Digital Signal Processing Techniques:Calculating Biological Functionalities

Nwankwo, Norbert; Şeker, Hüseyin

doi:10.4172/jpb.1000199

Cited by 6 publications

(16 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, Helicity-, EIIP-and Hydrophobicity-oriented biological parameters were obtained from [10] and utilized. Our ISM-based findings [9,19] show correlation with the clinical outcomes. Sifuvirtide, adjudged superior to Enfuvirtide clinically [20] recorded greater interaction (85.42%) than Enfuvirtide (72.33%).…”

Section: Introductionmentioning

confidence: 77%

“…This is because; N is halved since the output of the DFT processing is a mirror (symmetric) image. For example, in the analysis of protein residues of P32 and P18, where N is 32, the IS characteristics presented N/2 as 16 values (running from 0-15 in case of Mathlab program or 1-16 using Python) [19]. In the case of CD4 residues and HIV gp120 where N is 482 and 508, the IS characteristics showed 240 and 253 respectively [31], excluding the first and last values called DC.…”

Section: (Ii) Processing Of the Numerical Sequences (Signals) Using mentioning

confidence: 99%

“…Engaging all the biological parameters and sequence information involved, we have computationally investigated the pharmacological activities of two anti-retroviral agents, Enfuvirtide and Sifuvirtide using ISM, and further compared their potencies [9,19]. Sifuvirtide, a product of biomedical modification of CHR motif including Enfuvirtide was found to be more efficacious.…”

Section: Introductionmentioning

confidence: 99%

“…These preliminarily computational assessments [7][8][9]19] are therefore used to demonstrate how a computerized approach (ISM) could be engaged to assess pharmacological activities. Studies carried out on the pharmacological activities of these agents with the aim of extracting their sequence information and biological parameters are reported in section 2.1.…”

Section: Introductionmentioning

confidence: 99%

“…Equally, we investigated potencies of two peptidic vaccine candidates, P18 and P32 using these computerized approaches [9,19]. P18 and P32 were found to interact with their target protein, Glycosaminoglycan (GAG) using negatively charged carboxyl group [21,22].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Novel Computerized Approaches to Investigating Pharmacological Activities

Nwankwo¹

2015

CBB

View full text Add to dashboard Cite

Abstract:Complementing clinical assessments using computerized procedures with the view of completely disengaging from clinical procedures may become inevitable in future. Huge biological and pharmacological data (such as sequences) are churned out daily such that it is becoming difficult to process them without the aid of computers. Computerized approaches including Digital Signal Processing (DSP)-based Bioinformatics procedures like Informational Spectrum Method (ISM) are rational techniques that need be incorporated into pharmacological studies. By means of ISM and one biological parameter or Amino Acid Scale (AAS), we have preliminarily shown how pharmacological activities can be decoded using computerized techniques. However, for effective engagement of ISM, some basic information must be made available and engaged. Firstly, the sequence information comprising of the consensus sequences and all the mutations involved must be assembled and engaged. Pharmacological activities (e.g. drug resistance) are known to be expressed in the genes/proteins (e.g. MDR1 and MDR2, pfdr1, etc). Secondly, biological parameters must be identified and engaged. This calls for good knowledge of the drugs' mechanisms of action at the atomic level. This is because it has been identified that, at one point mutation; more than one biological parameter may be involved. To obtain the entirety of pharmacological activities exhibited therefore, aggregation of the contributions from each mutation and parameter is needed.We have then unveiled and compared the pharmacological activities of anti-retroviral agents (Enfuvirtide and Sifuvirtide), and potencies of Malaria vaccine candidates, peptides P18 and P32 (Innocentive Challenge Winning Solver Award, ID: 9933477), etc. A biomedical device called Computer-Aided Drug Resistance Calculator (Patent Application filed in 2014) is developed using this novel computerized approach. The device will rationally help assess a pharmacological property (drug resistance). Other researchers have recorded in-silico pharmacological assessments. Clinically and computationally derived outcomes are found to correlate. We therefore propose that these computerized approaches be engaged in deciphering pharmacological activities where sequence information and biological parameters are available. These approaches are rational. They also present pharmacological findings in numerical terms. In this era of rational, computerized, informatics-and robotics-based procedures, these approaches are envisaged to transform pharmacological investigation procedures especially now that pharmacological activities could be deciphered from their protein sequences or those of their protein targets and the genes/proteins expressing them. The procedures engaged in this study are expected to be embodied into Pharmaco-informatics program.

show abstract

Section: Introductionmentioning

confidence: 77%

Section: (Ii) Processing Of the Numerical Sequences (Signals) Using mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Novel Computerized Approaches to Investigating Pharmacological Activities

Nwankwo¹

2015

CBB

View full text Add to dashboard Cite

show abstract

A machine learning approach for reliable prediction of amino acid interactions and its application in the directed evolution of enantioselective enzymes

Cadet¹,

Fontaine²,

et al. 2018

Sci Rep

123

118

View full text Add to dashboard Cite

Directed evolution is an important research activity in synthetic biology and biotechnology. Numerous reports describe the application of tedious mutation/screening cycles for the improvement of proteins. Recently, knowledge-based approaches have facilitated the prediction of protein properties and the identification of improved mutants. However, epistatic phenomena constitute an obstacle which can impair the predictions in protein engineering. We present an innovative sequence-activity relationship (innov’SAR) methodology based on digital signal processing combining wet-lab experimentation and computational protein design. In our machine learning approach, a predictive model is developed to find the resulting property of the protein when the n single point mutations are permuted (2n combinations). The originality of our approach is that only sequence information and the fitness of mutants measured in the wet-lab are needed to build models. We illustrate the application of the approach in the case of improving the enantioselectivity of an epoxide hydrolase from Aspergillus niger. n = 9 single point mutants of the enzyme were experimentally assessed for their enantioselectivity and used as a learning dataset to build a model. Based on combinations of the 9 single point mutations (29), the enantioselectivity of these 512 variants were predicted, and candidates were experimentally checked: better mutants with higher enantioselectivity were indeed found.

show abstract

A comprehensive framework for advanced protein classification and function prediction using synergistic approaches: Integrating bispectral analysis, machine learning, and deep learning

Alquran,

Al Fahoum,

Zyout

et al. 2023

PLoS ONE

View full text Add to dashboard Cite

Proteins are fundamental components of diverse cellular systems and play crucial roles in a variety of disease processes. Consequently, it is crucial to comprehend their structure, function, and intricate interconnections. Classifying proteins into families or groups with comparable structural and functional characteristics is a crucial aspect of this comprehension. This classification is crucial for evolutionary research, predicting protein function, and identifying potential therapeutic targets. Sequence alignment and structure-based alignment are frequently ineffective techniques for identifying protein families.This study addresses the need for a more efficient and accurate technique for feature extraction and protein classification. The research proposes a novel method that integrates bispectrum characteristics, deep learning techniques, and machine learning algorithms to overcome the limitations of conventional methods. The proposed method uses numbers to represent protein sequences, utilizes bispectrum analysis, uses different topologies for convolutional neural networks to pull out features, and chooses robust features to classify protein families. The goal is to outperform existing methods for identifying protein families, thereby enhancing classification metrics. The materials consist of numerous protein datasets, whereas the methods incorporate bispectrum characteristics and deep learning strategies. The results of this study demonstrate that the proposed method for identifying protein families is superior to conventional approaches. Significantly enhanced quality metrics demonstrated the efficacy of the combined bispectrum and deep learning approaches. These findings have the potential to advance the field of protein biology and facilitate pharmaceutical innovation. In conclusion, this study presents a novel method that employs bispectrum characteristics and deep learning techniques to improve the precision and efficiency of protein family identification. The demonstrated advancements in classification metrics demonstrate this method’s applicability to numerous scientific disciplines. This furthers our understanding of protein function and its implications for disease and treatment.

show abstract

Digital Signal Processing Techniques:Calculating Biological Functionalities

Cited by 6 publications

References 36 publications

Novel Computerized Approaches to Investigating Pharmacological Activities

Novel Computerized Approaches to Investigating Pharmacological Activities

A machine learning approach for reliable prediction of amino acid interactions and its application in the directed evolution of enantioselective enzymes

A comprehensive framework for advanced protein classification and function prediction using synergistic approaches: Integrating bispectral analysis, machine learning, and deep learning

Contact Info

Product

Resources

About