About

  MatSolCa (MSC) is a free access and usefull Materials informatics tool as Solubility Calculater with in-phases deep neural network which is our special method of 3-step DNN.


Prediction Information

Overview of dataset
  No of total compounds   General 307 low molecular weight compounds
  No of C atoms/compound   1–9
  M.W.   32.0–252.7 (ave. 98.6)
  Solubility data   HSPs (δD, δH, δP), SP & LogP
  Analytical data   H/C-NMR assignments, density & refractive index
  Molecular data   Molecular components (7 items) & RDKIT's descriptors (14 items)
  Downlaod   dataset
  
Machine learning
  Algorithm   in-phases (3-step) deep neural network
     
 
     
  Validation method   5-division cross-validation
  Hyper parameter selection   Bayesian optimization method
  R2   δD:0.81, δH:0.61, δP:0.61, SP:0.58, LogP:0.69
  RMSE   δD:0.51, δH:3.00, δP:2.16, SP:1.85, LogP:0.59


MSC in Brief

  The solubility, such as HSPs composed three elements (δD, δH, δP), SP, and LogP, is one of important physical parameter for understanding the characteristics of a substance. These solubility parameters have been used in several situations (e.g., materials science, biorefinery, cosmetic chemistry, and drug discovery). Here we've developed a useful and agile materials informatics tool, named MatSolCa (MSC), as solubility calculator created with special DNN model. The tool can calculate solubility parameters of HSPs, SP and LogP from only analytical data, such as 1D-H/C-NMR data, density and refractive index. We have expectations for effective R & D with MSC.


Citation

  Atsushi KUROTANI, Toshifumi KAKIUCHI and Jun KIKUCHI, Solubility prediction from molecular properties and analytical data using an in-phase deep neural network (ip-DNN). ACS Omega, 2021, vol6, 22, 14278-14287

Policy

  We just use your input data for solubility calculation.
  Copyright license agreement on this webpage must be in accordance with CC BY-NC.

Contact

  Environmental metabolic analysis research team of RIKEN CSRS
  


 ©MatSolCa (MSC) since 2021, RIKEN Center for Sustainable Resource Science, 1-7-22 Suehiro-cho Tsurumi-ku Yokohama City Kanagawa 230-0045 Japan