Optimization of serine phosphorylation prediction in proteins by comparing human engineered features and deep representations.

Deep representations can be used to replace human-engineered representations, as such features are constrained by certain limitations. For the prediction of protein post-translation modifications (PTMs) sites, research community uses different feature extraction techniques applied on Pseudo amino acid compositions (PseAAC). Serine phosphorylation is one of the most important PTM as it is the most occurring, and is important for various biological functions. Creating efficient representations from large protein sequences, to predict PTM sites, is a time and resource intensive task. In this study we propose, implement and evaluate use of Deep learning to learn effective protein data representations from PseAAC to develop data driven PTM detection systems and compare the same with two human representations.. The comparisons are performed by training an xgboost based classifier using each representation. The best scores were achieved by RNN-LSTM based deep representation and CNN based representation with an accuracy score of 81.1% and 78.3% respectively. Human engineered representations scored 77.3% and 74.9% respectively. Based on these results, it is concluded that the deep features are promising feature engineering replacement to identify PhosS sites in a very efficient and accurate manner which can help scientists understand the mechanism of this modification in proteins.

Biological perspective of thiazolide derivatives against Mpro and MTase of SARS-CoV-2: Molecular docking, DFT and MD simulation investigations.

Humans around the globe have been severely affected by SARS-CoV-2 and no treatment has yet been authorized for the treatment of this severe condition brought by COVID-19. Here, an in silico research was executed to elucidate the inhibitory potential of selected thiazolides derivatives against SARS-CoV-2 Protease (Mpro) and Methyltransferase (MTase). Based on the analysis; 4 compounds were discovered to have efficacious and remarkable results against the proteins of the interest. Primarily, results obtained through this study not only allude these compounds as potential inhibitors but also pave the way for in vivo and in vitro validation of these compounds.

iProtease-PseAAC(2L): A two-layer predictor for identifying proteases and their types using Chou's 5-step-rule and general PseAAC.

Proteases are a type of enzymes, which perform the process of proteolysis. Proteolysis normally refers to protein and peptide degradation which is crucial for the survival, growth and wellbeing of a cell. Moreover, proteases have a strong association with therapeutics and drug development. The proteases are classified into five different types according to their nature and physiochemical characteristics. Mostly the methods used to differentiate protease from other proteins and identify their class requires a clinical test which is usually time-consuming and operator dependent. Herein, we report a classifier named iProtease-PseAAC (2L) for identifying proteases and their classes. The predictor is developed employing the flow of 5-step rule, initiating from the collection of benchmark dataset and terminating at the development of predictor. Rigorous verification and validation tests are performed and metrics are collected to calculate the authenticity of the trained model. The self-consistency validation gives the 98.32% accuracy, for cross-validation the accuracy is 90.71% and jackknife gives 96.07% accuracy. The average accuracy for level-2 i.e. protease classification is 95.77%. Based on the above-mentioned results, it is concluded that iProtease-PseAAC (2L) has the great ability to identify the proteases and their classes using a given protein sequence.

Prevalence of thyroid stimulating hormone dysfunction among sofosbuvir-treated HCV-infected patients: A real-world clinical experience.

Thyroid dysfunctions occur frequently among hepatitis C virus (HCV)-infected patients. Accumulating evidence has shown the higher incidence of thyroid dysfunctions in interferon-treated patients that was previously the standard of care therapy. However, the prevalence of thyroid disorders has not been studied in the recently developed interferon-free regimens or direct-acting antiviral (DAA) drugs-treated patients. We recruited 37 patients who had just completed 6 months long sofosbuvir-based treatment, and 26 interferon-treated patients were also included in the study. Serum thyrotropin level of all participants was measured using VIDAS. We observed thyroid dysfunctions in both pegylated interferon-experienced and DAA drug-experienced patients but the prevalence of hyperthyroidism was found significantly higher in patients treated with interferon-based regimen as compared with interferon-free regimens. This high prevalence of hypothyroidism in patients with HCV posttreatment highlights the need for regular periodic screening of patients during the treatment.

SPalmitoylC-PseAAC: A sequence-based model developed via Chou's 5-steps rule and general PseAAC for identifying S-palmitoylation sites in proteins.

S-Palmitoylation is a uniquely reversible and biologically important post-translational modification as it plays an essential role in a variety of cellular processes including signal transduction, protein-membrane interactions, neuronal development, lipid raft targeting, subcellular localization and apoptosis. Due to its association with the neuronal development, it plays a pivotal role in a variety of neurodegenerative diseases, mainly Alzheimer's, Schizophrenia and Huntington's disease. It is also essential for developmental life cycles and pathogenesis of Toxoplasma gondii and Plasmodium falciparum, known to cause toxoplasmosis and malaria, respectively. This depicts the strong biological significance of S-Palmitoylation, thus, the timely and accurate identification of S-palmitoylation sites is crucial. Herein, we propose a predictor for S-Palmitoylation sites in proteins namely SPalmitoylC-PseAAC by integrating the Chou's Pseudo Amino Acid Composition (PseAAC) and relative/absolute position-based features. Self-consistency testing and 10-fold cross-validation are performed to evaluate the performance of SPalmitoylC-PseAAC, using accuracy metrics. For self-consistency testing, 99.79% Acc, 99.77% Sp, 99.80% Sn and 1.00 MCC was observed, whereas, for 10-fold cross validation 97.22% Acc, 98.85% Sp, 95.80% Sn and 0.94 MCC was observed. Thus the proposed predictor can help in predicting the palmitoylation sites in an efficient and accurate way. The SPalmitoylC-PseAAC is available at (biopred.org/palm).

Prediction of antioxidant proteins by incorporating statistical moments based features into Chou's PseAAC.

Antioxidant proteins are considered crucial in the areas of research on life sciences and pharmacology. They prevent damage to cells and DNA which are caused by free radicals. The role of antioxidants in the ageing process makes them more significant in their accurate identification. Disease preventions through antioxidant protein have also been the area of study in recent past. The existing process to identify and test every single antioxidant protein in order to obtain its properties is inefficient and expensive. Due to this nature, many pharmaceutical agents have reflected antioxidant proteins as attractive targets. Approaches based on computational methodologies have appeared to be as a highly desirable resource in the annotation and determination process of antioxidant proteins. In this study, we have developed a method that is built on computation intelligence and statistical moments based features for prediction. Our proposed system has achieved better accuracy than state-of-art systems in the prediction of antioxidant proteins from non-antioxidant proteins using 10-fold-cross-validation tests. These outcomes suggest that the use of statistical moments with a multilayer neural network could bear more effective and efficient results.

SPrenylC-PseAAC: A sequence-based model developed via Chou's 5-steps rule and general PseAAC for identifying S-prenylation sites in proteins.

The protein prenylation (or S-prenylation) is one of the most essential modifications, required for the association of membrane of a plethora of signalling proteins with the key biological process such as protein trafficking, cell growth, proliferation and differentiation. Due to the ubiquitous nature of S-prenylation and its role in cellular functions, any defect in the biosynthesis or regulation of the isoprenoid leads to the occurrence of a variety of diseases including neurodegenerative disorders, metabolic issues, cardiovascular diseases and one of the most fatal diseases, cancer. This depicts the strong biological significance of S-prenylation, thus, the timely and accurate identification of S-prenylation sites is crucial and may provide with possible ways to understand the mechanism of this modification in proteins. To avoid laborious, resource demanding and expensive experimental techniques of identifying S-prenylation sites, here, we propose a novel predictor namely SPrenylC-PseAAC by integrating the Chou's Pseudo Amino Acid Composition (PseAAC) and relative/absolute position-based features. A 2-tier classification was performed i.e., at first level, identification of prenylation and non-prenylation sites is performed, while at the second level, identification of S-farnesylation and S-geranylgeranylation sites is performed. Using jackknife, perdition model validation gave 95.31% accuracy for tier-1 classification and 91.42% for tier 2 classification, while for 10-fold cross-validation, it gave 93.68% accuracy for tier-1 classification and 89.70% for tier 2 classification. Thus the proposed predictor can help in predicting the Prenylation sites in an efficient and accurate way. The SPrenylC-PseAAC is available at (biopred.org/prenyl).

pSSbond-PseAAC: Prediction of disulfide bonding sites by integration of PseAAC and statistical moments.

The structure of protein gains additional stability against various detrimental effects by the presence of disulfide bonds. The formation of correct disulfide bonds between cysteine residues ensures proper in vivo and in vitro folding of the protein. Many cysteine residues can be present in the polypeptide chain of a protein, however, not all cysteine residues are involved in the formation of a disulfide bond, and therefore, accurate prediction of these bonds is crucial for identifying biophysical characteristics of a protein. In the present study, a novel method is proposed for the prediction of intramolecular disulfide bonds accurately using statistical moments and PseAAC. The pSSbond-PseAAC uses PseAAC along with position and composition relative features to calculate statistical moments. Statistical moments are important as they are very sensitive regarding the position of data sequences and for prediction of intramolecular disulfide bonds, moments are combined together to train neural networks. The overall accuracy of the pSSbond-PseAAC is 98.97% to sensitivity value 98.92%, specificity 98.99% and 0.98 MCC; and it outperforms various previously reported studies.

iPhosT-PseAAC: Identify phosphothreonine sites by incorporating sequence statistical moments into PseAAC.

Among all the post-translational modifications (PTMs) of proteins, Phosphorylation is known to be the most important and highly occurring PTM in eukaryotes and prokaryotes. It has an important regulatory mechanism which is required in most of the pathological and physiological processes including neural activity and cell signalling transduction. The process of threonine phosphorylation modifies the threonine by the addition of a phosphoryl group to the polar side chain, and generates phosphothreonine sites. The investigation and prediction of phosphorylation sites is important and various methods have been developed based on high throughput mass-spectrometry but such experimentations are time consuming and laborious therefore, an efficient and accurate novel method is proposed in this study for the prediction of phosphothreonine sites. The proposed method uses context-based data to calculate statistical moments. Position relative statistical moments are combined together to train neural networks. Using 10-fold cross validation, 94.97% accurate result has been obtained whereas for Jackknife testing, 96% accurate results have been obtained. The overall accuracy of the system is 94.4% to sensitivity value 94% and specificity 94.6%. These results suggest that the proposed method may play an essential role to the other existing methods for phosphothreonine sites prediction.

Predicting membrane proteins and their types by extracting various sequence features into Chou's general PseAAC.

For many biological functions membrane proteins (MPs) are considered crucial. Due to this nature of MPs, many pharmaceutical agents have reflected them as attractive targets. It bears indispensable importance that MPs are predicted with accurate measures using effective and efficient computational models (CMs). Annotation of MPs using in vitro analytical techniques is time-consuming and expensive; and in some cases, it can prove to be intractable. Due to this scenario, automated prediction and annotation of MPs through CM based techniques have appeared to be useful. Based on the use of computational intelligence and statistical moments based feature set, an MP prediction framework is proposed. Furthermore, the previously used dataset has been enhanced by incorporating new MPs from the latest release of UniProtKB. Rigorous experimentation proves that the use of statistical moments with a multilayer neural network, trained using back-propagation based prediction techniques allows more thorough results.

iPhosY-PseAAC: identify phosphotyrosine sites by incorporating sequence statistical moments into PseAAC.

Protein phosphorylation is one of the most fundamental types of post-translational modifications and it plays a vital role in various cellular processes of eukaryotes. Among three types of phosphorylation i.e. serine, threonine and tyrosine phosphorylation, tyrosine phosphorylation is one of the most frequent and it is important for mediation of signal transduction in eukaryotic cells. Site-directed mutagenesis and mass spectrometry help in the experimental determination of cellular signalling networks, however, these techniques are costly, time taking and labour associated. Thus, efficient and accurate prediction of these sites through computational approaches can be beneficial to reduce cost and time. Here, we present a more accurate and efficient sequence-based computational method for prediction of phosphotyrosine (PhosY) sites by incorporation of statistical moments into PseAAC. The study is carried out based on Chou's 5-step rule, and various position-composition relative features are used to train a neural network for the prediction purpose. Validation of results through Jackknife testing is performed to validate the results of the proposed prediction method. Overall accuracy validated through Jackknife testing was calculated 93.9%. These results suggest that the proposed prediction model can play a fundamental role in the prediction of PhosY sites in an accurate and efficient way.

A Treatise to Computational Approaches Towards Prediction of Membrane Protein and Its Subtypes.

Membrane proteins are vital mediating molecules responsible for the interaction of a cell with its surroundings. These proteins are involved in different functionalities such as ferrying of molecules and nutrients across membrane, recognizing foreign bodies, receiving outside signals and translating them into the cell. Membrane proteins play significant role in drug interaction as nearly 50% of the drug targets are membrane proteins. Due to the momentous role of membrane protein in cell activity, computational models able to predict membrane protein with accurate measures bears indispensable importance. The conventional experimental methods used for annotating membrane proteins are time-consuming and costly and in some cases impossible. Computationally intelligent techniques have emerged to be as a useful resource in the automation of prediction and hence the annotation process. In this study, various techniques have been reviewed that are based on different computational intelligence models used for prediction process. These techniques were formulated by different researchers and were further evaluated to provide a comparative analysis. Analysis shows that the usage of support vector machine-based prediction techniques bears more assiduous results.

Computer-aided analysis of phytochemicals as potential dengue virus inhibitors based on molecular docking, ADMET and DFT studies.

BACKGROUND & OBJECTIVES: Dengue fever, caused by dengue virus (DENV), has become a serious threat to human lives. Phytochemicals are known to have great potential to eradicate viral, bacterial and fungal-borne diseases in human beings. This study was aimed at in silico drug development against nonstructural protein 4B (NS4B) of dengue virus 4 (DENV4). METHODS: A total of 2750 phytochemicals from different medicinal plants were selected for this study. These plants grow naturally in the climate of Pakistan and India and have been used for the treatment of various pathologies in human for long-time. The ADMET studies, molecular docking and density functional theory (DFT) based analysis were carried out to determine the potential inhibitory properties of these phytochemicals. RESULTS: The ADMET analysis and docking results revealed nine phytochemicals, i.e. Silymarin, Flavobion, Derrisin, Isosilybin, Mundulinol, Silydianin, Isopomiferin, Narlumicine and Oxysanguinarine to have potential inhibitory properties against DENV and can be considered for additional in vitro and in vivo studies to assess their inhibitory effects against DENV replication. They exhibited binding affinity ≥ -8 kcal/mol against DENV4-NS4B. Furthermore, DFT based analysis revealed high reactivity for these nine phytochemicals in the binding pocket of DENV4-NS4B, based on ELUMO, EHOMO and band energy gap. INTERPRETATION & CONCLUSION: Five out of nine phytochemicals are reported for the first time as novel DENV inhibitors. These included three phytochemicals from Silybum marianum, i.e. Derrisin, Mundulinol, Isopomiferin, and two phytochemicals from Fumaria indica, i.e. Narlumicine and Oxysanguinarine. However, all the nine phytochemicals can be considered for in vitro and in vivo analysis for the development of potential DENV inhibitors.

iPhosS(Deep)-PseAAC: Identification of Phosphoserine Sites in Proteins Using Deep Learning on General Pseudo Amino Acid Compositions.

Among all the PTMs, the protein phosphorylation is pivotal for various pathological and physiological processes. About 30 percent of eukaryotic proteins undergo the phosphorylation modification, leading to various changes in conformation, function, stability, localization, and so forth. In eukaryotic proteins, phosphorylation occurs on serine (S), Threonine (T) and Tyrosine (Y) residues. Among these all, serine phosphorylation has its own importance as it is associated with various importance biological processes, including energy metabolism, signal transduction pathways, cell cycling, and apoptosis. Thus, its identification is important, however, the in vitro, ex vivo and in vivo identification can be laborious, time-taking and costly. There is a dire need of an efficient and accurate computational model to help researchers and biologists identifying these sites, in an easy manner. Herein, we propose a novel predictor for identification of Phosphoserine sites (PhosS) in proteins, by integrating the Chou's Pseudo Amino Acid Composition (PseAAC) with deep features. We used well-known DNNs for both the tasks of learning a feature representation of peptide sequences and performing classifications. Among different DNNs, the best score is shown by Covolutional Neural Network based model which renders CNN based prediction model the best for Phosphoserine prediction. Based on these results, it is concluded that the proposed model can help to identify PhosS sites in a very efficient and accurate manner which can help scientists understand the mechanism of this modification in proteins.

Genome-wide comparison and identification of myosin gene family in Arabidopsis thaliana and Helianthus annuus.

Myosins are essential components of organelle trafficking in all the eukaryotic cells. Myosin driven movement plays a vital role in the development of pollen tubes, root hairs and root tips of flowering plants. The present research characterized the myosin genes in Arabidopsis thaliana and Helianthus annuus by using different computational tools. We discovered a total of 50 myosin genes and their splice variants in both pant species. Phylogenetic analysis indicated that myosin genes were divided into four subclasses. Chromosomal location revealed that myosin genes were located on all five chromosomes in A. thaliana, whereas they were present on nine chromosomes in H. annuus. Conserved motifs showed that conserved regions were closely similar within subgroups. Gene structure analysis showed that Atmyosin2.2 and Atmyosin2.3 had the highest number of introns/exons. Gene ontology analysis indicated that myosin genes were involved in vesicle transport along actin filament and cytoskeleton trafficking. Expression analysis showed that expression of myosin genes was higher during the flowering stage as compared to the seedling and budding stages. Tissue specific expression indicated that HanMYOSIN11.2, HanMYOSIN16.2 were highly expressed in stamen, whereas HanMYOSIN 2.2, HanMYOSIN 12.1 and HanMYOSIN 17.1 showed higher expression in nectary. This study enhance our understanding the function of myosins in plant development, and forms the basis for future research about the comparative genomics of plant myosin in other crop plants.

Analysis of Inhibitor Binding Combined with Reactivity Studies to Discover the Potentially Inhibiting Phytochemicals Targeting Chikungunya Viral Replication.

BACKGROUND: Chikungunya fever is a challenging threat to human health in various parts of the world nowadays. Many attempts have been made for developing an effective drug against this viral disease and no effective antiviral treatment has been developed to control the spread of the Chikungunya virus (CHIKV) in humans. OBJECTIVE: This research is aimed at the discovery of potential inhibitors against this virus by employing computational techniques to study the interactions between non-structural proteins of Chikungunya virus and phytochemicals from plants. METHODS: Four non-structural proteins were docked with 2035 phytochemicals from various plants. The ligands having binding energies ≥ -8.0 kcal/mol were considered as potential inhibitors for these proteins. ADMET studies were also performed to analyze different pharmacological properties of these docked compounds and to further analyze the reactivity of these phytochemicals against CHIKV, DFT analysis was carried out based on HOMO and LUMO energies. RESULTS: By analyzing the binding energies, Ki, ADMET properties and band energy gaps, it was observed that 13 phytochemicals passed all the criteria to be a potent inhibitor against CHIKV in humans. CONCLUSION: A total of 13 phytochemicals were identified as potent inhibiting candidates, which can be used against the Chikungunya virus.

Insights into Machine Learning-based Approaches for Virtual Screening in Drug Discovery: Existing Strategies and Streamlining Through FP-CADD.

BACKGROUND: Machine learning is an active area of research in computer science by the availability of big data collection of all sorts prompting interest in the development of novel tools for data mining. Machine learning methods have wide applications in computer-aided drug discovery methods. Most incredible approaches to machine learning are used in drug designing, which further aid the process of biological modelling in drug discovery. Mainly, two main categories are present which are Ligand-Based Virtual Screening (LBVS) and Structure-Based Virtual Screening (SBVS), however, the machine learning approaches fall mostly in the category of LBVS. OBJECTIVES: This study exposits the major machine learning approaches being used in LBVS. Moreover, we have introduced a protocol named FP-CADD which depicts a 4-steps rule of thumb for drug discovery, the four protocols of computer-aided drug discovery (FP-CADD). Various important aspects along with SWOT analysis of FP-CADD are also discussed in this article. CONCLUSION: By this thorough study, we have observed that in LBVS algorithms, Support Vector Machines (SVM) and Random Forest (RF) are those which are widely used due to high accuracy and efficiency. These virtual screening approaches have the potential to revolutionize the drug designing field. Also, we believe that the process flow presented in this study, named FP-CADD, can streamline the whole process of computer-aided drug discovery. By adopting this rule, the studies related to drug discovery can be made homogeneous and this protocol can also be considered as an evaluation criterion in the peer-review process of research articles.

Virtual Screening of Phytochemicals by Targeting HR1 Domain of SARS-CoV-2 S Protein: Molecular Docking, Molecular Dynamics Simulations, and DFT Studies.

The recent COVID-19 pandemic has impacted nearly the whole world due to its high morbidity and mortality rate. Thus, scientists around the globe are working to find potent drugs and designing an effective vaccine against COVID-19. Phytochemicals from medicinal plants are known to have a long history for the treatment of various pathogens and infections; thus, keeping this in mind, this study was performed to explore the potential of different phytochemicals as candidate inhibitors of the HR1 domain in SARS-CoV-2 spike protein by using computer-aided drug discovery methods. Initially, the pharmacological assessment was performed to study the drug-likeness properties of the phytochemicals for their safe human administration. Suitable compounds were subjected to molecular docking to screen strongly binding phytochemicals with HR1 while the stability of ligand binding was analyzed using molecular dynamics simulations. Quantum computation-based density functional theory (DFT) analysis was constituted to analyze the reactivity of these compounds with the receptor. Through analysis, 108 phytochemicals passed the pharmacological assessment and upon docking of these 108 phytochemicals, 36 were screened passing a threshold of -8.5 kcal/mol. After analyzing stability and reactivity, 5 phytochemicals, i.e., SilybinC, Isopomiferin, Lycopene, SilydianinB, and Silydianin are identified as novel and potent candidates for the inhibition of HR1 domain in SARS-CoV-2 spike protein. Based on these results, it is concluded that these compounds can play an important role in the design and development of a drug against COVID-19, after an exhaustive in vitro and in vivo examination of these compounds, in future.

iDRP-PseAAC: Identification of DNA Replication Proteins Using General PseAAC and Position Dependent Features.

DNA replication is one of the specific processes to be considered in all the living organisms, specifically eukaryotes. The prevalence of DNA replication is significant for an evolutionary transition at the beginning of life. DNA replication proteins are those proteins which support the process of replication and are also reported to be important in drug design and discovery. This information depicts that DNA replication proteins have a very important role in human bodies, however, to study their mechanism, their identification is necessary. Thus, it is a very important task but, in any case, an experimental identification is time-consuming, highly-costly and laborious. To cope with this issue, a computational methodology is required for prediction of these proteins, however, no prior method exists. This study comprehends the construction of novel prediction model to serve the proposed purpose. The prediction model is developed based on the artificial neural network by integrating the position relative features and sequence statistical moments in PseAAC for training neural networks. Highest overall accuracy has been achieved through tenfold cross-validation and Jackknife testing that was computed to be 96.22% and 98.56%, respectively. Our astonishing experimental results demonstrated that the proposed predictor surpass the existing models that can be served as a time and cost-effective stratagem for designing novel drugs to strike the contemporary bacterial infection.

iPhosH-PseAAC: Identify Phosphohistidine Sites in Proteins by Blending Statistical Moments and Position Relative Features According to the Chou's 5-Step Rule and General Pseudo Amino Acid Composition.

Protein phosphorylation is one of the key mechanism in prokaryotes and eukaryotes and is responsible for various biological functions such as protein degradation, intracellular localization, the multitude of cellular processes, molecular association, cytoskeletal dynamics, and enzymatic inhibition/activation. Phosphohistidine (PhosH) has a key role in a number of biological processes, including central metabolism to signalling in eukaryotes and bacteria. Thus, identification of phosphohistidine sites in a protein sequence is crucial, and experimental identification can be expensive, time-taking, and laborious. To address this problem, here, we propose a novel computational model namely iPhosH-PseAAC for prediction of phosphohistidine sites in a given protein sequence using pseudo amino acid composition (PseAAC), statistical moments, and position relative features. The results of the proposed predictor are validated through self-consistency testing, 10-fold cross-validation, and jackknife testing. The self-consistency validation gave the 100 percent accuracy, whereas, for cross-validation, the accuracy achieved is 94.26 percent. Moreover, jackknife testing gave 97.07 percent accuracy for the proposed model. Thus, the proposed model iPhosH-PseAAC for prediction of iPhosH site has the great ability to predict the PhosH sites in given proteins.