Free-Energy Landscape and Rate Estimation of the Aromatic Ring Flips in Basic Pancreatic Trypsin Inhibitors Using Metadynamics.

Aromatic side chains (phenylalanine and tyrosine) of a protein flip by 180° around the Cß-Cγ axis (χ2 dihedral of the side chain), producing two symmetry-equivalent states. The study of ring flip dynamics with nuclear magnetic resonance (NMR) experiments helps to understand local conformational fluctuations. Ring flips are categorized as slow (milliseconds and onward) or fast (nanoseconds to near milliseconds) based on timescales accessible to NMR experiments. In this study, we investigated the ability of the infrequent metadynamics approach to estimate the flip rate and discriminate between slow and fast ring flips for eight individual aromatic side chains (F4, Y10, Y21, F22, Y23, F33, Y35, and F45) of the basic pancreatic trypsin inhibitor. Well-tempered metadynamics simulations were performed to estimate the ring-flipping free-energy surfaces for all eight aromatic residues. The results indicate that χ2 as a standalone collective variable (CV) is not sufficient to obtain computationally consistent results. Inclusion of a complementary CV, such as χ1(Cα-Cß), solved the problem for most residues and enabled us to classify fast and slow ring flips. This indicates the importance of librational motions in ring flips. Multiple pathways and mechanisms were observed for residues F4, Y10, and F22. Recrossing events were observed for residues F22 and F33, indicating a possible role of friction effects in ring flipping. The results demonstrate the successful application of infrequent metadynamics to estimate ring flip rates and identify certain limitations of the approach.

Lipid exchange in crystal-confined fatty acid binding proteins: X-ray evidence and molecular dynamics explanation.

Fatty acid binding proteins (FABPs) are responsible for the long-chain fatty acids (FAs) transport inside the cell. However, despite the years, since their structure is known and the many studies published, there is no definitive answer about the stages of the lipid entry-exit mechanism. Their structure forms a ß -barrel of 10 anti-parallel strands with a cap in a helix-turn-helix motif, and there is some consensus on the role of the so-called portal region, involving the second α -helix from the cap ( α 2), ß C- ß D, and ß E- ß F turns in FAs exchange. To test the idea of a lid that opens, we performed a soaking experiment on an h-FABP crystal in which the cap is part of the packing contacts, and its movement is strongly restricted. Even in these conditions, we observed the replacement of palmitic acid by 2-Bromohexadecanoic acid (Br-palmitic acid). Our MD simulations reveal a two-step lipid entry process: (i) The travel of the lipid head through the cavity in the order of tens of nanoseconds, and (ii) The accommodation of its hydrophobic tail in hundreds to thousands of nanoseconds. We observed this even in the cases in which the FAs enter the cavity by their tail. During this process, the FAs do not follow a single trajectory, but multiple ones through which they get into the protein cavity. Thanks to the complementary views between experiment and simulation, we can give an approach to a mechanistic view of the exchange process.

DeepBindGCN: Integrating Molecular Vector Representation with Graph Convolutional Neural Networks for Protein-Ligand Interaction Prediction.

The core of large-scale drug virtual screening is to select the binders accurately and efficiently with high affinity from large libraries of small molecules in which non-binders are usually dominant. The binding affinity is significantly influenced by the protein pocket, ligand spatial information, and residue types/atom types. Here, we used the pocket residues or ligand atoms as the nodes and constructed edges with the neighboring information to comprehensively represent the protein pocket or ligand information. Moreover, the model with pre-trained molecular vectors performed better than the one-hot representation. The main advantage of DeepBindGCN is that it is independent of docking conformation, and concisely keeps the spatial information and physical-chemical features. Using TIPE3 and PD-L1 dimer as proof-of-concept examples, we proposed a screening pipeline integrating DeepBindGCN and other methods to identify strong-binding-affinity compounds. It is the first time a non-complex-dependent model has achieved a root mean square error (RMSE) value of 1.4190 and Pearson r value of 0.7584 in the PDBbind v.2016 core set, respectively, thereby showing a comparable prediction power with the state-of-the-art affinity prediction models that rely upon the 3D complex. DeepBindGCN provides a powerful tool to predict the protein-ligand interaction and can be used in many important large-scale virtual screening application scenarios.

Sparse pseudocontact shift NMR data obtained from a non-canonical amino acid-linked lanthanide tag improves integral membrane protein structure prediction.

A single experimental method alone often fails to provide the resolution, accuracy, and coverage needed to model integral membrane proteins (IMPs). Integrating computation with experimental data is a powerful approach to supplement missing structural information with atomic detail. We combine RosettaNMR with experimentally-derived paramagnetic NMR restraints to guide membrane protein structure prediction. We demonstrate this approach using the disulfide bond formation protein B (DsbB), an α-helical IMP. Here, we attached a cyclen-based paramagnetic lanthanide tag to an engineered non-canonical amino acid (ncAA) using a copper-catalyzed azide-alkyne cycloaddition (CuAAC) click chemistry reaction. Using this tagging strategy, we collected 203 backbone HN pseudocontact shifts (PCSs) for three different labeling sites and used these as input to guide de novo membrane protein structure prediction protocols in Rosetta. We find that this sparse PCS dataset combined with 44 long-range NOEs as restraints in our calculations improves structure prediction of DsbB by enhancements in model accuracy, sampling, and scoring. The inclusion of this PCS dataset improved the Cα-RMSD transmembrane segment values of the best-scoring and best-RMSD models from 9.57 Å and 3.06 Å (no NMR data) to 5.73 Å and 2.18 Å, respectively.

Interpreting Transient Interactions of Intrinsically Disordered Proteins.

The flexible nature of intrinsically disordered proteins (IDPs) gives rise to a conformational ensemble with a diverse set of conformations. The simplest way to describe this ensemble is through a homopolymer model without any specific interactions. However, there has been growing evidence that the conformational properties of IDPs and their relevant functions can be affected by transient interactions between specific and even nonlocal pairs of amino acids. Interpreting these interactions from experimental methods, each of which is most sensitive to a different distance regime referred to as probing length, remains a challenging and unsolved problem. Here, we first show that transient interactions can be realized between short fragments of charged amino acids by generating conformational ensembles using model disordered peptides and coarse-grained simulations. Using these ensembles, we investigate how sensitive different types of experimental measurements are to the presence of transient interactions. We find methods with shorter probing lengths to be more appropriate for detecting these transient interactions, but one experimental method is not sufficient due to the existence of other weak interactions typically seen in IDPs. Finally, we develop an adjusted polymer model with an additional short-distance peak which can robustly reproduce the distance distribution function from two experimental measurements with complementary short and long probing lengths. This new model can suggest whether a homopolymer model is insufficient for describing a specific IDP and meets the challenge of quantitatively identifying specific, transient interactions from a background of nonspecific, weak interactions.

High-accuracy protein model quality assessment using attention graph neural networks.

Great improvement has been brought to protein tertiary structure prediction through deep learning. It is important but very challenging to accurately rank and score decoy structures predicted by different models. CASP14 results show that existing quality assessment (QA) approaches lag behind the development of protein structure prediction methods, where almost all existing QA models degrade in accuracy when the target is a decoy of high quality. How to give an accurate assessment to high-accuracy decoys is particularly useful with the available of accurate structure prediction methods. Here we propose a fast and effective single-model QA method, QATEN, which can evaluate decoys only by their topological characteristics and atomic types. Our model uses graph neural networks and attention mechanisms to evaluate global and amino acid level scores, and uses specific loss functions to constrain the network to focus more on high-precision decoys and protein domains. On the CASP14 evaluation decoys, QATEN performs better than other QA models under all correlation coefficients when targeting average LDDT. QATEN shows promising performance when considering only high-accuracy decoys. Compared to the embedded evaluation modules of predicted ${C}_{\alpha^{-}} RMSD$ (pRMSD) in RosettaFold and predicted LDDT (pLDDT) in AlphaFold2, QATEN is complementary and capable of achieving better evaluation on some decoy structures generated by AlphaFold2 and RosettaFold. These results suggest that the new QATEN approach can be used as a reliable independent assessment algorithm for high-accuracy protein structure decoys.

Conformational Dynamics of Phytoglobin BvPgb1.2 from Beta vulgaris ssp. vulgaris.

Plant hemoglobins, often referred to as phytoglobins, play important roles in abiotic stress tolerance. Several essential small physiological metabolites can be bound to these heme proteins. In addition, phytoglobins can catalyze a range of different oxidative reactions in vivo. These proteins are often oligomeric, but the degree and relevance of subunit interactions are largely unknown. In this study, we delineate which residues are involved in dimer formation of a sugar beet phytoglobin type 1.2 (BvPgb1.2) using NMR relaxation experiments. E. coli cells harboring a phytoglobin expression vector were cultivated in isotope-labeled (2H, 13C and 15N) M9 medium. The triple-labeled protein was purified to homogeneity using two chromatographic steps. Two forms of BvPgb1.2 were examined, the oxy-form and the more stable cyanide-form. Using three-dimensional triple-resonance NMR experiments, sequence-specific assignments for CN-bound BvPgb1.2 were achieved for 137 backbone amide cross-peaks in the 1H-15N TROSY spectrum, which amounts to 83% of the total number of 165 expected cross-peaks. A large proportion of the non-assigned residues are located in α-helixes G and H, which are proposed to be involved in protein dimerization. Such knowledge around dimer formation will be instrumental for developing a better understanding of phytoglobins' roles in planta.

Coevolution and smFRET Enhances Conformation Sampling and FRET Experimental Design in Tandem PDZ1-2 Proteins.

The structural flexibility of proteins is crucial for their functions. Many experimental and computational approaches can probe protein dynamics across a range of time and length-scales. Integrative approaches synthesize the complementary outputs of these techniques and provide a comprehensive view of the dynamic conformational space of proteins, including the functionally relevant limiting conformational states and transition pathways between them. Here, we introduce an integrative paradigm to model the conformational states of multidomain proteins. As a model system, we use the first two tandem PDZ domains of postsynaptic density protein 95. First, we utilize available sequence information collected from genomic databases to identify potential amino acid interactions in the PDZ1-2 tandem that underlie modeling of the functionally relevant conformations maintained through evolution. This was accomplished through combination of coarse-grained structural modeling with outputs from direct coupling analysis measuring amino acid coevolution, a hybrid approach called SBM+DCA. We recapitulated five distinct, experimentally derived PDZ1-2 tandem conformations. In addition, SBM+DCA unveiled an unidentified, twisted conformation of the PDZ1-2 tandem. Finally, we implemented an integrative framework for the design of single-molecule Förster resonance energy transfer (smFRET) experiments incorporating the outputs of SBM+DCA with simulated FRET observables. This resulting FRET network is designed to mutually resolve the predicted limiting state conformations through global analysis. Using simulated FRET observables, we demonstrate that structural modeling with the newly designed FRET network is expected to outperform a previously used empirical FRET network at resolving all states simultaneously. Integrative approaches to experimental design have the potential to provide a new level of detail in characterizing the evolutionarily conserved conformational landscapes of proteins, and thus new insights into functional relevance of protein dynamics in biological function.

Advances of targeting the YAP/TAZ-TEAD complex in the hippo pathway for the treatment of cancers.

The Hippo pathway is an evolutionarily conserved signaling pathway that plays critical roles in the tumorigenesis and progression of breast cancer, oral cancer, rectal cancer, colloid cancer, and so on. YAP/TAZ-TEAD complex is a key knot in the Hippo pathway regulating cell proliferation and stem cell functions. Activation or overexpression of this complex has been proved to lead to cell transformation, proliferation and eventually cancerization. In this review, the association between the alterations of hippo pathway and tumorigenesis of various cancer had been elucidated. The structural basis of YAP/TAZ-TEAD complex is analyzed, and the targeting inhibitors are summarized within the medicinal chemistry classification. Moreover, we have also discussed the clinical status and current challenges of these drug candidates, and provide guidance for the future development of inhibitors targeting this pathway, especially YAP/TAZ-TEAD complex.

Protein Function Analysis through Machine Learning.

Machine learning (ML) has been an important arsenal in computational biology used to elucidate protein function for decades. With the recent burgeoning of novel ML methods and applications, new ML approaches have been incorporated into many areas of computational biology dealing with protein function. We examine how ML has been integrated into a wide range of computational models to improve prediction accuracy and gain a better understanding of protein function. The applications discussed are protein structure prediction, protein engineering using sequence modifications to achieve stability and druggability characteristics, molecular docking in terms of protein-ligand binding, including allosteric effects, protein-protein interactions and protein-centric drug discovery. To quantify the mechanisms underlying protein function, a holistic approach that takes structure, flexibility, stability, and dynamics into account is required, as these aspects become inseparable through their interdependence. Another key component of protein function is conformational dynamics, which often manifest as protein kinetics. Computational methods that use ML to generate representative conformational ensembles and quantify differences in conformational ensembles important for function are included in this review. Future opportunities are highlighted for each of these topics.

Substrate size-dependent conformational changes of bacterial pectin-binding protein crucial for chemotaxis and assimilation.

Gram-negative Sphingomonas sp. strain A1 exhibits positive chemotaxis toward acidic polysaccharide pectin. SPH1118 has been identified as a pectin-binding protein involved in both pectin chemotaxis and assimilation. Here we show tertiary structures of SPH1118 with six different conformations as determined by X-ray crystallography. SPH1118 consisted of two domains with a large cleft between the domains and substrates bound to positively charged and aromatic residues in the cleft through hydrogen bond and stacking interactions. Substrate-free SPH1118 adopted three different conformations in the open form. On the other hand, the two domains were closed in substrate-bound form and the domain closure ratio was changed in response to the substrate size, suggesting that the conformational change upon binding to the substrate triggered the expression of pectin chemotaxis and assimilation. This study first clarified that the solute-binding protein with dual functions recognized the substrate through flexible conformational changes in response to the substrate size.

Pectinase from Microorganisms and Its Industrial Applications.

The utilization of microbial pectinase in different industries has been increased in its world demand. The major sources of pectinase are microorganisms mainly bacteria, fungi and yeast. The utilization of low-cost agro-industrial wastes as substrates has been preferable in pectinase production. Pectinase production faced various parameters optimization constraints such as temperature, pH and production times which are the main factors in pectinase production. The pectinase enzyme is getting attention due to its several advantages; hence, it needs to be explored further to take its maximum advantage in different industries. This review discusses the pectin substance structure, substrate for pectinase production, factors influencing pectinase production, the industrial application of microbial pectinase and also discusses challenges and future opportunities of applying microbial pectinase in industry.

Rationalisation of Antifungal Properties of α-Helical Pore-Forming Peptide, Mastoparan B.

The high mortality associated with invasive fungal infections, narrow spectrum of available antifungals, and increasing evolution of antifungal resistance necessitate the development of alternative therapies. Host defense peptides are regarded as the first line of defense against microbial invasion in both vertebrates and invertebrates. In this work, we investigated the effectiveness of four naturally occurring pore-forming antimicrobial peptides (melittin, magainin 2, cecropin A, and mastoparan B) against a panel of clinically relevant pathogens, including Candida albicans, Candida parapsilosis, Candida tropicalis, and Candida glabrata. We present data on the antifungal activities of the four pore-forming peptides, assessed with descriptive statistics, and their cytocompatibility with cultured human cells. Among the four peptides, mastoparan B (MB) displayed potent antifungal activity, whereas cecropin A was the least potent. We show that MB susceptibility of phylogenetically distant non-candida albicans can vary and be described by different intrinsic physicochemical parameters of pore-forming α-helical peptides. These findings have potential therapeutic implications for the design and development of safe antifungal peptide-based drugs.

Hepatitis C Virus NS3/4A Inhibition and Host Immunomodulation by Tannins from Terminalia chebula: A Structural Perspective.

Terminalia chebula Retz. forms a key component of traditional folk medicine and is also reported to possess antihepatitis C virus (HCV) and immunomodulatory activities. However, information on the intermolecular interactions of phytochemicals from this plant with HCV and human proteins are yet to be established. Thus, by this current study, we investigated the HCV NS3/4A inhibitory and host immune-modulatory activity of phytocompounds from T. chebula through in silico strategies involving network pharmacology and structural bioinformatics techniques. To start with, the phytochemical dataset of T. chebula was curated from biological databases and the published literature. Further, the target ability of the phytocompounds was predicted using BindingDB for both HCV NS3/4A and other probable host targets involved in the immune system. Further, the identified targets were docked to the phytochemical dataset using AutoDock Vina executed through the POAP pipeline. The resultant docked complexes with significant binding energy were subjected to 50 ns molecular dynamics (MD) simulation in order to infer the stability of complex formation. During network pharmacology analysis, the gene set pathway enrichment of host targets was performed using the STRING and Reactome pathway databases. Further, the biological network among compounds, proteins, and pathways was constructed using Cytoscape 3.6.1. Furthermore, the druglikeness, side effects, and toxicity of the phytocompounds were also predicted using the MolSoft, ADVERpred, and PreADMET methods, respectively. Out of 41 selected compounds, 10 were predicted to target HCV NS3/4A and also to possess druglike and nontoxic properties. Among these 10 molecules, Chebulagic acid and 1,2,3,4,6-Pentagalloyl glucose exhibited potent HCV NS3/4A inhibitory activity, as these scored a lowest binding energy (BE) of -8.6 kcal/mol and -7.7 kcal/mol with 11 and 20 intermolecular interactions with active site residues, respectively. These findings are highly comparable with Asunaprevir (known inhibitor of HCV NS3/4A), which scored a BE of -7.4 kcal/mol with 20 key intermolecular interactions. MD studies also strongly suggest that chebulagic acid and 1,2,3,4,6-Pentagalloyl glucose as promising leads, as these molecules showed stable binding during 50 ns of production run. Further, the gene set enrichment and network analysis of 18 protein targets prioritized 10 compounds and were predicted to potentially modulate the host immune system, hemostasis, cytokine levels, interleukins signaling pathways, and platelet aggregation. On overall analysis, this present study predicts that tannins from T. chebula have a potential HCV NS3/4A inhibitory and host immune-modulatory activity. However, further experimental studies are required to confirm the efficacies.

DisEnrich: database of enriched regions in human dark proteome.

MOTIVATION: Intrinsically disordered proteins (IDPs) are involved in numerous processes crucial for living organisms. Bias in amino acid composition of these proteins determines their unique biophysical and functional features. Distinct intrinsically disordered regions (IDRs) with compositional bias play different important roles in various biological processes. IDRs enriched in particular amino acids in human proteome have not been described consistently. RESULTS: We developed DisEnrich-the database of human proteome IDRs that are significantly enriched in particular amino acids. Each human protein is described using Gene Ontology (GO) function terms, disorder prediction for the full-length sequence using three methods, enriched IDR composition and ranks of human proteins with similar enriched IDRs. Distribution analysis of enriched IDRs among broad functional categories revealed significant overrepresentation of R- and Y-enriched IDRs in metabolic and enzymatic activities and F-enriched IDRs in transport. About 75% of functional categories contain IDPs with IDRs significantly enriched in hydrophobic residues that are important for protein-protein interactions. AVAILABILITY AND IMPLEMENTATION: The database is available at http://prodata.swmed.edu/DisEnrichDB/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics Advances online.

Ephedrae Herba and Cinnamomi Cortex interactions with G glycoprotein inhibit respiratory syncytial virus infectivity.

Although respiratory syncytial virus (RSV) is a major cause of respiratory tract infection in children, no effective therapies are available. Recently, RSV G, the attachment glycoprotein, has become a major focus in the development of therapeutic strategies against RSV infection. Treatment of RSV-infected cultured cells with maoto, a traditional herbal medicine for acute febrile diseases, significantly reduced the viral RNA and titers. RSV attachment to the cell surface was inhibited both in the presence of maoto and when RSV particles were pre-treated with maoto. We demonstrated that maoto components, Ephedrae Herba (EH) and Cinnamomi Cortex (CC), specifically interacted with the central conserved domain (CCD) of G protein, and also found that this interaction blocked viral attachment to the cellular receptor CX3CR1. Genetic mutation of CX3C motif on the CCD, the epitope for CX3CR1, decreased the binding capacity to EH and CC, suggesting that CX3C motif was the target for EH and CC. Finally, oral administration of maoto for five days to RSV-infected mice significantly reduced the lung viral titers. These experiments clearly showed the anti-RSV activity of EH and CC mixed in maoto. Taken together, this study provides insights for the rational design of therapies against RSV infection.

Structural biology of SARS-CoV-2: open the door for novel therapies.

Severe Acute Respiratory Syndrome Coronavirus-2 (SARS-CoV-2) is the causative agent of the pandemic disease COVID-19, which is so far without efficacious treatment. The discovery of therapy reagents for treating COVID-19 are urgently needed, and the structures of the potential drug-target proteins in the viral life cycle are particularly important. SARS-CoV-2, a member of the Orthocoronavirinae subfamily containing the largest RNA genome, encodes 29 proteins including nonstructural, structural and accessory proteins which are involved in viral adsorption, entry and uncoating, nucleic acid replication and transcription, assembly and release, etc. These proteins individually act as a partner of the replication machinery or involved in forming the complexes with host cellular factors to participate in the essential physiological activities. This review summarizes the representative structures and typically potential therapy agents that target SARS-CoV-2 or some critical proteins for viral pathogenesis, providing insights into the mechanisms underlying viral infection, prevention of infection, and treatment. Indeed, these studies open the door for COVID therapies, leading to ways to prevent and treat COVID-19, especially, treatment of the disease caused by the viral variants are imperative.

Synthesis of novel thiazolyl hydrazone derivatives as potent dual monoamine oxidase-aromatase inhibitors.

The inhibitory effects of 2-thiazolyl hydrazones on monoamine oxidase enzymes are known for a long time. In this study, a new series of 2-thiazolyl hydrazone derivatives were synthesized starting from 6-methoxy-2-naphthaldehyde. All of the synthesized compounds were investigated in terms of their monoamine oxidase (MAO) inhibitory effects and significant results were found. The results showed that compound 2j potently inhibited MAO-A and MAO-B, while compound 2t strongly and selectively inhibited MAO-B compared to standard drugs. Compounds 2k and 2q exhibited selective and satisfying inhibition on MAO-B. In the aromatase inhibition studies of the compounds, it was determined that compounds 2q and 2u had high inhibitory properties. Molecular docking studies on MAO-A, MAO-B, and aromatase enzymes were carried out for the aforementioned compounds. Additionally, molecular dynamics simulation was studied for compound 2q on MAO-B and aromatase complexes. Finally, the Field-based QSAR study was developed and the structure-activity relationship (SAR) was explained. For the first time, dual inhibitors on MAO and aromatase enzyme were investigated together. The aim of this approach is for finding the potential agents that do not cause the cognitive disorders and may even treat neurodegenerative symptoms, thus, the aim was reached successfully.

SPOP-mutant prostate cancer: Translating fundamental biology into patient care.

Comprehensive cancer genome studies have revealed genetically-defined subtypes of prostate cancer with distinct truncal driver mutations. Because prostate cancer has been largely seen as a rather uniform disease, the clinical significance of this discovery remained largely obscure. However, recent findings imply distinct biological features and therapeutic vulnerabilities linked to specific truncal mutations. Here we review our current understanding of prostate cancers harboring recurrent point mutations in the ubiquitin ligase adaptor protein SPOP and discuss opportunities for future clinical translation. More specifically, activation of the androgen receptor (AR) signaling emerges as the key oncogenic pathway. SPOP-mutant prostate cancer patients respond to AR inhibition in various clinical settings. Molecular insights on how mutant SPOP promotes tumorigenesis may open more specific therapeutic avenues which, in combination with conventional AR-targeting agents, could improve the outcome of patients with SPOP-mutant prostate cancer.

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

In 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 .