Discovering highly selective and diverse PPAR-delta agonists by ligand based machine learning and structural modeling

From Sequence to Solution: Intelligent Learning Engine Optimization in Drug Discovery and Protein Analysis

This study introduces the intelligent learning engine (ILE) optimization technology, a novel approach designed to revolutionize screening processes in bioinformatics, cheminformatics, and a range of other scientific fields. By focusing on the efficient and precise identification of candidates with desirable characteristics, the ILE technology marks a significant leap forward in addressing the complexities of candidate selection in drug discovery, protein classification, and beyond. The study's primary objective is to address the challenges associated with optimizing screening processes to efficiently select candidates across various fields, including drug discovery and protein classification. The methodology employed involves a detailed algorithmic process that includes dataset preparation, encoding of protein sequences, sensor nucleation, and optimization, culminating in the empirical evaluation of molecular activity indexing, homology-based modeling, and classification of proteins such as G-protein-coupled receptors. This process showcases the method's success in multiple sequence alignment, protein identification, and classification. Key results demonstrate the ILE's superior accuracy in protein classification and virtual high-throughput screening, with a notable breakthrough in drug development for assessing drug-induced long QT syndrome risks through hERG potassium channel interaction analysis. The technology showcased exceptional results in the formulation and evaluation of novel cancer drug candidates, highlighting its potential for significant advancements in pharmaceutical innovations. The findings underline the ILE optimization technology as a transformative tool in screening processes due to its proven effectiveness and broad applicability across various domains. This breakthrough contributes substantially to the fields of systems optimization and holds promise for diverse applications, enhancing the process of selecting candidate molecules with target properties and advancing drug discovery, protein classification, and modeling.

Addressing chemically-induced obesogenic metabolic disruption: selection of chemicals for in vitro human PPARα, PPARγ transactivation, and adipogenesis test methods

Whilst western diet and sedentary lifestyles heavily contribute to the global obesity epidemic, it is likely that chemical exposure may also contribute. A substantial body of literature implicates a variety of suspected environmental chemicals in metabolic disruption and obesogenic mechanisms. Chemically induced obesogenic metabolic disruption is not yet considered in regulatory testing paradigms or regulations, but this is an internationally recognised human health regulatory development need. An early step in the development of relevant regulatory test methods is to derive appropriate minimum chemical selection lists for the target endpoint and its key mechanisms, such that the test method can be suitably optimised and validated. Independently collated and reviewed reference and proficiency chemicals relevant for the regulatory chemical universe that they are intended to serve, assist regulatory test method development and validation, particularly in relation to the OECD Test Guidelines Programme. To address obesogenic mechanisms and modes of action for chemical hazard assessment, key initiating mechanisms include molecular-level Peroxisome Proliferator-Activated Receptor (PPAR) α and γ agonism and the tissue/organ-level key event of perturbation of the adipogenesis process that may lead to excess white adipose tissue. Here we present a critical literature review, analysis and evaluation of chemicals suitable for the development, optimisation and validation of human PPARα and PPARγ agonism and human white adipose tissue adipogenesis test methods. The chemical lists have been derived with consideration of essential criteria needed for understanding the strengths and limitations of the test methods. With a weight of evidence approach, this has been combined with practical and applied aspects required for the integration and combination of relevant candidate test methods into test batteries, as part of an Integrated Approach to Testing and Assessment for metabolic disruption. The proposed proficiency and reference chemical list includes a long list of negatives and positives (20 chemicals for PPARα, 21 for PPARγ, and 11 for adipogenesis) from which a (pre-)validation proficiency chemicals list has been derived.

Development of a Robust Read-Across Model for the Prediction of Biological Potency of Novel Peroxisome Proliferator-Activated Receptor Delta Agonists

A robust predictive model was developed using 136 novel peroxisome proliferator-activated receptor delta (PPARδ) agonists, a distinct subtype of lipid-activated transcription factors of the nuclear receptor superfamily that regulate target genes by binding to characteristic sequences of DNA bases. The model employs various structural descriptors and docking calculations and provides predictions of the biological activity of PPARδ agonists, following the criteria of the Organization for Economic Co-operation and Development (OECD) for the development and validation of quantitative structure-activity relationship (QSAR) models. Specifically focused on small molecules, the model facilitates the identification of highly potent and selective PPARδ agonists and offers a read-across concept by providing the chemical neighbours of the compound under study. The model development process was conducted on Isalos Analytics Software (v. 0.1.17) which provides an intuitive environment for machine-learning applications. The final model was released as a user-friendly web tool and can be accessed through the Enalos Cloud platform's graphical user interface (GUI).

Lipodystrophy in methylmalonic acidemia associated with elevated FGF21 and abnormal methylmalonylation

A distinct adipose tissue distribution pattern was observed in patients with methylmalonyl-CoA mutase deficiency, an inborn error of branched-chain amino acid (BCAA) metabolism, characterized by centripetal obesity with proximal upper and lower extremity fat deposition and paucity of visceral fat, that resembles familial multiple lipomatosis syndrome. To explore brown and white fat physiology in methylmalonic acidemia (MMA), body composition, adipokines, and inflammatory markers were assessed in 46 patients with MMA and 99 matched controls. Fibroblast growth factor 21 levels were associated with acyl-CoA accretion, aberrant methylmalonylation in adipose tissue, and an attenuated inflammatory cytokine profile. In parallel, brown and white fat were examined in a liver-specific transgenic MMA mouse model (Mmut-/- TgINS-Alb-Mmut). The MMA mice exhibited abnormal nonshivering thermogenesis with whitened brown fat and had an ineffective transcriptional response to cold stress. Treatment of the MMA mice with bezafibrates led to clinical improvement with beiging of subcutaneous fat depots, which resembled the distribution seen in the patients. These studies defined what we believe to be a novel lipodystrophy phenotype in patients with defects in the terminal steps of BCAA oxidation and demonstrated that beiging of subcutaneous adipose tissue in MMA could readily be induced with small molecules.

Activity Models of Key GPCR Families in the Central Nervous System: A Tool for Many Purposes

G protein-coupled receptors (GPCRs) are targets of many drugs, of which ∼25% are indicated for central nervous system (CNS) disorders. Drug promiscuity affects their efficacy and safety profiles. Predicting the polypharmacology profile of compounds against GPCRs can thus provide a basis for producing more precise therapeutics by considering the targets and the anti-targets in that family of closely related proteins. We provide a tool for predicting the polypharmacology of compounds within prominent GPCR families in the CNS: serotonin, dopamine, histamine, muscarinic, opioid, and cannabinoid receptors. Our in-house algorithm, "iterative stochastic elimination" (ISE), produces high-quality ligand-based models for agonism and antagonism at 31 GPCRs. The ISE models correctly predict 68% of CNS drug-GPCR interactions, while the "similarity ensemble approach" predicts only 33%. The activity models correctly predict 56% of reported activities of DrugBank molecules for these CNS receptors. We conclude that the combination of interactions and activity profiles generated by screening through our models form the basis for subsequent designing and discovering novel therapeutics, either single, multitargeting, or repurposed.

Predicting the Likelihood of Molecules to Act as Modulators of Protein-Protein Interactions

Targeting protein-protein interactions (PPIs) by small molecule modulators (iPPIs) is an attractive strategy for drug therapy, and some iPPIs have already been introduced into the clinic. Blocking PPIs is however considered to be a more difficult task than inhibiting enzymes or antagonizing receptor activity. In this paper, we examine whether it is possible to predict the likelihood of molecules to act as iPPIs. Using our in-house iterative stochastic elimination (ISE) algorithm, we constructed two classification models that successfully distinguish between iPPIs from the iPPI-DB database and decoy molecules from either the Enamine HTS collection (ISE 1) or the ZINC database (ISE 2). External test sets of iPPIs taken from the TIMBAL database and decoys from Enamine HTS or ZINC were screened by the models: the area under the curve for the receiver operating characteristic curve was 0.85-0.89, and the Enrichment Factor increased from an initial 1 to as much as 66 for ISE 1 and 57 for ISE 2. Screening of the Enamine HTS and ZINC data sets through both models results in a library of ∼1.3 million molecules that pass either one of the models. This library is enriched with iPPI candidates that are structurally different from known iPPIs, and thus, it is useful for target-specific screenings and should accelerate the discovery of iPPI drug candidates. The entire library is available in Table S6.

Machine Learning and Computational Chemistry for the Endocannabinoid System

Computational methods in medicinal chemistry facilitate drug discovery and design. In particular, machine learning methodologies have recently gained increasing attention. This chapter provides a structured overview of the current state of computational chemistry and its applications for the interrogation of the endocannabinoid system (ECS), highlighting methods in structure-based drug design, virtual screening, ligand-based quantitative structure-activity relationship (QSAR) modeling, and de novo molecular design. We emphasize emerging methods in machine learning and anticipate a forecast of future opportunities of computational medicinal chemistry for the ECS.

In silico Docking Analysis for Blocking JUNO-IZUMO1 Interaction Identifies Two Small Molecules that Block in vitro Fertilization

Combined hormone drugs are the basis for orally administered contraception. However, they are associated with severe side effects that are even more impactful for women in developing countries, where resources are limited. The risk of side effects may be reduced by non-hormonal small molecules which specifically target proteins involved in fertilization. In this study, we present a virtual docking experiment directed to discover molecules that target the crucial fertilization interactions of JUNO (oocyte) and IZUMO1 (sperm). We docked 913,000 molecules to two crystal structures of JUNO and ranked them on the basis of energy-related criteria. Of the 32 tested candidates, two molecules (i.e., Z786028994 and Z1290281203) demonstrated fertilization inhibitory effect in both an in vitro fertilization (IVF) assay in mice and an in vitro penetration of human sperm into hamster oocytes. Despite this clear effect on fertilization, these two molecules did not show JUNO–IZUMO1 interaction blocking activity as assessed by AVidity-based EXtracellular Interaction Screening (AVEXIS). Therefore, further research is required to determine the mechanism of action of these two fertilization inhibitors.

Candidate Therapeutics by Screening for Multitargeting Ligands: Combining the CB2 Receptor With CB1, PPARγ and 5-HT4 Receptors

In recent years, the cannabinoid type 2 receptor (CB2R) has become a major target for treating many disease conditions. The old therapeutic paradigm of “one disease-one target-one drug” is being transformed to “complex disease-many targets-one drug.” Multitargeting, therefore, attracts much attention as a promising approach. We thus focus on designing single multitargeting agents (MTAs), which have many advantages over combined therapies. Using our ligand-based approach, the “Iterative Stochastic Elimination” (ISE) algorithm, we produce activity models of agonists and antagonists for desired therapeutic targets and anti-targets. These models are used for sequential virtual screening and scoring large libraries of molecules in order to pick top-scored candidates for testing in vitro and in vivo. In this study, we built activity models for CB2R and other targets for combinations that could be used for several indications. Those additional targets are the cannabinoid 1 receptor (CB1R), peroxisome proliferator-activated receptor gamma (PPARγ), and 5-Hydroxytryptamine receptor 4 (5-HT4R). All these models have high statistical parameters and are reliable. Many more CB2R/CBIR agonists were found than combined CB2R agonists with CB1R antagonist activity (by 200 fold). CB2R agonism combined with PPARγ or 5-HT4R agonist activity may be used for treating Inflammatory Bowel Disease (IBD). Combining CB2R agonism with 5-HT4R generates more candidates (14,008) than combining CB2R agonism with agonists for the nuclear receptor PPARγ (374 candidates) from an initial set of ∼2.1 million molecules. Improved enrichment of true vs. false positives may be achieved by requiring a better ISE score cutoff or by performing docking. Those candidates can be purchased and tested experimentally to validate their activity. Further, we performed docking to CB2R structures and found lower statistical performance of the docking (“structure-based”) compared to ISE modeling (“ligand-based”). Therefore, ISE modeling may be a better starting point for molecular discovery than docking.

A review on machine learning approaches and trends in drug discovery

Drug discovery aims at finding new compounds with specific chemical properties for the treatment of diseases. In the last years, the approach used in this search presents an important component in computer science with the skyrocketing of machine learning techniques due to its democratization. With the objectives set by the Precision Medicine initiative and the new challenges generated, it is necessary to establish robust, standard and reproducible computational methodologies to achieve the objectives set. Currently, predictive models based on Machine Learning have gained great importance in the step prior to preclinical studies. This stage manages to drastically reduce costs and research times in the discovery of new drugs. This review article focuses on how these new methodologies are being used in recent years of research. Analyzing the state of the art in this field will give us an idea of where cheminformatics will be developed in the short term, the limitations it presents and the positive results it has achieved. This review will focus mainly on the methods used to model the molecular data, as well as the biological problems addressed and the Machine Learning algorithms used for drug discovery in recent years.

PPARdelta in Affected Atopic Dermatitis and Psoriasis: A Possible Role in Metabolic Reprograming

Peroxisome proliferator-activated receptors (PPARs) are nuclear hormone receptors expressed in the skin. Three PPAR isotypes, α (NRC1C1), β or δ (NRC1C2) and γ (NRC1C3), have been identified. After activation through ligand binding, PPARs heterodimerize with the 9-cis-retinoic acid receptor (RXR), another nuclear hormone receptor, to bind to specific PPAR-responsive elements in regulatory regions of target genes mainly involved in organogenesis, cell proliferation, cell differentiation, inflammation and metabolism of lipids or carbohydrates. Endogenous PPAR ligands are fatty acids and fatty acid metabolites. In past years, much emphasis has been given to PPARα and γ in skin diseases. PPARβ/δ is the least studied PPAR family member in the skin despite its key role in several important pathways regulating inflammation, keratinocyte proliferation and differentiation, metabolism and the oxidative stress response. This review focuses on the role of PPARβ/δ in keratinocytes and its involvement in psoriasis and atopic dermatitis. Moreover, the relevance of targeting PPARβ/δ to alleviate skin inflammation is discussed.

Exploring dual agonists for PPARα/γ receptors using pharmacophore modeling, docking analysis and molecule dynamics simulation

BACKGROUND

The peroxisome proliferator-activated receptors (PPARs) are ligand-activated transcription factors belonging to the nuclear receptor family. The roles of PPARα in fatty acid oxidation and PPARγ in adipocyte differentiation and lipid storage have been widely characterized. Compounds with dual PPARα/γ activity have been proposed, combining the benefits of insulin sensitization and lipid-lowering into one drug, allowing a single drug to reduce hyperglycemia and hyperlipidemia while preventing the development of cardiovascular complications.

METHODS

The new PPARα/γ agonists were screened through virtual screening of pharmacophores and molecular dynamics simulations. First, in the article, the constructed pharmacophore was used to screen the Ligand Expo Components-pub database to obtain the common structural characteristics of representative PPARα/γ agonist ligands. Then, the obtained ligand structure was modified and replaced to obtain 12 new compounds. Using molecular docking, ADMET and molecular dynamics simulation methods, the designed 12 ligands were screened, their docking scores were analyzed when they bound to the PPARα/γ dual targets, and also their stability and pharmacological properties were assessed when they were bound to the PPARα/γ dual targets.

RESULTS

We performed pharmacophore-based virtual screening for 22949 molecules in the Ligand Expo Components-pub database. Structural analysis and modification were performed on the compounds that were superior to the original ligand , and a series of compounds with novel structures were designed. Using precise docking, ADMET prediction and molecular dynamics methods, newly designed compounds were screened and verified, and the above compounds showed higher docking scores and lower side effects.

CONCLUSION

9 new PPARα/γ agonists were obtained by pharmacophore modeling, docking analysis and molecule dynamics simulation.

PPARs in liver physiology

Peroxisome proliferator-activated receptors (PPARs) are nuclear receptors and transcriptional modulators with crucial functions in hepatic and whole-body energy homeostasis. Besides their well-documented roles in lipid and glucose metabolism, emerging evidence also implicate PPARs in the control of other processes such as inflammatory responses. Recent technological advances, such as single-cell RNA sequencing, have allowed to unravel an unexpected complexity in the regulation of PPAR expression, activity and downstream signaling. Here we provide an overview of the latest advances in the study of PPARs in liver physiology, with a specific focus on formerly neglected aspects of PPAR regulation, such as tissular zonation, cellular heterogeneity, circadian rhythms, sexual dimorphism and species-specific features.

PPARα Ligand-Binding Domain Structures with Endogenous Fatty Acids and Fibrates

Most triacylglycerol-lowering fibrates have been developed in the 1960s–1980s before their molecular target, peroxisome proliferator-activated receptor alpha (PPARα), was identified. Twenty-one ligand-bound PPARα structures have been deposited in the Protein Data Bank since 2001; however, binding modes of fibrates and physiological ligands remain unknown. Here we show thirty-four X-ray crystallographic structures of the PPARα ligand-binding domain, which are composed of a “Center” and four “Arm” regions, in complexes with five endogenous fatty acids, six fibrates in clinical use, and six synthetic PPARα agonists. High-resolution structural analyses, in combination with coactivator recruitment and thermostability assays, demonstrate that stearic and palmitic acids are presumably physiological ligands; coordination to Arm III is important for high PPARα potency/selectivity of pemafibrate and GW7647; and agonistic activities of four fibrates are enhanced by the partial agonist GW9662. These results renew our understanding of PPARα ligand recognition and contribute to the molecular design of next-generation PPAR-targeted drugs.

•

X-ray crystallography reveals 34 high-resolution human PPARα-ligand structures

•

Stearic acid and palmitic acid are presumably physiological PPARα ligands

•

Coordination to Arm III domain is important for high PPARα potency/selectivity

•

Agonistic activities of four fibrates are enhanced by the partial agonist GW9662

Current and Future Treatments in the Fight Against Non-Alcoholic Fatty Liver Disease

Obesity is recognised as a risk factor for many types of cancers, in particular hepatocellular carcinoma (HCC). A critical factor in the development of HCC from non-alcoholic fatty liver disease (NAFLD) is the presence of non-alcoholic steatohepatitis (NASH). Therapies aimed at NASH to reduce the risk of HCC are sparse and largely unsuccessful. Lifestyle modifications such as diet and regular exercise have poor adherence. Moreover, current pharmacological treatments such as pioglitazone and vitamin E have limited effects on fibrosis, a key risk factor in HCC progression. As NAFLD is becoming more prevalent in developed countries due to rising rates of obesity, a need for directed treatment is imperative. Numerous novel therapies including PPAR agonists, anti-fibrotic therapies and agents targeting inflammation, oxidative stress and the gut-liver axis are currently in development, with the aim of targeting key processes in the progression of NASH and HCC. Here, we critically evaluate literature on the aetiology of NAFLD-related HCC, and explore the potential treatment options for NASH and HCC.

Computational design of substrate selective inhibition

Most enzymes act on more than a single substrate. There is frequently a need to block the production of a single pathogenic outcome of enzymatic activity on a substrate but to avoid blocking others of its catalytic actions. Full blocking might cause severe side effects because some products of that catalysis may be vital. Substrate selectivity is required but not possible to achieve by blocking the catalytic residues of an enzyme. That is the basis of the need for "Substrate Selective Inhibitors" (SSI), and there are several molecules characterized as SSI. However, none have yet been designed or discovered by computational methods. We demonstrate a computational approach to the discovery of Substrate Selective Inhibitors for one enzyme, Prolyl Oligopeptidase (POP) (E.C 3.4.21.26), a serine protease which cleaves small peptides between Pro and other amino acids. Among those are Thyrotropin Releasing Hormone (TRH) and Angiotensin-III (Ang-III), differing in both their binding (K_m) and in turnover (k_cat). We used our in-house "Iterative Stochastic Elimination" (ISE) algorithm and the structure-based "Pharmacophore" approach to construct two models for identifying SSI of POP. A dataset of ~1.8 million commercially available molecules was initially reduced to less than 12,000 which were screened by these models to a final set of 20 molecules which were sent for experimental validation (five random molecules were tested for comparison). Two molecules out of these 20, one with a high score in the ISE model, the other successful in the pharmacophore model, were confirmed by in vitro measurements. One is a competitive inhibitor of Ang-III (increases its K_m), but non-competitive towards TRH (decreases its V_max).

Many proteins are enzymes—"catalytic machines" performing chemical reactions on "substrates"–which may be small or large molecules. Evolution optimized the speed of enzyme reactions, but mutations or excessive enzyme production could lead to non-controlled, accelerated activity, which must be blocked to avoid a product that promotes disease. Many inhibitors of enzymatic activity became drugs which can block the production of the aberrant product, due to blocking the enzymatic "machinery", the amino acids involved in catalysis. Most enzymes have several substrates and so, those other substrates are blocked too. Those may be vital to the well-being of cells and life and total inhibition is prone to cause serious side effects. It is therefore essential to solve the need for inhibition of a single substrate without inhibiting others. We have thus developed computational methods to block specifically the "culprit" substrate while allowing the enzyme machine to act on other substrates. By applying these computational methods, we predicted candidates for inhibiting one out of two substrates ("substrate selective inhibition") of a well-known enzyme reaction. In collaboration with a research group that excels in studying that specific enzyme (prolyl oligopeptidase) we found that two candidates out of a set of twenty that we picked out of 1.8 million molecules by filtering through computer models—are indeed selective to one substrate vis-a-vis the other (five random molecules were tested for comparison). This may be the first example of a computational method leading to substrate selective inhibitor drugs which could avoid side effects.

DeepSnap-Deep Learning Approach Predicts Progesterone Receptor Antagonist Activity With High Performance

The progesterone receptor (PR) is important therapeutic target for many malignancies and endocrine disorders due to its role in controlling ovulation and pregnancy via the reproductive cycle. Therefore, the modulation of PR activity using its agonists and antagonists is receiving increasing interest as novel treatment strategy. However, clinical trials using the PR modulators have not yet been found conclusive evidences. Recently, increasing evidence from several fields shows that the classification of chemical compounds, including agonists and antagonists, can be done with recent improvements in deep learning (DL) using deep neural network. Therefore, we recently proposed a novel DL-based quantitative structure-activity relationship (QSAR) strategy using transfer learning to build prediction models for agonists and antagonists. By employing this novel approach, referred as DeepSnap-DL method, which uses images captured from 3-dimension (3D) chemical structure with multiple angles as input data into the DL classification, we constructed prediction models of the PR antagonists in this study. Here, the DeepSnap-DL method showed a high performance prediction of the PR antagonists by optimization of some parameters and image adjustment from 3D-structures. Furthermore, comparison of the prediction models from this approach with conventional machine learnings (MLs) indicated the DeepSnap-DL method outperformed these MLs. Therefore, the models predicted by DeepSnap-DL would be powerful tool for not only QSAR field in predicting physiological and agonist/antagonist activities, toxicity, and molecular bindings; but also for identifying biological or pathological phenomena.

Prediction of novel mouse TLR9 agonists using a random forest approach

BACKGROUND

Toll-like receptor 9 is a key innate immune receptor involved in detecting infectious diseases and cancer. TLR9 activates the innate immune system following the recognition of single-stranded DNA oligonucleotides (ODN) containing unmethylated cytosine-guanine (CpG) motifs. Due to the considerable number of rotatable bonds in ODNs, high-throughput in silico screening for potential TLR9 activity via traditional structure-based virtual screening approaches of CpG ODNs is challenging. In the current study, we present a machine learning based method for predicting novel mouse TLR9 (mTLR9) agonists based on features including count and position of motifs, the distance between the motifs and graphically derived features such as the radius of gyration and moment of Inertia. We employed an in-house experimentally validated dataset of 396 single-stranded synthetic ODNs, to compare the results of five machine learning algorithms. Since the dataset was highly imbalanced, we used an ensemble learning approach based on repeated random down-sampling.

RESULTS

Using in-house experimental TLR9 activity data we found that random forest algorithm outperformed other algorithms for our dataset for TLR9 activity prediction. Therefore, we developed a cross-validated ensemble classifier of 20 random forest models. The average Matthews correlation coefficient and balanced accuracy of our ensemble classifier in test samples was 0.61 and 80.0%, respectively, with the maximum balanced accuracy and Matthews correlation coefficient of 87.0% and 0.75, respectively. We confirmed common sequence motifs including 'CC', 'GG','AG', 'CCCG' and 'CGGC' were overrepresented in mTLR9 agonists. Predictions on 6000 randomly generated ODNs were ranked and the top 100 ODNs were synthesized and experimentally tested for activity in a mTLR9 reporter cell assay, with 91 of the 100 selected ODNs showing high activity, confirming the accuracy of the model in predicting mTLR9 activity.

CONCLUSION

We combined repeated random down-sampling with random forest to overcome the class imbalance problem and achieved promising results. Overall, we showed that the random forest algorithm outperformed other machine learning algorithms including support vector machines, shrinkage discriminant analysis, gradient boosting machine and neural networks. Due to its predictive performance and simplicity, the random forest technique is a useful method for prediction of mTLR9 ODN agonists.

Prediction and Experimental Confirmation of Novel Peripheral Cannabinoid-1 Receptor Antagonists

Small molecules targeting peripheral CB1 receptors have therapeutic potential in a variety of disorders including obesity-related, hormonal, and metabolic abnormalities, while avoiding the psychoactive effects in the central nervous system. We applied our in-house algorithm, iterative stochastic elimination, to produce a ligand-based model that distinguishes between CB1R antagonists and random molecules by physicochemical properties only. We screened ∼2 million commercially available molecules and found that about 500 of them are potential candidates to antagonize the CB1R. We applied a few criteria for peripheral activity and narrowed that set down to 30 molecules, out of which 15 could be purchased. Ten out of those 15 showed good affinity to the CB1R and two of them with nanomolar affinities (K_i of ∼400 nM). The eight molecules with top affinities were tested for activity: two compounds were pure antagonists, and five others were inverse agonists. These molecules are now being examined in vivo for their peripheral versus central distribution and subsequently will be tested for their effects on obesity in small animals.