1
|
Ong WJG, Kirubakaran P, Karanicolas J. Poor Generalization by Current Deep Learning Models for Predicting Binding Affinities of Kinase Inhibitors. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2023:2023.09.04.556234. [PMID: 37732243 PMCID: PMC10508770 DOI: 10.1101/2023.09.04.556234] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 09/22/2023]
Abstract
The extreme surge of interest over the past decade surrounding the use of neural networks has inspired many groups to deploy them for predicting binding affinities of drug-like molecules to their receptors. A model that can accurately make such predictions has the potential to screen large chemical libraries and help streamline the drug discovery process. However, despite reports of models that accurately predict quantitative inhibition using protein kinase sequences and inhibitors' SMILES strings, it is still unclear whether these models can generalize to previously unseen data. Here, we build a Convolutional Neural Network (CNN) analogous to those previously reported and evaluate the model over four datasets commonly used for inhibitor/kinase predictions. We find that the model performs comparably to those previously reported, provided that the individual data points are randomly split between the training set and the test set. However, model performance is dramatically deteriorated when all data for a given inhibitor is placed together in the same training/testing fold, implying that information leakage underlies the models' performance. Through comparison to simple models in which the SMILES strings are tokenized, or in which test set predictions are simply copied from the closest training set data points, we demonstrate that there is essentially no generalization whatsoever in this model. In other words, the model has not learned anything about molecular interactions, and does not provide any benefit over much simpler and more transparent models. These observations strongly point to the need for richer structure-based encodings, to obtain useful prospective predictions of not-yet-synthesized candidate inhibitors.
Collapse
Affiliation(s)
- Wern Juin Gabriel Ong
- Cancer Signaling & Microenvironment Program, Fox Chase Cancer Center, Philadelphia, PA 19111
- Bowdoin College, Brunswick, ME 04011
| | - Palani Kirubakaran
- Cancer Signaling & Microenvironment Program, Fox Chase Cancer Center, Philadelphia, PA 19111
| | - John Karanicolas
- Cancer Signaling & Microenvironment Program, Fox Chase Cancer Center, Philadelphia, PA 19111
| |
Collapse
|
2
|
Zhang Y, Liu M, Wang J, Huang J, Guo M, Zuo L, Xu B, Cao S, Lin X. Targeting Protein Kinase Inhibitors with Traditional Chinese Medicine. Curr Drug Targets 2019; 20:1505-1516. [DOI: 10.2174/1389450120666190802125959] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/14/2019] [Revised: 06/21/2019] [Accepted: 06/25/2019] [Indexed: 02/07/2023]
Abstract
Protein kinases play critical roles in the control of cell growth, proliferation, migration, and
angiogenesis, through their catalytic activity. Over the past years, numerous protein kinase inhibitors
have been identified and are being successfully used clinically. Traditional Chinese medicine (TCM)
represents a large class of bioactive substances, and some of them display anticancer activity via inhibiting
protein kinases signal pathway. Some of the TCM have been used to treat tumors clinically in
China for many years. The p38mitogen-activated protein kinase (MAPK), phosphoinositide 3-kinase,
serine/threonine-specific protein kinases (PI3K/AKT/mTOR), and extracellular signal-regulated kinases
(ERK) pathways are considered important signals in cancer cell development. In the present article,
the recent progress of TCM that exhibited significant inhibitory activity towards a range of protein
kinases is discussed. The clinical efficacy of TCM with inhibitory effects on protein kinases in
treating a tumor is also presented. The article also discussed the prospects and problems in the development
of anticancer agents with TCM.
Collapse
Affiliation(s)
- Yangyang Zhang
- Department of Pharmacology, School of Pharmacy, Southwest Medical University, Luzhou, Sichuan 646000, China
| | - Minghua Liu
- Department of Pharmacology, School of Pharmacy, Southwest Medical University, Luzhou, Sichuan 646000, China
| | - Jun Wang
- Department of Pharmacology, School of Pharmacy, Southwest Medical University, Luzhou, Sichuan 646000, China
| | - Jianlin Huang
- Department of Pharmacology, School of Pharmacy, Southwest Medical University, Luzhou, Sichuan 646000, China
| | - Mingyue Guo
- Department of Pharmacology, School of Pharmacy, Southwest Medical University, Luzhou, Sichuan 646000, China
| | - Ling Zuo
- Department of Pharmacology, School of Pharmacy, Southwest Medical University, Luzhou, Sichuan 646000, China
| | - Biantiao Xu
- Department of Pharmacology, School of Pharmacy, Southwest Medical University, Luzhou, Sichuan 646000, China
| | - Shousong Cao
- Department of Pharmacology, School of Pharmacy, Southwest Medical University, Luzhou, Sichuan 646000, China
| | - Xiukun Lin
- Department of Pharmacology, School of Pharmacy, Southwest Medical University, Luzhou, Sichuan 646000, China
| |
Collapse
|
3
|
Parca L, Ariano B, Cabibbo A, Paoletti M, Tamburrini A, Palmeri A, Ausiello G, Helmer-Citterich M. Kinome-wide identification of phosphorylation networks in eukaryotic proteomes. Bioinformatics 2019; 35:372-379. [PMID: 30016513 PMCID: PMC6361239 DOI: 10.1093/bioinformatics/bty545] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/19/2018] [Revised: 06/06/2018] [Accepted: 07/12/2018] [Indexed: 01/10/2023] Open
Abstract
Motivation Signaling and metabolic pathways are finely regulated by a network of protein phosphorylation events. Unraveling the nature of this intricate network, composed of kinases, target proteins and their interactions, is therefore of crucial importance. Although thousands of kinase-specific phosphorylations (KsP) have been annotated in model organisms their kinase-target network is far from being complete, with less studied organisms lagging behind. Results In this work, we achieved an automated and accurate identification of kinase domains, inferring the residues that most likely contribute to peptide specificity. We integrated this information with the target peptides of known human KsP to predict kinase-specific interactions in other eukaryotes through a deep neural network, outperforming similar methods. We analyzed the differential conservation of kinase specificity among eukaryotes revealing the high conservation of the specificity of tyrosine kinases. With this approach we discovered 1590 novel KsP of potential clinical relevance in the human proteome. Availability and implementation http://akid.bio.uniroma2.it. Supplementary information Supplementary data are available at Bioinformatics online.
Collapse
Affiliation(s)
- Luca Parca
- Department of Biology, Centro di Bioinformatica Molecolare, University of Rome “Tor Vergata”, Rome, Italy
| | - Bruno Ariano
- Department of Biology, Centro di Bioinformatica Molecolare, University of Rome “Tor Vergata”, Rome, Italy
| | - Andrea Cabibbo
- Department of Biology, Centro di Bioinformatica Molecolare, University of Rome “Tor Vergata”, Rome, Italy
| | - Marco Paoletti
- Department of Biology, Centro di Bioinformatica Molecolare, University of Rome “Tor Vergata”, Rome, Italy
| | - Annalaura Tamburrini
- Department of Biology, Centro di Bioinformatica Molecolare, University of Rome “Tor Vergata”, Rome, Italy
| | - Antonio Palmeri
- Department of Biology, Centro di Bioinformatica Molecolare, University of Rome “Tor Vergata”, Rome, Italy
| | - Gabriele Ausiello
- Department of Biology, Centro di Bioinformatica Molecolare, University of Rome “Tor Vergata”, Rome, Italy
| | - Manuela Helmer-Citterich
- Department of Biology, Centro di Bioinformatica Molecolare, University of Rome “Tor Vergata”, Rome, Italy
| |
Collapse
|
4
|
Avram S, Bora A, Halip L, Curpăn R. Modeling Kinase Inhibition Using Highly Confident Data Sets. J Chem Inf Model 2018; 58:957-967. [DOI: 10.1021/acs.jcim.7b00729] [Citation(s) in RCA: 11] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/14/2022]
Affiliation(s)
- Sorin Avram
- Department of Computational Chemistry, Institute of Chemistry Timişoara of Romanian Academy, 24 Mihai Viteazu Avenue, 300223-Timişoara, Romania
| | - Alina Bora
- Department of Computational Chemistry, Institute of Chemistry Timişoara of Romanian Academy, 24 Mihai Viteazu Avenue, 300223-Timişoara, Romania
| | - Liliana Halip
- Department of Computational Chemistry, Institute of Chemistry Timişoara of Romanian Academy, 24 Mihai Viteazu Avenue, 300223-Timişoara, Romania
| | - Ramona Curpăn
- Department of Computational Chemistry, Institute of Chemistry Timişoara of Romanian Academy, 24 Mihai Viteazu Avenue, 300223-Timişoara, Romania
| |
Collapse
|
5
|
Liu M, Zhao G, Cao S, Zhang Y, Li X, Lin X. Development of Certain Protein Kinase Inhibitors with the Components from Traditional Chinese Medicine. Front Pharmacol 2017; 7:523. [PMID: 28119606 PMCID: PMC5220067 DOI: 10.3389/fphar.2016.00523] [Citation(s) in RCA: 11] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/13/2016] [Accepted: 12/15/2016] [Indexed: 12/27/2022] Open
Abstract
Traditional Chinese medicines (TCMs) have been used in China for more than two thousand years, and some of them have been confirmed to be effective in cancer treatment. Protein kinases play critical roles in control of cell growth, proliferation, migration, survival, and angiogenesis and mediate their biological effects through their catalytic activity. In recent years, numerous protein kinase inhibitors have been developed and are being used clinically. Anticancer TCMs represent a large class of bioactive substances, and some of them display anticancer activity via inhibiting protein kinases to affect the phosphoinositide 3-kinase, serine/threonine-specific protein kinases, pechanistic target of rapamycin (PI3K/AKT/mTOR), P38, mitogen-activated protein kinase (MAPK) and extracellular signal-regulated kinases (ERK) pathways. In the present article, we comprehensively reviewed several components isolated from anticancer TCMs that exhibited significantly inhibitory activity toward a range of protein kinases. These components, which belong to diverse structural classes, are reviewed herein, based upon the kinases that they inhibit. The prospects and problems in development of the anticancer TCMs are also discussed.
Collapse
Affiliation(s)
- Minghua Liu
- Department of Pharmacology, School of Pharmacy, Southwest Medical University Luzhou, China
| | - Ge Zhao
- Department of Pharmacology, School of Pharmacy, Southwest Medical University Luzhou, China
| | - Shousong Cao
- Department of Pharmacology, School of Pharmacy, Southwest Medical University Luzhou, China
| | - Yangyang Zhang
- Department of Pharmacology, School of Pharmacy, Southwest Medical University Luzhou, China
| | - Xiaofang Li
- Department of Pharmacology, School of Pharmacy, Southwest Medical University Luzhou, China
| | - Xiukun Lin
- Department of Pharmacology, School of Pharmacy, Southwest Medical University Luzhou, China
| |
Collapse
|
6
|
Merget B, Turk S, Eid S, Rippmann F, Fulle S. Profiling Prediction of Kinase Inhibitors: Toward the Virtual Assay. J Med Chem 2016; 60:474-485. [PMID: 27966949 DOI: 10.1021/acs.jmedchem.6b01611] [Citation(s) in RCA: 73] [Impact Index Per Article: 9.1] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/26/2022]
Abstract
Kinome-wide screening would have the advantage of providing structure-activity relationships against hundreds of targets simultaneously. Here, we report the generation of ligand-based activity prediction models for over 280 kinases by employing Machine Learning methods on an extensive data set of proprietary bioactivity data combined with open data. High quality (AUC > 0.7) was achieved for ∼200 kinases by (1) combining open with proprietary data, (2) choosing Random Forest over alternative tested Machine Learning methods, and (3) balancing the training data sets. Tests on left-out and external data indicate a high value for virtual screening projects. Importantly, the derived models are evenly distributed across the kinome tree, allowing reliable profiling prediction for all kinase branches. The prediction quality was further improved by employing experimental bioactivity fingerprints of a small kinase subset. Overall, the generated models can support various hit identification tasks, including virtual screening, compound repurposing, and the detection of potential off-targets.
Collapse
Affiliation(s)
- Benjamin Merget
- BioMed X Innovation Center , Im Neuenheimer Feld 515, 69120 Heidelberg, Germany
| | - Samo Turk
- BioMed X Innovation Center , Im Neuenheimer Feld 515, 69120 Heidelberg, Germany
| | - Sameh Eid
- BioMed X Innovation Center , Im Neuenheimer Feld 515, 69120 Heidelberg, Germany
| | - Friedrich Rippmann
- Global Computational Chemistry, Merck KGaA , Frankfurter Strasse 250, 64293 Darmstadt, Germany
| | - Simone Fulle
- BioMed X Innovation Center , Im Neuenheimer Feld 515, 69120 Heidelberg, Germany
| |
Collapse
|
7
|
Bora A, Avram S, Ciucanu I, Raica M, Avram S. Predictive Models for Fast and Effective Profiling of Kinase Inhibitors. J Chem Inf Model 2016; 56:895-905. [DOI: 10.1021/acs.jcim.5b00646] [Citation(s) in RCA: 19] [Impact Index Per Article: 2.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/22/2022]
Affiliation(s)
- Alina Bora
- Department of Chemistry, Faculty of Chemistry-Biology-Geography, West University of Timisoara, 16 Pestalozzi Str., 300115, Timisoara, Romania
- Department
of Computational Chemistry, Institute of Chemistry, Timisoara of Romanian Academy, 24 Mihai Viteazu Avenue, Timisoara, 300223, Romania
| | - Sorin Avram
- Department
of Computational Chemistry, Institute of Chemistry, Timisoara of Romanian Academy, 24 Mihai Viteazu Avenue, Timisoara, 300223, Romania
| | - Ionel Ciucanu
- Department of Chemistry, Faculty of Chemistry-Biology-Geography, West University of Timisoara, 16 Pestalozzi Str., 300115, Timisoara, Romania
| | | | | |
Collapse
|
8
|
Abstract
Attrition due to nonclinical safety represents a major issue for the productivity of pharmaceutical research and development (R&D) organizations, especially during the compound optimization stages of drug discovery and the early stages of clinical development. Focusing on decreasing nonclinical safety-related attrition is not a new concept, and various approaches have been experimented with over the last two decades. Front-loading testing funnels in Discovery with in vitro toxicity assays designed to rapidly identify unfavorable molecules was the approach adopted by most pharmaceutical R&D organizations a few years ago. However, this approach has also a non-negligible opportunity cost. Hence, significant refinements to the "fail early, fail often" paradigm have been proposed recently to reflect the complexity of accurately categorizing compounds with early data points without taking into account other important contextual aspects, in particular efficacious systemic and tissue exposures. This review provides an overview of toxicology approaches and models that can be used in pharmaceutical Discovery at the series/lead identification and lead optimization stages to guide and inform chemistry efforts, as well as a personal view on how to best use them to meet nonclinical safety-related attrition objectives consistent with a sustainable pharmaceutical R&D model. The scope of this review is limited to small molecules, as large molecules are associated with challenges that are quite different. Finally, a perspective on how several emerging technologies may impact toxicity evaluation is also provided.
Collapse
Affiliation(s)
- Eric A G Blomme
- Global Preclinical Safety, AbbVie Inc. , 1 North Waukegan Road, North Chicago, Illinois 60064, United States
| | - Yvonne Will
- Drug Safety Research and Development, Pfizer , Eastern Point Road, Groton, Connecticut 06340, United States
| |
Collapse
|
9
|
Karasev DA, Veselovsky AV, Oparina NY, Filimonov DA, Sobolev BN. Prediction of amino acid positions specific for functional groups in a protein family based on local sequence similarity. J Mol Recognit 2015; 29:159-69. [DOI: 10.1002/jmr.2515] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/31/2015] [Revised: 09/28/2015] [Accepted: 09/30/2015] [Indexed: 01/24/2023]
Affiliation(s)
- Dmitry A. Karasev
- Russian National Research Medical University; Moscow Russia
- Laboratory of Structure-Function Based Drug Design; Institute of Biomedical Chemistry (IBMC); Moscow Russia
| | - Alexander V. Veselovsky
- Laboratory of Structure Bioinformatics; Institute of Biomedical Chemistry (IBMC); Moscow Russia
| | - Nina Yu. Oparina
- Department of Medical Biochemistry and Microbiology; Uppsala University; Uppsala Sweden
- Engelhardt Institute of Molecular Biology; Moscow Russia
| | - Dmitry A. Filimonov
- Laboratory of Structure Bioinformatics; Institute of Biomedical Chemistry (IBMC); Moscow Russia
| | - Boris N. Sobolev
- Laboratory of Structure-Function Based Drug Design; Institute of Biomedical Chemistry (IBMC); Moscow Russia
| |
Collapse
|
10
|
Via A, Zanzoni A. A prismatic view of protein phosphorylation in health and disease. Front Genet 2015; 6:131. [PMID: 25904935 PMCID: PMC4387955 DOI: 10.3389/fgene.2015.00131] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/05/2015] [Accepted: 03/18/2015] [Indexed: 11/13/2022] Open
Affiliation(s)
- Allegra Via
- Department of Physics, Sapienza University of Rome Rome, Italy
| | - Andreas Zanzoni
- Technological Advances for Genomics and Clinics (TAGC), UMR_S1090, INSERM Marseille, France ; Technological Advances for Genomics and Clinics (TAGC), UMR_S1090, Aix Marseille Université Marseille, France
| |
Collapse
|