Reducing hERG Toxicity Using hERG Classification Model and Fragment-growing Network

Drug-induced cardiotoxicity has become one of the major reasons leading to drug withdrawal in past decades, which is closely related to the blockade of human Ether-a-go-go-related gene (hERG) potassium channel. Developing reliable hERG predicting model and optimizing model can greatly reduce the risk faced in drug discovery. In this study, we constructed eight hERG classification models, the best of which shows desirable generalization ability on low-similarity clinical compounds, as well as advantages in perceiving activity gap caused by small structural changes. Furthermore, we developed a hERG optimizer based on fragment grow strategy and explored its usage in four cases. After reinforcement learning, our model successfully suggests same or similar compounds as chemists’ optimization. Results suggest that our model can provide reasonable optimizing direction to reduce hERG toxicity when hERG risk is corresponding to lipophilicity, basicity, the number of rotatable bonds and pi-pi interactions. Overall, we demonstrate our model as a promising tool for medicinal chemists in hERG optimization attempts.

Download Full-text

Reducing hERG Toxicity Using Reliable hERG Classification Model and Fragment Grow Model

10.26434/chemrxiv.13153112 ◽

2020 ◽

Author(s):

Yan Yang ◽

Yanmin Zhang ◽

Yihang Zhang ◽

Xingye Chen ◽

Yi Hua ◽

...

Keyword(s):

Reinforcement Learning ◽

Structural Changes ◽

Drug Withdrawal ◽

Classification Model ◽

Classification Models ◽

Related Gene ◽

Drug Induced ◽

Promising Tool ◽

Optimizing Model ◽

Pi Interactions

Drug-induced cardiotoxicity has become one of the major reasons leading to drug withdrawal in past decades, which is closely related to the blockade of human Ether-a-go-go-related gene (hERG) potassium channel. Developing reliable hERG predicting model and optimizing model can greatly reduce the risk faced in drug discovery. In this study, we constructed eight hERG classification models, the best of which shows desirable generalization ability on low-similarity clinical compounds, as well as advantages in perceiving activity gap caused by small structural changes. Furthermore, we developed a hERG optimizer based on fragment grow strategy. Results reveal that after reinforcement learning, our model can provide reasonable optimizing direction to reduce hERG toxicity, especially when hERG risk is corresponding to lipophilicity, basicity and pi-pi interactions. We also prove its usage in helping chemists quickly pick out core fragments and fix on the region to be optimized. Overall, we demonstrate our model as a promising tool for medicinal chemists in hERG optimization attempts.

Download Full-text

Reducing hERG Toxicity Using Reliable hERG Classification Model and Fragment Grow Model

10.26434/chemrxiv.13153112.v1 ◽

2020 ◽

Author(s):

Yan Yang ◽

Yanmin Zhang ◽

Yihang Zhang ◽

Xingye Chen ◽

Yi Hua ◽

...

Keyword(s):

Reinforcement Learning ◽

Structural Changes ◽

Drug Withdrawal ◽

Classification Model ◽

Classification Models ◽

Related Gene ◽

Drug Induced ◽

Promising Tool ◽

Optimizing Model ◽

Pi Interactions

Drug-induced cardiotoxicity has become one of the major reasons leading to drug withdrawal in past decades, which is closely related to the blockade of human Ether-a-go-go-related gene (hERG) potassium channel. Developing reliable hERG predicting model and optimizing model can greatly reduce the risk faced in drug discovery. In this study, we constructed eight hERG classification models, the best of which shows desirable generalization ability on low-similarity clinical compounds, as well as advantages in perceiving activity gap caused by small structural changes. Furthermore, we developed a hERG optimizer based on fragment grow strategy. Results reveal that after reinforcement learning, our model can provide reasonable optimizing direction to reduce hERG toxicity, especially when hERG risk is corresponding to lipophilicity, basicity and pi-pi interactions. We also prove its usage in helping chemists quickly pick out core fragments and fix on the region to be optimized. Overall, we demonstrate our model as a promising tool for medicinal chemists in hERG optimization attempts.

Download Full-text

Comparison of Spectroscopic Techniques Combined with Chemometrics for Cocaine Powder Analysis

Journal of Analytical Toxicology ◽

10.1093/jat/bkaa101 ◽

2020 ◽

Vol 44 (8) ◽

pp. 851-860

Author(s):

Joy Eliaerts ◽

Natalie Meert ◽

Pierre Dardenne ◽

Vincent Baeten ◽

Juan-Antonio Fernandez Pierna ◽

...

Keyword(s):

Gas Chromatography ◽

Near Infrared ◽

Evaluation Criteria ◽

Classification Model ◽

Support Vector ◽

Spectroscopic Techniques ◽

Data Set ◽

Promising Tool ◽

Powder Analysis ◽

Mir Spectra

Abstract Spectroscopic techniques combined with chemometrics are a promising tool for analysis of seized drug powders. In this study, the performance of three spectroscopic techniques [Mid-InfraRed (MIR), Raman and Near-InfraRed (NIR)] was compared. In total, 364 seized powders were analyzed and consisted of 276 cocaine powders (with concentrations ranging from 4 to 99 w%) and 88 powders without cocaine. A classification model (using Support Vector Machines [SVM] discriminant analysis) and a quantification model (using SVM regression) were constructed with each spectral dataset in order to discriminate cocaine powders from other powders and quantify cocaine in powders classified as cocaine positive. The performances of the models were compared with gas chromatography coupled with mass spectrometry (GC–MS) and gas chromatography with flame-ionization detection (GC–FID). Different evaluation criteria were used: number of false negatives (FNs), number of false positives (FPs), accuracy, root mean square error of cross-validation (RMSECV) and determination coefficients (R2). Ten colored powders were excluded from the classification data set due to fluorescence background observed in Raman spectra. For the classification, the best accuracy (99.7%) was obtained with MIR spectra. With Raman and NIR spectra, the accuracy was 99.5% and 98.9%, respectively. For the quantification, the best results were obtained with NIR spectra. The cocaine content was determined with a RMSECV of 3.79% and a R2 of 0.97. The performance of MIR and Raman to predict cocaine concentrations was lower than NIR, with RMSECV of 6.76% and 6.79%, respectively and both with a R2 of 0.90. The three spectroscopic techniques can be applied for both classification and quantification of cocaine, but some differences in performance were detected. The best classification was obtained with MIR spectra. For quantification, however, the RMSECV of MIR and Raman was twice as high in comparison with NIR. Spectroscopic techniques combined with chemometrics can reduce the workload for confirmation analysis (e.g., chromatography based) and therefore save time and resources.

Download Full-text

Allopurinol-Induced Oral Lichenoid Drug Reaction with Complete Regression after Drug Withdrawal

Dermatopathology ◽

10.3390/dermatopathology7020004 ◽

2020 ◽

Vol 7 (2) ◽

pp. 18-25

Author(s):

Alexandre Perez ◽

Benjamin Lazzarotto ◽

Jean-Pierre Carrel ◽

Tommaso Lombardi

Keyword(s):

Drug Reaction ◽

Lichen Planus ◽

Drug Withdrawal ◽

Acute Onset ◽

Complete Regression ◽

Oral Manifestations ◽

First Line ◽

Drug Induced ◽

Case Presentation ◽

Oral Lichenoid Lesions

Background: Lichen planus is a chronic mucocutaneous inflammatory disease. Oral manifestations are common, and may remain exclusive to the oral mucosa without involvement of the skin or other mucosae. A differential diagnosis includes oral lichenoid drug reactions. Allopurinol, which is the first line hypo-uricemic treatment, is often quoted as being a possible offending drug, though oral reactions have rarely been reported. Case presentation: We describe a 59-year-old male gout patient, successfully treated with allopurinol, who developed acute onset of oral lichenoid lesions, involving bilaterally the buccal mucosa, the tongue and the labial mucosa. Histopathology was consistent with a lichen planus or a drug-induced lichenoid reaction. Improvement of the patient’s condition after withdrawal of allopurinol confirmed the lichenoid nature of the lesion. Remission was complete after a few weeks. Discussion: Although unusual, allopurinol may induce a lichenoid drug reaction. These reactions may mimic clinically and histopathologically idiopathic lichen planus. Improvement or complete regression of the lesions may be attempted to confirm the diagnosis. According to the latest WHO recommendations, these lesions have a potential for malignant transformation.

Download Full-text

Research on Real-Time Multiple Single Garbage Classification Based on Convolutional Neural Network

Mathematical Problems in Engineering ◽

10.1155/2020/5795976 ◽

2020 ◽

Vol 2020 ◽

pp. 1-6

Author(s):

Jian-ye Yuan ◽

Xin-yuan Nan ◽

Cheng-rong Li ◽

Le-le Sun

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Real Time ◽

Environmental Science ◽

Fine Tuning ◽

Classification Model ◽

Classification Models ◽

Data Set ◽

Classification Tasks ◽

Accuracy Rates

Considering that the garbage classification is urgent, a 23-layer convolutional neural network (CNN) model is designed in this paper, with the emphasis on the real-time garbage classification, to solve the low accuracy of garbage classification and recycling and difficulty in manual recycling. Firstly, the depthwise separable convolution was used to reduce the Params of the model. Then, the attention mechanism was used to improve the accuracy of the garbage classification model. Finally, the model fine-tuning method was used to further improve the performance of the garbage classification model. Besides, we compared the model with classic image classification models including AlexNet, VGG16, and ResNet18 and lightweight classification models including MobileNetV2 and SuffleNetV2 and found that the model GAF_dense has a higher accuracy rate, fewer Params, and FLOPs. To further check the performance of the model, we tested the CIFAR-10 data set and found the accuracy rates of the model (GAF_dense) are 0.018 and 0.03 higher than ResNet18 and SufflenetV2, respectively. In the ImageNet data set, the accuracy rates of the model (GAF_dense) are 0.225 and 0.146 higher than Resnet18 and SufflenetV2, respectively. Therefore, the garbage classification model proposed in this paper is suitable for garbage classification and other classification tasks to protect the ecological environment, which can be applied to classification tasks such as environmental science, children’s education, and environmental protection.

Download Full-text

Drug-induced liver injury classification model based on in vitro human transcriptomics and in vivo rat clinical chemistry data

Systems Biomedicine ◽

10.4161/sysb.29400 ◽

2014 ◽

Vol 2 (4) ◽

pp. 63-70 ◽

Cited By ~ 10

Author(s):

Danyel Jennen ◽

Jan Polman ◽

Mark Bessem ◽

Maarten Coonen ◽

Joost van Delft ◽

...

Keyword(s):

Liver Injury ◽

Clinical Chemistry ◽

Classification Model ◽

Drug Induced ◽

Drug Induced Liver Injury ◽

Chemistry Data ◽

Model Based ◽

Injury Classification

Download Full-text

Characterisation of the conformational changes in platelet factor 4 induced by polyanions: towards in vitro prediction of antigenicity

Thrombosis and Haemostasis ◽

10.1160/th13-08-0634 ◽

2014 ◽

Vol 112 (07) ◽

pp. 53-64 ◽

Cited By ~ 42

Author(s):

Sven Brandt ◽

Krystin Krauel ◽

Kay E. Gottschalk ◽

Thomas Renné ◽

Christiane A. Helm ◽

...

Keyword(s):

Conformational Changes ◽

Structural Changes ◽

Cd Spectroscopy ◽

Platelet Factor 4 ◽

Drug Induced ◽

Platelet Factor ◽

Preclinical Drug Development ◽

Varying Length ◽

Endogenous Proteins

SummaryHeparin-induced thrombocytopenia (HIT) is the most frequent drug-induced immune reaction affecting blood cells. Its antigen is formed when the chemokine platelet factor 4 (PF4) complexes with polyanions. By assessing polyanions of varying length and degree of sulfation using immunoassay and circular dichroism (CD)-spectroscopy, we show that PF4 structural changes resulting in antiparallel β-sheet content >30% make PF4/polyanion complexes antigenic. Further, we found that polyphosphates (polyP-55) induce antigenic changes on PF4, whereas fondaparinux does not. We provide a model suggesting that conformational changes exposing antigens on PF4/polyanion complexes occur in the hairpin involving AA 32–38, which form together with C-terminal AA (66–70) of the adjacent PF4 monomer a continuous patch on the PF4 tetramer surface, explaining why only tetrameric PF4 molecules express “HIT antigens”. The correlation of antibody binding in immunoassays with PF4 structural changes provides the intriguing possibility that CD-spectroscopy could become the first antibody-independent, in vitro method to predict potential immunogenicity of drugs. CD-spectroscopy could identify compounds during preclinical drug development that induce PF4 structural changes correlated with antigenicity. The clinical relevance can then be specifically addressed during clinical trials. Whether these findings can be transferred to other endogenous proteins requires further studies.

Download Full-text

MicroRNA Profiling as a Methodology to Diagnose Ménière’s Disease: Potential Application of Machine Learning

Otolaryngology ◽

10.1177/0194599820940649 ◽

2020 ◽

pp. 019459982094064

Author(s):

Matthew Shew ◽

Helena Wichova ◽

Andres Bur ◽

Devin C. Koestler ◽

Madeleine St Peter ◽

...

Keyword(s):

Machine Learning ◽

Hearing Loss ◽

Meniere’S Disease ◽

Menière’S Disease ◽

Classification Model ◽

Meniere's Disease ◽

Ménière’S Disease ◽

Classification Models ◽

Menière's Disease ◽

Ménière's Disease

Objective Diagnosis and treatment of Ménière’s disease remains a significant challenge because of our inability to understand what is occurring on a molecular level. MicroRNA (miRNA) perilymph profiling is a safe methodology and may serve as a “liquid biopsy” equivalent. We used machine learning (ML) to evaluate miRNA expression profiles of various inner ear pathologies to predict diagnosis of Ménière’s disease. Study Design Prospective cohort study. Setting Tertiary academic hospital. Subjects and Methods Perilymph was collected during labyrinthectomy (Ménière’s disease, n = 5), stapedotomy (otosclerosis, n = 5), and cochlear implantation (sensorineural hearing loss [SNHL], n = 9). miRNA was isolated and analyzed with the Affymetrix miRNA 4.0 array. Various ML classification models were evaluated with an 80/20 train/test split and cross-validation. Permutation feature importance was performed to understand miRNAs that were critical to the classification models. Results In terms of miRNA profiles for conductive hearing loss versus Ménière’s, 4 models were able to differentiate and identify the 2 disease classes with 100% accuracy. The top-performing models used the same miRNAs in their decision classification model but with different weighted values. All candidate models for SNHL versus Ménière’s performed significantly worse, with the best models achieving 66% accuracy. Ménière’s models showed unique features distinct from SNHL. Conclusions We can use ML to build Ménière’s-specific prediction models using miRNA profile alone. However, ML models were less accurate in predicting SNHL from Ménière’s, likely from overlap of miRNA biomarkers. The power of this technique is that it identifies biomarkers without knowledge of the pathophysiology, potentially leading to identification of novel biomarkers and diagnostic tests.

Download Full-text

Antibodies causing thrombocytopenia in patients treated with RGD-mimetic platelet inhibitors recognize ligand-specific conformers of αIIb/β3 integrin

Blood ◽

10.1182/blood-2012-01-406322 ◽

2012 ◽

Vol 119 (26) ◽

pp. 6317-6325 ◽

Cited By ~ 27

Author(s):

Daniel W. Bougie ◽

Mark Rasmussen ◽

Jieqing Zhu ◽

Richard H. Aster

Keyword(s):

Binding Sites ◽

Structural Changes ◽

Recognition Site ◽

Platelet Inhibitors ◽

Head Region ◽

Drug Induced ◽

Naturally Occurring ◽

Β3 Integrin ◽

Effect Of Treatment ◽

Arginine Glycine Aspartic Acid

Arginine-glycine-aspartic acid (RGD)–mimetic platelet inhibitors act by occupying the RGD recognition site of αIIb/β3 integrin (GPIIb/IIIa), thereby preventing the activated integrin from reacting with fibrinogen. Thrombocytopenia is a well-known side effect of treatment with this class of drugs and is caused by Abs, often naturally occurring, that recognize αIIb/β3 in a complex with the drug being administered. RGD peptide and RGD-mimetic drugs are known to induce epitopes (ligand-induced binding sites [LIBS]) in αIIb/β3 that are recognized by certain mAbs. It has been speculated, but not shown experimentally, that Abs from patients who develop thrombocytopenia when treated with an RGD-mimetic inhibitor similarly recognize LIBS determinants. We addressed this question by comparing the reactions of patient Abs and LIBS-specific mAbs against αIIb/β3 in a complex with RGD and RGD-mimetic drugs, and by examining the ability of selected non-LIBS mAbs to block binding of patient Abs to the liganded integrin. Findings made provide evidence that the patient Abs recognize subtle, drug-induced structural changes in the integrin head region that are clustered about the RGD recognition site. The target epitopes differ from classic LIBS determinants, however, both in their location and by virtue of being largely drug-specific.

Download Full-text

Visual exploration of classification models for various data types in risk assessment

Information Visualization ◽

10.1177/1473871611433715 ◽

2012 ◽

Vol 11 (3) ◽

pp. 237-251 ◽

Cited By ~ 6

Author(s):

Malgorzata Migut ◽

Marcel Worring

Keyword(s):

Risk Assessment ◽

Visual Analytics ◽

Ordinal Data ◽

Visual Exploration ◽

Classification Model ◽

Classification Models ◽

Data Types ◽

Suggested Approach ◽

Wrong Decision ◽

Data Elements

In risk assessment applications well-informed decisions need to be made based on large amounts of multi-dimensional data. In many domains, not only the risk of a wrong decision, but also of the trade-off between the costs of possible decisions are of utmost importance. In this paper we describe a framework to support the decision-making process, which tightly integrates interactive visual exploration with machine learning. The proposed approach uses a series of interactive 2D visualizations of numerical and ordinal data combined with visualization of classification models. These series of visual elements are linked to the classifier’s performance, which is visualized using an interactive performance curve. This interaction allows the decision-maker to steer the classification model and instantly identify the critical, cost-changing data elements in the various linked visualizations. The critical data elements are represented as images in order to trigger associations related to the knowledge of the expert. In this way the data visualization and classification results are not only linked together, but are also linked back to the classification model. Such a visual analytics framework allows the user to interactively explore the costs of his decisions for different settings of the model and, accordingly, use the most suitable classification model. More informed and reliable decisions result. A case study in the forensic psychiatry domain reveals the usefulness of the suggested approach.

Download Full-text