1
|
Gorostiola González M, Rakers PRJ, Jespers W, IJzerman AP, Heitman LH, van Westen GJP. Computational Characterization of Membrane Proteins as Anticancer Targets: Current Challenges and Opportunities. Int J Mol Sci 2024; 25:3698. [PMID: 38612509 PMCID: PMC11011372 DOI: 10.3390/ijms25073698] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/21/2024] [Revised: 03/21/2024] [Accepted: 03/21/2024] [Indexed: 04/14/2024] Open
Abstract
Cancer remains a leading cause of mortality worldwide and calls for novel therapeutic targets. Membrane proteins are key players in various cancer types but present unique challenges compared to soluble proteins. The advent of computational drug discovery tools offers a promising approach to address these challenges, allowing for the prioritization of "wet-lab" experiments. In this review, we explore the applications of computational approaches in membrane protein oncological characterization, particularly focusing on three prominent membrane protein families: receptor tyrosine kinases (RTKs), G protein-coupled receptors (GPCRs), and solute carrier proteins (SLCs). We chose these families due to their varying levels of understanding and research data availability, which leads to distinct challenges and opportunities for computational analysis. We discuss the utilization of multi-omics data, machine learning, and structure-based methods to investigate aberrant protein functionalities associated with cancer progression within each family. Moreover, we highlight the importance of considering the broader cellular context and, in particular, cross-talk between proteins. Despite existing challenges, computational tools hold promise in dissecting membrane protein dysregulation in cancer. With advancing computational capabilities and data resources, these tools are poised to play a pivotal role in identifying and prioritizing membrane proteins as personalized anticancer targets.
Collapse
Affiliation(s)
- Marina Gorostiola González
- Leiden Academic Centre of Drug Research, Leiden University, Einsteinweg 55, 2333 CC Leiden, The Netherlands; (M.G.G.); (P.R.J.R.); (W.J.); (A.P.I.); (L.H.H.)
- Oncode Institute, 2333 CC Leiden, The Netherlands
| | - Pepijn R. J. Rakers
- Leiden Academic Centre of Drug Research, Leiden University, Einsteinweg 55, 2333 CC Leiden, The Netherlands; (M.G.G.); (P.R.J.R.); (W.J.); (A.P.I.); (L.H.H.)
| | - Willem Jespers
- Leiden Academic Centre of Drug Research, Leiden University, Einsteinweg 55, 2333 CC Leiden, The Netherlands; (M.G.G.); (P.R.J.R.); (W.J.); (A.P.I.); (L.H.H.)
| | - Adriaan P. IJzerman
- Leiden Academic Centre of Drug Research, Leiden University, Einsteinweg 55, 2333 CC Leiden, The Netherlands; (M.G.G.); (P.R.J.R.); (W.J.); (A.P.I.); (L.H.H.)
| | - Laura H. Heitman
- Leiden Academic Centre of Drug Research, Leiden University, Einsteinweg 55, 2333 CC Leiden, The Netherlands; (M.G.G.); (P.R.J.R.); (W.J.); (A.P.I.); (L.H.H.)
- Oncode Institute, 2333 CC Leiden, The Netherlands
| | - Gerard J. P. van Westen
- Leiden Academic Centre of Drug Research, Leiden University, Einsteinweg 55, 2333 CC Leiden, The Netherlands; (M.G.G.); (P.R.J.R.); (W.J.); (A.P.I.); (L.H.H.)
| |
Collapse
|
2
|
Duan H, Lou C, Gu Y, Wang Y, Li W, Liu G, Tang Y. In Silico prediction of inhibitors for multiple transporters via machine learning methods. Mol Inform 2024; 43:e202300270. [PMID: 38235949 DOI: 10.1002/minf.202300270] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/07/2023] [Revised: 01/02/2024] [Accepted: 01/17/2024] [Indexed: 01/19/2024]
Abstract
Transporters play an indispensable role in facilitating the transport of nutrients, signaling molecules and the elimination of metabolites and toxins in human cells. Contemporary computational methods have been employed in the prediction of transporter inhibitors. However, these methods often focus on isolated endpoints, overlooking the interactions between transporters and lacking good interpretation. In this study, we integrated a comprehensive dataset and constructed models to assess the inhibitory effects on seven transporters. Both conventional machine learning and multi-task deep learning methods were employed. The results demonstrated that the MLT-GAT model achieved superior performance with an average AUC value of 0.882. It is noteworthy that our model excels not only in prediction performance but also in achieving robust interpretability, aided by GNN-Explainer. It provided valuable insights into transporter inhibition. The reliability of our model's predictions positioned it as a promising and valuable tool in the field of transporter inhibition research. Related data and code are available at https://gitee.com/wutiantian99/transporter_code.git.
Collapse
Affiliation(s)
- Hao Duan
- Shanghai Frontiers Science Center of Optogenetic Techniques for Cell Metabolism, Shanghai Key Laboratory of New Drug Design, School of Pharmacy, East China University of Science and Technology, Shanghai, 200237, China
| | - Chaofeng Lou
- Shanghai Frontiers Science Center of Optogenetic Techniques for Cell Metabolism, Shanghai Key Laboratory of New Drug Design, School of Pharmacy, East China University of Science and Technology, Shanghai, 200237, China
| | - Yaxin Gu
- Shanghai Frontiers Science Center of Optogenetic Techniques for Cell Metabolism, Shanghai Key Laboratory of New Drug Design, School of Pharmacy, East China University of Science and Technology, Shanghai, 200237, China
| | - Yimeng Wang
- Shanghai Frontiers Science Center of Optogenetic Techniques for Cell Metabolism, Shanghai Key Laboratory of New Drug Design, School of Pharmacy, East China University of Science and Technology, Shanghai, 200237, China
| | - Weihua Li
- Shanghai Frontiers Science Center of Optogenetic Techniques for Cell Metabolism, Shanghai Key Laboratory of New Drug Design, School of Pharmacy, East China University of Science and Technology, Shanghai, 200237, China
| | - Guixia Liu
- Shanghai Frontiers Science Center of Optogenetic Techniques for Cell Metabolism, Shanghai Key Laboratory of New Drug Design, School of Pharmacy, East China University of Science and Technology, Shanghai, 200237, China
| | - Yun Tang
- Shanghai Frontiers Science Center of Optogenetic Techniques for Cell Metabolism, Shanghai Key Laboratory of New Drug Design, School of Pharmacy, East China University of Science and Technology, Shanghai, 200237, China
| |
Collapse
|
3
|
Dudas B, Miteva MA. Computational and artificial intelligence-based approaches for drug metabolism and transport prediction. Trends Pharmacol Sci 2024; 45:39-55. [PMID: 38072723 DOI: 10.1016/j.tips.2023.11.001] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/02/2023] [Revised: 11/09/2023] [Accepted: 11/09/2023] [Indexed: 01/07/2024]
Abstract
Drug metabolism and transport, orchestrated by drug-metabolizing enzymes (DMEs) and drug transporters (DTs), are implicated in drug-drug interactions (DDIs) and adverse drug reactions (ADRs). Reliable and precise predictions of DDIs and ADRs are critical in the early stages of drug development to reduce the rate of drug candidate failure. A variety of experimental and computational technologies have been developed to predict DDIs and ADRs. Recent artificial intelligence (AI) approaches offer new opportunities for better predicting and understanding the complex processes related to drug metabolism and transport. We summarize the role of major DMEs and DTs, and provide an overview of current progress in computational approaches for the prediction of drug metabolism, transport, and DDIs, with an emphasis on AI including machine learning (ML) and deep learning (DL) modeling.
Collapse
Affiliation(s)
- Balint Dudas
- Université Paris Cité, CNRS UMR 8038 CiTCoM, Inserm U1268 MCTR, Paris, France
| | - Maria A Miteva
- Université Paris Cité, CNRS UMR 8038 CiTCoM, Inserm U1268 MCTR, Paris, France.
| |
Collapse
|
4
|
Shchulkin AV, Abalenikhina YV, Slepnev AA, Rokunov ED, Yakusheva EN. The Role of Adopted Orphan Nuclear Receptors in the Regulation of an Organic Anion Transporting Polypeptide 1B1 (OATP1B1) under the Action of Sex Hormones. Curr Issues Mol Biol 2023; 45:9593-9605. [PMID: 38132446 PMCID: PMC10741745 DOI: 10.3390/cimb45120600] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/31/2023] [Revised: 11/14/2023] [Accepted: 11/27/2023] [Indexed: 12/23/2023] Open
Abstract
Organic anion transporting polypeptide 1B1 (OATP1B1) is an influx transporter protein of the SLC superfamily, expressed mainly in the liver and some tumor cells. The mechanisms of its regulation are being actively studied. In the present study, the effect of sex hormones (estradiol, progesterone and testosterone) on OATP1B1 expression in HepG2 cells was examined. The role of adopted orphan receptors, farnasoid X receptor (FXR), constitutive androstane receptor (CAR), pregnane X receptor (PXR) and liver X receptor subtype alpha (LXRa), was also evaluated. Hormones were used in concentrations of 1, 10 and 100 μM, with incubation for 24 h. The protein expression of OATP1B1, FXR, CAR, PXR and LXRa was analyzed by Western blot. It was shown that estradiol (10 and 100 μM) increased the expression of OATP1B1, acting through CAR. Testosterone (1, 10 and 100 μM) increased the expression of OATP1B1, acting through FXR, PXR and LXRa. Progesterone (10 and 100 μM) decreased the expression of OATP1B1 (10 and 100 μM) and adopted orphan receptors are not involved in this process. The obtained results have important practical significance and determine ways for targeted regulation of the transporter, in particular in cancer.
Collapse
Affiliation(s)
- Aleksey V. Shchulkin
- Department of Pharmacology, Ryazan State Medical University, 390026 Ryazan, Russia; (Y.V.A.); (A.A.S.); (E.N.Y.)
| | | | | | | | | |
Collapse
|
5
|
Kong X, Lin K, Wu G, Tao X, Zhai X, Lv L, Dong D, Zhu Y, Yang S. Machine Learning Techniques Applied to the Study of Drug Transporters. Molecules 2023; 28:5936. [PMID: 37630188 PMCID: PMC10459831 DOI: 10.3390/molecules28165936] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/30/2023] [Revised: 07/27/2023] [Accepted: 08/02/2023] [Indexed: 08/27/2023] Open
Abstract
With the advancement of computer technology, machine learning-based artificial intelligence technology has been increasingly integrated and applied in the fields of medicine, biology, and pharmacy, thereby facilitating their development. Transporters have important roles in influencing drug resistance, drug-drug interactions, and tissue-specific drug targeting. The investigation of drug transporter substrates and inhibitors is a crucial aspect of pharmaceutical development. However, long duration and high expenses pose significant challenges in the investigation of drug transporters. In this review, we discuss the present situation and challenges encountered in applying machine learning techniques to investigate drug transporters. The transporters involved include ABC transporters (P-gp, BCRP, MRPs, and BSEP) and SLC transporters (OAT, OATP, OCT, MATE1,2-K, and NET). The aim is to offer a point of reference for and assistance with the progression of drug transporter research, as well as the advancement of more efficient computer technology. Machine learning methods are valuable and attractive for helping with the study of drug transporter substrates and inhibitors, but continuous efforts are still needed to develop more accurate and reliable predictive models and to apply them in the screening process of drug development to improve efficiency and success rates.
Collapse
Affiliation(s)
- Xiaorui Kong
- Department of Pharmacy, First Affiliated Hospital of Dalian Medical University, Dalian 116011, China; (X.K.); (K.L.); (X.T.); (X.Z.); (L.L.); (D.D.)
| | - Kexin Lin
- Department of Pharmacy, First Affiliated Hospital of Dalian Medical University, Dalian 116011, China; (X.K.); (K.L.); (X.T.); (X.Z.); (L.L.); (D.D.)
| | - Gaolei Wu
- Department of Pharmacy, Dalian Women and Children’s Medical Group, Dalian 116024, China;
| | - Xufeng Tao
- Department of Pharmacy, First Affiliated Hospital of Dalian Medical University, Dalian 116011, China; (X.K.); (K.L.); (X.T.); (X.Z.); (L.L.); (D.D.)
| | - Xiaohan Zhai
- Department of Pharmacy, First Affiliated Hospital of Dalian Medical University, Dalian 116011, China; (X.K.); (K.L.); (X.T.); (X.Z.); (L.L.); (D.D.)
| | - Linlin Lv
- Department of Pharmacy, First Affiliated Hospital of Dalian Medical University, Dalian 116011, China; (X.K.); (K.L.); (X.T.); (X.Z.); (L.L.); (D.D.)
| | - Deshi Dong
- Department of Pharmacy, First Affiliated Hospital of Dalian Medical University, Dalian 116011, China; (X.K.); (K.L.); (X.T.); (X.Z.); (L.L.); (D.D.)
| | - Yanna Zhu
- Department of Pharmacy, First Affiliated Hospital of Dalian Medical University, Dalian 116011, China; (X.K.); (K.L.); (X.T.); (X.Z.); (L.L.); (D.D.)
| | - Shilei Yang
- Department of Pharmacy, First Affiliated Hospital of Dalian Medical University, Dalian 116011, China; (X.K.); (K.L.); (X.T.); (X.Z.); (L.L.); (D.D.)
| |
Collapse
|
6
|
Ishikawa R, Saito K, Misawa T, Demizu Y, Saito Y. Identification of the Stapled α-Helical Peptide ATSP-7041 as a Substrate and Strong Inhibitor of OATP1B1 In Vitro. Biomolecules 2023; 13:1002. [PMID: 37371582 DOI: 10.3390/biom13061002] [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: 05/19/2023] [Revised: 06/13/2023] [Accepted: 06/14/2023] [Indexed: 06/29/2023] Open
Abstract
ATSP-7041, a stapled α-helical peptide that inhibits murine double minute-2 (MDM2) and MDMX activities, is a promising modality targeting protein-protein interactions. As peptides of molecular weights over 1000 Da are not usually evaluated, data on the drug-drug interaction (DDI) potential of stapled α-helical peptides remain scarce. Here, we evaluate the interaction of ATSP-7041 with hepatic cytochrome P450s (CYPs; CYP1A2, CYP2C9, CYP2C19, CYP3A4, and CYP2D6) and transporters (organic anion transporting polypeptides (OATPs; OATP1B1 and OATP1B3), P-glycoprotein (P-gp), and breast cancer resistance protein (BCRP)). ATSP-7041 demonstrated negligible metabolism in human liver S9 fraction and a limited inhibition of CYP activities in yeast microsomes or S9 fractions. On the contrary, a substantial uptake by OATPs in HEK 293 cells, a strong inhibition of OATP activities in the cells, and an inhibition of P-gp and BCRP activities in reversed membrane vesicles were observed for ATSP-7041. A recent report describes that ALRN-6924, an ATSP-7041 analog, inhibited OATP activities in vivo; therefore, we focused on the interaction between ATSP-7041 and OATP1B1 to demonstrate that ATSP-7041, as a higher molecular weight stapled peptide, is a substrate and strong inhibitor of OATP1B1 activity. Our findings demonstrated the possibility of transporter-mediated DDI potential by high molecular weight stapled peptides and the necessity of their evaluation for drug development.
Collapse
Affiliation(s)
- Rika Ishikawa
- Division of Medical Safety Science, National Institute of Health Sciences, Kawasaki 210-9501, Japan
| | - Kosuke Saito
- Division of Medical Safety Science, National Institute of Health Sciences, Kawasaki 210-9501, Japan
| | - Takashi Misawa
- Division of Organic Chemistry, National Institute of Health Sciences, Kawasaki 210-9501, Japan
| | - Yosuke Demizu
- Division of Organic Chemistry, National Institute of Health Sciences, Kawasaki 210-9501, Japan
| | - Yoshiro Saito
- Division of Medical Safety Science, National Institute of Health Sciences, Kawasaki 210-9501, Japan
| |
Collapse
|
7
|
Özvegy-Laczka C, Ungvári O, Bakos É. Fluorescence-based methods for studying activity and drug-drug interactions of hepatic solute carrier and ATP binding cassette proteins involved in ADME-Tox. Biochem Pharmacol 2023; 209:115448. [PMID: 36758706 DOI: 10.1016/j.bcp.2023.115448] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/04/2023] [Revised: 01/31/2023] [Accepted: 02/01/2023] [Indexed: 02/11/2023]
Abstract
In humans, approximately 70% of drugs are eliminated through the liver. This process is governed by the concerted action of membrane transporters and metabolic enzymes. Transporters mediating hepatocellular uptake of drugs belong to the SLC (Solute carrier) superfamily of transporters. Drug efflux either toward the portal vein or into the bile is mainly mediated by active transporters of the ABC (ATP Binding Cassette) family. Alteration in the function and/or expression of liver transporters due to mutations, disease conditions, or co-administration of drugs or food components can result in altered pharmacokinetics. On the other hand, drugs or food components interacting with liver transporters may also interfere with liver function (e.g., bile acid homeostasis) and may even cause liver toxicity. Accordingly, certain transporters of the liver should be investigated already at an early stage of drug development. Most frequently radioactive probes are applied in these drug-transporter interaction tests. However, fluorescent probes are cost-effective and sensitive alternatives to radioligands, and are gaining wider application in drug-transporter interaction tests. In our review, we summarize our current understanding about hepatocyte ABC and SLC transporters affected by drug interactions. We provide an update of the available fluorescent and fluorogenic/activable probes applicable in in vitro or in vivo testing of these ABC and SLC transporters, including near-infrared transporter probes especially suitable for in vivo imaging. Furthermore, our review gives a comprehensive overview of the available fluorescence-based methods, not directly relying on the transport of the probe, suitable for the investigation of hepatic ABC or SLC-type drug transporters.
Collapse
Affiliation(s)
- Csilla Özvegy-Laczka
- Institute of Enzymology, RCNS, Eötvös Loránd Research Network, H-1117 Budapest, Magyar tudósok krt. 2., Hungary.
| | - Orsolya Ungvári
- Institute of Enzymology, RCNS, Eötvös Loránd Research Network, H-1117 Budapest, Magyar tudósok krt. 2., Hungary; Doctoral School of Biology, Institute of Biology, ELTE Eötvös Loránd University, Budapest, Hungary
| | - Éva Bakos
- Institute of Enzymology, RCNS, Eötvös Loránd Research Network, H-1117 Budapest, Magyar tudósok krt. 2., Hungary
| |
Collapse
|
8
|
Gui C, Li Y, Peng T. Development of predictive QSAR models for the substrates/inhibitors of OATP1B1 by deep neural networks. Toxicol Lett 2023; 376:20-25. [PMID: 36649904 DOI: 10.1016/j.toxlet.2023.01.006] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/21/2022] [Revised: 01/10/2023] [Accepted: 01/12/2023] [Indexed: 01/15/2023]
Abstract
The organic anion transporting polypeptide 1B1 (OATP1B1) is an important hepatic uptake transporter. Inhibition of its normal function could lead to drug-drug interactions. In silico prediction is an effective means to identify potential OATP1B1 inhibitors and quantitative structure-activity relationship (QSAR) modeling is extensively used. As the structures of OATP1B1 substrates/inhibitors are quite diverse, machine learning based methods should be a good option for their QSAR analysis. In the present study, deep neural networks (DNNs) were employed to develop QSAR models for the substrates/inhibitors of OATP1B1 with different molecular fingerprints. Our results showed that QSAR models based on 4-hidden layer DNNs and ECFP4/FCFP4 fingerprints had the best generalization performance. The correlation coefficients (R2) of test set for ECFP4 and FCFP4 models were 0.641 and 0.653, respectively. Model application domain (AD) was calculated with Euclidean distance-based method, and AD could improve the performance of ECFP4 model but has little effect on FCFP4 model. Finally, the prediction of additional 8 compounds that not included in the data set further demonstrated that our QSAR models had a good predictive ability (averaged prediction accuracy >92%). The developed QSAR models could be used to screen large data sets and discover novel inhibitors for OATP1B1.
Collapse
Affiliation(s)
- Chunshan Gui
- College of Pharmaceutical Sciences, Soochow University, 199 Renai Road, Suzhou Industrial Park, Suzhou 215123, China.
| | - Ying Li
- College of Pharmaceutical Sciences, Soochow University, 199 Renai Road, Suzhou Industrial Park, Suzhou 215123, China
| | - Taotao Peng
- College of Pharmaceutical Sciences, Soochow University, 199 Renai Road, Suzhou Industrial Park, Suzhou 215123, China
| |
Collapse
|
9
|
Cournia Z, Soares TA, Wahab HA, Amaro RE. Celebrating Diversity, Equity, Inclusion, and Respect in Computational and Theoretical Chemistry. J Chem Inf Model 2022; 62:6287-6291. [PMID: 36567670 DOI: 10.1021/acs.jcim.2c01543] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/27/2022]
Affiliation(s)
- Zoe Cournia
- Biomedical Research Foundation, Academy of Athens, 11527 Athens, Greece
| | - Thereza A Soares
- Department of Chemistry, University of São Paulo, 14040-901 Ribeirão Preto, Brazil.,Hylleraas Centre for Quantum Molecular Sciences, University of Oslo, 0315 Oslo, Norway
| | - Habibah A Wahab
- School of Pharmaceutical Sciences, Universiti Sains Malaysia, 11800 Minden, Pulau Pinang, Malaysia
| | - Rommie E Amaro
- Department of Chemistry and Biochemistry, University of California, 3234 Urey Hall, #0340, 9500 Gilman Drive, La Jolla, 92093-0340 San Diego, California, United States
| |
Collapse
|
10
|
Comparative Modelling of Organic Anion Transporting Polypeptides: Structural Insights and Comparison of Binding Modes. MOLECULES (BASEL, SWITZERLAND) 2022; 27:molecules27238531. [PMID: 36500622 PMCID: PMC9738416 DOI: 10.3390/molecules27238531] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 10/27/2022] [Revised: 11/28/2022] [Accepted: 12/01/2022] [Indexed: 12/12/2022]
Abstract
To better understand the functionality of organic anion transporting polypeptides (OATPs) and to design new ligands, reliable structural data of each OATP is needed. In this work, we used a combination of homology model with molecular dynamics simulations to generate a comprehensive structural dataset, that encompasses a diverse set of OATPs but also their relevant conformations. Our OATP models share a conserved transmembrane helix folding harbouring a druggable binding pocket in the shape of an inner pore. Our simulations suggest that the conserved salt bridges at the extracellular region between residues on TM1 and TM7 might influence the entrance of substrates. Interactions between residues on TM1 and TM4 within OATP1 family shown their importance in transport of substrates. Additionally, in transmembrane (TM) 1/2, a known conserved element, interact with two identified motifs in the TM7 and TM11. Our simulations suggest that TM1/2-TM7 interaction influence the inner pocket accessibility, while TM1/2-TM11 salt bridges control the substrate binding stability.
Collapse
|
11
|
Lane TR, Urbina F, Zhang X, Fye M, Gerlach J, Wright SH, Ekins S. Machine Learning Models Identify New Inhibitors for Human OATP1B1. Mol Pharm 2022; 19:4320-4332. [PMID: 36269563 PMCID: PMC9873312 DOI: 10.1021/acs.molpharmaceut.2c00662] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/26/2023]
Abstract
The uptake transporter OATP1B1 (SLC01B1) is largely localized to the sinusoidal membrane of hepatocytes and is a known victim of unwanted drug-drug interactions. Computational models are useful for identifying potential substrates and/or inhibitors of clinically relevant transporters. Our goal was to generate OATP1B1 in vitro inhibition data for [3H] estrone-3-sulfate (E3S) transport in CHO cells and use it to build machine learning models to facilitate a comparison of seven different classification models (Deep learning, Adaboosted decision trees, Bernoulli naïve bayes, k-nearest neighbors (knn), random forest, support vector classifier (SVC), logistic regression (lreg), and XGBoost (xgb)] using ECFP6 fingerprints to perform 5-fold, nested cross validation. In addition, we compared models using 3D pharmacophores, simple chemical descriptors alone or plus ECFP6, as well as ECFP4 and ECFP8 fingerprints. Several machine learning algorithms (SVC, lreg, xgb, and knn) had excellent nested cross validation statistics, particularly for accuracy, AUC, and specificity. An external test set containing 207 unique compounds not in the training set demonstrated that at every threshold SVC outperformed the other algorithms based on a rank normalized score. A prospective validation test set was chosen using prediction scores from the SVC models with ECFP fingerprints and were tested in vitro with 15 of 19 compounds (84% accuracy) predicted as active (≥20% inhibition) showed inhibition. Of these compounds, six (abamectin, asiaticoside, berbamine, doramectin, mobocertinib, and umbralisib) appear to be novel inhibitors of OATP1B1 not previously reported. These validated machine learning models can now be used to make predictions for drug-drug interactions for human OATP1B1 alongside other machine learning models for important drug transporters in our MegaTrans software.
Collapse
Affiliation(s)
- Thomas R. Lane
- Collaborations Pharmaceuticals, Inc., 840 Main Campus Drive, Lab 3510 Raleigh, NC 27606, USA
| | - Fabio Urbina
- Collaborations Pharmaceuticals, Inc., 840 Main Campus Drive, Lab 3510 Raleigh, NC 27606, USA
| | - Xiaohong Zhang
- Department of Physiology, College of Medicine, University of Arizona, Tucson, AZ, 85724, USA
| | - Margret Fye
- Department of Physiology, College of Medicine, University of Arizona, Tucson, AZ, 85724, USA
| | - Jacob Gerlach
- Collaborations Pharmaceuticals, Inc., 840 Main Campus Drive, Lab 3510 Raleigh, NC 27606, USA
| | - Stephen H. Wright
- Department of Physiology, College of Medicine, University of Arizona, Tucson, AZ, 85724, USA
| | - Sean Ekins
- Collaborations Pharmaceuticals, Inc., 840 Main Campus Drive, Lab 3510 Raleigh, NC 27606, USA
| |
Collapse
|