DNA computing inspired deep networks design

Mixtures Recomposition by Neural Nets: A Multidisciplinary Overview

Artificial Neural Networks (ANNs) are transforming how we understand chemical mixtures, providing an expressive view of the chemical space and multiscale processes. Their hybridization with physical knowledge can bridge the gap between predictivity and understanding of the underlying processes. This overview explores recent progress in ANNs, particularly their potential in the 'recomposition' of chemical mixtures. Graph-based representations reveal patterns among mixture components, and deep learning models excel in capturing complexity and symmetries when compared to traditional Quantitative Structure-Property Relationship models. Key components, such as Hamiltonian networks and convolution operations, play a central role in representing multiscale mixtures. The integration of ANNs with Chemical Reaction Networks and Physics-Informed Neural Networks for inverse chemical kinetic problems is also examined. The combination of sensors with ANNs shows promise in optical and biomimetic applications. A common ground is identified in the context of statistical physics, where ANN-based methods iteratively adapt their models by blending their initial states with training data. The concept of mixture recomposition unveils a reciprocal inspiration between ANNs and reactive mixtures, highlighting learning behaviors influenced by the training environment.

Three-input logic gate based on DNA strand displacement reaction

In this paper, three kinds of three-input logic gates are designed based on DNA strand displacement reaction, which are three-input OR logic gate, three-input AND logic gate, and three-input MAJORITY logic gate. The logic gates designed in this paper takes different DNA strands as input and fluorescence signals as output. The biochemical experimental results verify my designs. The results show that DNA strand displacement technology has important application value in DNA computing, especially in the construction of DNA molecular logic gates.

A Parallel DNA Algorithm for Solving the Quota Traveling Salesman Problem Based on Biocomputing Model

The quota traveling salesman problem (QTSP) is a variant of the traveling salesman problem (TSP), which is a classical optimization problem. In the QTSP, the salesman visits some of the n cities to meet a given sales quota Q while having minimized travel costs. In this paper, we develop a DNA algorithm based on Adleman-Lipton model to solve the quota traveling salesman problem. Its time complexity is O(n²+Q), which is a significant improvement over previous algorithms with exponential complexity. A coding scheme of element information is pointed out, and a reasonable biological algorithm is raised by using limited conditions, whose feasibility is verified by simulation experiments. The innovation of this study is to propose a polynomial time complexity algorithm to solve the QTSP. This advantage will become more obvious as the problem scale increases compared with the algorithm of exponential computational complexity. The proposed DNA algorithm also has the significant advantages of having a large storage capacity and consuming less energy during the operation. With the maturity of DNA manipulation technology, DNA computing, as one of the parallel biological computing methods, has the potential to solve more complex NP-hard problems.

Detection of intra-family coronavirus genome sequences through graphical representation and artificial neural network

In this study, chaos game representation (CGR) is introduced for investigating the pattern of genome sequences. It is an image representation of the genome for the overall visualization of the sequence. The CGR representation is a mapping technique that assigns each sequence base into the respective position in the two-dimension plane to portray the DNA sequence. Importantly, CGR provides one to one mapping to nucleotides as well as sequence. A coordinate of the CGR plane can tell the corresponding base and its location in the original genome. Therefore, the whole nucleotide sequence (until the current nucleotide) can be restored from the one point of the CGR. In this study, CGR coupled with artificial neural network (ANN) is introduced as a new way to represent the genome and to classify intra-coronavirus sequences. A hierarchy clustering study is done to validate the approach and found to be more than 90% accurate while comparing the result with the phylogenetic tree of the corresponding genomes. Interestingly, the method makes the genome sequence significantly shorter (more than 99% compressed) saving the data space while preserving the genome features.

NoAS-DS: Neural optimal architecture search for detection of diverse DNA signals

Neural network architectures are high-performing variable models that can solve many learning tasks. Designing architectures manually require substantial time and also prior knowledge and expertise to develop a high-accuracy model. Most of the architecture search methods are developed over the task of image classification resulting in the building of complex architectures intended for large data inputs such as images. Motivated by the applications of DNA computing in Neural Architecture Search (NAS), we propose NoAS-DS which is specifically built for the architecture search of sequence-based classification tasks. Furthermore, NoAS-DS is applied to the task of predicting binding sites. Unlike other methods that implement only Convolution layers, NoAS-DS, specifically combines Convolution and LSTM layers that helps in the process of automatic architecture building. This hybrid approach helped in achieving high accuracy results on TFBS and RBP datasets which outperformed other models in TF-DNA binding prediction tasks. The best architectures generated by the proposed model can be applied to other DNA datasets of similar nature using transfer learning technique that demonstrates its generalization capability. This greatly reduces the effort required to build new architectures for other prediction tasks.

Solving the Family Traveling Salesperson Problem in the Adleman-Lipton model based on DNA computing

The Family Traveling Salesperson Problem (FTSP) is a variant of the Traveling Salesperson Problem (TSP), in which all vertices are divided into several different families, and the goal of the problem is to find a loop that concatenates a specified number of vertices with minimal loop overhead. As a Non-deterministic Polynomial Complete (NP-complete) problem, it is difficult to deal with it by the traditional computing. On the contrary, as a computer with strong parallel ability, the DNA computer has incomparable advantages over digital computers when dealing with NP problems. Based on this, a DNA algorithm is proposed to deal with FTSP based on the Adleman-Lipton model. In the algorithm, the solution of the problem can be obtained by executing several basic biological manipulations on DNA molecules with O(N2) computing complexity (N is the number of vertices in the problem without the origin). Through the simulation experiments on some benchmark instances, the results show that the parallel DNA algorithm has better performance than traditional computing. The effectiveness of the algorithm is verified by deducing the algorithm process in detail. Furthermore, the algorithm further proves that DNA computing, as one of the parallel computing methods, has the potential to solve more complex big data problems.

Programmable DNA-Based Boolean Logic Microfluidic Processing Unit

As molecular computing materials, information-encoded deoxyribonucleic acid (DNA) strands provide a logical computing process by cascaded and parallel chain reactions. However, the reactions in DNA-based combinational logic computing are mostly achieved through a manual process by adding desired DNA molecules in a single microtube or a substrate. For DNA-based Boolean logic, using microfluidic chips can afford automated operation, programmable control, and seamless combinational logic operation, similar to electronic microprocessors. In this paper, we present a programmable DNA-based microfluidic processing unit (MPU) chip that can be controlled via a personal computer for performing DNA calculations. To fabricate this DNA-based MPU, polydimethylsiloxane was cast using double-sided molding techniques for alignment between the microfluidics and valve switch. For a uniform surface, molds fabricated using a three-dimensional printer were spin-coated by a polymer. For programming control, the valve switch arms were operated by servo motors. In the MPU controlled via a personal computer or smartphone application, the molecules with two input DNAs and a logic template DNA were reacted for the basic AND and OR operations. Furthermore, the DNA molecules reacted in a cascading manner for combinational AND and OR operations. Finally, we demonstrated a 2-to-1 multiplexer and the XOR operation with a three-step cascade reaction using the simple DNA-based MPU, which can perform Boolean logic operations (AND, OR, and NOT). Through logic combination, this DNA-based Boolean logic MPU, which can be operated using programming language, is expected to facilitate the development of complex functional circuits such as arithmetic logical units and neuromorphic circuits.