Lead Optimization Using Matched Molecular Pairs: Inclusion of Contextual Information for Enhanced Prediction of hERG Inhibition, Solubility, and Lipophilicity

Papadatos, George; Alkarouri, M.; Gillet, Valerie J.; Willett, Peter; Kadirkamanathan, Visakan; Luscombe, Christopher N.; Bravi, Gianpaolo; Richmond, Nicola J.; Pickett, Stephen D.; Hussain, Jameed; Pritchard, John B.; Cooper, Anthony W. J.; Macdonald, Simon J. F.

doi:10.1021/ci100258p

Cited by 121 publications

(147 citation statements)

References 32 publications

(64 reference statements)

Supporting

Mentioning

147

Contrasting

Order By: Relevance

“…To a certain extent, proposed methodology could be considered as somewhat similar to matched molecular pairs approach (MMPA) [47][48][49] in application to QSAR field. The difference between the property of two related structures, e.g., A-B and A-C, containing the common fragment A is explained by the difference in the structure of fragments B and C. To estimate the influence of B to C transformation, in MMPA one can calculate the difference between observed property values for compounds A-B and A-C or between predicted property values by corresponding QSAR models.…”

Section: Universal Approach For Structural Interpretation Of Qsar Modelsmentioning

confidence: 99%

Universal Approach for Structural Interpretation of QSAR/QSPR Models

Polishchuk

Кузьмин

Artemenko

et al. 2013

Molecular Informatics

View full text Add to dashboard Cite

In this paper we offer a novel approach for the structural interpretation of QSAR models. The major advantage of our developed methodology is its universality, i.e., it can be applied to any QSAR/QSPR model irrespective of chemical descriptors and machine learning methods applied. This universality was achieved by using only the information obtained from substructures of the compounds of interest to interpret model outcomes. Reliability of the offered approach was confirmed by the results of three case studies, including end-points of different types (continuous and binary classification) and nature (solubility, mutagenicity, and inhibition of Transglutaminase 2), various fragment and whole-molecule descriptors (Simplex and Dragon), and multiple modeling techniques (partial least squares, random forest, and support vector machines). We compared the global contributions of molecular fragments obtained using our methodology with known SAR rules derived experimentally. In all cases high concordance between our interpretation and results published by others was observed. Although the proposed interpretation approach could be easily extended to any type of descriptors, we would recommend using Simplex descriptors to achieve a larger variety of investigated molecular fragments. The developed approach is a good tool for interpretation of such "black box" models like random forest, neural networks, etc. Analysis of fragment global contributions and their deviation across a dataset could be useful for the identification of key fragments and structural alerts. This information could be helpful to maximize the positive influence of structural surroundings on the given fragment and to decrease the negative effects.

show abstract

Section: Universal Approach For Structural Interpretation Of Qsar Modelsmentioning

confidence: 99%

Universal Approach for Structural Interpretation of QSAR/QSPR Models

Polishchuk

Кузьмин

Artemenko

et al. 2013

Molecular Informatics

View full text Add to dashboard Cite

show abstract

“…Along these lines, matched molecular pairs have been analysed for the effect against various antitargets, such as CYPs or hERG. [18,21] Generally, a stronger effect was observed for those substituents which have a large influence on lipophilicity (logD). [21] Both for progressive and conservative substituent changes, a significant number of matched molecular pairs without significant effects on the antitarget response has been observed.…”

Section: Discussionmentioning

confidence: 99%

“…Some efficient algorithms for computing MMPs [15,16] and extracting trends from large databases are reported for different molecular properties such as primary activity, liver microsomal stability or other ADMET properties . [14,[17][18][19][20][21][22] We use an in-house implementation based on the algorithm described by Hussain and Rea. [16] Relevant MMPs are further filtered by the substituent size, i.e.…”

Section: Conceptmentioning

confidence: 99%

Identification and Application of Antitarget Activity Hotspots to Guide Compound Optimization

Heßler

Matter

Schmidt

et al. 2011

Molecular Informatics

View full text Add to dashboard Cite

The optimization of a lead structure to a development candidate often requires removal of undesirable antitarget activities. To this end, we have developed an approach to extract antitarget activity hotspots from larger databases and to transfer this knowledge onto novel chemical series. These antitarget activity hotspots will be captured as pairs of informative molecules, which are chemically closely related, but differ significantly in biological activity. We illustrate the application of antitarget activity hotspots as informative compound pairs for the optimization of side effects in lead structures for relevant antitargets in pharmaceutical research. The use for prospective design requires establishing a structural link between known antitarget hotspot pairs and a new lead structure: we employ 3D-based similarity comparison for this task. The entire workflow serves as idea generator in early optimization. The feasibility of this approach is demonstrated in several optimization problems related to hERG inhibition, and CYP3A4 inhibition. Several structural examples demonstrate the ability of the 3D-shape searching to identify related scaffolds and the usefulness of the antitarget hotspot information to guide optimization by modulating the undesirable antitarget activity. Such a concept based on the analysis of local similarities and the transfer to 3D-related series is especially promising in those cases, where the construction of antitarget QSAR models fails to detect local SAR trends for guiding the next optimization cycle.

show abstract

“…However, we have also made other contributions, e.g., in the application of chemoinformatics techniques to the representation and searching of biological macromolecules such as protein and RNA structures, [71][72][73][74][75] in the analysis of matched molecular pairs [76] and in charting the historical development of chemoinformatics and of its associated literature. [77][78][79][80] We have also sought to influence the development of the field by means of conferences and educational programmes.…”

Section: Other Contributionsmentioning

confidence: 99%