Hostname: page-component-7b7567c8c-kwt9d Total loading time: 0 Render date: 2026-11-12T17:06:23.341Z Has data issue: false hasContentIssue false
  • English
  • Français

The Rational Discovery FrameworkTM: A Novel Tool for Computationally Guided High-Throughput Discovery

Published online by Cambridge University Press:  17 March 2011

Gregory A. Landrum and
Hugh Genin
Gregory A. Landrum
Affiliation:
Rational Discovery LLC 555 Bryant St. #467 Palo Alto, CA 94301, USA
Hugh Genin
Affiliation:
Rational Discovery LLC 555 Bryant St. #467 Palo Alto, CA 94301, USA
Get access

Abstract

The Rational Discovery Framework(TM) is a novel approach for providing computational guidance in the high-throughput discovery process. The Framework uses a proprietary machine-learning algorithm to construct predictive models from existing experimental data. These predictive models are used to computationally screen the contents of large virtual libraries. A variety of experimental design techniques can be brought to bear on the results of a virtual library screen in order to suggest an optimal set of synthesis candidates for the next round of experimentation. We have demonstrated the power and generality of the Rational Discovery Framework in a series of proofs of concept. Here we present an overview of the Framework as well as the results of studies aimed at developing predictive models for materials properties: ferromagnetism in ordered and disordered transition-metal alloys; and prediction of Tc values for superconductors.

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Article purchase

Temporarily unavailable

References

1 Landrum, G. A. and Dronskowski, R., Angew. Chem. Int. Ed. Engl. 38, 1389 (1999); R. E. Cohen, Nature 358, 136 (1992).Google Scholar
2 Hansen, E. W. and Neurock, M., Chem. Engr. Sci. 54, 3411 (1999); M. Neurock, in Dynamics of Surfaces and Reactions in Heterogeneous Catalysis, edited by G. F. Froment and K. C. Waugh (Elsevier, New York, 1997), pp. 3; M. Neurock and E. W. Hansen, Comp. chem. Eng. 22, S1045 (1998).Google Scholar
3 Mitchell, T., Machine Learning. (McGraw-Hill, New York, 1997); V. Cherkassky and F. Mulier, Learning from Data: Concepts, Theory, and Methods. (Wiley, New York, 1998).Google Scholar
4 Dietterich, T. G., AI Magazine 18, 97 (1997).Google Scholar
5 Breiman, L., Machine Learning 24, 123 (1996).Google Scholar
6 Bauer, E. and Kohavi, R., Machine Learning 36, 105 (1999); R. E. Schapire, Computational Learning Theory: Fourth European Conference, EuroCOLT99, 1 (1999).Google Scholar
7 Villars, P. and Calvert, L. D., Pearson's Handbook of Crystallographic Data for Intermetallic Phases, 2nd ed. (ASM International, Ohio, 1991).Google Scholar
8 Adachi, K., Bonnenberg, D., Franse, J. J. M. et al., Landolt Börnstein Group III/19: Magnetic Properties of Metals. (Springer, Berlin, 1986).Google Scholar
9 Kotochigova, S., Levine, Z., Shirley, E. et al., Atomic Reference Data for Electronic Structure Calculations (National Institute of Standards and Technology, 1997).Google Scholar
10 Lide, D.R., (New York, 2000).Google Scholar
11 Burdett, J. K., Chemical Bonding in Solids. (Oxford University Press, Oxford, 1995); A.P. Sutton, Electronic Structure of Materials. (Oxford University Press, Oxford, 1993); A. Cox, The Electronic Structure and Chemistry of Solids. (Oxford University Press, Oxford, 1987).Google Scholar
12K.M. Rabe, J.C. Phillips, Villars, P. et al., Phys. Rev. B 45, 7650 (1992).Google Scholar
13 Villars, P. and Daams, J. L.C., J. Alloys and Compounds 197, 177 (1993); J. K. Burdett, J. Alloys and Compounds 197, 281 (1993).Google Scholar
14 Rabe, K. M., MRS Bulletin, 31 (1993).Google Scholar