Consensus model for identification of novel PI3K inhibitors in large chemical library

Phosphoinositide 3-kinases (PI3Ks) inhibitors have treatment potential for cancer, diabetes, cardiovascular disease, chronic inflammation and asthma. A consensus model consisting of three base classifiers (AODE, kNN, and SVM) trained with 1,283 positive compounds (PI3K inhibitors), 16 negative compounds (PI3K non-inhibitors) and 64,078 generated putative negatives was developed for predicting compounds with PI3K inhibitory activity of IC50 ≤ 10 μM. The consensus model has an estimated false positive rate of 0.75%. Nine novel potential inhibitors were identified using the consensus model and several of these contain structural features that are consistent with those found to be important for PI3K inhibitory activities. An advantage of the current model is that it does not require knowledge of 3D structural information of the various PI3K isoforms, which is not readily available for all isoforms.

[1]  Yu Zong Chen,et al.  Prediction of Cytochrome P450 3A4, 2D6, and 2C9 Inhibitors and Substrates by Using Support Vector Machines , 2005, J. Chem. Inf. Model..

[2]  Paola Gramatica,et al.  Principles of QSAR models validation: internal and external , 2007 .

[3]  B. Matthews.  Comparison of the predicted and observed secondary structure of T4 phage lysozyme. , 1975, Biochimica et biophysica acta.

[4]  Jürgen Bajorath,et al.  Towards Unified Compound Screening Strategies: A Critical Evaluation of Error Sources in Experimental and Virtual High‐Throughput Screening , 2006 .

[5]  M. Herlyn,et al.  Structure-based design of an organoruthenium phosphatidyl-inositol-3-kinase inhibitor reveals a switch governing lipid kinase potency and selectivity. , 2008, ACS chemical biology.

[6]  D. Wiederschain,et al.  Class IA phosphoinositide 3-kinase isoforms and human tumorigenesis: implications for cancer drug discovery and development , 2008, Current opinion in oncology.

[7]  Xianghui Liu,et al.  SVM Model for Virtual Screening of Lck Inhibitors , 2009, J. Chem. Inf. Model..

[8]  C. Rommel,et al.  Furan-2-ylmethylene thiazolidinediones as novel, potent, and selective inhibitors of phosphoinositide 3-kinase gamma. , 2006, Journal of medicinal chemistry.

[9]  Lewis C Cantley,et al.  The phosphoinositide 3-kinase pathway. , 2002, Science.

[10]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[11]  Bernd Giese,et al.  Targeting phosphoinositide 3-kinase: moving towards therapy. , 2008, Biochimica et biophysica acta.

[12]  Vipin Kumar,et al.  Introduction to Data Mining , 2022, Data Mining and Machine Learning Applications.

[13]  W. Denny,et al.  Synthesis, biological evaluation and molecular modelling of sulfonohydrazides as selective PI3K p110α inhibitors , 2007 .

[14]  Pierre Baldi,et al.  Assessing the accuracy of prediction algorithms for classification: an overview , 2000, Bioinform..

[15]  Brian K. Shoichet,et al.  Virtual screening of chemical libraries , 2004, Nature.

[16]  J. F. Wang,et al.  Prediction of P-Glycoprotein Substrates by a Support Vector Machine Approach , 2004, J. Chem. Inf. Model..

[17]  Markus H. J. Seifert,et al.  Essential factors for successful virtual screening. , 2008, Mini reviews in medicinal chemistry.

[18]  Amanda C. Schierz.  Virtual screening of bioassay data , 2009, J. Cheminformatics.

[19]  Boon Chuan Low,et al.  Evaluation of Virtual Screening Performance of Support Vector Machines Trained by Sparsely Distributed Active Compounds , 2008, J. Chem. Inf. Model..

[20]  Marketa Zvelebil,et al.  Phosphoinositide 3-kinase signalling--which way to target? , 2003, Trends in pharmacological sciences.

[21]  W. Denny,et al.  Phosphoinositide-3-kinase (PI3K) inhibitors: identification of new scaffolds using virtual screening. , 2009, Bioorganic & medicinal chemistry letters.

[22]  Xin Chen,et al.  Virtual screening to successfully identify novel janus kinase 3 inhibitors: a sequential focused screening approach. , 2008, Journal of medicinal chemistry.

[23]  M. Waterfield,et al.  Synthesis and biological evaluation of 4-morpholino-2-phenylquinazolines and related derivatives as novel PI3 kinase p110alpha inhibitors. , 2006, Bioorganic & medicinal chemistry.

[24]  Xin Chen,et al.  Effect of Molecular Descriptor Feature Selection in Support Vector Machine Classification of Pharmacokinetic and Toxicological Properties of Chemical Agents , 2004, J. Chem. Inf. Model..

[25]  Z R Li,et al.  Prediction of compounds with specific pharmacodynamic, pharmacokinetic or toxicological property by statistical learning methods. , 2006, Mini reviews in medicinal chemistry.

[26]  Paola Gramatica,et al.  The Importance of Being Earnest: Validation is the Absolute Essential for Successful Application and Interpretation of QSPR Models , 2003 .

[27]  Raphaël Frédérick,et al.  Phosphoinositide-3-kinases (PI3Ks): Combined Comparative Modeling and 3D-QSAR To Rationalize the Inhibition of p110α , 2008, J. Chem. Inf. Model..

[28]  Bernard F. Buxton,et al.  Support Vector Machines in Combinatorial Chemistry , 2001 .

[29]  Z. R. Li,et al.  A support vector machines approach for virtual screening of active compounds of single and multiple mechanisms from large libraries at an improved hit-rate and enrichment factor. , 2008, Journal of molecular graphics & modelling.

[30]  Pablo San Segundo,et al.  Exploiting CPU Bit Parallel Operations to Improve Efficiency in Search , 2007 .

[31]  B. Shoichet,et al.  A common mechanism underlying promiscuous inhibitors from virtual and high-throughput screening. , 2002, Journal of medicinal chemistry.

[32]  Christopher I. Bayly,et al.  Evaluating Virtual Screening Methods: Good and Bad Metrics for the "Early Recognition" Problem , 2007, J. Chem. Inf. Model..

[33]  R. Czerminski,et al.  Use of Support Vector Machine in Pattern Classification: Application to QSAR Studies , 2001 .

[34]  P. Fischer,et al.  Computational chemistry approaches to drug discovery in signal transduction , 2008, Biotechnology journal.

[35]  Juan J Perez,et al.  Managing molecular diversity. , 2005, Chemical Society reviews.

[36]  Nina Nikolova-Jeliazkova,et al.  QSAR Applicability Domain Estimation by Projection of the Training Set in Descriptor Space: A Review , 2005, Alternatives to laboratory animals : ATLA.

[37]  Robbie Loewith,et al.  A Pharmacological Map of the PI3-K Family Defines a Role for p110α in Insulin Signaling , 2006, Cell.