scholarly journals Using MAP-Elites to Optimize Self-Assembling Behaviors in a Swarm of Bio-micro-robots

2019 ◽  
Author(s):  
Leo Cazenille ◽  
Nicolas Bredeche ◽  
Nathanael Aubert-Kato
Keyword(s):  
Self Assembly ◽  
State Of The Art ◽  
Optimization Methods ◽  
Search Space ◽  
Reaction Networks ◽  
High Performing ◽  
Robot Swarms ◽  
Self Assembling ◽  
Previous State ◽  
Molecular Robots

AbstractWe are interested in programming a swarm of molecular robots that can perform self-assembly to form specific shapes at a specific location. Programming such robot swarms is challenging for two reasons. First, the goal is to optimize both the parameters and the structure of chemical reaction networks. Second, the search space is both high-dimensional and deceptive. In this paper, we show that MAP-Elites, an algorithm that searches for both high-performing and diverse solutions, outperforms previous state-of-the-art optimization methods.

scholarly journals Self-assembling Peptide Discovery: Overcoming Human Bias With Machine Learning

2021 ◽  
Author(s):  
Rohit Batra ◽  
Troy Loeffler ◽  
Henry Chan ◽  
Srilok Sriniva ◽  
Honggang Cui ◽  
...  
Keyword(s):  
Machine Learning ◽  
Self Assembly ◽  
Search Space ◽  
Sequence Length ◽  
Monte Carlo Tree Search ◽  
Self Assembling ◽  
Naturally Occurring ◽  
Peptide Materials ◽  
Dynamics Simulations ◽  
Better Than

Abstract Peptide materials have a wide array of functions from tissue engineering, surface coatings to catalysis and sensing. This class of biopolymer is composed of a sequence, comprised of 20 naturally occurring amino acids whose arrangement dictate the peptide functionality. While it is highly desirable to tailor the amino acid sequence, a small increase in their sequence length leads to dramatic increase in the possible candidates (e.g., from tripeptide = 20^3 or 8,000 peptides to a pentapeptide = 20^5 or 3.2 M). Traditionally, peptide design is guided by the use of structural propensity tables, hydrophobicity scales, or other desired properties and typically yields <10 peptides per study, barely scraping the surface of the search space. These approaches, driven by human expertise and intuition, are not easily scalable and are riddled with human bias. Here, we introduce a machine learning workflow that combines Monte Carlo tree search and random forest, with molecular dynamics simulations to develop a fully autonomous computational search engine (named, AI-expert) to discover peptide sequences with high potential for self-assembly (as a representative target functionality). We demonstrate the efficacy of the AI-expert to efficiently search large spaces of tripeptides and pentapeptides. Subsequent experiments on the proposed peptide sequences are performed to compare the predictability of the AI-expert with those of human experts. The AI performs on-par or better than human experts and suggests several non-intuitive sequences with high self-assembly propensity, outlining its potential to overcome human bias and accelerate peptide discovery.

scholarly journals Automated exploration of DNA-based structure self-assembly networks

2021 ◽  
Vol 8 (10) ◽  
Author(s):  
L. Cazenille ◽  
A. Baccouche ◽  
N. Aubert-Kato
Keyword(s):  
Dna Sequences ◽  
Self Assembly ◽  
Search Space ◽  
Dna Origami ◽  
Reaction Pathways ◽  
Reaction Networks ◽  
Dna Structures ◽  
Search Spaces ◽  
Dna Strands ◽  
Domain Level

Finding DNA sequences capable of folding into specific nanostructures is a hard problem, as it involves very large search spaces and complex nonlinear dynamics. Typical methods to solve it aim to reduce the search space by minimizing unwanted interactions through restrictions on the design (e.g. staples in DNA origami or voxel-based designs in DNA Bricks). Here, we present a novel methodology that aims to reduce this search space by identifying the relevant properties of a given assembly system to the emergence of various families of structures (e.g. simple structures, polymers, branched structures). For a given set of DNA strands, our approach automatically finds chemical reaction networks (CRNs) that generate sets of structures exhibiting ranges of specific user-specified properties, such as length and type of structures or their frequency of occurrence. For each set, we enumerate the possible DNA structures that can be generated through domain-level interactions, identify the most prevalent structures, find the best-performing sequence sets to the emergence of target structures, and assess CRNs' robustness to the removal of reaction pathways. Our results suggest a connection between the characteristics of DNA strands and the distribution of generated structure families.

scholarly journals Illuminating Elite Patches of Chemical Space

2020 ◽  
Author(s):  
Jonas Verhellen ◽  
Jeriek Van den Abeele
Keyword(s):  
Machine Learning ◽  
Genetic Algorithm ◽  
State Of The Art ◽  
Chemical Space ◽  
Search Space ◽  
Robot Design ◽  
Soft Robot ◽  
Learning Approaches ◽  
High Performing ◽  
The Past

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. Here we describe a new and fundamentally different type of approach that provides a holistic overview of how high-performing molecules are distributed throughout a search space. Based on an open-source, graph-based implementation [Jensen, Chem. Sci., 2019, 12, 3567-3572] of a traditional genetic algorithm for molecular optimisation, and influenced by state-of-the-art concepts from soft robot design [Mouret et al., IEEE Trans. Evolut. Comput., 2016, 22, 623-630], we provide an algorithm that (i) produces a large diversity of high-performing, yet qualitatively different molecules, (ii) illuminates the distribution of optimal solutions, and (iii) improves search efficiency compared to both machine learning and traditional genetic algorithm approaches.

scholarly journals Illuminating Elite Patches of Chemical Space

2020 ◽  
Author(s):  
Jonas Verhellen ◽  
Jeriek Van den Abeele
Keyword(s):  
Machine Learning ◽  
Genetic Algorithm ◽  
State Of The Art ◽  
Chemical Space ◽  
Search Space ◽  
Robot Design ◽  
Soft Robot ◽  
Learning Approaches ◽  
High Performing ◽  
The Past

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. Here we describe a new and fundamentally different type of approach that provides a holistic overview of how high-performing molecules are distributed throughout a search space. Based on an open-source, graph-based implementation [Jensen, Chem. Sci., 2019, 12, 3567-3572] of a traditional genetic algorithm for molecular optimisation, and influenced by state-of-the-art concepts from soft robot design [Mouret et al., IEEE Trans. Evolut. Comput., 2016, 22, 623-630], we provide an algorithm that (i) produces a large diversity of high-performing, yet qualitatively different molecules, (ii) illuminates the distribution of optimal solutions, and (iii) improves search efficiency compared to both machine learning and traditional genetic algorithm approaches.

scholarly journals Binarized Neural Architecture Search

2020 ◽  
Vol 34 (07) ◽  
pp. 10526-10533 ◽  
Author(s):  
Hanlin Chen ◽  
Li'an Zhuo ◽  
Baochang Zhang ◽  
Xiawu Zheng ◽  
Jianzhuang Liu ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
State Of The Art ◽  
Optimization Methods ◽  
Search Space ◽  
Network Architectures ◽  
Neural Architecture ◽  
Space Reduction ◽  
The Cost ◽  
A Performance

Neural architecture search (NAS) can have a significant impact in computer vision by automatically designing optimal neural network architectures for various tasks. A variant, binarized neural architecture search (BNAS), with a search space of binarized convolutions, can produce extremely compressed models. Unfortunately, this area remains largely unexplored. BNAS is more challenging than NAS due to the learning inefficiency caused by optimization requirements and the huge architecture space. To address these issues, we introduce channel sampling and operation space reduction into a differentiable NAS to significantly reduce the cost of searching. This is accomplished through a performance-based strategy used to abandon less potential operations. Two optimization methods for binarized neural networks are used to validate the effectiveness of our BNAS. Extensive experiments demonstrate that the proposed BNAS achieves a performance comparable to NAS on both CIFAR and ImageNet databases. An accuracy of 96.53% vs. 97.22% is achieved on the CIFAR-10 dataset, but with a significantly compressed model, and a 40% faster search than the state-of-the-art PC-DARTS.

scholarly journals Efficient Hyperparameter Optimization for Physics-based Character Animation

2021 ◽  
Vol 4 (1) ◽  
pp. 1-19
Author(s):  
Zeshi Yang ◽  
Zhiqi Yin
Keyword(s):  
Control Systems ◽  
Task Difficulty ◽  
State Of The Art ◽  
Optimization Methods ◽  
Search Space ◽  
Character Animation ◽  
Bayesian Optimization ◽  
Efficiency Gain ◽  
Hyperparameter Optimization ◽  
Optimization Framework

Physics-based character animation has seen significant advances in recent years with the adoption of Deep Reinforcement Learning (DRL). However, DRL-based learning methods are usually computationally expensive and their performance crucially depends on the choice of hyperparameters. Tuning hyperparameters for these methods often requires repetitive training of control policies, which is even more computationally prohibitive. In this work, we propose a novel Curriculum-based Multi-Fidelity Bayesian Optimization framework (CMFBO) for efficient hyperparameter optimization of DRL-based character control systems. Using curriculum-based task difficulty as fidelity criterion, our method improves searching efficiency by gradually pruning search space through evaluation on easier motor skill tasks. We evaluate our method on two physics-based character control tasks: character morphology optimization and hyperparameter tuning of DeepMimic. Our algorithm significantly outperforms state-of-the-art hyperparameter optimization methods applicable for physics-based character animation. In particular, we show that hyperparameters optimized through our algorithm result in at least 5x efficiency gain comparing to author-released settings in DeepMimic.

Factors Affecting Molecular Self-Assembly and Its Mechanism

2012 ◽  
Vol 9 (1) ◽  
pp. 43 ◽  
Author(s):  
Hueyling Tan
Keyword(s):  
Self Assembly ◽  
Building Blocks ◽  
Molecular Engineering ◽  
Molecular Structures ◽  
Polymer Science ◽  
New Approach ◽  
Factors Affecting ◽  
Dna Structures ◽  
Self Assembling ◽  
Wide Range

Molecular self-assembly is ubiquitous in nature and has emerged as a new approach to produce new materials in chemistry, engineering, nanotechnology, polymer science and materials. Molecular self-assembly has been attracting increasing interest from the scientific community in recent years due to its importance in understanding biology and a variety of diseases at the molecular level. In the last few years, considerable advances have been made in the use ofpeptides as building blocks to produce biological materials for wide range of applications, including fabricating novel supra-molecular structures and scaffolding for tissue repair. The study ofbiological self-assembly systems represents a significant advancement in molecular engineering and is a rapidly growing scientific and engineering field that crosses the boundaries ofexisting disciplines. Many self-assembling systems are rangefrom bi- andtri-block copolymers to DNA structures as well as simple and complex proteins andpeptides. The ultimate goal is to harness molecular self-assembly such that design andcontrol ofbottom-up processes is achieved thereby enabling exploitation of structures developed at the meso- and macro-scopic scale for the purposes oflife and non-life science applications. Such aspirations can be achievedthrough understanding thefundamental principles behind the selforganisation and self-synthesis processes exhibited by biological systems.

Multi-Resolution Autoregressive Graph-to-Graph Translation for Molecules

2019 ◽  
Author(s):  
Wengong Jin ◽  
Regina Barzilay ◽  
Tommi S Jaakkola
Keyword(s):  
Drug Discovery ◽  
State Of The Art ◽  
Molecular Graph ◽  
Biochemical Properties ◽  
Large Margin ◽  
Previous State ◽  
Translation Methods ◽  
Atom Level ◽  
Precursor Molecules ◽  
Prior State

The problem of accelerating drug discovery relies heavily on automatic tools to optimize precursor molecules to afford them with better biochemical properties. Our work in this paper substantially extends prior state-of-the-art on graph-to-graph translation methods for molecular optimization. In particular, we realize coherent multi-resolution representations by interweaving trees over substructures with the atom-level encoding of the original molecular graph. Moreover, our graph decoder is fully autoregressive, and interleaves each step of adding a new substructure with the process of resolving its connectivity to the emerging molecule. We evaluate our model on multiple molecular optimization tasks and show that our model outperforms previous state-of-the-art baselines by a large margin.

Directive Effect of Chain Length in Modulating Peptide Nano-assemblies

2020 ◽  
Vol 27 (9) ◽  
pp. 923-929
Author(s):  
Gaurav Pandey ◽  
Prem Prakash Das ◽  
Vibin Ramakrishnan
Keyword(s):  
Electron Microscopy ◽  
Amino Acids ◽  
Light Scattering ◽  
Chain Length ◽  
Self Assembly ◽  
The Self ◽  
Ionic Charge ◽  
Self Assembling ◽  
Biophysical Techniques

Background: RADA-4 (Ac-RADARADARADARADA-NH2) is the most extensively studied and marketed self-assembling peptide, forming hydrogel, used to create defined threedimensional microenvironments for cell culture applications. Objectives: In this work, we use various biophysical techniques to investigate the length dependency of RADA aggregation and assembly. Methods: We synthesized a series of RADA-N peptides, N ranging from 1 to 4, resulting in four peptides having 4, 8, 12, and 16 amino acids in their sequence. Through a combination of various biophysical methods including thioflavin T fluorescence assay, static right angle light scattering assay, Dynamic Light Scattering (DLS), electron microscopy, CD, and IR spectroscopy, we have examined the role of chain-length on the self-assembly of RADA peptide. Results: Our observations show that the aggregation of ionic, charge-complementary RADA motifcontaining peptides is length-dependent, with N less than 3 are not forming spontaneous selfassemblies. Conclusion: The six biophysical experiments discussed in this paper validate the significance of chain-length on the epitaxial growth of RADA peptide self-assembly.

Self-assembling behaviour of a modified aromatic amino acid in competitive medium

Soft Matter ◽  
2020 ◽  
Vol 16 (28) ◽  
pp. 6599-6607 ◽  
Author(s):  
Pijush Singh ◽  
Souvik Misra ◽  
Nayim Sepay ◽  
Sanjoy Mondal ◽  
Debes Ray ◽  
...  
Keyword(s):  
Amino Acid ◽  
Self Assembly ◽  
Aromatic Amino Acid ◽  
Photophysical Properties ◽  
Solvent Mixture ◽  
The Self ◽  
Solvent Ratio ◽  
Self Assembling

The self-assembly and photophysical properties of 4-nitrophenylalanine (4NP) are changed with the alteration of solvent and final self-assembly state of 4NP in competitive solvent mixture and are dictated by the solvent ratio.

Sign in / Sign up

Export Citation Format

Share Document