer-aided organic synthesis

    Matthew H Todd · 2005

    Earlier work this paper cites.

  • A survey of monte carlo tree search methods

    Cameron B Browne, Edward Powley, Daniel Whitehouse, Simon M Lucas, Peter I Cowling, Philipp Rohlfshagen, Stephen Tavener, Diego Perez, Spyridon Samothrakis, and Simon Colton · 2012

    Earlier work this paper cites.

  • Generic strategies for chemical space exploration

    Jakob L Andersen, Christoph Flamm, Daniel Merkle, and Peter F Stadler · 2014

    Earlier work this paper cites.

Similar

  • Move evaluation in go using deep convolutional neural networks

    Original

    Chris J Maddison, Aja Huang, Ilya Sutskever, and David Silver · 2014

    Cited alongside, same era.

  • Fast and accurate deep network learning by exponential linear units (elus)

    Original

    Djork-Arné Clevert, Thomas Unterthiner, and Sepp Hochreiter · 2015

    Cited alongside, same era.

  • Training very deep networks

    Rupesh K Srivastava, Klaus Greff, and Jürgen Schmidhuber · 2015

    Cited alongside, same era.

  • Mastering the game of go with deep neural networks and tree search

    David Silver, Aja Huang, Chris J Maddison, Arthur Guez, Laurent Sifre, George Van Den Driessche, Julian Schrittwieser, Ioannis Antonoglou, Veda Panneershelvam, Marc Lanctot, et al · 2016

    Cited alongside, same era.

  • Neural-symbolic machine-learning for retrosynthesis and reaction prediction

    Marwin HS Segler and Mark P Waller

    Cited in the paper.

  • Modelling chemical reasoning to predict and invent reactions

    Marwin HS Segler and Mark P Waller

    Cited in the paper.

Then

  • Computer-assisted synthetic planning: The end of the beginning

    Sara Szymkuć, Ewa P Gajewska, Tomasz Klucznik, Karol Molga, Piotr Dittwald, Michał Startek, Michał Bajczyk, and Bartosz A Grzybowski · 2016

    Later among the works it cites.

  • Reaxys is a registered trade mark of RELX Intellectual Properties SA, used under license, 2017

    Reaxys · 2017

    Closest in time.

  • Generating focussed molecule libraries for drug discovery with recurrent neural networks

    Original

    Marwin HS Segler, Thierry Kogej, Christian Tyrchan, and Mark P Waller · 2017

    Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…