Combining Multi-Dimensional Molecular Fingerprints to Predict hERG Cardiotoxicity of Compounds

At present, drug toxicity has become a critical problem with heavy medical and economic burdens. acLQTS (acquired Long QT Syndrome) is acquired cardiac ion channel disease caused by drugs blocking the hERG channel. Therefore, it is necessary to avoid cardiotoxicity in the drug design and computer models have been widely used to fix this plight. In this study, we present a molecular fingerprint based on the molecular dynamic simulation and uses it combined with other molecular fingerprints (multi-dimensional molecular fingerprints) to predict hERG cardiotoxicity of compounds. 203 compounds with hERG inhibitory activity (pIC50) were retrieved from a previous study and predicting models were established using four machine learning algorithms based on the single and multi-dimensional molecular fingerprints. Results showed that MDFP has the potential to be an alternative to traditional molecular fingerprints and the combination of MDFP and traditional molecular fingerprints can achieve higher prediction accuracy. Meanwhile, the accuracy of the best model, which was generated by consensus of four algorithms with multi-dimensional molecular fingerprints, was 0.694 (RMSE) in the test dataset. Besides, the number of hydrogen bonds from MDFP has been determined as a critical factor in the predicting models, followed by rgyr and sasa. Our findings provide a new sight of MDFP and multi-dimensional molecular fingerprints in building models of hERG cardiotoxicity prediction.

Download Full-text

Abstract 5316: hERG 1b as a Potential Target for Inherited and Acquired Long QT Syndrome

Circulation ◽

10.1161/circ.118.suppl_18.s_525-c ◽

2008 ◽

Vol 118 (suppl_18) ◽

Author(s):

Gail A Robertson ◽

Harinath Sale ◽

David Tester ◽

Thomas J O’Hara ◽

Pallavi Phartiyal ◽

...

Keyword(s):

Action Potential ◽

Long Qt Syndrome ◽

Time Course ◽

Drug Sensitivity ◽

Long Qt ◽

Hek 293 ◽

Hek 293 Cells ◽

Acquired Long Qt Syndrome ◽

293 Cells ◽

Qt Syndrome

Cardiac I Kr is a critical repolarizing current in the heart and a target for inherited and acquired long QT syndrome. Biochemical studies show that native I Kr channels are heteromers composed of both hERG 1a and 1b subunits, yet our current understanding of I Kr functional properties derives primarily from studies of homo-oligomers of the original hERG 1a isolate. The hERG 1a and 1b subunits are identical except at the amino (NH2) terminus, which in hERG 1b is much shorter and has a unique primary sequence. We compared the biophysical properties of currents produced by hERG 1a and 1a/1b channels expressed in HEK-293 cells at near-physiological temperatures. We found that heteromeric hERG 1a/1b currents are much larger than hERG 1a currents and conduct 80% more charge during an action potential. This surprising difference corresponds to a two-fold increase in the apparent rates of activation and recovery from inactivation, which reduces rectification and facilitates current rebound during repolarization. Kinetic modeling shows these gating differences account quantitatively for the differences in current amplitude between the two channel types. Depending on the action potential model used, loss of 1b predicts an increase in action potential duration of 27 ms (7%) or 41 ms (17%), respectively. Drug sensitivity was also different. Compared to homomeric 1a channels, heteromeric 1a/1b channels were inhibited by E-4031 with a slower time course and a corresponding four-fold positive shift in the IC 50 . Differences in current kinetics and drug sensitivity were modeled by “NH2 mode” gating with conformational states bound by the amino terminus in hERG 1a homomers but not 1a/1b heteromers. The importance of hERG 1b in vivo is supported by the identification of a 1b-specific A8V missense mutation in 1/269 unrelated genotype-negative LQTS patients and absent in 400 control alleles. Mutant 1bA8V expressed alone or with hERG 1a in HEK-293 cells nearly eliminated 1b protein. Thus, mutations specifically disrupting hERG 1b function are expected to reduce cardiac I Kr , prolong QT interval and enhance drug sensitivity, thus representing a potential mechanism underlying inherited or acquired LQTS.

Download Full-text

Multimodal Sensor Data Fusion for Activity Recognition Using Filtered Classifier

Proceedings ◽

10.3390/proceedings2191262 ◽

2018 ◽

Vol 2 (19) ◽

pp. 1262 ◽

Cited By ~ 4

Author(s):

Muhammad Razzaq ◽

Ian Cleland ◽

Chris Nugent ◽

Sungyoung Lee

Keyword(s):

Activity Recognition ◽

Confusion Matrix ◽

Machine Learning Algorithms ◽

Training Data ◽

Sensor Data ◽

Test Dataset ◽

Sensory Data ◽

Multimodal Sensors ◽

Imbalanced Class Distribution ◽

Single Modality

Activity recognition (AR) is a subtask in pervasive computing and context-aware systems, which presents the physical state of human in real-time. These systems offer a new dimension to the widely spread applications by fusing recognized activities obtained from the raw sensory data generated by the obtrusive as well as unobtrusive revolutionary digital technologies. In recent years, an exponential growth has been observed for AR technologies and much literature exists focusing on applying machine learning algorithms on obtrusive single modality sensor devices. However, University of Jaén Ambient Intelligence (UJAmI), a Smart Lab in Spain has initiated a 1st UCAmI Cup challenge by sharing aforementioned varieties of the sensory data in order to recognize the human activities in the smart environment. This paper presents the fusion, both at the feature level and decision level for multimodal sensors by preprocessing and predicting the activities within the context of training and test datasets. Though it achieves 94% accuracy for training data and 47% accuracy for test data. However, this study further evaluates post-confusion matrix also and draws a conclusion for various discrepancies such as imbalanced class distribution within the training and test dataset. Additionally, this study also highlights challenges associated with the datasets for which, could improve further analysis.

Download Full-text

Pro- and antiarrhythmic effects of fast cardiac pacing in a canine model of acquired long QT syndrome

Naunyn-Schmiedeberg s Archives of Pharmacology ◽

10.1007/s00210-004-0874-0 ◽

2004 ◽

Vol 369 (4) ◽

pp. 447-454 ◽

Cited By ~ 3

Author(s):

Alexander Bauer ◽

J. Kevin Donahue ◽

Frederik Voss ◽

Ruediger Becker ◽

Patricia Kraft ◽

...

Keyword(s):

Long Qt Syndrome ◽

Cardiac Pacing ◽

Canine Model ◽

Long Qt ◽

Acquired Long Qt Syndrome ◽

Qt Syndrome ◽

Antiarrhythmic Effects

Download Full-text

Prolonged QTc: "Mind the Gap"

Bangladesh Critical Care Journal ◽

10.3329/bccj.v2i1.19970 ◽

2014 ◽

Vol 2 (1) ◽

pp. 44-45

Author(s):

Ahmad Mursel Anam ◽

Raihan Rabbani ◽

Farzana Shumy ◽

M Mufizul Islam Polash ◽

M Motiul Islam ◽

...

Keyword(s):

Cardiac Arrest ◽

Long Qt Syndrome ◽

Qt Interval ◽

Torsades De Pointes ◽

Junior Doctors ◽

Long Qt ◽

Acquired Long Qt Syndrome ◽

Prolonged Qt Interval ◽

Prolonged Qt ◽

Qt Syndrome

We report a case of drug induced torsades de pointes, following acquired long QT syndrome. The patient got admitted for shock with acute abdomen. The initial prolonged QT-interval was missed, and a torsadogenic drug was introduced post-operatively. Patient developed torsades de pointes followed by cardiac arrest. She was managed well and discharged without complications. The clinical manifestations of long QT syndromes, syncope or cardiac arrest, result from torsades de pointes. As syncope or cardiac arrest have more common differential diagnoses, even the symptomatic long QT syndrome are commonly missed or misdiagnosed. In acquired long QT syndrome with no prior suggestive feature, it is not impossible to miss the prolonged QT-interval on the ECG tracing. We share our experience so that the clinicians, especially the junior doctors, will be more alert on checking the QT-interval even in asymptomatic patients. DOI: http://dx.doi.org/10.3329/bccj.v2i1.19970 Bangladesh Crit Care J March 2014; 2 (1): 44-45

Download Full-text

Fragmented QRS: The new high-risk kid on the block in acquired long QT syndrome

Heart Rhythm ◽

10.1016/j.hrthm.2010.09.019 ◽

2010 ◽

Vol 7 (12) ◽

pp. 1815-1816 ◽

Cited By ~ 3

Author(s):

Arthur J. Moss

Keyword(s):

High Risk ◽

Long Qt Syndrome ◽

Long Qt ◽

Fragmented Qrs ◽

Acquired Long Qt Syndrome ◽

Qt Syndrome

Download Full-text

Acquired long QT syndrome and torsade de pointes

Pacing and Clinical Electrophysiology ◽

10.1111/pace.13296 ◽

2018 ◽

Vol 41 (4) ◽

pp. 414-421 ◽

Cited By ~ 15

Author(s):

Nabil El-Sherif ◽

Gioia Turitto ◽

Mohamed Boutjdir

Keyword(s):

Long Qt Syndrome ◽

Torsade De Pointes ◽

Long Qt ◽

Acquired Long Qt Syndrome ◽

Qt Syndrome

Download Full-text

Dynamics of Acquired Long QT Syndrome

Dynamic Electrocardiography ◽

10.1002/9780470987483.ch40 ◽

2007 ◽

pp. 406-416

Author(s):

Elijah R. Behr ◽

A. John Camm

Keyword(s):

Long Qt Syndrome ◽

Long Qt ◽

Acquired Long Qt Syndrome ◽

Qt Syndrome

Download Full-text

Consensus rank orderings of molecular fingerprints illustrate the most genuine similarities between marketed drugs and small endogenous human metabolites, but highlight exogenous natural products as the most important ‘natural’ drug transporter substrates

ADMET & DMPK ◽

10.5599/admet.5.2.376 ◽

2017 ◽

Vol 5 (2) ◽

pp. 85 ◽

Cited By ~ 23

Author(s):

Steve O'Hagan ◽

Douglas Bruce Kell

Keyword(s):

Natural Products ◽

Natural Product ◽

Rank Order ◽

Great Majority ◽

Structural Similarity ◽

Molecular Fingerprint ◽

Molecular Fingerprints ◽

Small Molecule Drugs ◽

Tanimoto Similarity ◽

Drug Scaffolds

We compare several molecular fingerprint encodings for marketed, small molecule drugs, and assess how their rank order varies with the fingerprint in terms of the Tanimoto similarity to the most similar endogenous human metabolite as taken from Recon2. For the great majority of drugs, the rank order varies very greatly depending on the encoding used, and also somewhat when the Tanimoto similarity (TS) is replaced by the Tversky similarity. However, for a subset of such drugs, amounting to some 10 % of the set and a Tanimoto similarity of ~0.8 or greater, the similarity coefficient is relatively robust to the encoding used. This leads to a metric that, while arbitrary, suggests that a Tanimoto similarity of 0.75-0.8 or greater genuinely does imply a considerable structural similarity of two molecules in the drug-endogenite space. Although comparatively few (<10 % of) marketed drugs are, in this sense, robustly similar to an endogenite, there is often at least one encoding with which they are genuinely similar (e.g. TS > 0.75). This is referred to as the Take Your Pick Improved Cheminformatic Analytical Likeness or TYPICAL encoding, and on this basis some 66 % of drugs are within a TS of 0.75 to an endogenite.We next explicitly recognise that natural evolution will have selected for the ability to transport dietary substances, including plant, animal and microbial ‘secondary’ metabolites, that are of benefit to the host. These should also be explored in terms of their closeness to marketed drugs. We thus compared the TS of marketed drugs with the contents of various databases of natural products. When this is done, we find that some 80 % of marketed drugs are within a TS of 0.7 to a natural product, even using just the MACCS encoding. For patterned and TYPICAL encodings, 80 % and 98 % of drugs are within a TS of 0.8 to (an endogenite or) an exogenous natural product. This implies strongly that it is these exogeneous (dietary and medicinal) natural products that are more to be seen as the ‘natural’ substrates of drug transporters (as is recognised, for instance, for the solute carrier SLC22A4 and ergothioneine). This novel analysis casts an entirely different light on the kinds of natural molecules that are to be seen as most like marketed drugs, and hence potential transporter substrates, and further suggests that a renewed exploitation of natural products as drug scaffolds would be amply rewarded.

Download Full-text