Fipronil disturbs the antigen-specific immune responses and GABAergic gene expression in the ovalbumin-immunized BALB/c mice.

BACKGROUND: Fipronil (FPN) is a broad-spectrum pesticide and commonly known as low toxicity to vertebrates. However, increasing evidence suggests that exposure to FPN might induce unexpected adverse effects in the liver, reproductive, and nervous systems. Until now, the influence of FPN on immune responses, especially T-cell responses has not been well examined. Our study is designed to investigate the immunotoxicity of FPN in ovalbumin (OVA)-sensitized mice. The mice were administered with FPN by oral gavage and immunized with OVA. Primary splenocytes were prepared to examine the viability and functionality of antigen-specific T cells ex vivo. The expression of T cell cytokines, upstream transcription factors, and GABAergic signaling genes was detected by qPCR. RESULTS: Intragastric administration of FPN (1-10 mg/kg) for 11 doses did not show any significant clinical symptoms. The viability of antigen-stimulated splenocytes, the production of IL-2, IL-4, and IFN-γ by OVA-specific T cells, and the serum levels of OVA-specific IgG1 and IgG2a were significantly increased in FPN-treated groups. The expression of the GABAergic signaling genes was notably altered by FPN. The GAD67 gene was significantly decreased, while the GABAR ß2 and GABAR δ were increased. CONCLUSION: FPN disturbed antigen-specific immune responses by affecting GABAergic genes in vivo. We propose that the immunotoxic effects of FPN may enhance antigen-specific immunity by dysregulation of the negative regulation of GABAergic signaling on T cell immunity.

Probing the hair detectability of prohibited substances in sports: an in vivo-in silico-clinical approach and analytical implications compared with plasma, urine, and faeces.

Hair analysis is a crucial method in forensic toxicology with potential applications in revealing doping histories in sports. Despite its widespread use, knowledge about detectable substances in hair is limited. This study systematically assessed the detectability of prohibited substances in sports using a multifaceted approach. Initially, an animal model received a subset of 17 model drugs to compare dose dependencies and detection windows across different matrices. Subsequently, hair incorporation data from the animal experiment were extrapolated to all substances on the World Anti-Doping Agency's List through in-silico prediction. The detectability of substances in hair was further validated in a proof-of-concept human study involving the consumption of diuretics and masking agents. Semi-quantitative analysis of substances in specimens was performed using ultra-performance liquid chromatography-tandem mass spectrometry. Results showed plasma had optimal dose dependencies with limited detection windows, while urine, faeces, and hair exhibited a reasonable relationship with the administered dose. Notably, hair displayed the highest detection probability (14 out of 17) for compounds, including anabolic agents, hormones, and diuretics, with beta-2 agonists undetected. Diuretics such as furosemide, canrenone, and hydrochlorothiazide showed the highest hair incorporation. Authentic human hair confirmed diuretic detectability, and their use duration was determined via segmental analysis. Noteworthy is the first-time reporting of canrenone in human hair. Anabolic agents were expected in hair, whereas undetectable compounds, such as peptide hormones and beta-2 agonists, were likely due to large molecular mass or high polarity. This study enhances understanding of hair analysis in doping investigations, providing insights into substance detectability.

Canine diffuse large b-cell lymphoma downregulates the activity of CD8 + T-cells through tumor-derived extracellular vesicles.

BACKGROUND: Tumor-derived extracellular vesicles (EVs) have been proposed as the essential mediator between host immunity and cancer development. These EVs conduct cellular communication to facilitate tumor growth, enable invasion and metastasis, and shape the favorable tumor microenvironment. Lymphoma is one of the most common hematological malignancies in humans and dogs. Effective T-cell responses are required for the control of these malignancies. However, the immune crosstalk between CD8 + T-cells, which dominates anti-tumor responses, and canine lymphoma has rarely been described. METHODS: This study investigates the immune manipulating effects of EVs, produced from the clinical cases and cell line of canine B cell lymphoma, on CD8 + T-cells isolated from canine donors. RESULTS: Lymphoma-derived EVs lead to the apoptosis of CD8 + T-cells. Furthermore, EVs trigger the overexpression of CTLA-4 on CD8 + T-cells, which indicates that EV blockade could serve as a potential therapeutic strategy for lymphoma patients. Notably, EVs transform the CD8 + T-cells into regulatory phenotypes by upregulating their PD-1, PD-L1, and FoxP3 mRNA expression. The regulatory CD8 + T-cells secret the panel of inhibitory cytokines and angiogenic factors and thus create a pro-tumorigenic microenvironment. CONCLUSION: In summary, the current study demonstrated that the EVs derived from canine B cell lymphoma impaired the anti-tumor activity of CD8 + T-cells and manipulated the possible induction of regulatory CD8 + T-cells to fail the activation of host cellular immunity.

Using random forest to predict antimicrobial minimum inhibitory concentrations of nontyphoidal Salmonella in Taiwan.

Antimicrobial resistance (AMR) is a global health issue and surveillance of AMR can be useful for understanding AMR trends and planning intervention strategies. Salmonella, widely distributed in food-producing animals, has been considered the first priority for inclusion in the AMR surveillance program by the World Health Organization (WHO). Recent advances in rapid and affordable whole-genome sequencing (WGS) techniques lead to the emergence of WGS as a one-stop test to predict the antimicrobial susceptibility. Since the variation of sequencing and minimum inhibitory concentration (MIC) measurement methods could result in different results, this study aimed to develop WGS-based random forest models for predicting MIC values of 24 drugs using data generated from the same laboratories in Taiwan. The WGS data have been transformed as a feature vector of 10-mers for machine learning. Based on rigorous validation and independent tests, a good performance was obtained with an average mean absolute error (MAE) less than 1 for both validation and independent test. Feature selection was then applied to identify top-ranked 10-mers that can further improve the prediction performance. For surveillance purposes, the genome sequence-based machine learning methods could be utilized to monitor the difference between predicted and experimental MIC, where a large difference might be worthy of investigation on the emerging genomic determinants.

Analysis of structure-activity relationship of indol-3-yl-N-phenylcarbamic amides as potent STING inhibitors.

A structure-activity relationship (SAR) study of stimulator of interferon gene (STING) inhibition was performed using a series of indol-3-yl-N-phenylcarbamic amides and indol-2-yl-N-phenylcarbamic amides. Among these analogs, compounds 10, 13, 15, 19, and 21 inhibited the phosphorylation of STING and interferon regulatory factor 3 (IRF3) to a greater extent than the reference compound, H-151. All five analogs showed stronger STING inhibition than H-151 on the 2',3'-cyclic GMP-AMP-induced expression of interferon regulatory factors (IRFs) in a STINGR232 knock-in THP-1 reporter cell line. The half-maximal inhibitory concentration of the most potent compound, 21, was 11.5 nM. The molecular docking analysis of compound 21 and STING combined with the SAR study suggested that the meta- and para-positions of the benzene ring of the phenylcarbamic amide moiety could be structurally modified by introducing halides or alkyl substituents.

Ensemble learning for predicting ex vivo human placental barrier permeability.

BACKGROUND: The placental barrier protects the fetus from exposure to some toxicants and is vital for drug development and risk assessment of environmental chemicals. However, in vivo experiments for assessing the placental barrier permeability of chemicals is not ethically acceptable. Although ex vivo placental perfusion methods provide good alternatives for the assessment of placental barrier permeability, the application to a large number of test chemicals could be time- and resource-consuming. Computational prediction models for ex vivo placental barrier permeability are therefore desirable. METHODS: A total of 87 chemicals and corresponding 1444 physicochemical properties were divided into training and test datasets. Three types of algorithms including linear regression, random forest, and ensemble models were applied to develop prediction models for ex vivo placental barrier permeability. RESULTS: Among the tested models, the ensemble model integrating the previous two methods performed best for predicting ex vivo human placental barrier permeability with correlation coefficients of 0.887 and 0.825 when considering the applicability domain. An additional test on seven newly curated chemicals from the literature showed a good correlation coefficient of 0.879 which was further improved to 0.921 by considering the variation of experiments. CONCLUSION: In this study, the first valid predicting model for ex vivo human placental barrier permeability was developed following the OECD guideline. The model is expected to be useful for assessing the human placental barrier permeability and can be integrated with developmental toxicity prediction models for investigating the toxic effects of chemicals on the fetus.

In silico prediction of parkinsonian motor deficits-related neurotoxicants based on the adverse outcome pathway concept.

Exposure to neurotoxicants has been associated with Parkinson's disease (PD). Limited by the clinical variation in the signs and symptoms as well as the slow disease progression, the identification of parkinsonian neurotoxicants relies on animal models. Here, we propose an innovative in silico model for the prediction of parkinsonian neurotoxicants. The model was designed based on a validated adverse outcome pathway (AOP) for parkinsonian motor deficits initiated from the inhibition of mitochondrial complex I. The model consists of a molecular docking model for mitochondrial complex I protein to predict the molecular initiating event and a neuronal cytotoxicity Quantitative Structure-Activity Relationships (QSAR) model to predict the cellular outcome of the AOP. Four known PD-related complex I inhibitors and four non-neurotoxic chemicals were utilized to develop the threshold of the models and to validate the model, respectively. The integrated model showed 100% specificity in ruling out the non-neurotoxic chemicals. The screening of 41 neurotoxicants and complex I inhibitors with the model resulted in 16 chemicals predicted to induce parkinsonian disorder through the molecular initiating event of mitochondrial complex I inhibition. Five of them, namely cyhalothrin, deguelin, deltamethrin, diazepam, and permethrin, are cases with direct evidence linking them to parkinsonian motor deficit-related signs and symptoms. The neurotoxicant prediction model for parkinsonian motor deficits based on the AOP concept may be useful in prioritizing chemicals for further evaluations on PD potential.

Computational prediction of Calu-3-based in vitro pulmonary permeability of chemicals.

Pulmonary is a potential route for drug delivery and exposure to toxic chemicals. The human bronchial epithelial cell line Calu-3 is generally considered to be a useful in vitro model of pulmonary permeability by calculating the apparent permeability coefficient (Papp) values. Since in vitro experiments are time-consuming and labor-intensive, computational models for pulmonary permeability are desirable for accelerating drug design and toxic chemical assessment. This study presents the first attempt for developing quantitative structure-activity relationship (QSAR) models for addressing this goal. A total of 57 chemicals with Papp values based on Calu-3 experiments was first curated from literature for model development and testing. Subsequently, eleven descriptors were identified by a sequential forward feature selection algorithm to maximize the cross-validation performance of a voting regression model integrating linear regression and nonlinear random forest algorithms. With applicability domain adjustment, the developed model achieved high performance with correlation coefficient values of 0.935 and 0.824 for cross-validation and independent test, respectively. The preliminary results showed that computational models could be helpful for predicting Calu-3-based in vitro pulmonary permeability of chemicals. Future works include the collection of more data for further validating and improving the model.

Computational identification of preservatives with potential neuronal cytotoxicity.

Preservatives play a vital role in cosmetics by preventing microbiological contamination for keeping products safe to use. However, a few commonly used preservatives have been suggested to be neurotoxic. Cytotoxicity to neuronal cells is commonly used as the first-tier assay for assessing chemical-induced neurotoxicity. Given the time and resources required for chemical screening, computational methods are attractive alternatives over experimental approaches in prioritizing chemicals prior to further experimental evaluations. In this study, we developed a Quantitative Structure-Activity Relationships (QSAR) model for the identification of potential neurotoxicants. A set of 681 chemicals was utilized to construct a robust prediction model using oversampling and Random Forest algorithms. Within a defined applicability domain, the independent test on 452 chemicals showed a high accuracy of 87.7%. The application of the model to 157 preservatives identified 15 chemicals potentially toxic to neuronal cells. Three of them were further validated by in vitro experiments. The results suggested that further experiments are desirable for assessing the neurotoxicity of the identified preservatives with potential neuronal cytotoxicity.

Leveraging complementary computational models for prioritizing chemicals of developmental and reproductive toxicity concern: an example of food contact materials.

The evaluation of developmental and reproductive toxicity of food contact materials (FCMs) is an important task for food safety. Since traditional experiments are both time-consuming and labor-intensive, only a small number of FCMs have sufficient toxicological data for evaluating their effects on human health. While computational methods such as structural alerts and quantitative structure-activity relationships can serve as first-line tools for the identification of chemicals of high toxicity concern, models with binary outputs and unsatisfied accuracy and coverage prevent the use of computational methods for prioritizing chemicals of high concern. This study proposed a genetic algorithm-based method to develop a weight-of-evidence (WoE) model leveraging complementary methods of structural alerts, quantitative structure-activity relationships and in silico toxicogenomics models for chemical prioritization. The WoE model was applied to evaluate 623 food contact chemicals and identify 26 chemicals of high toxicity concern, where 13 chemicals have been reported to be developmental or reproductive toxic and further experiments are suggested for the remaining 13 chemicals without toxicity data related to developmental and reproductive effects. The proposed WoE model is potentially useful for prioritizing chemicals of high toxicity concern and the methodology may be applied to toxicities other than developmental and reproductive toxicity.

Transfer learning for predicting human skin sensitizers.

Computational prioritization of chemicals for potential skin sensitization risks plays essential roles in the risk assessment of environmental chemicals and drug development. Given the huge number of chemicals for testing, computational methods enable the fast identification of high-risk chemicals for experimental validation and design of safer alternatives. However, the development of robust prediction model requires a large dataset of tested chemicals that is usually not available for most toxicological endpoints, especially for human data. A small training dataset makes the development of effective models difficult with insufficient coverage and accuracy. In this study, an ensemble tree-based multitask learning method was developed incorporating three relevant tasks in the well-defined adverse outcome pathway (AOP) of skin sensitization to transfer shared knowledge to the major task of human sensitizers. The results show both largely improved coverage and accuracy compared with three state-of-the-art methods. A user-friendly prediction server was available at https://cwtung.kmu.edu.tw/skinsensdb/predict . As AOPs for various toxicity endpoints are being actively developed, the proposed method can be applied to develop prediction models for other endpoints.

Human immunodeficiency virus Tat-TIP30 interaction promotes metastasis by enhancing the nuclear translocation of Snail in lung cancer cell lines.

Lung cancer patients with human immunodeficiency virus (HIV) have a poorer prognosis than do patients without HIV infection. HIV1 Tat is a secreted viral protein that penetrates the plasma membrane and interacts with a number of proteins in non-HIV-infected cells. The loss of function of Tat-interacting protein 30 (TIP30) has been linked to metastasis in non-small cell lung cancer (NSCLC). However, it is unknown how the interaction of HIV1 Tat with TIP30 regulates the metastasis of NSCLC cells. In this study, the overexpression of TIP30 decreased tumor growth factor-ß-induced epithelial-to-mesenchymal transition (EMT) and invasion of NSCLC cells, whereas the knockdown of TIP30 promoted EMT, invasion and stemness. Exposure to recombinant HIV1 Tat proteins promoted EMT and invasion. A mechanistic study showed that the interaction of HIV1 Tat with TIP30 blocked the binding of TIP30 to importin-ß, which is required for the nuclear translocation of Snail. Indeed, the loss of TIP30 promoted the nuclear translocation of Snail. In vivo studies demonstrated that the overexpression of TIP30 inhibited the metastasis of NSCLC cells. In contrast, the coexpression of HIV1 Tat and TIP30 diminished the inhibitory effect of TIP30 on metastasis. Immunohistochemistry confirmed that TIP30 overexpression reduced the nuclear localization of Snail, whereas the coexpression of HIV1 Tat and TIP30 increased nuclear Snail in metastatic tumors. In conclusion, the binding of HIV1 Tat to TIP30 enhanced EMT and metastasis by regulating the nuclear translocation of Snail. Targeting Tat-interacting proteins may be a potential therapeutic strategy to prevent metastasis in NSCLC patients with HIV infection.

Mechanism-informed read-across assessment of skin sensitizers based on SkinSensDB.

Integrative testing strategies using adverse outcome pathway (AOP)-based alternative assays for assessing skin sensitizers show the potential for replacing animal testing. However, the application of alternative assays for a large number of chemicals is still time-consuming and expensive. In order to facilitate the assessment of skin sensitizers based on integrative testing strategies, a mechanism-informed read-across assessment method was proposed and evaluated using data from SkinSensDB. First, the prediction performance of two integrated testing strategy models was evaluated giving the highest area under the receiver operating characteristic curve (AUC) values of 0.928 and 0.837 for predicting human and LLNA data, respectively. The proposed read-across prediction method achieves AUC values of 0.957 and 0.802 for predicting human and LLNA data, respectively, with interpretable activation statuses of AOP events. As data grows, a better prediction performance is expected. A user-friendly tool has been constructed and integrated into SkinSensDB that is publicly accessible at http://cwtung.kmu.edu.tw/skinsensdb.

Discovery of Pyrazolo[4,3-c]quinolines Derivatives as Potential Anti-Inflammatory Agents through Inhibiting of NO Production.

The synthesis and anti-inflammatory effects of certain pyrazolo[4,3-c]quinoline derivatives 2a⁻2r are described. The anti-inflammatory activities of these derivatives were evaluated by means of inhibiting nitric oxide (NO) production in lipopolysaccharide (LPS)-induced RAW 264.7 cells. Among them, 3-amino-4-(4-hydroxyphenylamino)-1H-pyrazolo[4,3-c]-quinoline (2i) and 4-(3-amino-1H-pyrazolo[4,3-c]quinolin-4-ylamino)benzoic acid (2m) exhibited significant inhibition of LPS-stimulated NO production with a potency approximately equal to that of the positive control, 1400 W. Important structure features were analyzed by quantitative structure⁻activity relationship (QSAR) analysis to give better insights into the structure determinants for predicting the inhibitory effects on the accumulation of nitric oxide for RAW 264.7 cells in response to LPS. In addition, our results indicated that their anti-inflammatory effects involve the inhibition of inducible nitric oxide synthase (iNOS) and cyclooxygenase 2 (COX-2) protein expression. Further studies on the structural optimization are ongoing.

Identification of informative features for predicting proinflammatory potentials of engine exhausts.

BACKGROUND: The immunotoxicity of engine exhausts is of high concern to human health due to the increasing prevalence of immune-related diseases. However, the evaluation of immunotoxicity of engine exhausts is currently based on expensive and time-consuming experiments. It is desirable to develop efficient methods for immunotoxicity assessment. METHODS: To accelerate the development of safe alternative fuels, this study proposed a computational method for identifying informative features for predicting proinflammatory potentials of engine exhausts. A principal component regression (PCR) algorithm was applied to develop prediction models. The informative features were identified by a sequential backward feature elimination (SBFE) algorithm. RESULTS: A total of 19 informative chemical and biological features were successfully identified by SBFE algorithm. The informative features were utilized to develop a computational method named FS-CBM for predicting proinflammatory potentials of engine exhausts. FS-CBM model achieved a high performance with correlation coefficient values of 0.997 and 0.943 obtained from training and independent test sets, respectively. CONCLUSIONS: The FS-CBM model was developed for predicting proinflammatory potentials of engine exhausts with a large improvement on prediction performance compared with our previous CBM model. The proposed method could be further applied to construct models for bioactivities of mixtures.

Discovery of Indeno[1,2-c]quinoline Derivatives as Potent Dual Antituberculosis and Anti-Inflammatory Agents.

A series of indeno[1,2-c]quinoline derivatives were designed, synthesized and evaluated for their anti-tuberculosis (anti-TB) and anti-inflammatory activities. The minimum inhibitory concentration (MIC) of the newly synthesized compound was tested against Mycobacterium tuberculosis H37RV. Among the tested compounds, (E)-N'-[6-(4-hydroxypiperidin-1-yl)-11H-indeno[1,2-c]quinolin-11-ylidene]isonicotino-hydrazide (12), exhibited significant activities against the growth of M. tuberculosis (MIC values of 0.96 µg/mL) with a potency approximately equal to that of isoniazid (INH), an anti-TB drug. Important structure features were analyzed by quantitative structure-activity relationship (QSAR) analysis to give better insights into the structure determinants for predicting the anti-TB activity. The anti-inflammatory activity was induced by superoxide anion generation and neutrophil elastase (NE) release using the formyl-l-methionyl-l-leucyl-l-phenylalanine (fMLF)-activated human neutrophils method. Results indicated that compound 12 demonstrated a potent dual inhibitory effect on NE release and superoxide anion generation with IC50 values of 1.76 and 1.72 µM, respectively. Our results indicated that compound 12 is a potential lead compound for the discovery of dual anti-TB and anti-inflammatory drug candidates. In addition, 6-[3-(hydroxymethyl)piperidin-1-yl]-9-methoxy-11H-indeno[1,2-c]quinolin-11-one (4g) showed a potent dual inhibitory effect on NE release and superoxide anion generation with IC50 values of 0.46 and 0.68 µM, respectively, and is a potential lead compound for the discovery of anti-inflammatory drug candidates.

A testing strategy to predict risk for drug-induced liver injury in humans using high-content screen assays and the 'rule-of-two' model.

Drug-induced liver injury (DILI) is a major cause of drug failures in both the preclinical and clinical phase. Consequently, improving prediction of DILI at an early stage of drug discovery will reduce the potential failures in the subsequent drug development program. In this regard, high-content screening (HCS) assays are considered as a promising strategy for the study of DILI; however, the predictive performance of HCS assays is frequently insufficient. In the present study, a new testing strategy was developed to improve DILI prediction by employing in vitro assays that was combined with the RO2 model (i.e., 'rule-of-two' defined by daily dose ≥100 mg/day & logP ≥3). The RO2 model was derived from the observation that high daily doses and lipophilicity of an oral medication were associated with significant DILI risk in humans. In the developed testing strategy, the RO2 model was used for the rational selection of candidates for HCS assays, and only the negatives predicted by the RO2 model were further investigated by HCS. Subsequently, the effects of drug treatment on cell loss, nuclear size, DNA damage/fragmentation, apoptosis, lysosomal mass, mitochondrial membrane potential, and steatosis were studied in cultures of primary rat hepatocytes. Using a set of 70 drugs with clear evidence of clinically relevant DILI, the testing strategy improved the accuracies by 10 % and reduced the number of drugs requiring experimental assessment by approximately 20 %, as compared to the HCS assay alone. Moreover, the testing strategy was further validated by including published data (Cosgrove et al. in Toxicol Appl Pharmacol 237:317-330, 2009) on drug-cytokine-induced hepatotoxicity, which improved the accuracies by 7 %. Taken collectively, the proposed testing strategy can significantly improve the prediction of in vitro assays for detecting DILI liability in an early drug discovery phase.

Rule-based knowledge acquisition method for promoter prediction in human and Drosophila species.

The rapid and reliable identification of promoter regions is important when the number of genomes to be sequenced is increasing very speedily. Various methods have been developed but few methods investigate the effectiveness of sequence-based features in promoter prediction. This study proposes a knowledge acquisition method (named PromHD) based on if-then rules for promoter prediction in human and Drosophila species. PromHD utilizes an effective feature-mining algorithm and a reference feature set of 167 DNA sequence descriptors (DNASDs), comprising three descriptors of physicochemical properties (absorption maxima, molecular weight, and molar absorption coefficient), 128 top-ranked descriptors of 4-mer motifs, and 36 global sequence descriptors. PromHD identifies two feature subsets with 99 and 74 DNASDs and yields test accuracies of 96.4% and 97.5% in human and Drosophila species, respectively. Based on the 99- and 74-dimensional feature vectors, PromHD generates several if-then rules by using the decision tree mechanism for promoter prediction. The top-ranked informative rules with high certainty grades reveal that the global sequence descriptor, the length of nucleotide A at the first position of the sequence, and two physicochemical properties, absorption maxima and molecular weight, are effective in distinguishing promoters from non-promoters in human and Drosophila species, respectively.

Multitask learning for predicting pulmonary absorption of chemicals.

Pulmonary absorption is an important route for drug delivery and chemical exposure. To streamline the chemical assessment process for the reduction of animal experiments, several animal-free models were developed for pulmonary absorption research. While Calu-3 and Caco-2 cells and their derived computational models were used in estimating pulmonary permeability, the ex vivo isolated perfused lung (IPL) models are considered more clinically relevant measurements. However, the IPL experiments are resource-consuming making it infeasible for the large-scale screening of potential inhaled toxicants and drugs. In silico models are desirable for estimating pulmonary absorption. This study presented a novel machine learning method that employed an extratrees-based multitask learning approach to predict the IPL absorption rate constant (kaIPL) of various chemicals. The shared permeability knowledge was extracted by simultaneously learning three relevant tasks of Caco-2 and Calu-3 cell permeability and IPL absorption rate. Seven informative physicochemical descriptors were identified. A rigorous evaluation of the developed prediction model showed good performance with a high correlation between predictions and observations (r = 0.84) in the independent test dataset. Two case studies of inhalation drugs and respiratory sensitizers revealed the potential application of this model, which may serve as a valuable tool for predicting pulmonary absorption of chemicals.

Decrypting orphan GPCR drug discovery via multitask learning.

The drug discovery of G protein-coupled receptors (GPCRs) superfamily using computational models is often limited by the availability of protein three-dimensional (3D) structures and chemicals with experimentally measured bioactivities. Orphan GPCRs without known ligands further complicate the process. To enable drug discovery for human orphan GPCRs, multitask models were proposed for predicting half maximal effective concentrations (EC50) of the pairs of chemicals and GPCRs. Protein multiple sequence alignment features, and physicochemical properties and fingerprints of chemicals were utilized to encode the protein and chemical information, respectively. The protein features enabled the transfer of data-rich GPCRs to orphan receptors and the transferability based on the similarity of protein features. The final model was trained using both agonist and antagonist data from 200 GPCRs and showed an excellent mean squared error (MSE) of 0.24 in the validation dataset. An independent test using the orphan dataset consisting of 16 receptors associated with less than 8 bioactivities showed a reasonably good MSE of 1.51 that can be further improved to 0.53 by considering the transferability based on protein features. The informative features were identified and mapped to corresponding 3D structures to gain insights into the mechanism of GPCR-ligand interactions across the GPCR family. The proposed method provides a novel perspective on learning ligand bioactivity within the diverse human GPCR superfamily and can potentially accelerate the discovery of therapeutic agents for orphan GPCRs.