What is ADMET Predictor?
ADMET Predictor is a software tool that quickly and accurately predicts over 175 properties including solubility, logP, pKa, sites of CYP metabolism, and Ames mutagenicity. The ADMET Modeler™ module in ADMET Predictor allows one to rapidly and easily create high quality QSAR/QSPR models based on your own data. The newest module offers advanced data mining, clustering, and matched molecular pair analysis. The program has an intuitive user interface that allows one to easily manipulate and visualize data.
The eight modules in ADMET Predictor are:
Physicochemical and Biopharmaceutical (PCB)
AI-Driven Drug Design (AIDD)
Each module can be purchased individually.
What are we providing with ADMET Predictor (AP)?
The ADMET Predictor development team strives to build the best QSAR/QSPR models and fast, efficient software. This dedication to science is a major reason why several of our models have ranked #1 in peer review articles. ADMET Predictor provides:
Over 175 predicted properties
Model applicability domain
pKa prediction including all microstates
CYP metabolite generation and kinetic parameters
Confidence estimates for classification models
A revamped, intuitive interface with pulldown menus, quick access icons, and context specific menus
Interactive distribution and 2D and 3D scatters plots
Ability to create your own QSPR/QSAR models
Excellent customer support
How is AP being applied?
Biotechnology, pharmaceutical, and chemical companies license ADMET Predictor for diverse number of applications including:
Physicochemical property prediction of real and virtual compounds
Prediction of dose needed to achieve a specific blood level concentration
Analysis of high throughput screening data
Matched molecule pair analysis and activity cliff detection
SAR analysis including R-group creation and analysis
Creating diverse compounds subsets
Enumerating combinatorial chemistry libraries
Calculation of various binding metrics, e.g. lipophillic ligand efficiency (LLE)
The original Rule of 5 is widely considered to be an important development in modern drug discovery (Lipinski, et al; 1997). The Rule of 5 takes on numeric values from 0 to 4 as a measure of the compounds potential absorption liability. As such, the Rule of 5 is a useful computational filter in drug candidate screening. In terms of ADMET Predictor descriptors and models, the Rule Of 5 model rules can be formulated as follow the following set of conditions:
MlogP > 4.15 (excessive lipophilicity)
MWt > 500 (large size)
HBDH > 5 (too many potential hydrogen bond donors)
M_NO > 10 (too many potential hydrogen bond acceptors)
Most commercial drugs suitable for oral dosing violate no more than one of the rules these conditions represent.
As an extension of that concept, Simulations Plus has created a series of “ADMET Risk” rule sets and calibrated them against our own ADMET models. They are parameterized to include thresholds for a wide range of calculated and predicted properties that represent potential obstacles to a compound being successfully developed as an orally bioavailable drug. These thresholds were obtained by focusing in on a specific subset of drugs in the World Drug Index (WDI). Similar to the methodology used by Lipinski et al., we removed irrelevant compounds from a 2008 version of the WDI. In particular, we removed phosphates, antiseptics, insecticides, emollients, laxatives, etc., as well as any compound that did not have an associated United States Adopted Name (USAN) or International Non-proprietary Name (INN) identifier. The structure of the principal component in salts was extracted and neutralized, after which duplicate structures were removed. This left us with a data set of 2,316 molecules, 8.3% of which violated more than one of Lipinski’s rules.
Rule of 5 only addresses a narrow slice of the full gamut of hurdles a compound must pass before it can become a drug. In addition, it relies on “hard” thresholds: a compound with a molecular weight of 499 satisfies the MWt rule but a compound with a molecular weight of 501 violates it.
We calculated a broad range of relevant molecular descriptors and ADMET property predictions for the focused subset of WDI and identified “soft” threshold ranges for each along the lines suggested by (Petit; 2012) such that approximately 85% of the compounds in the data set satisfy them completely and somewhat less than 10% violate them completely. The former contribute nothing to the overall Risk, whereas the latter contribute the full amount (weight) specified for the corresponding rule. Predictions falling in the gray area in between contribute fractional amounts to the Risk Score. The concept is illustrated on the left.
Highly correlated criteria were combined into single rules using Boolean operators. The rules for identifying overly large structures, for example, is:
size (Sz): MWt > [450,550] OR N_Atoms > [32,38] OR MolVol > [475,550] OR N_Bonds > [35,41]
where the values within the brackets indicate the boundaries of threshold regions. The Sz rule includes four individual criteria, all of which use the “>” relational operator. Predictions falling below the minimum threshold values contribute nothing to the Risk, whereas predictions above the maximum contribute 1 violation “point”. Intermediate values represent intermediate risks: a compound of molecular weight 500 violates the first criterion and so would represent an incremental Risk of 0.5 points for that criterion. Logical operators such as ORs and ANDs can also be included in the rules. The combined points from the criteria making up a rule then yield an overall value between 0 and 1, which is multiplied by the weight assigned to the rule as a whole.
The overall ADMET_Risk is the sum of three risks:
Absn_Risk – risk of low fraction absorbed (PCB Module models)
CYP_Risk – risk of high CYP metabolism (MET Module models)
TOX_Risk – toxicity related risks (TOX Module models)
Two additional pharmacokinetic risks (high plasma protein binding and high steady-state volume of distribution) are also included in the ADMET_Risk score.
Lipinski CA, Lombardo F, Dominy BW, Feeney PJ. “Experimental and Computational Approaches to Estimate Solubility and Permeability in Drug Discovery and Development Settings.” Adv Drug Delivery Rev. 1997; 23:3-25.
Petit J, Meurice N, Kaiser C, Maggiora G. “Softening the Rule of Five – where to draw the line?” Bioorg Med Chem. 2012; 20:5343-5351.
Physicochemical & Biopharmaceutical (PCB)
What is the PCB Module?
ADMET Predictor’s PCB Module contains models for physicochemical property prediction. Each model was built by Simulations Plus scientists using artificial neural network ensemble (ANNE) technology. The data sets were highly curated in order to generate highly accurate models. The data for our pKa model (S+pKa) was recently expanded in a collaboration with Bayer scientists. This resulted in more accurate predictions for a set of 16,000 compounds that were not used to train the model. Our logP (S+logP) and aqueous solubility (S+Sw) models have been ranked number one in peer reviewed journal articles.1,2 The models in the PCB module are also available in the ADMET Predictor module of GastroPlus® in order to perform PBPK simulations using in silico predicted properties.
Physicochemical property prediction
The image below lists the models in ADMET Predictor’s PCB Module.
The supersaturation (SupSatn), blood brain barrier penetration classification model (BBB_Filter), Pgp substrate (Pgp_Substr) and inhibition (Pgp_Inhib), and OATP1B1 inhibition (OATP1B1_Inh) models were rebuilt to improve their estimates of prediction confidence
Several new models based on data from the Extended Clearance Classification System journal article by Varma et al.3 were created for ADMET Predictor version 9.0
A model to prediction high or low permeability in a low efflux MDCK assay (S+MDCK-LE)
The Extended Clearance Classification System (ECCS) has been implemented
S+CL_Mech model predicts if a compound’s major clearance pathway is renal, metabolic, or hepatic uptake
S+CL_Renal, S+CL_Metab, S+CL_Uptake are binary classification models that predict if a compounds major clearance pathway is renal, metabolic, or hepatic uptake
The human plasma protein binding (hum_fup%) model was rebuilt with additional data
Plots of solubility and logD vs. pH
BCS4/DCS5 explorer window
1 J. Pharm. Sci. 2008, 98, 861.
2 a) Expert Opin. Drug Discov. 2006, 1, 31-52. b) Science of the Total Environment, 2013, 463-464, 781-789.
3 Varma MV, Steyn SJ, Allerton C, El-Kattan AF. “Predicting Clearance Mechanism in Drug Discovery: Extended Clearance Classification System (ECCS).” Pharm Res 2015; 32:3785.
4 Amidon, GL, Lennernas H, Shah VP, Crison JR”A theoretical basis for a biopharmaceutic drug classification: the correlation of in vitro drug product dissolution and in vivo bioavailability.” Pharm. Res. 1995; 12:413-20.
5 Butler JM and Dressman JB. “The developability classification system: application of biopharmaceutics concepts to formulation development.” J. Pharm. Sci. 2010; 99(12):4940-54.
Brief descriptions of the models are below.
pKa, partition, and transporters models
Multiprotic pKa model (S+Acidic_pKa, S+Mixed_pKa, S+Basic_pKa) – a thermodynamically accurate multiprotic model for multiple ionization sites based on atomic descriptors and neural networks – not a database lookup!
logP (S+logP, MlogP) – log of the octanol to water partition coefficient. There are two models, an artificial neural network ensemble (S+logP) and Moriguchi (MlogP)
logD (S+logD) – estimation of octanol-water distribution coefficient at user-defined pH
Air-water partition (logHLC) – estimation of air-water partition coefficient (Henry’s Law constant) from US EPA data
Inhibition of the hepatic OATP1B1 transporter in human (OATP1B1_Inh)
Inhibition of the intestinal P-gp transporter in human (Pgp_Inh)
Likelihood of intestinal efflux by P-gp transporter in human (Pgp_Substr)
Human effective permeability (S+Peff) – jejunal Peff
MDCK apparent permeability (S+MDCK) – in vitro Papp
Corneal permeability (Perm_Cornea) – ocular permeability through rabbit cornea based on literature data obtained in vitro
Skin permeability (Perm_Skin) – permeability through human skin of compounds dissolved in aqueous solution; based on literature data
Blood-brain barrier permeation – there are two models, classification (BBB_Filter) and regression (LogBB). The first classification model has a low cutoff such that compounds that are predicted to have low permeability have very little chance of penetrating the blood-brain barrier. Compounds that are predicted to have high blood-brain barrier penetration should be evaluated with the regression model that predicts the blood to brain concentration ratio.
Native solubility (S+Sw) – solubility in pure water
Native pH at saturation in pure water (S+pH_Satd)
Intrinsic solubility in pure water (S+S_Intrins)
Salt solubility factor (SolFactor)
Water solubility at user-specified pH (S+S_pH)
Solubility in the simulated gastrointestinal fluids (the models were built using data in our Biorelevant Solubility Database)
Fasted state simulated gastric fluid solubility (S+FaSSGF)
Fasted state simulated intestinal fluid (S+FaSSIF)
Fed state simulated intestinal fluid (S+FeSSIF)
Supersaturation ratio (SupSatn) – a tendency to supersaturate in water
Human and rat plasma protein binding as percent unbound (hum_fup% and rat_fup%
Human volume of distribution (Vd)
Human and rat blood-to-plasma concentration ratio (RBP and RBP_rat)
Fraction unbound in human liver microsomes (S+fumic)
In Silico Methods for Predicting DrugToxicity
【摘要】：药物发现与开发高投入、周期长的高风险项目，在过去几十年里，计算机辅助工具以及计算机虚拟预测insilico模型已被引入到药物发现阶段，用于预测化合物的ADMET (吸收、分布、代谢、排泄和毒性)性质特征，从而极大程度上避免药物研发后期由于代谢性质差和毒副作用大的失败风险。现在，研究人员已经广泛认识到应在药物发现阶段尽早熟知化合物的ADMET性质及可能存在的问题。在本书中，作者详细描述了商业软件程序ADMETPredictor™ 7.2 (ADMET Predictor v7.2. Simulations Plus, Inc., Lancaster, CA,USA)是如何构建ADMET模型以及如何采用建立好的模型预测化合物的ADMET性质参数。全章节分为背景、材料、方法三个部分，详细介绍了ADMETPredictor如何搭建内建模型、如何搭建用户自己的模型以及软件的基本操作和应用等内容。
Identification of impurities in macrolides by liquidchromatography-mass spectrometric detection and prediction of retention timesof impurities by constructing quantitative structure-retention relationship(QSRR)
Experimental versus theoretical log D7.4 , pKa and plasmaprotein binding values for benzodiazepines appearing as new psychoactivesubstances
Prediction of Estrogenic Bioactivity of EnvironmentalChemical Metabolites
CarolineL. Pinto, Kamel Mansouri, Richard Judson, Patience Browne. Chem Res Toxicol.2016 Sep 19; 29(9): 1410-27.
Assessment of in silico models for acute aquatic toxicitytowards fish under REACH regulation
CappelliCI, Cassano A, Golbamaki A, Moggio Y, Lombardo A, Colafranceschi M, BenfenatiE. SAR QSAR Environ Res. 2015 Dec;26(12):977-999.
【摘要】：文章评估8种QSAR模型软件(ACD/ToxSuite™,ADMET Predictor™, DEMETRA, ECOSAR, TerraQSAR™, Toxicity Estimation SoftwareTool, TOPKAT™和VEGA)对两个种属鱼(黑头呆鱼和虹鳟鱼)的急性水生生物毒性的预测能力。
Design, Synthesis and Biological Evaluation of NovelBenzothiazole Derivatives as Selective PI3Kβ Inhibitors
ShuangCao, Ruiyuan Cao, Xialing Liu, Xiang Luo, Wu Zhong. Molecules. 2016 Jul 2;21(7).
【摘要】：设计与合成了一系列全新的含有苯并噻唑结构的PI3Kβ (磷脂酰环己硫醇-3-beta 激酶亚族)抑制剂。评估所有化合物均对PI3Kα,β, γ, δ和mTOR (哺乳动物雷帕霉素靶点)的抑制活性。根据抑制PI3Ks/mTOR的IC50数值筛选出两个较为不错的化合物做进一步的评估。
Evaluating the Impact of Uncertainties in Clearance andExposure When Prioritizing Chemicals Screened in High-Throughput AssaysEnvironSci Technol. 2016 Jun 7;50(11):5961-71.
分别为：ADMET Predictor在药化、天然药化、CADD的应用；采用ADMET Predictor预测吸收与代谢性质的应用；采用ADMET Predictor预测化合物毒性的应用；ADMET Predictor在环境、食品安全等领域的应用；ADMET Predictor在预测资源或模型开发的应用及中国用户采用ADMET Predictor发表的应用文章。