Combining selectivity and affinity predictions using an integrated Support Vector Machine (SVM) approach: An alternative tool to discriminate between the human adenosine A2A and A3 receptor pyrazolo-triazolo-pyrimidine antagonists binding sites

Michielan, Lisa; Bolcato, Chiara; Federico, Stephanie; Cacciari, Barbara; Bacilieri, Magdalena; Klotz, Karl‐Norbert; Kachler, Sonja; Pastorin, Giorgia; Cardin, Riccardo; Sperduti, Alessandro; Spalluto, Giampiero; Moro, Stefano

doi:10.1016/j.bmc.2009.05.038

Cited by 25 publications

(44 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[65][66][67][68][69] In fact, the topological and electrostatic complementarities are crucial aspects in the molecular recognition processes and MEP vectors have been investigated on the molecular surface as a particularly useful method for rationalizing the interactions between molecules and molecular recognition processes. [48][49][50] Furthermore, the autocorrelation function transforms the constitution of a molecule into a fixed length representation to overcome the dependence of MEP information on the spatial rotation and translation of the molecule.…”

Section: Toxclass Modelmentioning

confidence: 99%

Support Vector Machine (SVM) as Alternative Tool to Assign Acute Aquatic Toxicity Warning Labels to Chemicals

Michielan¹,

Pireddu²,

Floris³

et al. 2010

Molecular Informatics

Self Cite

View full text Add to dashboard Cite

Quantitative structure-activity relationship (QSAR) analysis has been frequently utilized as a computational tool for the prediction of several eco-toxicological parameters including the acute aquatic toxicity. In the present study, we describe a novel integrated strategy to describe the acute aquatic toxicity through the combination of both toxicokinetic and toxicodynamic behaviors of chemicals. In particular, a robust classification model (TOXclass) has been derived by combining Support Vector Machine (SVM) analysis with three classes of toxicokinetic-like molecular descriptors: the autocorrelation molecular electrostatic potential (autoMEP) vectors, Sterimol topological descriptors and logP(o/w) property values. TOXclass model is able to assign chemicals to different levels of acute aquatic toxicity, providing an appropriate answer to the new regulatory requirements. Moreover, we have extended the above mentioned toxicokinetic-like descriptor set with a more toxicodynamic-like descriptors, as for example HOMO and LUMO energies, to generate a valuable SVM classifier (MOAclass) for the prediction of the mode of action (MOA) of toxic chemicals. As preliminary validation of our approach, the toxicokinetic (TOXclass) and the toxicodynamic (MOAclass) models have been applied in series to inspect both aquatic toxicity hazard and mode of action of 296 chemical substances with unknown or uncertain toxicodynamic information to assess the potential ecological risk and the toxic mechanism.

show abstract

Section: Toxclass Modelmentioning

confidence: 99%

Support Vector Machine (SVM) as Alternative Tool to Assign Acute Aquatic Toxicity Warning Labels to Chemicals

Michielan¹,

Pireddu²,

Floris³

et al. 2010

Molecular Informatics

Self Cite

View full text Add to dashboard Cite

show abstract

“…introduced a multi-label classification approach, the so-called cross-training with SVM (ct-SVM), to derive compound potency profiles against human AR subtypes and to predict the selectivity16. They further applied SVM classification and regression in combination in predicting the selectivity profiles of adenosine A 2A and A 3 antagonists and their binding affinities21. After leave-one-out (LOO), 10-fold and 5-fold cross-validation process, they achieved an over-all prediction accuracy 78.4% for the test set, confirmed the statistical reliability of this model21.…”

mentioning

confidence: 99%

“…They further applied SVM classification and regression in combination in predicting the selectivity profiles of adenosine A 2A and A 3 antagonists and their binding affinities21. After leave-one-out (LOO), 10-fold and 5-fold cross-validation process, they achieved an over-all prediction accuracy 78.4% for the test set, confirmed the statistical reliability of this model21. Two regression models for A 2A and A 3 antagonistic activity prediction yielded correlation coefficients 0.78 and 0.85, respectively, after LOO cross-validation2122.…”

mentioning

confidence: 99%

Predicting Subtype Selectivity for Adenosine Receptor Ligands with Three-Dimensional Biologically Relevant Spectrum (BRS-3D)

Kuang

et al. 2016

Sci Rep

View full text Add to dashboard Cite

Adenosine receptors (ARs) are potential therapeutic targets for Parkinson’s disease, diabetes, pain, stroke and cancers. Prediction of subtype selectivity is therefore important from both therapeutic and mechanistic perspectives. In this paper, we introduced a shape similarity profile as molecular descriptor, namely three-dimensional biologically relevant spectrum (BRS-3D), for AR selectivity prediction. Pairwise regression and discrimination models were built with the support vector machine methods. The average determination coefficient (r2) of the regression models was 0.664 (for test sets). The 2B-3 (A2B vs A3) model performed best with q2 = 0.769 for training sets (10-fold cross-validation), and r2 = 0.766, RMSE = 0.828 for test sets. The models’ robustness and stability were validated with 100 times resampling and 500 times Y-randomization. We compared the performance of BRS-3D with 3D descriptors calculated by MOE. BRS-3D performed as good as, or better than, MOE 3D descriptors. The performances of the discrimination models were also encouraging, with average accuracy (ACC) 0.912 and MCC 0.792 (test set). The 2A-3 (A2A vs A3) selectivity discrimination model (ACC = 0.882 and MCC = 0.715 for test set) outperformed an earlier reported one (ACC = 0.784). These results demonstrated that, through multiple conformation encoding, BRS-3D can be used as an effective molecular descriptor for AR subtype selectivity prediction.

show abstract

“…This gives the false impression that a specific ligand/target system has been measured several times even though it could be just been measured once and then cited a couple of times. For example compound CHEMBL349240 has a K i value of 0.21 nM for homo sapiens adenosine A3 receptor (Target ID CHEMBL256) recorded from Baraldi et al, [50] Moro et al, [51] Michielan et al [52] and Cheong et al [53] However, the three last articles [51,52,53] all cite the value reported in publication corresponding to Baraldi et al [50] As a rule of thumb, citations of previously published values can be identified and removed by grouping measurements of the same target/ligand system from different publications with identical activity and then taking the …”

Section: Redundancymentioning

confidence: 99%

Quality Issues with Public Domain Chemogenomics Data

Kalliokoski

Krämer

Vulpetti

2013

Molecular Informatics

View full text Add to dashboard Cite

The key concept in chemogenomics is the similarity principle that states that similar ligands should bind similar targets. Chemogenomic analysis requires large amounts of data and both powerful computational algorithms and computers. Data used for chemogenomics analysis can either be compiled from open sources, or they can be produced in-house as is often done in the pharmaceutical industry. The chemogenomic modeller often has to resort to mixing activity values from different laboratories and even assay types to facilitate chemogenomic analysis. The amount of chemogenomics data available in the public domain has dramatically increased in recent years, allowing fully traceable analysis on a continuously increasing scale. However, some warning flags about the data quality have been raised and because the primary data determine the accuracy of chemogenomic analysis, the quality of the data is one of the key questions in chemogenomics. This mini-review discusses some of the most common issues with public domain biological data related to chemogenomic analysis. The errors in data can originate from problems with the experiments themselves and their interpretation, or from more mundane issues such as data extraction and annotation. These issues are not unique for a certain database but are shared by all the public domain databases and can plague commercial and in-house bioactivity databases as well.

show abstract

Combining selectivity and affinity predictions using an integrated Support Vector Machine (SVM) approach: An alternative tool to discriminate between the human adenosine A2A and A3 receptor pyrazolo-triazolo-pyrimidine antagonists binding sites

Cited by 25 publications

References 45 publications

Support Vector Machine (SVM) as Alternative Tool to Assign Acute Aquatic Toxicity Warning Labels to Chemicals

Support Vector Machine (SVM) as Alternative Tool to Assign Acute Aquatic Toxicity Warning Labels to Chemicals

Predicting Subtype Selectivity for Adenosine Receptor Ligands with Three-Dimensional Biologically Relevant Spectrum (BRS-3D)

Quality Issues with Public Domain Chemogenomics Data

Contact Info

Product

Resources

About