sAMP-PFPDeep: Improving accuracy of short antimicrobial peptides prediction using three different sequence encodings and deep neural networks.

Short antimicrobial peptides (sAMPs) belong to a significant repertoire of antimicrobial agents and are known to possess enhanced antimicrobial activity, higher stability and less toxicity to human cells, as well as less complex than other large biological drugs. As these molecules are significantly important, herein, a prediction method for sAMPs (with a sequence length ≤ 30 residues) is proposed for accurate and efficient prediction of sAMPs instead of laborious and costly experimental approaches. Benchmark dataset was collected from a recently reported study and sequences were converted into three channel images comprising information related to the position, frequency and sum of 12 physiochemical features as the first, second and third channels, respectively. Two image-based deep neural networks (DNNs), i.e. RESNET-50 and VGG-16 were trained and evaluated using various metrics while a comparative analysis with previous techniques was also performed. Validation of sAMP-PFPDeep was also performed by using molecular docking based analysis. The results showed that VGG-16 provided more accurate results, i.e. 98.30% training accuracy and 87.37% testing accuracy for predicting sAMPs as compared to those of RESNET-50 having 96.14% training accuracy and 83.87% testing accuracy. However, the comparative analysis revealed that both these models outperformed previously reported state-of-the-art methods. Based on the results, it is concluded that sAMP-PFPDeep can help identify antimicrobial peptides with promising accuracy and efficiency. It can help biologists and scientists to identify antimicrobial peptides, by further aiding the computer-aided drug design and discovery, as well as virtual screening protocols against various pathologies. sAMP-PFPDeep is available at (https://github.com/WaqarHusain/sAMP-PFPDeep).

ORI-Deep: improving the accuracy for predicting origin of replication sites by using a blend of features and long short-term memory network.

Replication of DNA is an important process for the cell division cycle, gene expression regulation and other biological evolution processes. It also has a crucial role in a living organism's physical growth and structure. Replication of DNA comprises of three stages known as initiation, elongation and termination, whereas the origin of replication sites (ORI) is the location of initiation of the DNA replication process. There exist various methodologies to identify ORIs in the genomic sequences, however, these methods have used either extensive computations for execution, or have limited optimization for the large datasets. Herein, a model called ORI-Deep is proposed to identify ORIs from the multiple cell type genomic sequence benchmark data. An efficient method is proposed using a deep neural network to identify ORIs for four different eukaryotic species. For better representation of data, a feature vector is constructed using statistical moments for the training and testing of data and is further fed to a long short-term memory (LSTM) network. To prove the effectiveness of the proposed model, we applied several validation techniques at different levels to obtain seven accuracy metrics, and the accuracy score for self-consistency, 10-fold cross-validation, jackknife and the independent set test is observed to be 0.977, 0.948, 0.976 and 0.977, respectively. Based on the results, it can be concluded that ORI-Deep can efficiently predict the sites of origin replication in DNA sequence with high accuracy. Webserver for ORI-Deep is available at (https://share.streamlit.io/waqarhusain/orideep/main/app.py), whereas source code is available at (https://github.com/WaqarHusain/OriDeep).

EyeCNN: exploring the potential of convolutional neural networks for identification of multiple eye diseases through retinal imagery.

BACKGROUND: The eyes are the most important part of the human body as these are directly connected to the brain and help us perceive the imagery in daily life whereas, eye diseases are mostly ignored and underestimated until it is too late. Diagnosing eye disorders through manual diagnosis by the physician can be very costly and time taking. OBJECTIVE: Thus, to tackle this, a novel method namely EyeCNN is proposed for identifying eye diseases through retinal images using EfficientNet B3. METHODS: A dataset of retinal imagery of three diseases, i.e. Diabetic Retinopathy, Glaucoma, and Cataract is used to train 12 convolutional networks while EfficientNet B3 was the topperforming model out of all 12 models with a testing accuracy of 94.30%. RESULTS: After preprocessing of the dataset and training of models, various experimentations were performed to see where our model stands. The evaluation was performed using some well-defined measures and the final model was deployed on the Streamlit server as a prototype for public usage. The proposed model has the potential to help diagnose eye diseases early, which can facilitate timely treatment. CONCLUSION: The use of EyeCNN for classifying eye diseases has the potential to aid ophthalmologists in diagnosing conditions accurately and efficiently. This research may also lead to a deeper understanding of these diseases and it may lead to new treatments. The webserver of EyeCNN can be accessed at ( https://abdulrafay97-eyecnn-app-rd9wgz.streamlit.app/ ).

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.

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).

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.

iMethylK_pseAAC: Improving Accuracy of Lysine Methylation Sites Identification by Incorporating Statistical Moments and Position Relative Features into General PseAAC via Chou's 5-steps Rule.

BACKGROUND: Methylation is one of the most important post-translational modifications in the human body which usually arises on lysine among the most intensely modified residues. It performs a dynamic role in numerous biological procedures, such as regulation of gene expression, regulation of protein function and RNA processing. Therefore, to identify lysine methylation sites is an important challenge as some experimental procedures are time-consuming. OBJECTIVE: Herein, we propose a computational predictor named iMethylK_pseAAC to identify lysine methylation sites. METHODS: Firstly, we constructed feature vectors based on PseAAC using position and composition rel-ative features and statistical moments. A neural network is trained based on the extracted features. The performance of the proposed method is then validated using cross-validation and jackknife testing. RESULTS: The objective evaluation of the predictor showed accuracy of 96.7% for self-consistency, 91.61% for 10-fold cross-validation and 93.42% for jackknife testing. CONCLUSION: It is concluded that iMethylK_pseAAC outperforms the counterparts to identify lysine methylation sites such as iMethyl_pseACC, BPB_pPMS and PMeS.

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.

Experimental platform utilising melting curve technology for detection of mutations in Mycobacterium tuberculosis isolates.

Tuberculosis (TB) remains one of the most deadly infections with approximately a quarter of cases not being identified and/or treated mainly due to a lack of resources. Rapid detection of TB or drug-resistant TB enables timely adequate treatment and is a cornerstone of effective TB management. We evaluated the analytical performance of a single-tube assay for multidrug-resistant TB (MDR-TB) on an experimental platform utilising RT-PCR and melting curve analysis that could potentially be operated as a point-of-care (PoC) test in resource-constrained settings with a high burden of TB. Firstly, we developed and evaluated the prototype MDR-TB assay using specimens extracted from well-characterised TB isolates with a variety of distinct rifampicin and isoniazid resistance conferring mutations and nontuberculous Mycobacteria (NTM) strains. Secondly, we validated the experimental platform using 98 clinical sputum samples from pulmonary TB patients collected in high MDR-TB settings. The sensitivity of the platform for TB detection in clinical specimens was 75% for smear-negative and 92.6% for smear-positive sputum samples. The sensitivity of detection for rifampicin and isoniazid resistance was 88.9 and 96.0% and specificity was 87.5 and 100%, respectively. Observed limitations in sensitivity and specificity could be resolved by adjusting the sample preparation methodology and melting curve recognition algorithm. Overall technology could be considered a promising PoC methodology especially in resource-constrained settings based on its combined accuracy, convenience, simplicity, speed, and cost characteristics.

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.

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.

Bioremediation of Synthetic and Industrial Effluents by Aspergillus niger Isolated from Contaminated Soil Following a Sequential Strategy.

The present study aimed to assess and compare the ability to remediate synthetic textile and industrial wastewaters by Fenton treatment, a biological system and sequential treatments using Aspergillus niger (A. niger). All studied treatments were found to be effective in decolorization of the effluents under study. Fenton treatment followed by A. niger showed excellent potential for the maximum decolorization of the synthetic and industrial effluents under study. The effectiveness of sequential treatment was evaluated by water quality parameters such as total organic carbon (TOC), Biological Oxygen Demand (BOD5) and Chemical Oxygen Demand (COD) before and after each treatment. The results indicated that A. niger is an effective candidate for detoxification of textile wastewaters.

Low dose albumin for the prevention of renal impairment following large volume paracentesis in cirrhosis.

OBJECTIVES: To evaluate the effect of low dose Albumin i.e. 4 grams per litre of ascitic fluid after large volume paracentesis (LVP) for the prevention of paracentesis induced circulatory dysfunction (PICD) related renal impairment in cirrhosis. METHODS: Case records of all patients with cirrhosis who underwent LVP from January 12(th), 2011 till December 29(th), 2013 were reviewed. Patients were excluded if they had spontaneous bacterial peritonitis, creatinine >1.5 mg/dl, hepatoma or if volume of ascitic fluid removed was <5 litres. Data including age, gender, cause of cirrhosis, CTP score and volume of ascitic fluid drained were noted. In addition serum creatinine and serum sodium at baseline and one week post paracentesis were recorded. RESULTS: Two hundred and fourteen patients with cirrhosis underwent LVP during the study period. One hundred and thirty nine patients met the inclusion criteria and were analyzed. Patients were divided into two groups based on the amount of albumin given. The amount of albumin given was 25 grams and 50 grams while the volume of ascitic fluid removed were 6.2±1 litres and 10.4±1.5 litres in groups A and B respectively. One hundred and eight patients were in group A while thirty one patients were in group B respectively. Both groups received albumin at a dose of 4 grams per litre of ascitic fluid removed. Mean age in both groups were 53 years. Hepatitis C was the commonest etiology in both the groups, followed by Hepatitis B. More than 70% patients in both the groups were in child class C. Serum creatinine at baseline and one week post LVP was 1.04±0.24 mg/dl and 1.07±0.35 mg/dl in GROUP A while 1.11±0.23 mg/dl and 1.41±0.94 mg/dl in GROUP B. (P value 0.35). Similarly, serum sodium at baseline and one week post LVP was 130 ±5.6 meq/lit and 129.6±5.9 meq/lit in GROUP A while 127.6±5.8 meq/lit and 128±6.2 meq/lit in GROUP B respectively. (P value 0.14). CONCLUSION: This study suggests that 4 grams of albumin per litre of ascitic fluid drained is effective in preventing the PICD related renal impairment following large volume paracentesis in cirrhosis.

Effect of ascorbic acid on the degradation of cyanocobalamin and hydroxocobalamin in aqueous solution: a kinetic study.

The degradation kinetics of 5 × 10(-5) M cyanocobalamin (B12) and hydroxocobalamin (B12b) in the presence of ascorbic acid (AH2) was studied in the pH range of 1.0-8.0. B12 is degraded to B12b which undergoes oxidation to corrin ring cleavage products. B12b alone is directly oxidized to the ring cleavage products. B12 and B12b in degraded solutions were simultaneously assayed by a two-component spectrometric method at 525 and 550 nm without interference from AH2. Both degrade by first-order kinetics and the values of the rate constants at pH 1.0-8.0 range from 0.08 to 1.05 × 10(-5) s(-1) and 0.22-7.62 × 10(-5) s(-1), respectively, in the presence of 0.25 × 10(-3) M AH2. The t 1/2 values of B12 and B12b range from 13.7 to 137.5 h and 2.5-87.5 h, respectively. The second-order rate constants for the interaction of AH2 with B12 and B12b are 0.05-0.28 × 10(-2) and 1.10-30.08 × 10(-2) M(-1) s(-1), respectively, indicating a greater effect of AH2 on B12b compared to that of B12. The k obs-pH profiles for both B12 and B12b show the highest rates of degradation around pH 5. The degradation of B12 and B12b by AH2 is affected by the catalytic effect of phosphate ions on the oxidation of AH2 in the pH range 6.0-8.0.

Reproducible culture and differentiation of mouse embryonic stem cells using an automated microwell platform.

The use of embryonic stem cells (ESCs) and their progeny in high throughput drug discovery and regenerative medicine will require production at scale of well characterized cells at an appropriate level of purity. The adoption of automated bioprocessing techniques offers the possibility to overcome the lack of consistency and high failure rates seen with current manual protocols. To build the case for increased use of automation this work addresses the key question: "can an automated system match the quality of a highly skilled and experienced person working manually?" To answer this we first describe an integrated automation platform designed for the 'hands-free' culture and differentiation of ESCs in microwell formats. Next we outline a framework for the systematic investigation and optimization of key bioprocess variables for the rapid establishment of validatable Standard Operating Procedures (SOPs). Finally the experimental comparison between manual and automated bioprocessing is exemplified by expansion of the murine Oct-4-GiP ESC line over eight sequential passages with their subsequent directed differentiation into neural precursors. Our results show that ESCs can be effectively maintained and differentiated in a highly reproducible manner by the automated system described. Statistical analysis of the results for cell growth over single and multiple passages shows up to a 3-fold improvement in the consistency of cell growth kinetics with automated passaging. The quality of the cells produced was evaluated using a panel of biological markers including cell growth rate and viability, nutrient and metabolite profiles, changes in gene expression and immunocytochemistry. Automated processing of the ESCs had no measurable negative effect on either their pluripotency or their ability to differentiate into the three embryonic germ layers. Equally important is that over a 6-month period of culture without antibiotics in the medium, we have not had any cases of culture contamination. This study thus confirms the benefits of adopting automated bioprocess routes to produce cells for therapy and for use in basic discovery research.

Severe combined immunodeficiency due to adenosine deaminase deficiency.

Severe Combined Immunodeficiency is the term applied to a group of rare genetic disorders characterised by defective or absent T and B cell functions. Patients usually present in first 6 months of life with respiratory/gastrointestinal tract infections and failure to thrive. Among the various types of severe combined immunodeficiency, enzyme deficiencies are relatively less common. We report the case of a 6 years old girl having severe combined immunodeficiency due to adenosine deaminase deficiency.

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.