scholarly journals Computational identification of 4-carboxyglutamate sites to supplement physiological studies using deep learning

2022 ◽  
Vol 12 (1) ◽  
Author(s):  
Sheraz Naseer ◽  
Rao Faizan Ali ◽  
Suliman Mohamed Fati ◽  
Amgad Muneer

AbstractIn biological systems, Glutamic acid is a crucial amino acid which is used in protein biosynthesis. Carboxylation of glutamic acid is a significant post-translational modification which plays important role in blood coagulation by activating prothrombin to thrombin. Contrariwise, 4-carboxy-glutamate is also found to be involved in diseases including plaque atherosclerosis, osteoporosis, mineralized heart valves, bone resorption and serves as biomarker for onset of these diseases. Owing to the pathophysiological significance of 4-carboxyglutamate, its identification is important to better understand pathophysiological systems. The wet lab identification of prospective 4-carboxyglutamate sites is costly, laborious and time consuming due to inherent difficulties of in-vivo, ex-vivo and in vitro experiments. To supplement these experiments, we proposed, implemented, and evaluated a different approach to develop 4-carboxyglutamate site predictors using pseudo amino acid compositions (PseAAC) and deep neural networks (DNNs). Our approach does not require any feature extraction and employs deep neural networks to learn feature representation of peptide sequences and performing classification thereof. Proposed approach is validated using standard performance evaluation metrics. Among different deep neural networks, convolutional neural network-based predictor achieved best scores on independent dataset with accuracy of 94.7%, AuC score of 0.91 and F1-score of 0.874 which shows the promise of proposed approach. The iCarboxE-Deep server is deployed at https://share.streamlit.io/sheraz-n/carboxyglutamate/app.py.

2020 ◽  
Vol 15 ◽  
Author(s):  
Sheraz Naseer ◽  
Waqar Hussain ◽  
Yaser Daanial Khan ◽  
Nouman Rasool

Background: Among all the major Post-translational modification, lipid modifications possess special significance due to their widespread functional importance in eukaryotic cells. There exist multiple types of lipid modifications and Palmitoylation, among them, is one of the broader types of modification, having three different types. The N-Palmitoylation is carried out by attachment of palmitic acid to an N-terminal cysteine. Due to the association of N-Palmitoylation with various biological functions and diseases such as Alzheimer’s and other neurodegenerative diseases, carrying out important processes in the life cycle of various pathogens, its identification is very important. Objective: The in vitro, ex vivo and in vivo identification of Palmitoylation is 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 prediction model for identification of N-Palmitoylation sites in proteins. Method: Proposed prediction model is developed by combining the Chou’s Pseudo Amino Acid Composition (PseAAC) with deep neural networks. We used well-known deep neural networks (DNNs) for both the tasks of learning a feature representation of peptide sequences and developing prediction model to perform classification. Results: Among different DNNs, Gated Recurrent Unit (GRU) based RNN model showed highest scores in terms of accuracy, and all other computed measures, and outperforms all the previously reported predictors. Conclusion: The proposed GRU based RNN model can help identifying N-Palmitoylation in a very efficient and accurate manner which can help scientists understand the mechanism of this modification in proteins.


Symmetry ◽  
2021 ◽  
Vol 13 (4) ◽  
pp. 560
Author(s):  
Sheraz Naseer ◽  
Rao Faizan Ali ◽  
Amgad Muneer ◽  
Suliman Mohamed Fati

Amidation is an important post translational modification where a peptide ends with an amide group (–NH2) rather than carboxyl group (–COOH). These amidated peptides are less sensitive to proteolytic degradation with extended half-life in the bloodstream. Amides are used in different industries like pharmaceuticals, natural products, and biologically active compounds. The in-vivo, ex-vivo, and in-vitro identification of amidation sites is a costly and time-consuming but important task to study the physiochemical properties of amidated peptides. A less costly and efficient alternative is to supplement wet lab experiments with accurate computational models. Hence, an urgent need exists for efficient and accurate computational models to easily identify amidated sites in peptides. In this study, we present a new predictor, based on deep neural networks (DNN) and Pseudo Amino Acid Compositions (PseAAC), to learn efficient, task-specific, and effective representations for valine amidation site identification. Well-known DNN architectures are used in this contribution to learn peptide sequence representations and classify peptide chains. Of all the different DNN based predictors developed in this study, Convolutional neural network-based model showed the best performance surpassing all other DNN based models and reported literature contributions. The proposed model will supplement in-vivo methods and help scientists to determine valine amidation very efficiently and accurately, which in turn will enhance understanding of the valine amidation in different biological processes.


1974 ◽  
Vol 140 (3) ◽  
pp. 549-556 ◽  
Author(s):  
R. L. Boeckx ◽  
K. Dakshinamurti

The effect of administration of biotin to biotin-deficient rats on protein biosynthesis was studied. Biotin treatment resulted in stimulation by more than twofold of amino acid incorporation into protein, both in vivo and in vitro in rat liver, pancreas, intestinal mucosa and skin. Analysis of the products of amino acid incorporation into liver proteins in vivo and in vitro indicated that the synthesis of some proteins was stimulated more than twofold, but others were not stimulated at all. This indicates a specificity in the stimulation of protein synthesis mediated by biotin.


2019 ◽  
Vol 35 (14) ◽  
pp. i501-i509 ◽  
Author(s):  
Hossein Sharifi-Noghabi ◽  
Olga Zolotareva ◽  
Colin C Collins ◽  
Martin Ester

Abstract Motivation Historically, gene expression has been shown to be the most informative data for drug response prediction. Recent evidence suggests that integrating additional omics can improve the prediction accuracy which raises the question of how to integrate the additional omics. Regardless of the integration strategy, clinical utility and translatability are crucial. Thus, we reasoned a multi-omics approach combined with clinical datasets would improve drug response prediction and clinical relevance. Results We propose MOLI, a multi-omics late integration method based on deep neural networks. MOLI takes somatic mutation, copy number aberration and gene expression data as input, and integrates them for drug response prediction. MOLI uses type-specific encoding sub-networks to learn features for each omics type, concatenates them into one representation and optimizes this representation via a combined cost function consisting of a triplet loss and a binary cross-entropy loss. The former makes the representations of responder samples more similar to each other and different from the non-responders, and the latter makes this representation predictive of the response values. We validate MOLI on in vitro and in vivo datasets for five chemotherapy agents and two targeted therapeutics. Compared to state-of-the-art single-omics and early integration multi-omics methods, MOLI achieves higher prediction accuracy in external validations. Moreover, a significant improvement in MOLI’s performance is observed for targeted drugs when training on a pan-drug input, i.e. using all the drugs with the same target compared to training only on drug-specific inputs. MOLI’s high predictive power suggests it may have utility in precision oncology. Availability and implementation https://github.com/hosseinshn/MOLI. Supplementary information Supplementary data are available at Bioinformatics online.


RNA Biology ◽  
2019 ◽  
Vol 16 (8) ◽  
pp. 1044-1054 ◽  
Author(s):  
Haopeng Yu ◽  
Wenjing Meng ◽  
Yuanhui Mao ◽  
Yi Zhang ◽  
Qing Sun ◽  
...  

2016 ◽  
Vol 11 ◽  
pp. S55-S60
Author(s):  
Mingxian Shi ◽  
Rui Chen ◽  
Cen Guo ◽  
Li Gao

In order to study the influence of amino acid neurotransmitters secreted by the nerve cells after ketamine treatment, the nerve cells were cultured in vitro to exclude the interference of other factors in vivo and treated with three different doses of ketamine (1, 3 and 5 µg/mL). Then, the concentration of neuronal amino acid neurotransmitters was examined at 0, 15, 30, 45, 60, 90, 120 min after treatment. The trends of each amino acid concentration after ketamine treatment were nearly the same among the different treatment doses. After 15 min of adapting time, ketamine decreased the excitatory amino acid glutamic acid and aspartic acid concentration, and increased the concentration of the inhibitory amino acid glycine. Their concentrations showed a tendency to return approximately to the original level after 120 min. 


2016 ◽  
Vol 81 (8) ◽  
pp. 892-898 ◽  
Author(s):  
V. Y. Brodsky ◽  
L. A. Malchenko ◽  
D. S. Konchenko ◽  
N. D. Zvezdina ◽  
T. K. Dubovaya

2019 ◽  
Author(s):  
Hossein Sharifi-Noghabi ◽  
Olga Zolotareva ◽  
Colin C. Collins ◽  
Martin Ester

AbstractMotivationHistorically, gene expression has been shown to be the most informative data for drug response prediction. Recent evidence suggests that integrating additional omics can improve the prediction accuracy which raises the question of how to integrate the additional omics. Regardless of the integration strategy, clinical utility and translatability are crucial. Thus, we reasoned a multi-omics approach combined with clinical datasets would improve drug response prediction and clinical relevance.ResultsWe propose MOLI, a Multi-Omics Late Integration method based on deep neural networks. MOLI takes somatic mutation, copy number aberration, and gene expression data as input, and integrates them for drug response prediction. MOLI uses type-specific encoding subnetworks to learn features for each omics type, concatenates them into one representation and optimizes this representation via a combined cost function consisting of a triplet loss and a binary cross-entropy loss. The former makes the representations of responder samples more similar to each and different from the non-responders, and the latter makes this representation predictive of the response values. We validate MOLI on in vitro and in vivo datasets for five chemotherapy agents and two targeted therapeutics. Compared to state-of-the-art single-omics and early integration multi-omics methods, MOLI achieves higher prediction accuracy in external validations. Moreover, a significant improvement in MOLI’s performance is observed for targeted drugs when training on a pan-drug input, i.e. using all the drugs with the same target compared to training only on drug-specific inputs. MOLI’s high predictive power suggests it may have utility in precision oncology.Availability of the implemented codeshttps://github.com/hosseinshn/[email protected] and [email protected]


Blood ◽  
2006 ◽  
Vol 108 (11) ◽  
pp. 4283-4283
Author(s):  
Patricia Martín-Jiménez ◽  
Ramón García-Sanz ◽  
Enrique Ocio ◽  
María E. Sarasquete ◽  
Ana Balanzategui ◽  
...  

Abstract Waldenström Macroglobulinemia (WM) is characterized by monoclonal IgM paraprotein and bone marrow (BM) infiltration by lymphoplasmacytic lymphoma. The normal counterpart of WM malignant cell seems to be a post germinal centre IgM B-cell, which tumoral transformation occurs after cessation of somatic mutation (SM) but prior to Class switch recombination (CSR). However, recently has been reported that CSR can be possible “ex-vivo”, since clonotypic transcripts encoding post-switch isotypes have been observed in some WM cells cultured with CD40L/IL-40. However, this process has not been shown to occur “in vivo” until now. #3754, a 51-year-old woman, was diagnosed in 2001 of WM with a M-IgM spike (46 g/L), anemia (Hb 9·6 g/dL), 76% lymphoplasmacytic monoclonal B-cells in BM and normal cytogenetics. In April 2005, an important IgG increase was observed (23 g/L). Immunofixation demonstrated an IgG-k paraprotein in the mid g-region and a monoclonal IgM-k paraprotein at the b-region corresponding to the two monoclonal peaks detected on serum electrophoresis. After 6-mercaptoethanol treatment, a single band was seen at the line stained with kappa, suggesting the presence of a single clone. Other causes of IgG monoclonal components were excluded considering clinical factors, immunophenotype analyses (San Miguel et al, 2003), quantity of DNA and cell cycle analyses (Ocio et al, 2005). However, the definitive proof for a unique monoclonal population was provided through molecular analysis. A single clonotypic rearrangement was detected by amplifying the complete VDJH fragment at diagnosis moment, according to the protocol describes in Biomed II (Leukemia2003; 17.2257–2317). Method describes from Billadeu et al (Billadeau et al, 1993) was used for isotype identification. So, cDNA monoclonal amplification was observed at tubes corresponding to Cm, Cd and Cg. All monoclonal PCR products were directly sequenced in an automated ABI 377 DNA sequencer. VH, DH & JH segments identification, as well as SH recognition was made using the V-BASE sequence directory alignment program, and the CH regions were compared at BLAST. All sequences obtained showed the same clonotypic CDR3 sequence (VH4-59/JH6) as well as the same SH (10,75%) pattern that monoclonal amplification at diagnosis, indicating the presence of the same clone at that moment (Figure 1). In conclusion, we report for the first time a WM case in which tumor cells were able to carry out CSR, showing IgG and IgM clonotypic amplification, as well as producing both paraprotein components. This constitutes the first in vivo demonstration that CSR is possible in WM cells, and are able to develop a fully functional isotype class switch recombination not only in vitro but also in vivo. Figure 1: Deduced amino acid sequence of tumor-derived VDJH gene with the three heavy chain isotypes (A: Cμ, B: Cδ C: Cγ). Sequences indicates the somatic mulation pattern. Comparison for WM are made with the closest germline VH gone; uppercase, replacement (R) mutation; lower case, silent (S) mutation. Each mutation was defined by nuclieotide exchanges in a single codon, with successive mutations leading in some cases to 2 or 3 distinct R or S events. These are shown as aligned amino acid changes at specific sites. Figure 1:. Deduced amino acid sequence of tumor-derived VDJH gene with the three heavy chain isotypes (A: Cμ, B: Cδ C: Cγ). Sequences indicates the somatic mulation pattern. Comparison for WM are made with the closest germline VH gone; uppercase, replacement (R) mutation; lower case, silent (S) mutation. Each mutation was defined by nuclieotide exchanges in a single codon, with successive mutations leading in some cases to 2 or 3 distinct R or S events. These are shown as aligned amino acid changes at specific sites.


2021 ◽  
Vol 15 (8) ◽  
pp. 937-948
Author(s):  
Sheraz Naseer ◽  
Waqar Hussain ◽  
Yaser Daanial Khan ◽  
Nouman Rasool

Background: Among all the major post-translational modifications, amidation seems to be a small change, where a peptide ends with an amide group (-NH 2), not a carboxyl group (-COOH). Thus, to study their physicochemical properties, identification of the amidation mechanism is very important. However, the in vitro, ex vivo and in vivo identification can be laborious, time-taking and costly. There is a dire need for an efficient and accurate computational model to help researchers and biologists identifying these sites, in an easy manner. Objectives: Herein, we propose a novel predictor for the identification of arginine amide (R-Amide) sites in proteins, by integrating the Chou’s Pseudo Amino Acid Composition (PseAAC) with deep features. Methods: We use well-known DNNs for both the tasks of learning a feature representation of peptide sequences and performing classifications. Methods: We use well-known DNNs for both the tasks of learning a feature representation of peptide sequences and performing classifications. Results: Among different DNNs, CNN showed the highest scores in terms of accuracy, and all other computed measures outperformed all the previously reported predictors. Conclusions: Based on these results, it is concluded that the proposed model can help identify arginine amidation in a very efficient and accurate manner, which can help scientists understand the mechanism of this modification in proteins.


Sign in / Sign up

Export Citation Format

Share Document