BACKGROUND: Discovery biological motifs plays a fundamental role in understanding regulatory mechanisms. Computationally, they can be efficiently represented as kmers, making the counting of these elements a critical aspect for ensuring not only the accuracy but also the efficiency of the analytical process. This is particularly useful in scenarios involving large data volumes, such as those generated by the ChIP-seq protocol. Against this backdrop, we introduce BIOMAPP::CHIP, a tool specifically designed to optimize the discovery of biological motifs in large data volumes. RESULTS: We conducted a comprehensive set of comparative tests with state-of-the-art algorithms. Our analyses revealed that BIOMAPP::CHIP outperforms existing approaches in various metrics, excelling both in terms of performance and accuracy. The tests demonstrated a higher detection rate of significant motifs and also greater agility in the execution of the algorithm. Furthermore, the SMT component played a vital role in the system's efficiency, proving to be both agile and accurate in kmer counting, which in turn improved the overall efficacy of our tool. CONCLUSION: BIOMAPP::CHIP represent real advancements in the discovery of biological motifs, particularly in large data volume scenarios, offering a relevant alternative for the analysis of ChIP-seq data and have the potential to boost future research in the field. This software can be found at the following address: (https://github.com/jadermcg/biomapp-chip).

We hypothesize that sample species abundance, sequencing depth, and taxonomic relatedness influence the recovery of metagenome-assembled genomes (MAGs). To test this hypothesis, we assessed MAG recovery in three in silico microbial communities composed of 42 species with the same richness but different sample species abundance, sequencing depth, and taxonomic distribution profiles using three different pipelines for MAG recovery. The pipeline developed by Parks and colleagues (8K) generated the highest number of MAGs and the lowest number of true positives per community profile. The pipeline by Karst and colleagues (DT) showed the most accurate results (~ 92%), outperforming the 8K and Multi-Metagenome pipeline (MM) developed by Albertsen and collaborators. Sequencing depth influenced the accurate recovery of genomes when using the 8K and MM, even with contrasting patterns: the MM pipeline recovered more MAGs found in the original communities when employing sequencing depths up to 60 million reads, while the 8K recovered more true positives in communities sequenced above 60 million reads. DT showed the best species recovery from the same genus, even though close-related species have a low recovery rate in all pipelines. Our results highlight that more bins do not translate to the actual community composition and that sequencing depth plays a role in MAG recovery and increased community resolution. Even low MAG recovery error rates can significantly impact biological inferences. Our data indicates that the scientific community should curate their findings from MAG recovery, especially when asserting novel species or metabolic traits.

Finding transcription factor binding sites plays an important role inside bioinformatics. Its correct identification in the promoter regions of co-expressed genes is a crucial step for understanding gene expression mechanisms and creating new drugs and vaccines. The problem of finding motifs consists in seeking conserved patterns in biological datasets of sequences, through using unsupervised learning algorithms. This problem is considered one of the open problems of computational biology, which in its simplest formulation has been proven to be np-hard. Moreover, heuristics and meta-heuristics algorithms have been shown to be very promising in solving combinatorial problems with very large search spaces. In this paper we propose a new algorithm called Biomapp (Biological Motif Application) based on canonical Expectation Maximization that uses the Kullback-Leibler divergence to re-estimate the parameters of statistical model. Furthermore, the algorithm is embedded in an Iterated Local Search, as the local search step and then, we use a hierarchical perturbation operator in order to escape from local optima. The results obtained by this new approach were compared with the state-of-the-art algorithm MEME (Multiple EM Motif Elicitation) showing that Biomapp outperformed this classical technique in several datasets.

Improving results by optimizing process execution is one objective of major companies. For these corporations, the main point for achieving better results is the good maintenance of supply chain management. The most important supply chain metric is Delivery in Full and On Time (DIFOT). DIFOT measures how well a supply chain delivers value to the customer. In this work, we bring forward an analysis of DIFOT prediction from large Brazilian food company. More specifically, we compare a batch and online learning algorithm for DIFOT prediction and depict why the latter is suitable for this problem. Furthermore, we report a feature drift analysis to identify whether there are considerable shifts along with the dataset timespan. As a byproduct of this research, we make the dataset used in this analysis publicly available for future research in DIFOT prediction.

Recent technological advances have led to an exponential expansion of biological sequence data and extraction of meaningful information through Machine Learning (ML) algorithms. This knowledge has improved the understanding of mechanisms related to several fatal diseases, e.g. Cancer and coronavirus disease 2019, helping to develop innovative solutions, such as CRISPR-based gene editing, coronavirus vaccine and precision medicine. These advances benefit our society and economy, directly impacting people's lives in various areas, such as health care, drug discovery, forensic analysis and food processing. Nevertheless, ML-based approaches to biological data require representative, quantitative and informative features. Many ML algorithms can handle only numerical data, and therefore sequences need to be translated into a numerical feature vector. This process, known as feature extraction, is a fundamental step for developing high-quality ML-based models in bioinformatics, by allowing the feature engineering stage, with design and selection of suitable features. Feature engineering, ML algorithm selection and hyperparameter tuning are often manual and time-consuming processes, requiring extensive domain knowledge. To deal with this problem, we present a new package: BioAutoML. BioAutoML automatically runs an end-to-end ML pipeline, extracting numerical and informative features from biological sequence databases, using the MathFeature package, and automating the feature selection, ML algorithm(s) recommendation and tuning of the selected algorithm(s) hyperparameters, using Automated ML (AutoML). BioAutoML has two components, divided into four modules: (1) automated feature engineering (feature extraction and selection modules) and (2) Metalearning (algorithm recommendation and hyper-parameter tuning modules). We experimentally evaluate BioAutoML in two different scenarios: (i) prediction of the three main classes of noncoding RNAs (ncRNAs) and (ii) prediction of the eight categories of ncRNAs in bacteria, including housekeeping and regulatory types. To assess BioAutoML predictive performance, it is experimentally compared with two other AutoML tools (RECIPE and TPOT). According to the experimental results, BioAutoML can accelerate new studies, reducing the cost of feature engineering processing and either keeping or improving predictive performance. BioAutoML is freely available at https://github.com/Bonidia/BioAutoML.

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.

As consequence of the various genomic sequencing projects, an increasing volume of biological sequence data is being produced. Although machine learning algorithms have been successfully applied to a large number of genomic sequence-related problems, the results are largely affected by the type and number of features extracted. This effect has motivated new algorithms and pipeline proposals, mainly involving feature extraction problems, in which extracting significant discriminatory information from a biological set is challenging. Considering this, our work proposes a new study of feature extraction approaches based on mathematical features (numerical mapping with Fourier, entropy and complex networks). As a case study, we analyze long non-coding RNA sequences. Moreover, we separated this work into three studies. First, we assessed our proposal with the most addressed problem in our review, e.g. lncRNA and mRNA; second, we also validate the mathematical features in different classification problems, to predict the class of lncRNA, e.g. circular RNAs sequences; third, we analyze its robustness in scenarios with imbalanced data. The experimental results demonstrated three main contributions: first, an in-depth study of several mathematical features; second, a new feature extraction pipeline; and third, its high performance and robustness for distinct RNA sequence classification. Availability:https://github.com/Bonidia/FeatureExtraction_BiologicalSequences.

BACKGROUND: De novo prediction of Transcription Factor Binding Sites (TFBS) using computational methods is a difficult task and it is an important problem in Bioinformatics. The correct recognition of TFBS plays an important role in understanding the mechanisms of gene regulation and helps to develop new drugs. RESULTS: We here present Memetic Framework for Motif Discovery (MFMD), an algorithm that uses semi-greedy constructive heuristics as a local optimizer. In addition, we used a hybridization of the classic genetic algorithm as a global optimizer to refine the solutions initially found. MFMD can find and classify overrepresented patterns in DNA sequences and predict their respective initial positions. MFMD performance was assessed using ChIP-seq data retrieved from the JASPAR site, promoter sequences extracted from the ABS site, and artificially generated synthetic data. The MFMD was evaluated and compared with well-known approaches in the literature, called MEME and Gibbs Motif Sampler, achieving a higher f-score in the most datasets used in this work. CONCLUSIONS: We have developed an approach for detecting motifs in biopolymers sequences. MFMD is a freely available software that can be promising as an alternative to the development of new tools for de novo motif discovery. Its open-source software can be downloaded at https://github.com/jadermcg/mfmd .

A genetic algorithm using Edge Assemble Crossover (EAX) is one of the best heuristic solvers for large instances of the Traveling Salesman Problem. We propose using Partition Crossover to recombine solutions produced by EAX. Partition Crossover is a powerful deterministic recombination that is highly exploitive. When Partition Crossover decomposes two parents into q recombining components, partition crossover returns the best of 2q reachable offspring. If two parents are locally optimal, all of the offspring are also locally optimal in a hyperplane subspace that contains the two parents. One disadvantage of Partition Crossover, however, is that it cannot generate new edges. By contrast, the EAX operator is highly explorative; it not only inherits edges from parents, it also introduces new edges into the population of a genetic algorithm. Using both EAX and Partition Crossover together produces better performance, with improved exploitation and exploration.

The best known exact solver for generating provably optimal solutions to the Traveling Salesman Problem (TSP) is the Concorde algorithm. Concorde uses a branch and bound search strategy, as well as cutting planes to reduce the search space. The first step in using Concorde is to obtain a good initial solution. A good solution can be generated using a heuristic solver outside of Concorde, or Concorde can generate its own initial solution using the Chained Lin Kernighan (LK) algorithm. In this paper, we speed up Concorde by improving the initial solutions produced by Chained LK using Partition Crossover. Partition Crossover is a powerful deterministic recombination operator that is able to tunnel between local optima. In every instance we examined, the addition of recombination resulted in an average speed-up of Concorde, and in the majority of cases, the difference in the runtime costs was statistically significant.

The problem of converting a music in standard music notation (music sheet) to the alternative notation of guitar tablature is known as transcription. The process of transcription consists of indicating where each note from the original music sheet needs to be played in the guitar, i.e. which string and fret of the guitar that needs to be played to produce a particular note. However, considering that each note can be played in different positions of the guitar fretboard, this is not a straightforward process, and can be classified as a combinatorial optimization problem. For this reason, we have employed a comparative study of different algorithms: A-star, genetic algorithms (GA), genetic algorithms based on subpopulations (GA-SP), ant colony optimization (ACO) and differential evolution (DE). It was also included heuristics based on local search 2-opt and 3-opt in the approaches GA, GA-SP and DE. The experimental results with a dataset of 87 musics indicated that the approaches ACO, GA-SP with 2-opt and GA with 2-opt reached the best performance. Also, the results obtained with each approach were statistically compared using ANOVA test with post hoc Tukey.

Power system controllers are typically designed using trial-and-error techniques, which may require large effort and time from the part of the designer to find a satisfactory solution. This work proposes an algorithm to perform a simultaneous and coordinated tuning of the controllers (PSSs) in an automatic form. To perform this tuning, the algorithm uses an optimization technique based on ant colony metaheuristic. In addition, a parallel structure for the algorithm is proposed to minimize the computation time. Results show satisfactory performance of the tuned controllers, evidencing the effectiveness of the proposed technique. Furthermore, a significant productivity gain can be achieved if the engineer in charge of this design only supervises the automatic process, instead of performing all calculations himself/herself.

The network reconfiguration for service restoration (SR) in distribution systems is a combinatorial complex optimization problem since it involves multiple non-linear constraints and objectives. For large networks, no exact algorithm has found adequate SR plans in real-time. On the other hand, methods combining Multi-objective Evolutionary Algorithms (MOEAs) with the Node-depth encoding (NDE) have shown to be able to efficiently generate adequate SR plans for large distribution systems (with thousands of buses and switches). This paper presents a new method that combining NDE with three MOEAs: (i) NSGA-II; (iii) SPEA 2; and (iii) a MOEA based on subpopulation tables. The idea is to obtain a method that cannot-only obtain adequate SR plans for large scale distribution systems, but can also find plans for small or large networks with similar quality. The proposed method, called MEA2N-STR, explores the space of the objectives solutions better than the other MOEAs with NDE, approximating better the Pareto-optimal front. This statement has been demonstrated by several simulations with DSs ranging from 632 to 1,277 switches.

The problem of production scheduling of manufacturing systems is characterized by the large number of possible solutions. Several researches have been using the Genetic Algorithms (GA) as a search method to solve this problem since these algorithms have the capacity of globally exploring the search space and find good solutions quickly. Since the performance of the GA is directly related to the choice of the parameters of genetic operators, and a bad choice can depreciate the performance, this paper proposes the use of Adaptive Genetic Algorithm to solve this kind of scheduling problem considering the machines and the Automated Guided Vehicles (AGVs). The aim of this paper is to get a good production reactive schedule in order to achieve a good makespan value in a low response obtaining time. The results of this paper were validated in large scenarios and compared with the results of two other approaches. These results are presented and discussed in this paper.