Understanding the variability of the S1′ pocket to improve matrix metalloproteinase inhibitor selectivity profiles

Deep learning is developing as an important technology to perform various tasks in cheminformatics. In particular, graph convolutional neural networks (GCNs) have been reported to perform well in many types of prediction tasks related to molecules. Although GCN exhibits considerable potential in various applications, appropriate utilization of this resource for obtaining reasonable and reliable prediction results requires thorough understanding of GCN and programming. To leverage the power of GCN to benefit various users from chemists to cheminformaticians, an open-source GCN tool, kGCN, is introduced. To support the users with various levels of programming skills, kGCN includes three interfaces: a graphical user interface (GUI) employing KNIME for users with limited programming skills such as chemists, as well as command-line and Python library interfaces for users with advanced programming skills such as cheminformaticians. To support the three steps required for building a prediction model, i.e., pre-processing, model tuning, and interpretation of results, kGCN includes functions of typical pre-processing, Bayesian optimization for automatic model tuning, and visualization of the atomic contribution to prediction for interpretation of results. kGCN supports three types of approaches, single-task, multi-task, and multi-modal predictions. The prediction of compound-protein interaction for four matrixmetalloproteases, MMP-3,-9,-12 and-13, in the inhibition assays is performed as a representative case study using kGCN. Additionally, kGCN provides the visualization of atomic contributions to the prediction. Such visualization is useful for the validation of the prediction models and the design of molecules based on the prediction model, realizing "explainable AI" for understanding the factors affecting AI prediction. kGCN is available at https ://githu b.com/clinf o.

show abstract

“…The Table 1. These MMPs were selected because relatively large amounts of data were available for these in the ChEMBL dataset [39].…”

Section: Resultsmentioning

confidence: 99%

kGCN: a graph-based deep learning framework for chemical structures

Kojima

Ishida

Ohta³

et al. 2020

J Cheminform

View full text Add to dashboard Cite

show abstract

“…2 a). The zinc-chelating and hydrophobic interactions with the S1′ pocket, which is sequence-variable within the MMP family, are related to potency and selectivity of MMP inhibitors 19 , 20 . Although compounds synthesized in Scheme 1 were racemic, the ( R , S )-enantiomer of compound 4 was superimposed on SC44463 pharmacophore model and putative interactions were refined (Fig.…”

Section: Resultsmentioning

confidence: 99%

Prediction of an MMP-1 inhibitor activity cliff using the SAR matrix approach and its experimental validation

Asawa

Yoshimori²,

Bajorath

et al. 2020

Sci Rep

View full text Add to dashboard Cite

A matrix metalloproteinase 1 (MMP-1) inhibitor activity cliff was predicted using the SAR Matrix method. Compound 4 was predicted as a highly potent activity cliff partner and found to possess 60 times higher inhibitory activity against MMP-1 than the structurally related compound 3. Furthermore, pharmacophore fitting of synthesized compounds indicated that the correctly predicted activity cliff was caused by interactions between the trifluoromethyl group at para position in compound 4 and residue ARG214 of MMP-1.

show abstract

“…In fact, MMPs can be grouped in the order of the depth of their S 1 ′ pockets. MMPs have either “shallow”, “intermediate”, or “deep” S 1 ′ pockets [ 3 , 44 ]. MMP-8 is categorized as one with an “intermediate” S 1 ′ pocket.…”

Section: Resultsmentioning

confidence: 99%

“…Apart from the size of the S 1 ′ pocket, the residues in the S 1 ′ specificity loop are also considerably different among different MMPs [ 45 ]. These differences in the S 1 ′ pocket and its specificity loop are currently being exploited to develop selective MMP inhibitors [ 44 ]. Thus, to assess if the electropositive nature of the S 1 ′ pocket is common among MMPs in the “intermediate” category, we analyzed the ESPs of MMP-2 and -9, two other “intermediate” S 1 ′ MMPs [ 3 ].…”

Section: Resultsmentioning

confidence: 99%

Discovery of Sulfated Small Molecule Inhibitors of Matrix Metalloproteinase-8

Morla

Desai

2020

Biomolecules

View full text Add to dashboard Cite

Elevated matrix metalloproteinase-8 (MMP-8) activity contributes to the etiology of many diseases, including atherosclerosis, pulmonary fibrosis, and sepsis. Yet, very few small molecule inhibitors of MMP-8 have been identified. We reasoned that the synthetic non-sugar mimetics of glycosaminoglycans may inhibit MMP-8 because natural glycosaminoglycans are known to modulate the functions of various MMPs. The screening a library of 58 synthetic, sulfated mimetics consisting of a dozen scaffolds led to the identification of only two scaffolds, including sulfated benzofurans and sulfated quinazolinones, as promising inhibitors of MMP-8. Interestingly, the sulfated quinazolinones displayed full antagonism of MMP-8 and sulfated benzofuran appeared to show partial antagonism. Of the two, sulfated quinazolinones exhibited a >10-fold selectivity for MMP-8 over MMP-9, a closely related metalloproteinase. Molecular modeling suggested the plausible occupancy of the S1′ pocket on MMP-8 as the distinguishing feature of the interaction. Overall, this work provides the first proof that the sulfated mimetics of glycosaminoglycans could lead to potent, selective, and catalytic activity-tunable, small molecular inhibitors of MMP-8.

show abstract

Understanding the variability of the S1′ pocket to improve matrix metalloproteinase inhibitor selectivity profiles

Cited by 43 publications

References 95 publications

kGCN: a graph-based deep learning framework for chemical structures

kGCN: a graph-based deep learning framework for chemical structures

Prediction of an MMP-1 inhibitor activity cliff using the SAR matrix approach and its experimental validation

Discovery of Sulfated Small Molecule Inhibitors of Matrix Metalloproteinase-8

Contact Info

Product

Resources

About