Global Optimization: A Soft Computing Perspective

Pal, Ranita; Das, Prasenjit; Chattaraj, Pratim Kumar

doi:10.1021/acs.jpclett.3c00246

Cited by 8 publications

(3 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…128 Overall, we have showcased that GEBF-DL(ITA) is a promising theoretical tool for predicting the response properties of macromolecules and their aggregates. We are aware that the graph theory 129 may be further considered to enrich the associated DL method, which enables a comparison (at least qualitative) with other popular soft computing 130 techniques.…”

Section: Onicescu Information and Relative Reńyi Entropy The Onicescu...mentioning

confidence: 99%

Fragment-Based Deep Learning for Simultaneous Prediction of Polarizabilities and NMR Shieldings of Macromolecules and Their Aggregates

Zhao,

et al. 2024

J. Chem. Theory Comput.

View full text Add to dashboard Cite

Simultaneous prediction of the molecular response properties, such as polarizability and the NMR shielding constant, at a low computational cost is an unresolved issue. We propose to combine a linear-scaling generalized energy-based fragmentation (GEBF) method and deep learning (DL) with both molecular and atomic information-theoretic approach (ITA) quantities as effective descriptors. In GEBF, the total molecular polarizability can be assembled as a linear combination of the corresponding quantities calculated from a set of small embedded subsystems in GEBF. In the new GEBF-DL(ITA) protocol, one can predict subsystem polarizabilities based on the corresponding molecular wave function (thus electron density and ITA quantities) and DL model rather than calculate them from the computationally intensive coupled-perturbed Hartree−Fock or Kohn−Sham equations and finally obtain the total molecular polarizability via a linear combination equation. As a proof-of-concept application, we predict the molecular polarizabilities of large proteins and protein aggregates. GEBF-DL(ITA) is shown to be as accurate enough as GEBF, with mean absolute percentage error <1%. For the largest protein aggregate (>4000 atoms), GEBF-DL(ITA) gains a speedup ratio of 3 compared with GEBF. It is anticipated that when more advanced electronic structure methods are used, this advantage will be more appealing. Moreover, one can also predict the NMR chemical shieldings of proteins with reasonably good accuracy. Overall, the costefficient GEBF-DL(ITA) protocol should be a robust theoretical tool for simultaneously predicting polarizabilities and NMR shieldings of large systems.

show abstract

Section: Onicescu Information and Relative Reńyi Entropy The Onicescu...mentioning

confidence: 99%

Fragment-Based Deep Learning for Simultaneous Prediction of Polarizabilities and NMR Shieldings of Macromolecules and Their Aggregates

Zhao,

et al. 2024

J. Chem. Theory Comput.

View full text Add to dashboard Cite

show abstract

“…Notable examples include genetic algorithm (GA), − differential evolution (DE), , ant colony optimization (ACO), , artificial bee colony optimization (ABCO), − bees algorithm (BA), , firefly algorithm (FA), − particle swarm optimization (PSO), − and more. Additionally, other methods such as the random sampling method, − basin hopping, − and meta dynamics − had been developed and extensively applied in optimizing diverse chemical systems and properties …”

Section: Introductionmentioning

confidence: 99%

Bonobo Optimizer: A New Tool Toward the Global Optimization of Small Atomic Clusters

Chakraborty,

Pal,

Pratihar

et al. 2024

J. Phys. Chem. A

Self Cite

View full text Add to dashboard Cite

In the realm of structural and bonding investigations within chemical systems, elucidating global minimum energy configurations stands as a paramount goal. As the systems increase in size and complexity, this pursuit becomes progressively challenging. Herein, we introduce Bonobo optimizer (BO), a metaheuristic algorithm inspired by the social and reproductive behaviors of bonobos, to the domain of chemical problem solving. Focusing on small carbon clusters, this study systematically evaluates BO's performance, showcasing its robustness and efficiency. Parametric studies highlight the algorithm's adaptability, consistently converging to global minimum structures. Rigorous statistical validation supports the results, and a comparative analysis against established global optimization algorithms underlines BO's superior efficiency. This exploration extends the applicability of BO to the optimization of atomic clusters, providing a promising avenue for future advancements in computational chemistry.

show abstract

“…Optimizing complex systems in multiple dimensions presents a challenging task that requires new algorithms based on metaheuristics and emerging systemic and computational tools. Classical mathematical and computational tools are no longer sufficient to find quasioptimal solutions in a reasonable time [8,9].…”

mentioning

confidence: 99%

Engineering and Sustainable Challenges: Latest Advances in Computing and Systemic Tools

Seck-Tuoh-Mora,

Lizárraga-Mendiola,

Medina-Marín

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

Global Optimization: A Soft Computing Perspective

Cited by 8 publications

References 57 publications

Fragment-Based Deep Learning for Simultaneous Prediction of Polarizabilities and NMR Shieldings of Macromolecules and Their Aggregates

Fragment-Based Deep Learning for Simultaneous Prediction of Polarizabilities and NMR Shieldings of Macromolecules and Their Aggregates

Bonobo Optimizer: A New Tool Toward the Global Optimization of Small Atomic Clusters

Engineering and Sustainable Challenges: Latest Advances in Computing and Systemic Tools

Contact Info

Product

Resources

About