More Like this

1. DTL-DephosSite: Deep Transfer Learning Based Approach to Predict Dephosphorylation Sites

   Chaudhari M, Thapa ( June 2021 , Frontiers in cell and developmental biology)

   null (Ed.)

   Phosphorylation, which is mediated by protein kinases and opposed by protein phosphatases, is an important post-translational modification that regulates many cellular processes, including cellular metabolism, cell migration, and cell division. Due to its essential role in cellular physiology, a great deal of attention has been devoted to identifying sites of phosphorylation on cellular proteins and understanding how modification of these sites affects their cellular functions. This has led to the development of several computational methods designed to predict sites of phosphorylation based on a protein’s primary amino acid sequence. In contrast, much less attention has been paid to dephosphorylation and its role in regulating the phosphorylation status of proteins inside cells. Indeed, to date, dephosphorylation site prediction tools have been restricted to a few tyrosine phosphatases. To fill this knowledge gap, we have employed a transfer learning strategy to develop a deep learning-based model to predict sites that are likely to be dephosphorylated. Based on independent test results, our model, which we termed DTL-DephosSite, achieved efficiency scores for phosphoserine/phosphothreonine residues of 84%, 84% and 0.68 with respect to sensitivity (SN), specificity (SP) and Matthew’s correlation coefficient (MCC). Similarly, DTL-DephosSite exhibited efficiency scores of 75%, 88% and 0.64 for phosphotyrosine residues with respect to SN, SP, and MCC. 

   more » « less
2. DTL-DephosSite: Deep Transfer Learning Based Approach to Predict Dephosphorylation Sites

   https://doi.org/10.3389/fcell.2021.662983  

   Chaudhari, Meenal ; Thapa, Niraj ; Ismail, Hamid ; Chopade, Sandhya ; Caragea, Doina ; Köhn, Maja ; Newman, Robert H. ; KC, Dukka B. ( June 2021 , Frontiers in Cell and Developmental Biology)

   null (Ed.)

   Phosphorylation, which is mediated by protein kinases and opposed by protein phosphatases, is an important post-translational modification that regulates many cellular processes, including cellular metabolism, cell migration, and cell division. Due to its essential role in cellular physiology, a great deal of attention has been devoted to identifying sites of phosphorylation on cellular proteins and understanding how modification of these sites affects their cellular functions. This has led to the development of several computational methods designed to predict sites of phosphorylation based on a protein’s primary amino acid sequence. In contrast, much less attention has been paid to dephosphorylation and its role in regulating the phosphorylation status of proteins inside cells. Indeed, to date, dephosphorylation site prediction tools have been restricted to a few tyrosine phosphatases. To fill this knowledge gap, we have employed a transfer learning strategy to develop a deep learning-based model to predict sites that are likely to be dephosphorylated. Based on independent test results, our model, which we termed DTL-DephosSite, achieved efficiency scores for phosphoserine/phosphothreonine residues of 84%, 84% and 0.68 with respect to sensitivity (SN), specificity (SP) and Matthew’s correlation coefficient (MCC). Similarly, DTL-DephosSite exhibited efficiency scores of 75%, 88% and 0.64 for phosphotyrosine residues with respect to SN, SP, and MCC. 

   more » « less
3. Differentiating aspartic acid isomers and epimers with charge transfer dissociation mass spectrometry (CTD-MS)

   https://doi.org/10.1039/D1AN02279B  

   Edwards, Halle M. ; Wu, Hoi-Ting ; Julian, Ryan R. ; Jackson, Glen P. ( March 2022 , The Analyst)

   The ability to understand the function of a protein often relies on knowledge about its detailed structure. Sometimes, seemingly insignificant changes in the primary structure of a protein, like an amino acid substitution, can completely disrupt a protein's function. Long-lived proteins (LLPs), which can be found in critical areas of the human body, like the brain and eye, are especially susceptible to primary sequence alterations in the form of isomerization and epimerization. Because long-lived proteins do not have the corrective regeneration capabilities of most other proteins, points of isomerism and epimerization that accumulate within the proteins can severely hamper their functions and can lead to serious diseases like Alzheimer's disease, cancer and cataracts. Whereas tandem mass spectrometry (MS/MS) in the form of collision-induced dissociation (CID) generally excels at peptide characterization, MS/MS often struggles to pinpoint modifications within LLPs, especially when the differences are only isomeric or epimeric in nature. One of the most prevalent and difficult-to-identify modifications is that of aspartic acid between its four isomeric forms: l -Asp, l -isoAsp, d -Asp, and d -isoAsp. In this study, peptides containing isomers of Asp were analyzed by charge transfer dissociation (CTD) mass spectrometry to identify spectral features that could discriminate between the different isomers. For the four isomers of Asp in three model peptides, CTD produced diagnostic ions of the form c n +57 on the N-terminal side of iso-Asp residues, but not on the N-terminal side of Asp residues. Using CTD, the l - and d forms of Asp and isoAsp could also be differentiated based on the relative abundance of y - and z ions on the C-terminal side of Asp residues. Differentiation was accomplished through a chiral discrimination factor, R , which compares an ion ratio in a spectrum of one epimer or isomer to the same ion ratio in the spectrum of a different epimer or isomer. The R values obtained using CTD are as robust and statistically significant as other fragmentation techniques, like radical directed dissociation (RDD). In summary, the extent of backbone and side-chain fragments produced by CTD enabled the differentiation of isomers and epimers of Asp in a variety of peptides. 

   more » « less
4. Partner‐specific prediction of RNA‐binding residues in proteins: A critical assessment

   https://doi.org/10.1002/prot.25639  

   Jung, Yong ; EL‐Manzalawy, Yasser ; Dobbs, Drena ; Honavar, Vasant G. ( December 2018 , Proteins: Structure, Function, and Bioinformatics)

   RNA‐protein interactions play essential roles in regulating gene expression. While some RNA‐protein interactions are “specific”, that is, the RNA‐binding proteins preferentially bind to particular RNA sequence or structural motifs, others are “non‐RNA specific.” Deciphering the protein‐RNA recognition code is essential for comprehending the functional implications of these interactions and for developing new therapies for many diseases. Because of the high cost of experimental determination of protein‐RNA interfaces, there is a need for computational methods to identify RNA‐binding residues in proteins. While most of the existing computational methods for predicting RNA‐binding residues in RNA‐binding proteins are oblivious to the characteristics of the partner RNA, there is growing interest in methods for partner‐specific prediction of RNA binding sites in proteins. In this work, we assess the performance of two recently published partner‐specific protein‐RNA interface prediction tools, PS‐PRIP, and PRIdictor, along with our own new tools. Specifically, we introduce a novel metric, RNA‐specificity metric (RSM), for quantifying the RNA‐specificity of the RNA binding residues predicted by such tools. Our results show that the RNA‐binding residues predicted by previously published methods are oblivious to the characteristics of the putative RNA binding partner. Moreover, when evaluated using partner‐agnostic metrics, RNA partner‐specific methods are outperformed by the state‐of‐the‐art partner‐agnostic methods. We conjecture that either (a) the protein‐RNA complexes in PDB are not representative of the protein‐RNA interactions in nature, or (b) the current methods for partner‐specific prediction of RNA‐binding residues in proteins fail to account for the differences in RNA partner‐specific versus partner‐agnostic protein‐RNA interactions, or both.

    

   more » « less
5. Coupling dynamics and evolutionary information with structure to identify protein regulatory and functional binding sites

   https://doi.org/10.1002/prot.25749  

   Mishra, Sambit K. ; Kandoi, Gaurav ; Jernigan, Robert L. ( June 2019 , Proteins: Structure, Function, and Bioinformatics)

   Binding sites in proteins can be either specifically functional binding sites (active sites) that bind specific substrates with high affinity or regulatory binding sites (allosteric sites), that modulate the activity of functional binding sites through effector molecules. Owing to their significance in determining protein function, the identification of protein functional and regulatory binding sites is widely acknowledged as an important biological problem. In this work, we present a novel binding site prediction method, Active and Regulatory site Prediction (AR‐Pred), which supplements protein geometry, evolutionary, and physicochemical features with information about protein dynamics to predict putative active and allosteric site residues. As the intrinsic dynamics of globular proteins plays an essential role in controlling binding events, we find it to be an important feature for the identification of protein binding sites. We train and validate our predictive models on multiple balanced training and validation sets with random forest machine learning and obtain an ensemble of discrete models for each prediction type. Our models for active site prediction yield a median area under the curve (AUC) of 91% and Matthews correlation coefficient (MCC) of 0.68, whereas the less well‐defined allosteric sites are predicted at a lower level with a median AUC of 80% and MCC of 0.48. When tested on an independent set of proteins, our models for active site prediction show comparable performance to two existing methods and gains compared to two others, while the allosteric site models show gains when tested against three existing prediction methods. AR‐Pred is available as a free downloadable package athttps://github.com/sambitmishra0628/AR-PRED_source.

    

   more » « less