This study developed and implemented a semi-automatic material exploration scheme to modelize the solvent-solubility of tetraphenylporphyrin derivatives. In particular, the scheme involved the following steps: definition of a practical chemical search space, prioritization of molecules in the space using an extended algorithm for submodular function maximization without requiring biased variable selection or pre-existing data, synthesis & automatic measurement, and machine-learning model estimation. The optimal evaluation order selected using the algorithm covered several similar molecules (32% of all targeted molecules, whereas that obtained by random sampling and uncertainty sampling was ~7% and ~4%, respectively) with a small number of evaluations (10 molecules: 0.13% of all targeted molecules). The derived binary classification models predicted ‘good solvents’ with an accuracy > 0.8.
Overall, we confirmed the effectivity of the proposed semi-automatic scheme in early-stage material search projects for accelerating a wider range of material research.
For details:
Semi-automatic scheme for early-stage material search: developing solvent-solubility prediction of tetraphenylporphyrin derivatives securing chemical-space coverage
Raku Shirasawa 1, Ichiro Takemura 2, Shinnosuke Hattori 1, and Yuuya Nagata 3
- Advanced Research Laboratory, R&D Center, Sony Group Corporation, Atsugi Tec. 4-14-1
Asahi-cho, Atsugi-shi, Kanagawa, 243-0014, Japan - Tokyo Laboratory 26, R&D Center, Sony Group Corporation, Atsugi Tec. 4-14-1 Asahi-cho,
Atsugi-shi, Kanagawa, 243-0014, Japan - Institute for Chemical Reaction Design and Discovery, Hokkaido University, Kita 21 Nishi 10,
Kita-ku, Sapporo, Hokkaido, 001-0021, Japan
For more information about Chemspeed solutions:
SWING SP
FLEX ISYNTH for Library Synthesis Small Scale
FLEX ISYNTH Library Synthesis
ISYNTH REACTSCREEN
