TY - JOUR AU - Rajan, Kohulan AU - Zielesny, Achim AU - Steinbeck, Christoph PY - 2020 DA - 2020/10/27 TI - DECIMER: towards deep learning for chemical image recognition JO - Journal of Cheminformatics SP - 65 VL - 12 IS - 1 AB - The automatic recognition of chemical structure diagrams from the literature is an indispensable component of workflows to re-discover information about chemicals and to make it available in open-access databases. Here we report preliminary findings in our development of Deep lEarning for Chemical ImagE Recognition (DECIMER), a deep learning method based on existing show-and-tell deep neural networks, which makes very few assumptions about the structure of the underlying problem. It translates a bitmap image of a molecule, as found in publications, into a SMILES. The training state reported here does not yet rival the performance of existing traditional approaches, but we present evidence that our method will reach a comparable detection power with sufficient training time. Training success of DECIMER depends on the input data representation: DeepSMILES are superior over SMILES and we have a preliminary indication that the recently reported SELFIES outperform DeepSMILES. An extrapolation of our results towards larger training data sizes suggests that we might be able to achieve near-accurate prediction with 50 to 100 million training structures. This work is entirely based on open-source software and open data and is available to the general public for any purpose. SN - 1758-2946 UR - https://doi.org/10.1186/s13321-020-00469-w DO - 10.1186/s13321-020-00469-w ID - Rajan2020 ER -