Knowledge-driven Learning, Optimization, and Experimental Design Under Uncertainty for Materials Discovery

Overview

Journal Patterns (N Y)

Date 2023 Nov 30

PMID 38035192

Authors

Xiaoning Qian

Byung-Jun Yoon

Raymundo Arroyave

Xiaofeng Qian

Edward R Dougherty

Affiliations

Soon will be listed here.

Abstract

Significant acceleration of the future discovery of novel functional materials requires a fundamental shift from the current materials discovery practice, which is heavily dependent on trial-and-error campaigns and high-throughput screening, to one that builds on knowledge-driven advanced informatics techniques enabled by the latest advances in signal processing and machine learning. In this review, we discuss the major research issues that need to be addressed to expedite this transformation along with the salient challenges involved. We especially focus on Bayesian signal processing and machine learning schemes that are uncertainty aware and physics informed for knowledge-driven learning, robust optimization, and efficient objective-driven experimental design.

Citing Articles

Predicting Stress-Strain Curve with Confidence: Balance Between Data Minimization and Uncertainty Quantification by a Dual Bayesian Model.

Li T, Chen Z, Zhang Z, Wei Z, Zhong G, Li Z Polymers (Basel). 2025; 17(4).

PMID: 40006213 PMC: 11860118. DOI: 10.3390/polym17040550.

Optimizing Thermoplastic Starch Film with Heteroscedastic Gaussian Processes in Bayesian Experimental Design Framework.

White G, Siegel A, Tovar A Materials (Basel). 2024; 17(21).

PMID: 39517615 PMC: 11547296. DOI: 10.3390/ma17215345.

References

Dougherty E, Zollanvari A, Braga-Neto U . The illusion of distribution-free small-sample classification in genomics. Curr Genomics. 2012; 12(5):333-41. PMC: 3145263. DOI: 10.2174/138920211796429763. View

Xue D, Balachandran P, Hogden J, Theiler J, Xue D, Lookman T . Accelerated search for materials with targeted properties by adaptive design. Nat Commun. 2016; 7:11241. PMC: 4835535. DOI: 10.1038/ncomms11241. View

Coveney P, Dougherty E, Highfield R . Big data need big theory too. Philos Trans A Math Phys Eng Sci. 2016; 374(2080). PMC: 5052735. DOI: 10.1098/rsta.2016.0153. View

Krenn M, Pollice R, Guo S, Aldeghi M, Cervera-Lierta A, Friederich P . On scientific understanding with artificial intelligence. Nat Rev Phys. 2022; 4(12):761-769. PMC: 9552145. DOI: 10.1038/s42254-022-00518-3. View

Kohn . Density functional and density matrix method scaling linearly with the number of atoms. Phys Rev Lett. 1996; 76(17):3168-3171. DOI: 10.1103/PhysRevLett.76.3168. View

Jeffreys H . An invariant form for the prior probability in estimation problems. Proc R Soc Lond A Math Phys Sci. 2010; 186(1007):453-61. DOI: 10.1098/rspa.1946.0056. View

Mnih V, Kavukcuoglu K, Silver D, Rusu A, Veness J, Bellemare M . Human-level control through deep reinforcement learning. Nature. 2015; 518(7540):529-33. DOI: 10.1038/nature14236. View

Bengio Y, Courville A, Vincent P . Representation learning: a review and new perspectives. IEEE Trans Pattern Anal Mach Intell. 2013; 35(8):1798-828. DOI: 10.1109/TPAMI.2013.50. View

Wasserman . Bayesian Model Selection and Model Averaging. J Math Psychol. 2000; 44(1):92-107. DOI: 10.1006/jmps.1999.1278. View

10.

Shahrokh Esfahani M, Dougherty E . Incorporation of Biological Pathway Knowledge in the Construction of Priors for Optimal Bayesian Classification. IEEE/ACM Trans Comput Biol Bioinform. 2015; 11(1):202-18. DOI: 10.1109/TCBB.2013.143. View

11.

Wei P, Pan W . Bayesian Joint Modeling of Multiple Gene Networks and Diverse Genomic Data to Identify Target Genes of a Transcription Factor. Ann Appl Stat. 2012; 6(1):334-355. PMC: 3298193. DOI: 10.1214/11-AOAS502. View

12.

Boluki S, Shahrokh Esfahani M, Qian X, Dougherty E . Constructing Pathway-Based Priors within a Gaussian Mixture Model for Bayesian Regression and Classification. IEEE/ACM Trans Comput Biol Bioinform. 2018; 16(2):524-537. DOI: 10.1109/TCBB.2017.2778715. View

13.

Dougherty E, Dalton L . Scientific knowledge is possible with small-sample classification. EURASIP J Bioinform Syst Biol. 2013; 2013(1):10. PMC: 3765562. DOI: 10.1186/1687-4153-2013-10. View

14.

Qian X, Dougherty E . Bayesian Regression with Network Prior: Optimal Bayesian Filtering Perspective. IEEE Trans Signal Process. 2017; 64(23):6243-6253. PMC: 5560447. DOI: 10.1109/TSP.2016.2605072. View

15.

Dehghannasiri R, Yoon B, Dougherty E . Efficient experimental design for uncertainty reduction in gene regulatory networks. BMC Bioinformatics. 2015; 16 Suppl 13:S2. PMC: 4597030. DOI: 10.1186/1471-2105-16-S13-S2. View

16.

Ghiringhelli L, Vybiral J, Levchenko S, Draxl C, Scheffler M . Big data of materials science: critical role of the descriptor. Phys Rev Lett. 2015; 114(10):105503. DOI: 10.1103/PhysRevLett.114.105503. View

17.

Xue D, Balachandran P, Yuan R, Hu T, Qian X, Dougherty E . Accelerated search for BaTiO3-based piezoelectrics with vertical morphotropic phase boundary using Bayesian learning. Proc Natl Acad Sci U S A. 2016; 113(47):13301-13306. PMC: 5127307. DOI: 10.1073/pnas.1607412113. View

18.

Gopakumar A, Balachandran P, Xue D, Gubernatis J, Lookman T . Multi-objective Optimization for Materials Discovery via Adaptive Design. Sci Rep. 2018; 8(1):3738. PMC: 5829239. DOI: 10.1038/s41598-018-21936-3. View

19.

Dehghannasiri R, Yoon B, Dougherty E . Optimal Experimental Design for Gene Regulatory Networks in the Presence of Uncertainty. IEEE/ACM Trans Comput Biol Bioinform. 2015; 12(4):938-50. DOI: 10.1109/TCBB.2014.2377733. View

20.

Boluki S, Shahrokh Esfahani M, Qian X, Dougherty E . Incorporating biological prior knowledge for Bayesian learning via maximal knowledge-driven information priors. BMC Bioinformatics. 2018; 18(Suppl 14):552. PMC: 5751802. DOI: 10.1186/s12859-017-1893-4. View