1
|
Zhang Y, Li J, Lin S, Zhao J, Xiong Y, Wei DQ. An end-to-end method for predicting compound-protein interactions based on simplified homogeneous graph convolutional network and pre-trained language model. J Cheminform 2024; 16:67. [PMID: 38849874 PMCID: PMC11162000 DOI: 10.1186/s13321-024-00862-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/29/2023] [Accepted: 05/19/2024] [Indexed: 06/09/2024] Open
Abstract
Identification of interactions between chemical compounds and proteins is crucial for various applications, including drug discovery, target identification, network pharmacology, and elucidation of protein functions. Deep neural network-based approaches are becoming increasingly popular in efficiently identifying compound-protein interactions with high-throughput capabilities, narrowing down the scope of candidates for traditional labor-intensive, time-consuming and expensive experimental techniques. In this study, we proposed an end-to-end approach termed SPVec-SGCN-CPI, which utilized simplified graph convolutional network (SGCN) model with low-dimensional and continuous features generated from our previously developed model SPVec and graph topology information to predict compound-protein interactions. The SGCN technique, dividing the local neighborhood aggregation and nonlinearity layer-wise propagation steps, effectively aggregates K-order neighbor information while avoiding neighbor explosion and expediting training. The performance of the SPVec-SGCN-CPI method was assessed across three datasets and compared against four machine learning- and deep learning-based methods, as well as six state-of-the-art methods. Experimental results revealed that SPVec-SGCN-CPI outperformed all these competing methods, particularly excelling in unbalanced data scenarios. By propagating node features and topological information to the feature space, SPVec-SGCN-CPI effectively incorporates interactions between compounds and proteins, enabling the fusion of heterogeneity. Furthermore, our method scored all unlabeled data in ChEMBL, confirming the top five ranked compound-protein interactions through molecular docking and existing evidence. These findings suggest that our model can reliably uncover compound-protein interactions within unlabeled compound-protein pairs, carrying substantial implications for drug re-profiling and discovery. In summary, SPVec-SGCN demonstrates its efficacy in accurately predicting compound-protein interactions, showcasing potential to enhance target identification and streamline drug discovery processes.Scientific contributionsThe methodology presented in this work not only enables the comparatively accurate prediction of compound-protein interactions but also, for the first time, take sample imbalance which is very common in real world and computation efficiency into consideration simultaneously, accelerating the target identification and drug discovery process.
Collapse
Affiliation(s)
- Yufang Zhang
- School of Mathematical Sciences and SJTU-Yale Joint Center for Biostatistics and Data Science, Shanghai Jiao Tong University, Shanghai, 200240, China
- Peng Cheng Laboratory, Shenzhen, 518055, Guangdong, China
- Zhongjing Research and Industrialization, Institute of Chinese Medicine, Zhongguancun Scientific Park, Meixi, Nanyang, 473006, Henan, China
| | - Jiayi Li
- State Key Laboratory of Microbial Metabolism, School of Life Sciences and Biotechnology, and Joint Laboratory of International Cooperation in Metabolic and Developmental Sciences, Ministry of Education, Shanghai JiaoTong University, Shanghai, China
| | - Shenggeng Lin
- State Key Laboratory of Microbial Metabolism, School of Life Sciences and Biotechnology, and Joint Laboratory of International Cooperation in Metabolic and Developmental Sciences, Ministry of Education, Shanghai JiaoTong University, Shanghai, China
| | - Jianwei Zhao
- State Key Laboratory of Microbial Metabolism, School of Life Sciences and Biotechnology, and Joint Laboratory of International Cooperation in Metabolic and Developmental Sciences, Ministry of Education, Shanghai JiaoTong University, Shanghai, China
| | - Yi Xiong
- State Key Laboratory of Microbial Metabolism, School of Life Sciences and Biotechnology, and Joint Laboratory of International Cooperation in Metabolic and Developmental Sciences, Ministry of Education, Shanghai JiaoTong University, Shanghai, China.
- Shanghai Artificial Intelligence Laboratory, Shanghai, 200232, China.
| | - Dong-Qing Wei
- Peng Cheng Laboratory, Shenzhen, 518055, Guangdong, China.
- Zhongjing Research and Industrialization, Institute of Chinese Medicine, Zhongguancun Scientific Park, Meixi, Nanyang, 473006, Henan, China.
- State Key Laboratory of Microbial Metabolism, School of Life Sciences and Biotechnology, and Joint Laboratory of International Cooperation in Metabolic and Developmental Sciences, Ministry of Education, Shanghai JiaoTong University, Shanghai, China.
| |
Collapse
|
2
|
Pharmacological characterisation of a tool αvβ1 integrin small molecule RGD-mimetic inhibitor. Eur J Pharmacol 2018; 842:239-247. [PMID: 30389632 DOI: 10.1016/j.ejphar.2018.10.045] [Citation(s) in RCA: 13] [Impact Index Per Article: 2.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/20/2018] [Revised: 10/25/2018] [Accepted: 10/29/2018] [Indexed: 11/24/2022]
Abstract
Compound 8 is a selective αvβ1 small molecule inhibitor that has been used in pre-clinical studies to identify and characterise the αvβ1 integrin as a potential target in fibrotic disease. In this study we further investigated the selectivity and pharmacokinetics of compound 8 to determine a link between the levels of αvβ1 engagement required to achieve in vivo pharmacodynamic efficacy. The selectivity of compound 8 for the arginyl-glycinyl-aspartic acid and β1 integrins was measured using purified integrin protein preparations in radioligand binding studies with both labelled ([3H]compound 8) and unlabelled versions. The pharmacokinetic profile of compound 8 was completed in in vitro blood protein binding assays and in in vivo studies using male C57BL/6 mouse following i.v. dosing. The high selectivity of compound 8 for αvβ1 over the other αv integrins was confirmed, however a reduced selectivity was demonstrated for the β1 integrin family, with high affinity observed for α4β1 (comparable to αvβ1), moderate affinity for α2β1, α3β1 and α8β1, and low affinity for α5β1 and α9β1. Compound 8 was shown to be cleared quickly from the blood with a short half-life of 0.5 h. In conclusion, the data in this study suggest that compound 8 has the potential to engage a number of integrins in vivo beyond αvβ1, that raises a degree of uncertainty regarding its mechanism of action in models of fibrotic disease.
Collapse
|
3
|
Papst S, Noisier AF, Brimble MA, Yang Y, Krissansen GW. Synthesis and biological evaluation of tyrosine modified analogues of the α4β7 integrin inhibitor biotin-R8ERY. Bioorg Med Chem 2012; 20:5139-49. [DOI: 10.1016/j.bmc.2012.07.010] [Citation(s) in RCA: 13] [Impact Index Per Article: 1.1] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/09/2012] [Revised: 06/28/2012] [Accepted: 07/05/2012] [Indexed: 12/24/2022]
|
4
|
Tyrosine modified analogues of the α4β7 integrin inhibitor biotin-R8ERY prepared via Click Chemistry: Synthesis and biological evaluation. Bioorg Med Chem 2012; 20:2638-44. [DOI: 10.1016/j.bmc.2012.02.035] [Citation(s) in RCA: 10] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/19/2011] [Revised: 01/31/2012] [Accepted: 02/13/2012] [Indexed: 11/24/2022]
|
5
|
Papst S, Noisier AFM, Brimble MA, Yang Y, Chan YC, Krissansen GW. Synthesis and SAR of a Library of Cell-Permeable Biotin-R8ERY* Peptidomimetics Inhibiting α4β7 Integrin Mediated Adhesion of TK-1 Cells to MAdCAM-1-Fc. Aust J Chem 2012. [DOI: 10.1071/ch12227] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/04/2023]
Abstract
The α4β7 integrin is a well‐known target for the development of drugs against various inflammatory disease states including inflammatory bowel disease, type 1 diabetes, and multiple sclerosis. The β7 subunit contains the cell adhesion regulatory domain (CARD) motif YDRREY within its cytoplasmic domain, which is an effective peptide agent for inhibiting T-cell adhesion. The synthesis of a library of cell-permeable β7 integrin inhibitors based on the shortened biotin-R8ERY (R8 = (l-arginine)8) motif is reported, wherein the tyrosine residue has been modified. The synthesised peptidomimetics were evaluated in a cell adhesion assay and shown to inhibit Mn2+-activated adhesion of mouse TK-1 T-cells to mouse MAdCAM-1. Several analogues exhibited improved activity to that of the tyrosine-containing lead compound 1 (biotin-R8ERY). Specifically, analogues 4, 10, and 22 bearing a 4-chloro, a 4-nitro, and a 3,3-diphenyl substituent showed an increase in activity of approximately two-fold compared with that of the initial lead compound. The six most active compounds of the tested series had IC50’s between 25 and 50 μM.
Collapse
|
6
|
Rehman A, Soni A, Naik K, Nair S, Palle VP, Dastidar S, Ray A, Alam M, Salman M, Cliffe IA, Sattigeri V. Synthesis and biological activity of N-substituted aminocarbonyl-1,3-dioxolanes as VLA-4 antagonists. Bioorg Med Chem Lett 2010; 20:5514-20. [DOI: 10.1016/j.bmcl.2010.07.069] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/12/2010] [Revised: 07/10/2010] [Accepted: 07/16/2010] [Indexed: 12/22/2022]
|
7
|
Small-molecule inhibitors of integrin alpha2beta1 that prevent pathological thrombus formation via an allosteric mechanism. Proc Natl Acad Sci U S A 2009; 106:719-24. [PMID: 19141632 DOI: 10.1073/pnas.0811622106] [Citation(s) in RCA: 70] [Impact Index Per Article: 4.7] [Reference Citation Analysis] [Abstract] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022] Open
Abstract
There is a grave need for safer antiplatelet therapeutics to prevent heart attack and stroke. Agents targeting the interaction of platelets with the diseased vessel wall could impact vascular disease with minimal effects on normal hemostasis. We targeted integrin alpha(2)beta(1), a collagen receptor, because its overexpression is associated with pathological clot formation whereas its absence does not cause severe bleeding. Structure-activity studies led to highly potent and selective small-molecule inhibitors. Responses of integrin alpha(2)beta(1) mutants to these compounds are consistent with a computational model of their mode of inhibition and shed light on the activation mechanism of I-domain-containing integrins. A potent compound was proven efficacious in an animal model of arterial thrombosis, which demonstrates in vivo efficacy for inhibition of this platelet receptor. These results suggest that targeting integrin alpha(2)beta(1) could be a potentially safe, effective approach to long-term therapy for cardiovascular disease.
Collapse
|
8
|
Choi S, Vilaire G, Marcinkiewicz C, Winkler JD, Bennett JS, DeGrado WF. Small molecule inhibitors of integrin alpha2beta1. J Med Chem 2007; 50:5457-62. [PMID: 17915848 PMCID: PMC3828121 DOI: 10.1021/jm070252b] [Citation(s) in RCA: 33] [Impact Index Per Article: 1.9] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
Abstract
Interactions between the integrin, alpha2beta1, and extracellular matrix (ECM), particularly collagen, play a pivotal role in platelet adhesion and thrombus formation. Platelets interact with collagen in the subendothelial matrix that is exposed by vascular damage. To evaluate the potential of alpha2beta1 inhibitors for anticancer and antithrombotic applications, we have developed a series of small molecule inhibitors of this integrin based on a prolyl-2,3-diaminopropionic acid (DAP) scaffold using solid-phase parallel synthesis. A benzenesulfonamide substituent at the N-terminus of the dipepetide and a benzyl urea at the DAP side chain resulted in tight and highly selective inhibition of alpha2beta1-mediated adhesion of human platelets and other cells to collagen.
Collapse
|
9
|
Dyatkin AB, Gong Y, Miskowski TA, Kimball ES, Prouty SM, Fisher MC, Santulli RJ, Schneider CR, Wallace NH, Hornby PJ, Diamond C, Kinney WA, Maryanoff BE, Damiano BP, He W. Aza-bicyclic amino acid carboxamides as α4β1/α4β7 integrin receptor antagonists. Bioorg Med Chem 2005; 13:6693-702. [PMID: 16112583 DOI: 10.1016/j.bmc.2005.07.022] [Citation(s) in RCA: 11] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/10/2005] [Revised: 07/19/2005] [Accepted: 07/19/2005] [Indexed: 01/11/2023]
Abstract
A series of N-carboxy, N-alkyl, and N-carboxamido azabicyclo[2.2.2]octane carboxamides were prepared and assayed for inhibition of alpha4beta1-VCAM-1 and alpha4beta7-MAdCAM-1 interactions. Potency and alpha4beta1/alpha4beta7 selectivity were sensitive to the substituent R1-R3 in the structures 6, 7, and 8. Several compounds demonstrated low nanomolar balanced alpha4beta1/alpha4beta7 in vitro activity. Two compounds were selected for in vivo leukocytosis studies and demonstrated increases in circulating lymphocytes up to 250% over control.
Collapse
Affiliation(s)
- Alexey B Dyatkin
- Drug Discovery, Johnson & Johnson Pharmaceutical Research & Development, LLC., Spring House, PA 19477-0776, USA.
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
Collapse
|
10
|
|
11
|
Hoshina Y, Ikegami S, Okuyama A, Fukui H, Inoguchi K, Maruyama T, Fujimoto K, Matsumura Y, Aoyama A, Harada T, Tanaka H, Nakamura T. 2,3-Diphenylpropionic acids as potent VLA-4 antagonists. Bioorg Med Chem Lett 2005; 15:217-20. [PMID: 15582442 DOI: 10.1016/j.bmcl.2004.09.089] [Citation(s) in RCA: 10] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/19/2004] [Accepted: 09/30/2004] [Indexed: 10/26/2022]
Abstract
The discovery and SAR of 2,3-diphenylpropionic acid derivatives as highly potent VLA-4 antagonists are described. One representative compound, 9cc has inhibited intercellular adhesion by a VCAM-1/VLA-4 interaction with an IC(50) of 1.7 nM, and has good pharmacokinetics and oral bioavailability.
Collapse
Affiliation(s)
- Yoichiro Hoshina
- Central Research Laboratories, Kaken Pharmaceutical Co. Ltd, 14 Shinomiya-minamikawara, Yamashina, Kyoto 607-8042, Japan
| | | | | | | | | | | | | | | | | | | | | | | |
Collapse
|
12
|
Doherty GA, Yang GX, Borges E, Tong S, McCauley ED, Treonz KM, Van Riper G, Pacholok S, Si Q, Koo GC, Shah K, Mumford RA, Hagmann WK. N-isonicotinoyl-(L)-4-aminophenylalanine derivatives as tight binding VLA-4 antagonists. Bioorg Med Chem Lett 2003; 13:1891-5. [PMID: 12749892 DOI: 10.1016/s0960-894x(03)00308-1] [Citation(s) in RCA: 12] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/22/2022]
Abstract
A series of isonicotinoyl-(L)-aminophenylalanine derivatives was prepared and evaluated as VLA-4 antagonists. These compounds exhibit subnanomolar binding affinity to VLA-4 and significant off-rates. The interplay between off-rate, protein binding and pharmacokinetics is discussed.
Collapse
Affiliation(s)
- George A Doherty
- Department of Medicinal Chemistry, Merck Research Laboratories, Rahway, NJ 07065, USA.
| | | | | | | | | | | | | | | | | | | | | | | | | |
Collapse
|
13
|
Abstract
Many lead compounds with the potential to progress to viable drug candidates have been identified from libraries during the past two years. There are two key strategies most often employed to find leads from libraries: first, high-throughput biological screening of corporate compound collections; and second, synthesis and screening of project-directed libraries (i.e. target-based libraries). Numerous success stories, including the discovery of several clinical candidates, testify to the utility of chemical library collections as proven sources of new leads for drug development.
Collapse
Affiliation(s)
- Adam Golebiowski
- Procter & Gamble Pharmaceuticals, Health Care Research Center, Mason, OH 45040-8006, USA.
| | | | | |
Collapse
|
14
|
Castanedo GM, Sailes FC, Dubree NJP, Nicholas JB, Caris L, Clark K, Keating SM, Beresini MH, Chiu H, Fong S, Marsters JC, Jackson DY, Sutherlin DP. Solid-phase synthesis of dual α4β1/α4β7 integrin antagonists: two scaffolds with overlapping pharmacophores. Bioorg Med Chem Lett 2002; 12:2913-7. [PMID: 12270174 DOI: 10.1016/s0960-894x(02)00597-8] [Citation(s) in RCA: 9] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/27/2022]
Abstract
Two structural classes of dual alpha4beta1/alpha4beta7 integrin antagonists were investigated via solid-phase parallel synthesis. Using an acylated amino acid backbone, lead compounds containing biphenylalanine or tyrosine carbamate scaffolds were optimized for inhibition of alpha4beta1/VCAM and alpha4beta7/MAdCAM. A comparison of the structure-activity relationships in the inhibition of the alpha4beta7/MAdCAM interaction for substituted amines employed in both scaffolds suggests a similar binding mode for the compounds.
Collapse
Affiliation(s)
- Georgette M Castanedo
- Department of Bioorganic Chemistry, Genentech, Inc., South San Francisco, CA 94080, USA
| | | | | | | | | | | | | | | | | | | | | | | | | |
Collapse
|
15
|
Chen L, Trilles R, Miklowski D, Huang TN, Fry D, Campbell R, Rowan K, Schwinge V, Tilley JW. Focused library approach for identification of new N-acylphenylalanines as VCAM/VLA-4 antagonists. Bioorg Med Chem Lett 2002; 12:1679-82. [PMID: 12039589 DOI: 10.1016/s0960-894x(02)00201-9] [Citation(s) in RCA: 14] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/27/2022]
Abstract
A structure-based focused library approach was employed in an effort to identify more lipophilic replacements for the N-benzylpyroglutamyl group of the VCAM/VLA-4 antagonist 2. This effort led to the discovery of two new classes of potent antagonists characterized by the N-(alpha-phenylcyclopentanoyl- and the N-(2,6-dimethylbenzoyl)-derivatives 60 and 64.
Collapse
Affiliation(s)
- Li Chen
- Roche Research Center, Hoffmann-La Roche Inc., 340 Kingsland Street, Nutley, NJ 07110, USA.
| | | | | | | | | | | | | | | | | |
Collapse
|
16
|
Lin LS, Kopka IE, Mumford RA, Magriotis PA, Lanza T, Durette PL, Kamenecka T, Young DN, de Laszlo SE, McCauley E, Riper GV, Kidambi U, Egger LA, Tong X, Lyons K, Vincent S, Stearns R, Colletti A, Teffera Y, Fenyk-Melody J, Schmidt JA, MacCoss M, Hagmann WK. The discovery of acylated beta-amino acids as potent and orally bioavailable VLA-4 antagonists. Bioorg Med Chem Lett 2002; 12:611-4. [PMID: 11844683 DOI: 10.1016/s0960-894x(01)00818-6] [Citation(s) in RCA: 10] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
Abstract
Acylated beta-amino acids are described as potent, specific and orally bioavailable antagonists of VLA-4. The initial lead was identified from a combinatorial library. Subsequent optimization using a traditional medicinal chemistry approach led to significant improvement in potency (up to 8-fold) while maintaining good pharmacokinetic properties.
Collapse
Affiliation(s)
- Linus S Lin
- Department of Medicinal Chemistry, Merck Research Laboratories, Rahway, NJ 07065, USA.
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
Collapse
|