lnu.sePublications
Change search
Link to record
Permanent link

Direct link
BETA
Publications (5 of 5) Show all publications
Chavan, S., Abdelaziz, A., Wiklander, J. G. & Nicholls, I. A. (2016). A k-nearest neighbor classification of hERG K+ channel blockers. Journal of Computer-Aided Molecular Design, 30(3), 229-236
Open this publication in new window or tab >>A k-nearest neighbor classification of hERG K+ channel blockers
2016 (English)In: Journal of Computer-Aided Molecular Design, ISSN 0920-654X, E-ISSN 1573-4951, Vol. 30, no 3, p. 229-236Article in journal (Refereed) Published
Abstract [en]

A series of 172 molecular structures that block the hERG K+ channel were used to develop a classification model where, initially, eight types of PaDEL fingerprints were used for k-nearest neighbor model development. A consensus model constructed using Extended-CDK, PubChem and Substructure count fingerprint-based models was found to be a robust predictor of hERG activity. This consensus model demonstrated sensitivity and specificity values of 0.78 and 0.61 for the internal dataset compounds and 0.63 and 0.54 for the external (PubChem) dataset compounds, respectively. This model has identified the highest number of true positives (i.e. 140) from the PubChem dataset so far, as compared to other published models, and can potentially serve as a basis for the prediction of hERG active compounds. Validating this model against FDA-withdrawn substances indicated that it may even be useful for differentiating between mechanisms underlying QT prolongation.

Keywords
Classification model, hERG blockers, Ikr, KCNH2, k-nearest neighbor (k-NN), Toxicity
National Category
Bioinformatics (Computational Biology)
Research subject
Chemistry, Medical Chemistry
Identifiers
urn:nbn:se:lnu:diva-52222 (URN)10.1007/s10822-016-9898-z (DOI)000373117200004 ()26860111 (PubMedID)2-s2.0-84957695003 (Scopus ID)
Available from: 2016-04-25 Created: 2016-04-25 Last updated: 2020-03-20Bibliographically approved
Chavan, S. (2016). Towards new computational tools for predicting toxicity. (Doctoral dissertation). Växjö: Linnaeus University Press
Open this publication in new window or tab >>Towards new computational tools for predicting toxicity
2016 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

The toxicological screening of the numerous chemicals that we are exposed to requires significant cost and the use of animals. Accordingly, more efficient methods for the evaluation of toxicity are required to reduce cost and the number of animals used. Computational strategies have the potential to reduce both the cost and the use of animal testing in toxicity screening. The ultimate goal of this thesis is to develop computational models for the prediction of toxicological endpoints that can serve as an alternative to animal testing. In Paper I, an attempt was made to construct a global quantitative structure-activity relationship (QSAR)model for the acute toxicity endpoint (LD50 values) using the Munro database that represents a broad chemical landscape. Such a model could be used for acute toxicity screening of chemicals of diverse structures. Paper II focuses on the use of acute toxicity data to support the prediction of chronic toxicity. The results of this study suggest that for related chemicals having acute toxicities within a similar range, their lowest observed effect levels (LOELs) can be used in read-across strategies to fill gaps in chronic toxicity data. In Paper III a k-nearest neighbor (k-NN) classification model was developed to predict human ether-a-go-go related gene (hERG)-derived toxicity. The results suggest that the model has potential for use in identifying compounds with hERG-liabilities, e.g. in drug development.

Place, publisher, year, edition, pages
Växjö: Linnaeus University Press, 2016. p. 68
Series
Linnaeus University Dissertations ; 243/2016
Keywords
Acute toxicity, chronic toxicity, hERG, k-NN, LD50, LOEL, Munro database, QSAR, read-across, toxicity
National Category
Bioinformatics and Systems Biology
Research subject
Chemistry, Medical Chemistry
Identifiers
urn:nbn:se:lnu:diva-51336 (URN)978-91-88357-04-5 (ISBN)
Public defence
2016-04-15, N2007, Norra vägen 49, Kalmar, 09:30 (English)
Opponent
Supervisors
Available from: 2016-03-29 Created: 2016-03-24 Last updated: 2016-11-22Bibliographically approved
Chavan, S., Friedman, R. & Nicholls, I. A. (2015). Acute Toxicity-Supported Chronic Toxicity Prediction: A k-Nearest Neighbor Coupled Read-Across Strategy. International Journal of Molecular Sciences, 16(5), 11659-11677
Open this publication in new window or tab >>Acute Toxicity-Supported Chronic Toxicity Prediction: A k-Nearest Neighbor Coupled Read-Across Strategy
2015 (English)In: International Journal of Molecular Sciences, ISSN 1422-0067, E-ISSN 1422-0067, Vol. 16, no 5, p. 11659-11677Article in journal (Refereed) Published
Abstract [en]

k-nearest neighbor (k-NN) classification model was constructed for 118 RDT NEDO (Repeated Dose Toxicity New Energy and industrial technology Development Organization; currently known as the Hazard Evaluation Support System (HESS)) database chemicals, employing two acute toxicity (LD50)-based classes as a response and using a series of eight PaDEL software-derived fingerprints as predictor variables. A model developed using Estate type fingerprints correctly predicted the LD50 classes for 70 of 94 training set chemicals and 19 of 24 test set chemicals. An individual category was formed for each of the chemicals by extracting its corresponding k-analogs that were identified by k-NN classification. These categories were used to perform the read-across study for prediction of the chronic toxicity, i.e., Lowest Observed Effect Levels (LOEL). We have successfully predicted the LOELs of 54 of 70 training set chemicals (77%) and 14 of 19 test set chemicals (74%) to within an order of magnitude from their experimental LOEL values. Given the success thus far, we conclude that if the k-NN model predicts LD50classes correctly for a certain chemical, then the k-analogs of such a chemical can be successfully used for data gap filling for the LOEL. This model should support the in silico prediction of repeated dose toxicity.

Keywords
k-nearest neighbor;classification model; Estate fingerprint;LD50; LOEL; read-across; category formation
National Category
Analytical Chemistry
Research subject
Chemistry, Organic Chemistry
Identifiers
urn:nbn:se:lnu:diva-45017 (URN)10.3390/ijms160511659 (DOI)000356241400146 ()26006240 (PubMedID)2-s2.0-84930643618 (Scopus ID)
Funder
EU, FP7, Seventh Framework Programme, 238701
Available from: 2015-06-23 Created: 2015-06-23 Last updated: 2018-11-02Bibliographically approved
Nicholls, I. A., Chavan, S., Golker, K., Karlsson, B. C. G., Olsson, G. D., Rosengren, A. M., . . . Wiklander, J. G. (2015). Theoretical and Computational Strategies for the Study of the Molecular Imprinting Process and Polymer Performance. In: Mattiasson, B. & Ye, L. (Ed.), Molecularly Imprinted Polymers in Biotechnology: (pp. 25-50). Berlin: Springer
Open this publication in new window or tab >>Theoretical and Computational Strategies for the Study of the Molecular Imprinting Process and Polymer Performance
Show others...
2015 (English)In: Molecularly Imprinted Polymers in Biotechnology / [ed] Mattiasson, B. & Ye, L., Berlin: Springer, 2015, p. 25-50Chapter in book (Refereed)
Abstract [en]

The development of in silico strategies for the study of the molecular imprinting process and the properties of molecularly imprinted materials has been driven by a growing awareness of the inherent complexity of these systems and even by an increased awareness of the potential of these materials for use in a range of application areas. Here we highlight the development of theoretical and computational strategies that are contributing to an improved understanding of the mechanisms underlying molecularly imprinted material synthesis and performance, and even their rational design.

Place, publisher, year, edition, pages
Berlin: Springer, 2015
Series
Advances in Biochemical Engineering-Biotechnology, ISSN 0724-6145 ; 150
National Category
Polymer Technologies
Research subject
Chemistry, Organic Chemistry
Identifiers
urn:nbn:se:lnu:diva-42600 (URN)10.1007/10_2015_318 (DOI)000365222300003 ()2-s2.0-84938411248 (Scopus ID)978-3-319-20729-2 (ISBN)978-3-319-20728-5 (ISBN)
Available from: 2015-04-15 Created: 2015-04-15 Last updated: 2020-03-20Bibliographically approved
Chavan, S., Nicholls, I. A., Karlsson, B. C. G., Rosengren, A. M., Ballabio, D., Consonni, V. & Todeschini, R. (2014). Towards Global QSAR Model Building for Acute Toxicity: Munro Database Case Study. International Journal of Molecular Sciences, 15(10), 18162-18174
Open this publication in new window or tab >>Towards Global QSAR Model Building for Acute Toxicity: Munro Database Case Study
Show others...
2014 (English)In: International Journal of Molecular Sciences, ISSN 1422-0067, E-ISSN 1422-0067, Vol. 15, no 10, p. 18162-18174Article in journal (Refereed) Published
Abstract [en]

A series of 436 Munro database chemicals were studied with respect to their corresponding experimental LD50 values to investigate the possibility of establishing a global QSAR model for acute toxicity. Dragon molecular descriptors were used for the QSAR model development and genetic algorithms were used to select descriptors better correlated with toxicity data. Toxic values were discretized in a qualitative class on the basis of the Globally Harmonized Scheme: the 436 chemicals were divided into 3 classes based on their experimental LD50 values: highly toxic, intermediate toxic and low to non-toxic. The k-nearest neighbor (k-NN) classification method was calibrated on 25 molecular descriptors and gave a non-error rate (NER) equal to 0.66 and 0.57 for internal and external prediction sets, respectively. Even if the classification performances are not optimal, the subsequent analysis of the selected descriptors and their relationship with toxicity levels constitute a step towards the development of a global QSAR model for acute toxicity.

Keywords
k-nearest neighbor (k-NN), Munro database, genetic algorithm (GA), acute toxicity (LD50)
National Category
Biochemistry and Molecular Biology
Research subject
Chemistry, Organic Chemistry
Identifiers
urn:nbn:se:lnu:diva-39262 (URN)10.3390/ijms151018162 (DOI)000344457200032 ()2-s2.0-84907834013 (Scopus ID)
Available from: 2015-01-20 Created: 2015-01-20 Last updated: 2018-11-02Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0003-4158-4148

Search in DiVA

Show all publications