SaPt-CNN-LSTM-AR-EA: a hybrid ensemble learning framework for time series-based multivariate DNA sequence prediction.

Biological sequence classification is a key task in Bioinformatics. For research labs today, the classification of unknown biological sequences is essential for facilitating the identification, grouping and study of organisms and their evolution. This work focuses on the task of taxonomic classification of bacterial species into their hierarchical taxonomic ranks. Barcode sequences of the 16S rRNA dataset—which are known for their relatively short sequence lengths and highly discriminative characteristics—are used for classification. Several sequence representations and CNN architecture combinations are considered, each tested with the aim of learning and finding the best approaches for efficient and effective taxonomic classification. Sequence representations include k-mer based representations, integer-encoding, one-hot encoding and the usage of embedding layers in the CNN. Experimental results and comparisons have shown that representations which hold some sequential information about a sequence perform much better than a raw representation. A maximum accuracy of 91.7% was achieved with a deeper CNN when the employed sequence representation was more representative of the sequence. However with less representative representations a wide and shallow network was able to efficiently extract information and provide a reasonable accuracy of 90.6%.

With the democratization of molecular biology, more and more ecologists are required to analyse complex datasets including biological sequences. I present the R package bioseq, a comprehensive toolset to handle biological sequences in R. The package implements three classes to work with DNA, RNA and amino acid sequences. Biological sequences are stored as simple vectors of character strings with restricted alphabets. This storage mode makes it easy to work with dataframes. The package includes a collection of functions to perform basic editing operations on sequences and biological conversion among classes. The package can read and convert data from and to several formats. Thus, users can benefit from the richness of the R environment to perform advanced biological sequence analysis. The bioseq package is a free software intended to be of significant value to researchers who need a simple and solid framework to analyse biological sequence data in R.

Fine-Grained Parallel and Distributed Spatial Stochastic Simulation of Biological Reactions

Periodic pattern detection is an important data mining task that highlights the temporal regularities within the data. It aims at finding if a partial or full pattern has a cyclic repetition in the considered time series or data sequence. Periodicity is found in large number of datasets including meteorological data, transaction count, computer network traffic, power consumption, sunspots, Electrocardiography ECG, biological sequences such as DNA and protein [33]. Periodic pattern analysis not only helps in understanding the behavior of the data but also contributes in predicting the future trends of the data. There are several algorithms reported in the literature for periodicity detection in time series and biological sequences [3,34] but none of these algorithms discuss the non-uniformly sampled data. General assumption in the time series and sequence data is that the consecutive data values are sampled at regular or uniform interval of time. But this assumption hardly holds in real datasets; for example the stock market data analyzed in this paper record various features for each working day. This data has a quite a few missing values for weekly and arbitrary holidays. Although handling this issue is not very complex but requires careful handling. In this paper we analyze the stock market data in detail and show how the periodic pattern analysis may provide the understanding of the data to predict the future trends. Our experimental results show that consideration of missing values in stock market data results in much larger number of interesting results than the trivial periodicity detection approach ignoring the missing values.

As the key for biological sequence structure and function prediction, disease diagnosis and treatment, biological sequence similarity analysis has attracted more and more attentions. However, the exiting computational methods failed to accurately analyse the biological sequence similarities because of the various data types (DNA, RNA, protein, disease, etc) and their low sequence similarities (remote homology). Therefore, new concepts and techniques are desired to solve this challenging problem. Biological sequences (DNA, RNA and protein sequences) can be considered as the sentences of "the book of life", and their similarities can be considered as the biological language semantics (BLS). In this study, we are seeking the semantics analysis techniques derived from the natural language processing (NLP) to comprehensively and accurately analyse the biological sequence similarities. 27 semantics analysis methods derived from NLP were introduced to analyse biological sequence similarities, bringing new concepts and techniques to biological sequence similarity analysis. Experimental results show that these semantics analysis methods are able to facilitate the development of protein remote homology detection, circRNA-disease associations identification and protein function annotation, achieving better performance than the other state-of-the-art predictors in the related fields. Based on these semantics analysis methods, a platform called BioSeq-Diabolo has been constructed, which is named after a popular traditional sport in China. The users only need to input the embeddings of the biological sequence data. BioSeq-Diabolo will intelligently identify the task, and then accurately analyse the biological sequence similarities based on biological language semantics. BioSeq-Diabolo will integrate different biological sequence similarities in a supervised manner by using Learning to Rank (LTR), and the performance of the constructed methods will be evaluated and analysed so as to recommend the best methods for the users. The web server and stand-alone package of BioSeq-Diabolo can be accessed at http://bliulab.net/BioSeq-Diabolo/server/.

Identifying drug-target binding affinities (DTBA) is crucial in drug discovery, to understand how effectively drugs interact with their targets. However, traditional methods often struggle to accurately capture the complex relationships in biological data, leading to limitations in their predictive power. This paper introduces FusionNet, an advanced deep-learning model designed to improve DTBA prediction. FusionNet combines the strengths of Convolutional Neural Networks (CNNs), Long Short-Term Memory networks (LSTMs), and Transformers, to better understand both short-range and long-range interactions in biological sequences and employs the Layer-wise Adaptive Moments (LAMB) optimizer, which ensures the model is more efficient and stable, especially when working with large datasets. FusionNet achieved an MSE of 0.20 and an rm2 of 0.681 on the Davis dataset and an MSE of 0.18 and an rm2 of 0.71 on the KIBA dataset, significantly outperforming existing models like SimBoost, GANsDTA, DeepCDA, and DeepDTA, making it a powerful tool for drug discovery and bioinformatics. This work not only enhances the accuracy of DTBA prediction but also sets new performance standards by integrating advanced neural network architectures and optimizing their training process. FusionNet effectively addresses the limitations of previous approaches, offering a more reliable and efficient method for predicting drug-target interactions.

BackgroundMany open problems in bioinformatics involve elucidating underlying functional signals in biological sequences. DNA sequences, in particular, are characterized by rich architectures in which functional signals are increasingly found to combine local and distal interactions at the nucleotide level. Problems of interest include detection of regulatory regions, splice sites, exons, hypersensitive sites, and more. These problems naturally lend themselves to formulation as classification problems in machine learning. When classification is based on features extracted from the sequences under investigation, success is critically dependent on the chosen set of features.MethodologyWe present an algorithmic framework (EFFECT) for automated detection of functional signals in biological sequences. We focus here on classification problems involving DNA sequences which state-of-the-art work in machine learning shows to be challenging and involve complex combinations of local and distal features. EFFECT uses a two-stage process to first construct a set of candidate sequence-based features and then select a most effective subset for the classification task at hand. Both stages make heavy use of evolutionary algorithms to efficiently guide the search towards informative features capable of discriminating between sequences that contain a particular functional signal and those that do not.ResultsTo demonstrate its generality, EFFECT is applied to three separate problems of importance in DNA research: the recognition of hypersensitive sites, splice sites, and ALU sites. Comparisons with state-of-the-art algorithms show that the framework is both general and powerful. In addition, a detailed analysis of the constructed features shows that they contain valuable biological information about DNA architecture, allowing biologists and other researchers to directly inspect the features and potentially use the insights obtained to assist wet-laboratory studies on retainment or modification of a specific signal. Code, documentation, and all data for the applications presented here are provided for the community at http://www.cs.gmu.edu/~ashehu/?q=OurTools.

A phylogeny is a tree representation of the evolutionary history of a set of taxa (organisms, biological sequences, populations, or languages). Thus, phylogeny construction is among the basic computational problems in biology and linguistics. We will be concerned here with taxa described by the states they exhibit on a set of characters. A sample data set and a phylogeny for it (both adapted from [41]) are shown in Figure 1. The data is binary and in matrix form, rows are indexed by taxa and columns by characters. Entry (i, j) is “1” if taxon i has character j and it is “0” if the character is absent. The phylogeny shown is rooted and assumes that the taxa descend from a common ancestor where all characters are absent. Points at which characters emerge are indicated by labeled bars. 1

One of the main challenges in applying machine learning algorithms to biological sequence data is how to numerically represent a sequence in a numeric input vector. Feature extraction techniques capable of extracting numerical information from biological sequences have been reported in the literature. However, many of these techniques are not available in existing packages, such as mathematical descriptors. This paper presents a new package, MathFeature, which implements mathematical descriptors able to extract relevant numerical information from biological sequences, i.e. DNA, RNA and proteins (prediction of structural features along the primary sequence of amino acids). MathFeature makes available 20 numerical feature extraction descriptors based on approaches found in the literature, e.g. multiple numeric mappings, genomic signal processing, chaos game theory, entropy and complex networks. MathFeature also allows the extraction of alternative features, complementing the existing packages. To ensure that our descriptors are robust and to assess their relevance, experimental results are presented in nine case studies. According to these results, the features extracted by MathFeature showed high performance (0.6350–0.9897, accuracy), both applying only mathematical descriptors, but also hybridization with well-known descriptors in the literature. Finally, through MathFeature, we overcame several studies in eight benchmark datasets, exemplifying the robustness and viability of the proposed package. MathFeature has advanced in the area by bringing descriptors not available in other packages, as well as allowing non-experts to use feature extraction techniques.

The emerging science of sequences: Bioinformatics: A Practical Guide to the Analysis of Genes and Proteins, edited by Andreas Baxevanis and B. F. Francis Ouellette

Many life activities and key functions in organisms are maintained by different types of protein–protein interactions (PPIs). In order to accelerate the discovery of PPIs for different species, many computational methods have been developed. Unfortunately, even though computational methods are constantly evolving, efficient methods for predicting PPIs from protein sequence information have not been found for many years due to limiting factors including both methodology and technology. Inspired by the similarity of biological sequences and languages, developing a biological language processing technology may provide a brand new theoretical perspective and feasible method for the study of biological sequences. In this paper, a pure biological language processing model is proposed for predicting protein–protein interactions only using a protein sequence. The model was constructed based on a feature representation method for biological sequences called bio-to-vector (Bio2Vec) and a convolution neural network (CNN). The Bio2Vec obtains protein sequence features by using a “bio-word” segmentation system and a word representation model used for learning the distributed representation for each “bio-word”. The Bio2Vec supplies a frame that allows researchers to consider the context information and implicit semantic information of a bio sequence. A remarkable improvement in PPIs prediction performance has been observed by using the proposed model compared with state-of-the-art methods. The presentation of this approach marks the start of “bio language processing technology,” which could cause a technological revolution and could be applied to improve the quality of predictions in other problems.

Chemical oxygen demand (COD) is an important indicator of organic pollution in water. It plays a crucial role in assessing water quality and protecting the environment. The rapid and accurate detection of COD is essential for continuous water quality monitoring. Traditional methods are often time-consuming and require chemical reagents. To address these challenges, a novel approach based on a one-dimensional convolutional neural network (1D-CNN) combined with UV-vis spectroscopy is proposed. This method is efficient, fast, and reagent-free, offering significant advantages over conventional techniques. The proposed 1D-CNN method incorporates one-dimensional multi-scale feature fusion to enhance the accuracy of COD detection. The method improves spectral feature extraction by fusing features extracted from three parallel sub-convolutional and pooling layers within the same channel. Experimental results show that the fusion network performs well in COD detection. The proposed method demonstrates superior performance compared to traditional and deep learning methods such as partial least squares regression (PLSR), support vector machines (SVM), artificial neural network (ANN), and 1D-CNNs. It significantly improves the accuracy of UV-vis spectroscopy for COD detection, achieving higher precision in real-time water quality monitoring.

Prediction of PM2.5 concentration in urban agglomeration of China by hybrid network model

Accurate traffic prediction is crucial to alleviating traffic congestion in cities. Existing physical sensor-based traffic data acquisition methods have high transmission costs, serious traffic information redundancy, and large calculation volumes for spatiotemporal data processing, thus making it difficult to ensure accuracy and real-time traffic prediction. With the increasing resolution of UAV imagery, the use of unmanned aerial vehicles (UAV) imagery to obtain traffic information has become a hot spot. Still, analyzing and predicting traffic status after extracting traffic information is neglected. We develop a framework for traffic speed extraction and prediction based on UAV imagery processing, which consists of two parts: a traffic information extraction module based on UAV imagery recognition and a traffic speed prediction module based on deep learning. First, we use deep learning methods to automate the extraction of road information, implement vehicle recognition using convolutional neural networks and calculate the average speed of road sections based on panchromatic and multispectral image matching to construct a traffic prediction dataset. Then, we propose an attention-enhanced traffic speed prediction module that considers the spatiotemporal characteristics of traffic data and increases the weights of key roads by extracting important fine-grained spatiotemporal features twice to improve the prediction accuracy of the target roads. Finally, we validate the effectiveness of the proposed method on real data. Compared with the baseline algorithm, our algorithm achieves the best prediction performance regarding accuracy and stability.

A CNN encoder decoder LSTM model for sustainable wind power predictive analytics