Illuminating elite patches of chemical space

Verhellen, Jonas; Abeele, Jeriek Van den

doi:10.1039/d0sc03544k

Cited by 19 publications

(20 citation statements)

References 45 publications

(41 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Enforcing diversity 37 in the population of molecules a genetic algorithm uses can alleviate these issues. Quality-diversity algorithms 38 , such as the graph-based elite patch illumination algorithm 39 (GB-EPI), obtain this diversity by splitting the population into niches based on their physicochemical properties. In each generation, the best performing molecule in each of the individual niches is retained, rather than selecting the highest-scoring solutions regardless of their diversity.…”

Section: Quality-diversity Algorithmsmentioning

confidence: 99%

Graph-Based Molecular Pareto Optimisation

Verhellen

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Computer-assisted design of small molecules has experienced a resurgence in academic and indus- trial interest due to the widespread use of data-driven techniques such as deep generative models. While the ability to generate molecules that fulfill required chemical properties is encouraging, the use of deep learning models requires significant, if not prohibitive, amounts of data and computa- tional power. At the same time, open-sourcing of more traditional techniques such as graph-based genetic algorithms for molecular optimisation [Jensen, Chem. Sci., 2019, 12, 3567-3572] has shown that simple and training-free algorithms can be efficient and robust alternatives. Further research alleviated the common genetic algorithm issue of evolutionary stagnation by enforcing molecular diversity during optimisation [Van den Abeele, Chem. Sci., 2020, 42, 11485-11491]. The crucial lesson distilled from the simultaneous development of deep generative models and advanced genetic algorithms has been the importance of chemical space exploration [Aspuru-Guzik, Chem. Sci., 2021, 12, 7079-7090]. For single-objective optimisation problems, chemical space exploration had to be discovered as a usable resource but in multi-objective optimisation problems, an exploration of trade- offs between conflicting objectives is inherently present. In this paper we provide state-of-the-art and open-source implementations of two generations of graph-based non-dominated sorting genetic algorithms (NSGA-II, NSGA-III) for molecular multi-objective optimisation. In addition, we provide the results of a series of benchmarks for the inverse design of small molecule drugs for both the NSGA-II and NSGA-III algorithms.

show abstract

Section: Quality-diversity Algorithmsmentioning

confidence: 99%

Graph-Based Molecular Pareto Optimisation

Verhellen

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Expert rules-based systems can yield median molecules [38,51,52], but their use can be application-dependent. For example, a potential algorithm could disassemble the reference structures into fragments by breaking rotatable bonds and then recombine the fragments in a building block approach.…”

Section: E Median Molecules For Photovoltaicsmentioning

confidence: 99%

Beyond Generative Models: Superfast Traversal, Optimization, Novelty, Exploration and Discovery (STONED) Algorithm for Molecules using SELFIES

Nigam

Pollice²,

Krenn³

et al. 2021

Preprint

View full text Add to dashboard Cite

Inverse design allows the design of molecules with desirable properties using property optimization. Deep generative models have recently been applied to tackle inverse design, as they possess the ability to optimize molecular properties directly through structure modification using gradients. While the ability to carry out direct property optimizations is promising, the use of generative deep learning models to solve practical problems requires large amounts of data and is very time-consuming. In this work, we propose STONED – a simple and efficient algorithm to perform interpolation and exploration in the chemical space, comparable to deep generative models. STONED bypasses the need for large amounts of data and training times by using string modifications in the SELFIES molecular representation. We achieve comparable performance on typical benchmarks without any training. We demonstrate applications in high-throughput virtual screening for the design of drugs, photovoltaics, and the construction of chemical paths, allowing for both property and structure-based interpolation in the chemical space. We anticipate our results to be a stepping stone for developing more sophisticated inverse design models and benchmarking tools, ultimately helping generative models achieve wide adoption.

show abstract

“…GAs have been proven as efficient methods for finding molecules with a wide variety of tailored properties in the vastness of chemical space by exploring a small subset. 23,[30][31][32][33][34] This is in large part due to the many paths a GA may take through chemical space to a target molecule, and therefore the high probability of quickly finding a species on one of these paths by random chance. 35 GA searches through chemical space have also been found to be faster in some cases than generative machine learning models.…”

Section: Genetic Algorithmmentioning

confidence: 99%

Pareto Optimization of Oligomer Polarizability and Dipole Moment using a Genetic Algorithm

Hiener¹,

Hutchison

2021

Preprint

View full text Add to dashboard Cite

High performance electronic components are highly sought after in order to produce increasingly smaller and cheaper electronic devices. Drawing inspiration from inorganic dielectric materials, in which both polarizability and polarization contribute, organic materials can also maximize both. For a large set of small molecules drawn from PubChem, a Pareto-like front appears between polarizability and dipole moment indicating the presence of an apparent trade-off between these two properties. We tested this balance in π-conjugated materials by searching for novel conjugated hexamers with simultaneously large polarizabilities and dipole moments with potential use for dielectric materials. Using a genetic algorithm (GA) screening technique in conjunction with an approximate density functional tight binding method (GFN2-xTB) for property calculations, we were able to efficiently search chemical space for optimal hexamers. Given the scope of chemical space, using the GA technique saves considerable time and resources by speeding up molecular searches compared to a systematic search. We also explored the underlying structure-function relationships, including sequence and monomer properties, that characterize large polarizability and dipole moment regimes.

show abstract

Illuminating elite patches of chemical space

Abstract: In the past few years, there has been considerable activity in both academic and industrial research to develop innovative machine learning approaches to locate novel, high-performing molecules in chemical space....

Cited by 19 publications

References 45 publications

Graph-Based Molecular Pareto Optimisation

Graph-Based Molecular Pareto Optimisation

Beyond Generative Models: Superfast Traversal, Optimization, Novelty, Exploration and Discovery (STONED) Algorithm for Molecules using SELFIES

Pareto Optimization of Oligomer Polarizability and Dipole Moment using a Genetic Algorithm

Contact Info

Product

Resources

About