A novel graph convolutional neural network for predicting interaction sites on protein kinase inhibitors in phosphorylation

AbstractProtein kinase-inhibitor interactions are key to the phosphorylation of proteins involved in cell proliferation, differentiation, and apoptosis, which shows the importance of binding mechanism research and kinase inhibitor design. In this study, a novel machine learning module (i.e., the WL Box) was designed and assembled to the Prediction of Interaction Sites of Protein Kinase Inhibitors (PISPKI) model, which is a graph convolutional neural network (GCN) to predict the interaction sites of protein kinase inhibitors. The WL Box is a novel module based on the well-known Weisfeiler-Lehman algorithm, which assembles multiple switch weights to effectively compute graph features. The PISPKI model was evaluated by testing with shuffled datasets and ablation analysis using 11 kinase classes. The accuracy of the PISPKI model with the shuffled datasets varied from 83 to 86%, demonstrating superior performance compared to two baseline models. The effectiveness of the model was confirmed by testing with shuffled datasets. Furthermore, the performance of each component of the model was analyzed via the ablation study, which demonstrated that the WL Box module was critical. The code is available at https://github.com/feiqiwang/PISPKI.

Download Full-text

Effects of Sunitinib and Other Kinase Inhibitors on Cells Harboring a PDGFRB Mutation Associated with Infantile Myofibromatosis

International Journal of Molecular Sciences ◽

10.3390/ijms19092599 ◽

2018 ◽

Vol 19 (9) ◽

pp. 2599 ◽

Cited By ~ 6

Author(s):

Martin Sramek ◽

Jakub Neradil ◽

Petra Macigova ◽

Peter Mudry ◽

Kristyna Polaskova ◽

...

Keyword(s):

Protein Kinase ◽

Cell Line ◽

Tumor Cells ◽

Kinase Inhibitors ◽

Kinase Inhibitor ◽

Growth Factor Receptor ◽

Tumor Cell Line ◽

Protein Kinase Inhibitors ◽

Infantile Myofibromatosis ◽

Pdgfr Beta

Infantile myofibromatosis represents one of the most common proliferative fibrous tumors of infancy and childhood. More effective treatment is needed for drug-resistant patients, and targeted therapy using specific protein kinase inhibitors could be a promising strategy. To date, several studies have confirmed a connection between the p.R561C mutation in gene encoding platelet-derived growth factor receptor beta (PDGFR-beta) and the development of infantile myofibromatosis. This study aimed to analyze the phosphorylation of important kinases in the NSTS-47 cell line derived from a tumor of a boy with infantile myofibromatosis who harbored the p.R561C mutation in PDGFR-beta. The second aim of this study was to investigate the effects of selected protein kinase inhibitors on cell signaling and the proliferative activity of NSTS-47 cells. We confirmed that this tumor cell line showed very high phosphorylation levels of PDGFR-beta, extracellular signal-regulated kinases (ERK) 1/2 and several other protein kinases. We also observed that PDGFR-beta phosphorylation in tumor cells is reduced by the receptor tyrosine kinase inhibitor sunitinib. In contrast, MAPK/ERK kinases (MEK) 1/2 and ERK1/2 kinases remained constitutively phosphorylated after treatment with sunitinib and other relevant protein kinase inhibitors. Our study showed that sunitinib is a very promising agent that affects the proliferation of tumor cells with a p.R561C mutation in PDGFR-beta.

Download Full-text

New tools for carbohydrate sulfation analysis: heparan sulfate 2-O-sulfotransferase (HS2ST) is a target for small-molecule protein kinase inhibitors

Biochemical Journal ◽

10.1042/bcj20180265 ◽

2018 ◽

Vol 475 (15) ◽

pp. 2417-2433 ◽

Cited By ~ 8

Author(s):

Dominic P. Byrne ◽

Yong Li ◽

Krithika Ramakrishnan ◽

Igor L. Barsukov ◽

Edwin A. Yates ◽

...

Keyword(s):

Protein Kinase ◽

Heparan Sulfate ◽

Small Molecule ◽

Kinase Inhibitors ◽

Kinase Inhibitor ◽

Protein Kinase Inhibitors ◽

Fluorescent Substrate ◽

Raf Kinase ◽

Shift Analysis

Sulfation of carbohydrate residues occurs on a variety of glycans destined for secretion, and this modification is essential for efficient matrix-based signal transduction. Heparan sulfate (HS) glycosaminoglycans control physiological functions ranging from blood coagulation to cell proliferation. HS biosynthesis involves membrane-bound Golgi sulfotransferases, including HS 2-O-sulfotransferase (HS2ST), which transfers sulfate from the cofactor PAPS (3′-phosphoadenosine 5′-phosphosulfate) to the 2-O position of α-l-iduronate in the maturing polysaccharide chain. The current lack of simple non-radioactive enzyme assays that can be used to quantify the levels of carbohydrate sulfation hampers kinetic analysis of this process and the discovery of HS2ST inhibitors. In the present paper, we describe a new procedure for thermal shift analysis of purified HS2ST. Using this approach, we quantify HS2ST-catalysed oligosaccharide sulfation using a novel synthetic fluorescent substrate and screen the Published Kinase Inhibitor Set, to evaluate compounds that inhibit catalysis. We report the susceptibility of HS2ST to a variety of cell-permeable compounds in vitro, including polyanionic polar molecules, the protein kinase inhibitor rottlerin and oxindole-based RAF kinase inhibitors. In a related study, published back-to-back with the present study, we demonstrated that tyrosyl protein sulfotranferases are also inhibited by a variety of protein kinase inhibitors. We propose that appropriately validated small-molecule compounds could become new tools for rapid inhibition of glycan (and protein) sulfation in cells, and that protein kinase inhibitors might be repurposed or redesigned for the specific inhibition of HS2ST.

Download Full-text

New tools for carbohydrate sulphation analysis: Heparan Sulphate 2-O-sulphotranserase (HS2ST) is a target for small molecule protein kinase inhibitors

10.1101/296533 ◽

2018 ◽

Author(s):

Dominic P Byrne ◽

Yong Li ◽

Krithika Ramakrishnan ◽

Igor L Barsukov ◽

Edwin A Yates ◽

...

Keyword(s):

Protein Kinase ◽

Small Molecule ◽

Kinase Inhibitors ◽

Kinase Inhibitor ◽

Heparan Sulphate ◽

Protein Kinase Inhibitors ◽

Fluorescent Substrate ◽

Shift Analysis ◽

In Cells

ABSTRACTSulphation of carbohydrate residues occurs on a variety of glycans destined for secretion, and this modification is essential for efficient matrix-based signal transduction. Heparan sulphate (HS) glycosaminoglycans control physiological functions ranging from blood coagulation to cell proliferation. HS biosynthesis involves membrane-bound Golgi sulphotransferases, including heparan sulphate 2-O-sulphotransferase (HS2ST), which transfers sulphate from the co-factor PAPS (3’-phosphoadenosine 5’-phosphosulphate) to the 2-Oposition of α-L-iduronate in the maturing oligosaccharide chain. The current lack of simple non-radioactive enzyme assays that can be used to quantify the levels of carbohydrate sulphation hampers kinetic analysis of this process and the discovery of HS2ST inhibitors. In this paper, we describe a new procedure for thermal shift analysis of purified HS2ST. Using this approach, we quantify HS2ST-catalyzed oligosaccharide sulphation using a novel synthetic fluorescent substrate and screen the Published Kinase Inhibitor Set (PKIS), to evaluate compounds that inhibit catalysis. We report the susceptibility of HS2ST to a variety of cell permeable compoundsin vitro, including polyanionic polar molecules, the protein kinase inhibitor rottlerin and oxindole-based RAF kinase inhibitors. In a related study, published back-to-back with this article, we demonstrate that Tyrosyl Protein Sulpho Tranferases (TPSTs) are also inhibited by a variety of protein kinase inhibitors. We propose that appropriately validated small molecule compounds could become new tools for rapid inhibition of glycan (and protein) sulphation in cells, and that protein kinase inhibitors might be repurposed or redesigned for the specific inhibition of HS2ST.SUMMARY STATEMENTWe report that HS2ST, which is a PAPS-dependent glycan sulphotransferase, can be assayed using a variety of novel biochemical procedures, including a non-radioactive enzyme-based assay that detects glycan substrate sulphation in real time. HS2ST activity can be inhibited by different classes of compounds, including known protein kinase inhibitors, suggesting new approaches to evaluate the roles of HS2ST-dependent sulphation with small molecules in cells.

Download Full-text

Screening of Microbial Extracts for Anticancer Compounds Using Streptomyces Kinase Inhibitor Assay

Natural Product Communications ◽

10.1177/1934578x1501000738 ◽

2015 ◽

Vol 10 (7) ◽

pp. 1934578X1501000 ◽

Cited By ~ 2

Author(s):

Prashant Shanbhag ◽

Sarita Bhave ◽

Ashwini Vartak ◽

Asha Kulkarni-Almeida ◽

Girish Mahajan ◽

...

Keyword(s):

Protein Kinase ◽

Anticancer Agents ◽

Kinase Inhibitors ◽

Kinase Inhibitor ◽

Protein Kinase Inhibitors ◽

Kinase Assay ◽

Diffusion Method ◽

Eukaryotic Protein Kinase ◽

Eukaryotic Protein ◽

Microbial Extracts

Eukaryotic kinases are known to play an important role in signal transduction pathways by phosphorylating their respective substrates. Abnormal phosphorylations by these kinases have resulted in diseases. Hence inhibitors of kinases are of considerable pharmaceutical interest for a wide variety of disease targets, especially cancers. A number of reports have been published which indicate that eukaryotic-like kinases may complement two-component kinase systems in several bacteria. In Streptomyces sp. such kinases have been found to have a role in formation of aerial hyphae, spores, pigmentation & even in antibiotic production in some strains. Eukaryotic kinase inhibitors are seen to inhibit formation of aerial mycelia in Streptomyces without inhibiting vegetative mycelia. This property has been used to design an assay to screen for eukaryotic kinase inhibitors. The assay involves testing of compounds against Streptomyces 85E ATCC 55824 using agar well diffusion method. Inhibitors of kinases give rise to “bald” colonies where aerial mycelia and sporulation inhibition is seen. The assay has been standardized using known eukaryotic protein kinase inhibiting anticancer agents like AG-490, AG-1295, AG-1478, Flavopiridol and Imatinib as positive controls, at a concentration ranging from 10 μg/well to 100 μg/well. Anti-infective compounds which are not reported to inhibit eukaryotic protein kinases were used as negative controls. A number of microbial cultures have been screened for novel eukaryotic protein kinase inhibitors. Further these microbial extracts were tested in various cancer cell lines like Panc1, HCT116, Calu1, ACHN and H460 at a concentration of 10 μg/mL/ well. The anticancer data was seen correlating well with the Streptomyces kinase assay thus validating the assay.

Download Full-text

Comparative Assessment of Protein Kinase Inhibitors in Public Databases and in PKIDB

Molecules ◽

10.3390/molecules25143226 ◽

2020 ◽

Vol 25 (14) ◽

pp. 3226 ◽

Cited By ~ 2

Author(s):

Colin Bournez ◽

Fabrice Carles ◽

Gautier Peyrat ◽

Samia Aci-Sèche ◽

Stéphane Bourg ◽

...

Keyword(s):

Clinical Trials ◽

Protein Kinase ◽

Protein Kinases ◽

Kinase Inhibitors ◽

Kinase Inhibitor ◽

Chemical Space ◽

Principal Component ◽

Great Majority ◽

Protein Kinase Inhibitors ◽

Principal Moments Of Inertia

Since the first approval of a protein kinase inhibitor (PKI) by the Food and Drug Administration (FDA) in 2001, 55 new PKIs have reached the market, and many inhibitors are currently being evaluated in clinical trials. This is a clear indication that protein kinases still represent major drug targets for the pharmaceutical industry. In a previous work, we have introduced PKIDB, a publicly available database, gathering PKIs that have already been approved (Phase 4), as well as those currently in clinical trials (Phases 0 to 3). This database is updated frequently, and an analysis of the new data is presented here. In addition, we compared the set of PKIs present in PKIDB with the PKIs in early preclinical studies found in ChEMBL, the largest publicly available chemical database. For each dataset, the distribution of physicochemical descriptors related to drug-likeness is presented. From these results, updated guidelines to prioritize compounds for targeting protein kinases are proposed. The results of a principal component analysis (PCA) show that the PKIDB dataset is fully encompassed within all PKIs found in the public database. This observation is reinforced by a principal moments of inertia (PMI) analysis of all molecules. Interestingly, we notice that PKIs in clinical trials tend to explore new 3D chemical space. While a great majority of PKIs is located on the area of “flatland”, we find few compounds exploring the 3D structural space. Finally, a scaffold diversity analysis of the two datasets, based on frequency counts was performed. The results give insight into the chemical space of PKIs, and can guide researchers to reach out new unexplored areas. PKIDB is freely accessible from the following website: http://www.icoa.fr/pkidb.

Download Full-text

ConvsPPIS: Identifying Protein-protein Interaction Sites by an Ensemble Convolutional Neural Network with Feature Graph

Current Bioinformatics ◽

10.2174/1574893614666191105155713 ◽

2020 ◽

Vol 15 (4) ◽

pp. 368-378

Author(s):

Huaixu Zhu ◽

Xiuquan Du ◽

Yu Yao

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Protein Interaction ◽

Learning Ability ◽

Superior Performance ◽

Model Learning ◽

Protein Protein Interaction ◽

Interaction Sites ◽

Protein Interaction Sites ◽

Interface Residues

Background/Objective: Protein-protein interactions are essentials for most cellular processes and thus, unveiling how proteins interact with is a crucial question that can be better understood by recognizing which residues participate in the interaction. Although many computational approaches have been proposed to predict interface residues, their feature perspective and model learning ability are not enough to achieve ideal results. So, our objective is to improve the predictive performance under considering feature perspective and new learning algorithm. Method: In this study, we proposed an ensemble deep convolutional neural network, which explores the context and positional context of consecutive residues within a protein sub-sequence. Specifically, unlike the feature view of previous methods, ConvsPPIS uses evolutionary, physicochemical, and structural protein characteristics to construct their own feature graph respectively. After that, three independent deep convolutional neural networks are trained on each type of feature graph for learning the underlying pattern in sub-sequence. Lastly, we integrated those three deep networks into an ensemble predictor with leveraging complementary information of those features to predict potential interface residues. Results: Some comparative experiments have conducted through 10-fold cross-validation. The results indicated that ConvsPPIS achieved superior performance on DBv5-Sel dataset with an accuracy of 88%. Additional experiments on CAPRI-Alone dataset demonstrated ConvsPPIS has also better prediction performance. Conclusion: The ConvsPPIS method provided a new perspective to capture protein feature expression for identifying protein-protein interaction sites. The results proved the superiority of this method.

Download Full-text

Odd chromosome movement and inaccurate chromosome distribution in mitosis and meiosis after treatment with protein kinase inhibitors

Journal of Cell Science ◽

10.1242/jcs.104.4.961 ◽

1993 ◽

Vol 104 (4) ◽

pp. 961-973 ◽

Cited By ~ 4

Author(s):

R.B. Nicklas ◽

L.E. Krawitz ◽

S.C. Ward

Keyword(s):

Protein Kinase ◽

Kinase Inhibitors ◽

Kinase Inhibitor ◽

Protein Kinase Inhibitors ◽

Chromosome Movement ◽

Chromosome Distribution ◽

Protein Kinase Inhibition ◽

Spindle Microtubules ◽

Mitosis And Meiosis ◽

Normal Mitosis

Errors in chromosome orientation in mitosis and meiosis are inevitable, but normally they are quickly corrected. We find that such errors usually are not corrected in cells treated with protein kinase inhibitors. Highly inaccurate chromosome distribution is the result. When grasshopper spermatocytes were treated with the kinase inhibitor 6-dimethylaminopurine (DMAP), 84% of maloriented chromosomes failed to reorient; in anaphase, both partner chromosomes were distributed to the same daughter cell. These chromosomes were observed for a total of over 60 h, and not a single reorientation was seen. In contrast, in untreated cells, maloriented chromosomes invariably reoriented, and quickly: in 10 min, on average. A second protein kinase inhibitor, genistein, had exactly the same effect as DMAP. DMAP affected PtK1 cells in mitosis as it did spermatocytes in meiosis: improper chromosome orientations persisted, leading to frequent errors in distribution. We micromanipulated chromosomes in spermatocytes treated with DMAP to learn why maloriented chromosomes often fail to reorient. Reorientation requires the loss of improper microtubule attachments and the acquisition of new, properly directed kinetochore microtubules. Micromanipulation experiments disclose that neither the loss of old nor the acquisition of new microtubules is sufficiently affected by DMAP to account for the indefinite persistence of malorientations. Drug treatment causes a novel form of chromosome movement in which one kinetochore moves toward another kinetochore. Two kinetochores in the same chromosome or in different chromosomes can participate, producing varied, dance-like movements executed by one or two chromosomes. These kinetochore-kinetochore interactions evidently are at the expense of kinetochore-spindle interactions. We propose that malorientations persist in treated cells because the kinetochores have numerous, short microtubules with a free end that can be captured by a second kinetochore. Kinetochores capture each other's kinetochore microtubules, leaving too few sites available for the efficient capture of spindle microtubules. Since the efficient capture of spindle microtubules is essential for the correction of errors, failure of capture allows malorientations to persist. Whether the effects of DMAP actually are due to protein kinase inhibition remains to be seen. In any case, DMAP reveals interactions of one kinetochore with another, which, though ordinarily suppressed, have implications for normal mitosis.

Download Full-text

Involvement of different protein kinases and phospholipases A2in phorbol ester (TPA)-induced arachidonic acid liberation in bovine platelets

Mediators of Inflammation ◽

10.1080/09629350050024357 ◽

2000 ◽

Vol 9 (1) ◽

pp. 31-34 ◽

Cited By ~ 9

Author(s):

M. Lehr ◽

K. Griessbach

Keyword(s):

Arachidonic Acid ◽

Protein Kinase ◽

Map Kinase ◽

Kinase Inhibitors ◽

Kinase Inhibitor ◽

P38 Map Kinase ◽

Protein Kinase Inhibitors ◽

Arachidonic Acid Release ◽

Gf 109203X ◽

Acid Release

The effect of various phospholipase A2and protein kinase inhibitors on the arachidonic acid liberation in bovine platelets induced by the protein kinase activator 12-O-tetradecanoylphorbol–13-acetate (TPA) was studied. TPA stimulates arachidonic acid release mainly by activating group IV cytosolic PLA2(cPLA2), since inhibitors of this enzyme markedly inhibited arachidonic acid formation. However, group VI Ca2+-independent PLA2(iPLA2) seems to contribute to the arachidonic acid liberation too, since the relatively specific iPLA2inhibitor bromoenol lactone (BEL) decreased arachidonic acid generation in part. The pronounced inhibition of the TPA-induced arachidonic acid release by the protein kinase C (PKC) inhibitors GF 109203X and Ro 31–82220, respectively, and by the p38 MAP kinase inhibitor SB 202190 suggests that the activation of the PLA2s by TPA is mediated via PKC and p38 MAP kinase.

Download Full-text

Different effects of protein kinase inhibitors on the localization of junctional proteins at cell-cell contact sites

Journal of Cell Science ◽

10.1242/jcs.107.4.969 ◽

1994 ◽

Vol 107 (4) ◽

pp. 969-981 ◽

Cited By ~ 5

Author(s):

N. Denisenko ◽

P. Burighel ◽

S. Citi

Keyword(s):

Protein Kinase ◽

Tight Junctions ◽

Kinase Inhibitors ◽

Kinase Inhibitor ◽

Mdck Cells ◽

Protein Kinase Inhibitors ◽

Cell Contact ◽

Actin Microfilaments ◽

E Cadherin ◽

Cell Cell

The protein kinase inhibitor H-7 prevents the assembly of tight junctions in cultured Madin Darby Canine Kidney (MDCK) epithelial cells (Balda et al. (1991) J. Membr. Biol. 122, 193–202; Nigam et al. (1991) Biochem. Biophys. Res. Commun. 181, 548–553); however, its mechanism of action is unknown. To understand the basis of the activity of H-7 and other inhibitors we compared the effect of H-7 on the localization of proteins belonging to tight junctions and adherens-type junctions (zonula adhaerens and desmosome), and on the organization of actin microfilaments. Junction assembly was induced in MDCK cells either by the ‘Ca2+ switch’ procedure or by incubating trypsinized cells at normal extracellular Ca2+, and the cells were then immunofluorescently labeled with antibodies against cingulin, ZO-1, E-cadherin and desmoplakin, and with FITC-phalloidin. Here we show by measuring the transepithelial resistance that, in addition to H-7, H-8 and staurosporine can also significantly block the assembly of tight junctions, whereas HA1004 is poorly active. H-7 inhibited the accumulation of cingulin and ZO-1 in junctional areas most effectively when added during assembly at normal extracellular Ca2+. On the other hand, H-7 did not have major effects on the accumulation of E-cadherin and desmoplakin in the regions of cell-cell contact using either assembly protocol. Electron microscopy confirmed that H-7 does not abolish the formation of adherens-type junctions, suggesting that phosphorylation plays a different role in the assembly of tight junctions versus adherens-type junctions. Finally, in both protocols of junction assembly H-7 caused a major disorganization of actin microfilaments, suggesting that H-7 may prevent TJ assembly through its effect on the cytoskeleton.

Download Full-text

Clinically-weighted transcriptomic signatures for protein kinase inhibitor associated cardiotoxicity

10.1101/075754 ◽

2016 ◽

Cited By ~ 2

Author(s):

JGC van Hasselt ◽

J Hansen ◽

Y Xiong ◽

J Shim ◽

A Pickard ◽

...

Keyword(s):

Adverse Event ◽

Protein Kinase ◽

Kinase Inhibitors ◽

Kinase Inhibitor ◽

Adverse Event Reporting System ◽

Cardiac Contractility ◽

Digital Gene Expression ◽

Adverse Event Reporting ◽

Protein Kinase Inhibitors ◽

Risk Scores

ABSTRACTCardiotoxicity (CT) involving diminished cardiac contractility and heart failure is a major adverse event associated with otherwise efficacious protein kinase inhibitors (KIs). Here, we sought to develop clinically-weighted transcriptomic signatures to predict risk of CT and to better understand the biological processes associated with CT risk. We obtained transcriptome-wide response profiles in four human primary cardiomyocyte cell lines that were treated with 22 different KIs using mRNA sequencing with 3’ digital gene expression. The FDA Adverse Event Reporting System was used to derive relative risk scores for four types of CT for different KIs. We used elastic net regression to associate these transcriptomic profiles with KI-associated risk scores for CT subtypes to obtain clinically-weighted transcriptomic signatures, which showed good predictive properties (cross-validation R2>0.87). Our clinically-weighted transcriptomic signatures for KI-associated CT may be of relevance in early drug development for the prediction of KI-associated CT.

Download Full-text