@article{8748,
  author = {M. C. Sorkun and J. M. V. A. Koelman and S. Er},
  title = {Pushing the limits of solubility prediction via quality-oriented data selection},
  abstract = {Accurate prediction of the solubility of chemical substances in solvents remains a challenge. The sparsity of high-quality solubility data is recognized as the biggest hurdle in the development of robust data-driven methods for practical use. Nonetheless, the effects of the quality and quantity of data on aqueous solubility predictions have not yet been scrutinized. In this study, the roles of the size and the quality of data sets on the performances of the solubility prediction models are unraveled, and the concepts of actual and observed performances are introduced. In an effort to curtail the gap between actual and observed performances, a quality-oriented data selection method, which evaluates the quality of data and extracts the most accurate part of it through statistical validation, is designed. Applying this method on the largest publicly available solubility database and using a consensus machine learning approach, a top-performing solubility prediction model is achieved. Accompanying software codes are available at https://doi.org/10.24433/CO.3467849.v2
},
  year = {2021},
  journal = {iScience},
  volume = {24},
  pages = {101961},
  doi = {10.1016/j.isci.2020.101961},
  language = {eng},
}