2P2IHUNTER: a tool for filtering orthosteric protein–protein interaction modulators via a dedicated support vector machine

Over the last 10 years, protein–protein interactions (PPIs) have shown increasing potential as new therapeutic targets. As a consequence, PPIs are today the most screened target class in high-throughput screening (HTS). The development of broad chemical libraries dedicated to these particular targets is essential; however, the chemical space associated with this ‘high-hanging fruit’ is still under debate. Here, we analyse the properties of 40 non-redundant small molecules present in the 2P2I database (http://2p2idb.cnrs-mrs.fr/) to define a general profile of orthosteric inhibitors and propose an original protocol to filter general screening libraries using a support vector machine (SVM) with 11 standard Dragon molecular descriptors. The filtering protocol has been validated using external datasets from PubChem BioAssay and results from in-house screening campaigns. This external blind validation demonstrated the ability of the SVM model to reduce the size of the filtered chemical library by eliminating up to 96% of the compounds as well as enhancing the proportion of active compounds by up to a factor of 8. We believe that the resulting chemical space identified in this paper will provide the scientific community with a concrete support to search for PPI inhibitors during HTS campaigns.

[1]  Yanli Wang,et al.  A novel method for mining highly imbalanced high-throughput screening data in PubChem , 2009, Bioinform..

[2]  Rutger H A Folmer,et al.  Fragment screening to predict druggability (ligandability) and lead discovery success. , 2011, Drug discovery today.

[3]  L. Vassilev,et al.  Small-Molecule Inhibitors of Protein-Protein Interactions , 2011 .

[4]  J. Wells.  Structural and Functional Epitopes in the Growth Hormone Receptor Complex , 1995, Bio/Technology.

[5]  G. Schneider,et al.  Context-based identification of protein-protein interfaces and "hot-spot" residues. , 2011, Chemistry & biology.

[6]  Harald Mauser,et al.  Design of Libraries Targeting Protein–Protein Interfaces , 2013, ChemMedChem.

[7]  F. Lombardo,et al.  Experimental and computational approaches to estimate solubility and permeability in drug discovery and development settings. , 2001, Advanced drug delivery reviews.

[8]  David K. Johnson,et al.  Druggable Protein Interaction Sites Are More Predisposed to Surface Pocket Formation than the Rest of the Protein Surface , 2013, PLoS Comput. Biol..

[9]  B. Villoutreix,et al.  A leap into the chemical space of protein-protein interaction inhibitors. , 2012, Current pharmaceutical design.

[10]  Fuller Jonathan.  Druggability of protein-protein interactions and a peptidomimetic strategy for targeting the hDM2-p53 interaction , 2013 .

[11]  Laurie E. Grove,et al.  Structural conservation of druggable hot spots in protein–protein interfaces , 2011, Proceedings of the National Academy of Sciences.

[12]  Y. Miyagi,et al.  ABT-263, a Bcl-2 inhibitor, enhances the susceptibility of lung adenocarcinoma cells treated with Src inhibitors to anoikis. , 2011, Oncology reports.

[13]  Evan Bolton,et al.  An overview of the PubChem BioAssay resource , 2009, Nucleic Acids Res..

[14]  Olivier Sperandio,et al.  Designing Focused Chemical Libraries Enriched in Protein-Protein Interaction Inhibitors using Machine-Learning Methods , 2010, PLoS Comput. Biol..

[15]  David Ryan Koes,et al.  PocketQuery: protein–protein interaction inhibitor starting points from protein–protein interaction structure , 2012, Nucleic Acids Res..

[16]  Olivier Sperandio,et al.  iPPI-DB: a manually curated and interactive database of small non-peptide inhibitors of protein-protein interactions. , 2013, Drug discovery today.

[17]  F. Lombardo,et al.  Experimental and computational approaches to estimate solubility and permeability in drug discovery and development settings , 1997 .

[18]  Jan Tavernier,et al.  Large-scale protein interactome mapping: strategies and opportunities , 2010, Expert review of proteomics.

[19]  A. Barabasi,et al.  An empirical framework for binary interactome mapping , 2008, Nature Methods.

[20]  Tom L. Blundell,et al.  Database update TIMBAL v2: update of a database holding small molecules modulating protein-protein interactions , 2013 .

[21]  Andrew J. Wilson,et al.  Inhibition of α-helix-mediated protein-protein interactions using designed molecules. , 2013, Nature chemistry.

[22]  David Ryan Koes,et al.  Small-molecule inhibitor starting points learned from protein–protein interaction inhibitor structure , 2011, Bioinform..

[23]  T. Blundell,et al.  Using a Fragment-Based Approach To Target Protein–Protein Interactions , 2013, Chembiochem : a European journal of chemical biology.

[24]  M. Giulianotti,et al.  HTS by NMR of combinatorial libraries: a fragment-based approach to ligand discovery. , 2013, Chemistry & biology.

[25]  A. Marchand,et al.  Rational design of small-molecule inhibitors of the LEDGF/p75-integrase interaction and HIV replication. , 2010, Nature chemical biology.

[26]  Kareem Khoury,et al.  P53 mdm2 inhibitors. , 2012, Current pharmaceutical design.

[27]  Philippe Roche,et al.  Chemical and structural lessons from recent successes in protein-protein interaction inhibition (2P2I). , 2011, Current opinion in chemical biology.

[28]  Philippe Roche,et al.  Atomic Analysis of Protein-Protein Interfaces with Known Inhibitors: The 2P2I Database , 2010, PloS one.

[29]  M. Bunnage.  Getting pharmaceutical R&D back on target. , 2011, Nature chemical biology.

[30]  J Andrew McCammon,et al.  Statistical mechanics and molecular dynamics in evaluating thermodynamic properties of biomolecular recognition , 2011, Quarterly Reviews of Biophysics.

[31]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[32]  S. Fletcher,et al.  Targeting protein–protein interactions by rational design: mimicry of protein surfaces , 2006, Journal of The Royal Society Interface.

[33]  Marko Hyvönen,et al.  Targeting protein-protein interactions and fragment-based drug discovery. , 2012, Topics in current chemistry.

[34]  Tom L. Blundell,et al.  Biophysical and computational fragment-based approaches to targeting protein–protein interactions: applications in structure-guided drug discovery , 2012, Quarterly Reviews of Biophysics.

[35]  Philippe Roche,et al.  2P2Idb: a structural database dedicated to orthosteric modulation of protein–protein interactions , 2012, Nucleic Acids Res..

[36]  T. Komiyama,et al.  Inhibitors of difficult protein-protein interactions identified by high-throughput screening of multiprotein complexes. , 2013, ACS Chemical Biology.

[37]  M. Bolognesi,et al.  Designing Smac-mimetics as antagonists of XIAP, cIAP1, and cIAP2. , 2009, Biochemical and biophysical research communications.

[38]  Xiang-Qun Xie,et al.  Exploiting PubChem for virtual screening , 2010, Expert opinion on drug discovery.

[39]  Holger Gohlke,et al.  Modulating protein-protein interactions: from structural determinants of binding to druggability prediction to application. , 2012, Current pharmaceutical design.

[40]  C. Marson,et al.  New and unusual scaffolds in medicinal chemistry. , 2011, Chemical Society reviews.

[41]  P. Hajduk,et al.  Predicting protein druggability. , 2005, Drug discovery today.

[42]  Asher Mullard,et al.  Protein–protein interaction inhibitors get into the groove , 2012, Nature Reviews Drug Discovery.

[43]  C G M Wilson,et al.  Small-molecule inhibitors of IL-2/IL-2R: lessons learned and applied. , 2011, Current topics in microbiology and immunology.

[44]  Volkhard Helms,et al.  Druggability of dynamic protein-protein interfaces. , 2012, Current pharmaceutical design.

[45]  Ramaswamy Nilakantan,et al.  Discovery of novel inhibitors of the ZipA/FtsZ complex by NMR fragment screening coupled with structure-based design. , 2006, Bioorganic & medicinal chemistry.

[46]  Zhiwei Wang,et al.  Emerging Bcl-2 inhibitors for the treatment of cancer , 2011, Expert opinion on emerging drugs.

[47]  Robert S. Pearlman,et al.  Metric Validation and the Receptor-Relevant Subspace Concept , 1999, J. Chem. Inf. Comput. Sci..

[48]  Nobuyoshi Sugaya,et al.  Assessing the druggability of protein-protein interactions by a supervised machine-learning method , 2009, BMC Bioinformatics.

[49]  Thorsten Nowak,et al.  Expanding medicinal chemistry space. , 2013, Drug discovery today.

[50]  Tom L. Blundell,et al.  TIMBAL v2: update of a database holding small molecules modulating protein–protein interactions , 2013, Database J. Biol. Databases Curation.

[51]  Peter Buchwald,et al.  Small‐molecule protein–protein interaction inhibitors: Therapeutic potential in light of molecular size, chemical space, and ligand binding efficiency considerations , 2010, IUBMB life.

[52]  Olivier Sperandio,et al.  Rationalizing the chemical space of protein-protein interaction inhibitors. , 2010, Drug discovery today.

[53]  Zhengwei Peng,et al.  Druggability assessment of protein-protein interfaces. , 2011, Future medicinal chemistry.

[54]  Michelle R Arkin,et al.  The road less traveled: modulating signal transduction enzymes by inhibiting their protein-protein interactions. , 2009, Current opinion in chemical biology.

[55]  Harry Jubb,et al.  Protein-protein interactions as druggable targets: recent technological advances. , 2013, Current opinion in pharmacology.

[56]  Xavier Morelli,et al.  2P2Ichem: focused chemical libraries dedicated to orthosteric modulation of protein–protein interactions , 2013 .

[57]  Giovanna Zinzalla.  Understanding and Exploiting Protein–Protein Interactions as Drug Targets , 2013 .

[58]  Christopher L. McClendon,et al.  Reaching for high-hanging fruit in drug discovery at protein–protein interfaces , 2007, Nature.

[59]  Xiaohong Liu,et al.  New Class of HIV-1 Integrase (IN) Inhibitors with a Dual Mode of Action , 2012, The Journal of Biological Chemistry.

[60]  R. Neubig,et al.  Small Molecule Protein–Protein Interaction Inhibitors as CNS Therapeutic Agents: Current Progress and Future Hurdles , 2009, Neuropsychopharmacology.

[61]  Nobuyoshi Sugaya,et al.  Dr. PIAS: an integrative system for assessing the druggability of protein-protein interactions , 2011, BMC Bioinformatics.

[62]  Stephen R. Johnson,et al.  Molecular properties that influence the oral bioavailability of drug candidates. , 2002, Journal of medicinal chemistry.

[63]  Hyeong Jun An,et al.  Estimating the size of the human interactome , 2008, Proceedings of the National Academy of Sciences.

[64]  Thomas Madej,et al.  Modulating protein-protein interactions with small molecules: the importance of binding hotspots. , 2012, Journal of molecular biology.

[65]  David C Fry,et al.  Small-molecule inhibitors of protein-protein interactions: how to mimic a protein partner. , 2012, Current pharmaceutical design.

[66]  R. Hartmann,et al.  Prediction of protein-protein interaction inhibitors by chemoinformatics and machine learning methods. , 2007, Journal of medicinal chemistry.

[67]  T. Berg.  Small-molecule inhibitors of protein-protein interactions. , 2008, Current opinion in drug discovery & development.

[68]  Jonathan C. Fuller,et al.  Predicting druggable binding sites at the protein-protein interface. , 2009, Drug discovery today.

[69]  Jan van Dijk,et al.  Searching for the Holy Grail: Images of Interactive Television , 2001, New Media Soc..

[70]  K. Audouze,et al.  Emerging classes of protein-protein interaction inhibitors and new tools for their development. , 2004, Current opinion in chemical biology.

[71]  L. Vassilev,et al.  Small-molecule inhibitors of the p53-MDM2 interaction. , 2011, Current topics in microbiology and immunology.

[72]  Alicia P. Higueruelo,et al.  Atomic Interactions and Profile of Small Molecules Disrupting Protein–Protein Interfaces: the TIMBAL Database , 2009, Chemical biology & drug design.

[73]  Sébastien Lê,et al.  FactoMineR: An R Package for Multivariate Analysis , 2008 .

[74]  Xavier Morelli,et al.  Searching for the Holy Grail; protein–protein interaction analysis and modulation , 2012, EMBO reports.