Investigating Active Learning and Meta-Learning for Iterative Peptide Design

Barrett, Rainier; White, Andrew D.

doi:10.1021/acs.jcim.0c00946

Cited by 22 publications

(17 citation statements)

References 74 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Active learning is a common candidate selection algorithm in chemistry ,,− and in the computer science ML literature ,, in which the goal is to select the unlabeled points that, if labeled and included in the training set, would lead to the largest reduction of model error. This approach often relies on an uncertainty metric that can identify the unseen points on which the model performance is the poorest, which we saw was true of the PADRE σ̂ (eq ) in the previous section.…”

Section: Computational Experiments and Resultsmentioning

confidence: 99%

Pairwise Difference Regression: A Machine Learning Meta-algorithm for Improved Prediction and Uncertainty Quantification in Chemical Search

Tynes

Gao

Burrill

et al. 2021

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Machine learning (ML) plays a growing role in the design and discovery of chemicals, aiming to reduce the need to perform expensive experiments and simulations. ML for such applications is promising but difficult, as models must generalize to vast chemical spaces from small training sets and must have reliable uncertainty quantification metrics to identify and prioritize unexplored regions. Ab initio computational chemistry and chemical intuition alike often take advantage of differences between chemical conditions, rather than their absolute structure or state, to generate more reliable results. We have developed an analogous comparison-based approach for ML regression, called pairwise difference regression (PADRE), which is applicable to arbitrary underlying learning models and operates on pairs of input data points. During training, the model learns to predict differences between all possible pairs of input points. During prediction, the test points are paired with all training set points, giving rise to a set of predictions that can be treated as a distribution of which the mean is treated as a final prediction and the dispersion is treated as an uncertainty measure. Pairwise difference regression was shown to reliably improve the performance of the random forest algorithm across five chemical ML tasks. Additionally, the pair-derived dispersion is both well correlated with model error and performs well in active learning. We also show that this method is competitive with state-of-the-art neural network techniques. Thus, pairwise difference regression is a promising tool for candidate selection algorithms used in chemical discovery.

show abstract

Section: Computational Experiments and Resultsmentioning

confidence: 99%

Pairwise Difference Regression: A Machine Learning Meta-algorithm for Improved Prediction and Uncertainty Quantification in Chemical Search

Tynes

Gao

Burrill

et al. 2021

J. Chem. Inf. Model.

View full text Add to dashboard Cite

show abstract

“…Among ML techniques, Bayesian optimization is one of the most common active learning method. It is able to steer the experiments or simulations toward “next-best” candidates based on historical measurements ( Chen et al, 2008 ; Ling et al, 2017 ; Gómez-Bombarelli et al, 2018 ; Barrett and White, 2021 ). The first step is to define a fitness function that evaluates a particular property.…”

Section: Application Of ML For Understanding and Design Of Polymer Chainsmentioning

confidence: 99%

Integration of Machine Learning and Coarse-Grained Molecular Simulations for Polymer Materials: Physical Understandings and Molecular Design

2022

View full text Add to dashboard Cite

In recent years, the synthesis of monomer sequence-defined polymers has expanded into broad-spectrum applications in biomedical, chemical, and materials science fields. Pursuing the characterization and inverse design of these polymer systems requires our fundamental understanding not only at the individual monomer level, but also considering the chain scales, such as polymer configuration, self-assembly, and phase separation. However, our accessibility to this field is still rudimentary due to the limitations of traditional design approaches, the complexity of chemical space along with the burdened cost and time issues that prevent us from unveiling the underlying monomer sequence-structure-property relationships. Fortunately, thanks to the recent advancements in molecular dynamics simulations and machine learning (ML) algorithms, the bottlenecks in the tasks of establishing the structure-function correlation of the polymer chains can be overcome. In this review, we will discuss the applications of the integration between ML techniques and coarse-grained molecular dynamics (CGMD) simulations to solve the current issues in polymer science at the chain level. In particular, we focus on the case studies in three important topics—polymeric configuration characterization, feed-forward property prediction, and inverse design—in which CGMD simulations are leveraged to generate training datasets to develop ML-based surrogate models for specific polymer systems and designs. By doing so, this computational hybridization allows us to well establish the monomer sequence-functional behavior relationship of the polymers as well as guide us toward the best polymer chain candidates for the inverse design in undiscovered chemical space with reasonable computational cost and time. Even though there are still limitations and challenges ahead in this field, we finally conclude that this CGMD/ML integration is very promising, not only in the attempt of bridging the monomeric and macroscopic characterizations of polymer materials, but also enabling further tailored designs for sequence-specific polymers with superior properties in many practical applications.

show abstract

“…The essence of this approach is to train onthe-y sequence-property relationships over all computational screening data collected to date and use these models to guide subsequent rounds of the computational screen within a virtuous feedback loop. [23][24][25][26][27] For example, Li et al used machine learning algorithms such as random forests, gradient boosting, and logistic regression to predict the assembly and formation of hydrogels from possible peptidic precursors. 28 Nagasawa et al employed articial neural networks and random forests for the discovery of conjugated polymers for organic photovoltaic applications.…”

Section: Introductionmentioning

confidence: 99%

Hybrid computational–experimental data-driven design of self-assembling π-conjugated peptides

et al. 2022

View full text Add to dashboard Cite

show abstract

Investigating Active Learning and Meta-Learning for Iterative Peptide Design

Cited by 22 publications

References 74 publications

Pairwise Difference Regression: A Machine Learning Meta-algorithm for Improved Prediction and Uncertainty Quantification in Chemical Search

Pairwise Difference Regression: A Machine Learning Meta-algorithm for Improved Prediction and Uncertainty Quantification in Chemical Search

Integration of Machine Learning and Coarse-Grained Molecular Simulations for Polymer Materials: Physical Understandings and Molecular Design

Hybrid computational–experimental data-driven design of self-assembling π-conjugated peptides

Contact Info

Product

Resources

About