Automating Genetic Algorithm Mutations for Molecules Using a Masked Language Model
Andrew E. Blanchard, Mayanka Chandrashekar, Shang Bing Gao et al. · IEEE Transactions on Evolutionary Computation · 2022
Inspired by the evolution of biological systems, genetic algorithms have been applied to generate solutions for optimization problems in a variety of scientific and engineering disciplines. For a given problem, a suitable genome representation must be defined along with a mutation operator to generate subsequent generations. Unlike natural systems, which display a variety of complex rearrangements (e.g., mobile genetic elements), mutation for genetic algorithms commonly utilizes only random pointwise changes. Furthermore, generalizing beyond pointwise mutations poses a key difficulty as useful genome rearrangements depend on the representation and problem domain. To move beyond the limitations of manually defined pointwise changes, here we propose the use of techniques from masked language models to automatically generate mutations. As a first step, common subsequences within a given population are used to generate a vocabulary. The vocabulary is then used to tokenize each genome. A masked language model is trained on the tokenized data in order to generate possible rearrangements (i.e., mutations). In order to illustrate the proposed strategy, we use string representations of molecules and use a genetic algorithm to optimize for drug-likeness and synthesizability. Our results show that moving beyond random pointwise mutations accelerates genetic algorithm optimization.
Cited by 37 works. doi:10.1109/tevc.2022.3144045
Authors
- Andrew E. Blanchard
- Mayanka Chandrashekar
- Shang Bing Gao
- John P. Gounley
- Isaac Lyngaas
- Jens Gläser
- Debsindhu Bhowmik
References
- Adam: A Method for Stochastic Optimization
- AI-Assisted Pipeline for Dynamic Generation of Trustworthy Health Supplement Content at Scale
- HISTORIAE, History of Socio-Cultural Transformation as Linguistic Data Science. A Humanities Use Case
- Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
- SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules
- Transformers: State-of-the-Art Natural Language Processing
- Extended-Connectivity Fingerprints
- Japanese and Korean voice search
- Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing
- Quantifying the chemical beauty of drugs