A new fast technique for pattern matching in biological sequences

Abstract

At numerous phases of the computational process, pattern matching is essential. It enables users to search for specific DNA subsequences or DNA sequences in a database. In addition, some of these rapidly expanding biological databases are updated on a regular basis. Pattern searches can be improved by using high-speed pattern matching algorithms. Researchers are striving to improve solutions in numerous areas of computational bioinformatics as biological data grows exponentially. Faster algorithms with a low error rate are needed in real-world applications. As a result, this study offers two pattern matching algorithms that were created to help speed up DNA sequence pattern searches. The strategies recommended improve performance by utilizing word-level processing rather than character-level processing, which has been used in previous research studies. In terms of time cost, the proposed algorithms (EFLPM and EPAPM) increased performance by leveraging word-level processing with large pattern size. The experimental results show that the proposed methods are faster than other algorithms for short and long patterns. As a result, the EFLPM algorithm is 54% faster than the FLPM method, while the EPAPM algorithm is 39% faster than the PAPM method.

Optimizing classification efficiency with machine learning techniques for pattern matching

“…Table 4 provides a comparison of the machine learning techniques discussed above with traditional techniques, including our two proposed methods (EFLPM and EPAPM) [47] based on their execution time for different pattern lengths in DNA sequences.…”

“…We opted to build databases on DNA to examine the machine learning algorithms discussed in the following paragraphs. The rationale behind this decision was to sample some of the genes that we had worked on in our previous research endeavors [15], Our objective was to integrate automated learning algorithms and pattern-matching algorithms that are based on specific DNA sequences, in order to create a biological data collection that could be utilized in a classification process. We conducted experiments on a dataset that included DNA sequences, where we compared the effectiveness of searching for a specific pattern with other classification models, such as Random Forest [3,16], KNN [16][17][18][19][20], Naïve Bayes [21][22][23][24], Decision tree [23,[25][26][27][28][29][30], and Support Vector Machine [18,[31][32][33][34][35][36] with Linear [37,38], RBF [37,39], and sigmoid [21,40] classifiers, the results of these classifiers models are calculated by F1 score, recall, precision rate, execution time, and with the accuracy which calculates the most effective patternmatching classifier.…”

An Improved Hashing Approach for Biological Sequence to Solve Exact Pattern Matching Problems

“…//Create substring based on pattern length (5) for (i � 0 to m) do (6) sum ⟵ ASCII (s i ) (7) end for loop (8) //Create hash value using predefned prime number (9) h (s) ⟵ sum mod q (10) //Create quotient value using predefned prime number (11) r (s) ⟵ sum divide q (12) if h(p) � h(s) and r(p) � r(s)…”

“…To comprehend biological data, mainly when the datasets are enormous and complicated, the interdisciplinary discipline of bioinformatics develops techniques and software tools [5]. Pattern matching issues appear in many computational bioinformatics tasks, including basic local synchronization search, biomarker discovery, sequence matching, homologous sequence identifcation, and proteogenomic mapping [6,7]. Pattern matching can be used in biotechnology, forensics, medical, and agricultural research to look into probable disease or anomaly diagnoses [8].…”

Untitled

“…Computational methods, on the other hand, are efficient and effective, and they play an important role in many areas of bioinformatics. For example, in silico techniques are being used rapidly in research on diseasegene interactions [25,26], protein structure prediction [27], peptide therapeutic function, gene editing experiments [28], meaningful pattern detection [29], and drug repurposing [30,31]. Previously, researchers have been proposed a few computational models for predicting the 2-OM sites based on single machine learning (ML) and deep learning (DL) approaches [32][33][34][35][36][37][38][39].…”