scholarly journals Advancing the activity cliff concept

F1000Research ◽  
2013 ◽  
Vol 2 ◽  
pp. 199 ◽  
Author(s):  
Ye Hu ◽  
Dagmar Stumpfe ◽  
Jürgen Bajorath
Keyword(s):  
Chemical Modifications ◽  
Large Magnitude ◽  
Activity Data ◽  
General Audience ◽  
Structure Activity ◽  
Activity Cliff ◽  
Sar Analysis ◽  
Small Chemical ◽  
Detailed Picture ◽  
Activity Cliffs

The activity cliff concept has experienced increasing interest in medicinal chemistry and chemoinformatics. Activity cliffs have originally been defined as pairs of structurally similar compounds that are active against the same target but have a large difference in potency. Activity cliffs are relevant for structure-activity relationship (SAR) analysis and compound optimization because small chemical modifications can be deduced from cliffs that result in large-magnitude changes in potency. In addition to studying activity cliffs on the basis of individual compounds series, they can be systematically identified through mining of compound activity data. This commentary aims to provide a concise yet detailed picture of our current understanding of activity cliffs. It is also meant to introduce the further refined activity cliff concept to a general audience in drug development.

scholarly journals Prediction of activity cliffs on the basis of images using convolutional neural networks

2021 ◽  
Author(s):  
Javed Iqbal ◽  
Martin Vogt ◽  
Jürgen Bajorath
Keyword(s):  
Performance Measures ◽  
Image Data ◽  
Structural Features ◽  
High Accuracy ◽  
Black Box ◽  
Structure Activity ◽  
Activity Cliff ◽  
High Level ◽  
Feature Visualization ◽  
Activity Cliffs

AbstractAn activity cliff (AC) is formed by a pair of structurally similar compounds with a large difference in potency. Accordingly, ACs reveal structure–activity relationship (SAR) discontinuity and provide SAR information for compound optimization. Herein, we have investigated the question if ACs could be predicted from image data. Therefore, pairs of structural analogs were extracted from different compound activity classes that formed or did not form ACs. From these compound pairs, consistently formatted images were generated. Image sets were used to train and test convolutional neural network (CNN) models to systematically distinguish between ACs and non-ACs. The CNN models were found to predict ACs with overall high accuracy, as assessed using alternative performance measures, hence establishing proof-of-principle. Moreover, gradient weights from convolutional layers were mapped to test compounds and identified characteristic structural features that contributed to successful predictions. Weight-based feature visualization revealed the ability of CNN models to learn chemistry from images at a high level of resolution and aided in the interpretation of model decisions with intrinsic black box character.

scholarly journals Matched molecular pair-based data sets for computer-aided medicinal chemistry

F1000Research ◽  
2014 ◽  
Vol 3 ◽  
pp. 36 ◽  
Author(s):  
Ye Hu ◽  
Antonio de la Vega de León ◽  
Bijun Zhang ◽  
Jürgen Bajorath
Keyword(s):  
Scientific Community ◽  
Medicinal Chemistry ◽  
Data Sets ◽  
Research Projects ◽  
High Confidence ◽  
Activity Data ◽  
Structural Modifications ◽  
Matched Molecular Pairs ◽  
Structure Activity ◽  
Activity Cliffs

Matched molecular pairs (MMPs) are widely used in medicinal chemistry to study changes in compound properties including biological activity, which are associated with well-defined structural modifications. Herein we describe up-to-date versions of three MMP-based data sets that have originated from in-house research projects. These data sets include activity cliffs, structure-activity relationship (SAR) transfer series, and second generation MMPs based upon retrosynthetic rules. The data sets have in common that they have been derived from compounds included in the latest release of the ChEMBL database for which high-confidence activity data are available. Thus, the activity data associated with MMP-based activity cliffs, SAR transfer series, and retrosynthetic MMPs cover the entire spectrum of current pharmaceutical targets. Our data sets are made freely available to the scientific community.

scholarly journals Advancing the activity cliff concept, part II

F1000Research ◽  
2014 ◽  
Vol 3 ◽  
pp. 75 ◽  
Author(s):  
Dagmar Stumpfe ◽  
Antonio de la Vega de León ◽  
Dilyana Dimova ◽  
Jürgen Bajorath
Keyword(s):  
Medicinal Chemistry ◽  
Current Understanding ◽  
Activity Relationship ◽  
Ligand Efficiency ◽  
Research Activity ◽  
High Interest ◽  
Structure Activity ◽  
Activity Cliff ◽  
Activity Cliffs

We present a follow up contribution to further complement a previous commentary on the activity cliff concept and recent advances in activity cliff research. Activity cliffs have originally been defined as pairs of structurally similar compounds that display a large difference in potency against a given target. For medicinal chemistry, activity cliffs are of high interest because structure-activity relationship (SAR) determinants can often be deduced from them. Herein, we present up-to-date results of systematic analyses of the ligand efficiency and lipophilic efficiency relationships between activity cliff-forming compounds, which further increase their attractiveness for the practice of medicinal chemistry. In addition, we summarize the results of a new analysis of coordinated activity cliffs and clusters they form. Taken together, these findings considerably add to our evaluation and current understanding of the activity cliff concept. The results should be viewed in light of the previous commentary article.

scholarly journals Matched molecular pair-based data sets for computer-aided medicinal chemistry

F1000Research ◽  
2014 ◽  
Vol 3 ◽  
pp. 36 ◽  
Author(s):  
Ye Hu ◽  
Antonio de la Vega de León ◽  
Bijun Zhang ◽  
Jürgen Bajorath
Keyword(s):  
Scientific Community ◽  
Medicinal Chemistry ◽  
Data Sets ◽  
Research Projects ◽  
High Confidence ◽  
Activity Data ◽  
Structural Modifications ◽  
Matched Molecular Pairs ◽  
Structure Activity ◽  
Activity Cliffs

Matched molecular pairs (MMPs) are widely used in medicinal chemistry to study changes in compound properties including biological activity, which are associated with well-defined structural modifications. Herein we describe up-to-date versions of three MMP-based data sets that have originated from in-house research projects. These data sets include activity cliffs, structure-activity relationship (SAR) transfer series, and second generation MMPs based upon retrosynthetic rules. The data sets have in common that they have been derived from compounds included in the ChEMBL database (release 17) for which high-confidence activity data are available. Thus, the activity data associated with MMP-based activity cliffs, SAR transfer series, and retrosynthetic MMPs cover the entire spectrum of current pharmaceutical targets. Our data sets are made freely available to the scientific community.

Structure-activity relations and β-lactamase resistance

1980 ◽  
Vol 289 (1036) ◽  
pp. 197-205 ◽  
Keyword(s):  
Broad Spectrum ◽  
Product Inhibition ◽  
Sulphur Atom ◽  
Chemical Modifications ◽  
Gram Negative ◽  
Structure Activity ◽  
Broad Spectrum Resistance ◽  
Structure Activity Relations ◽  
Minor Influence ◽  
A Minor

β-Lactam antibiotics resistant to β-lactamase degradation can be produced by many chemical modifications, but often at the expense of antibacterial activity. Substitution onto several positions in the molecule produces different and often selective resistance; for instance, heavily sterically hindered acyl groups give staphylococcal P-lactamase resistance to penicillins, and resistance to some enzymes from Gram-negative pathogens to both penicillins and cephalosporins. 6-α- or 7-α-substituents respectively confer a broad spectrum of resistance (e.g. cefoxitin), but changes at positions 2 or 3 have only a minor influence on enzyme susceptibility. Changes in the ring condensed with the β-lactam, such as changing ceph-3-em to ceph-2-em may greatly enhance stability. Small improvements can occur when the nuclear sulphur atom is oxidized, but a much better effect is obtained when it is replaced by another atom such as oxygen, as in clavulanic acid. This compound appears to have broad spectrum resistance which is actually due to susceptibility and subsequent product inhibition.

Workshop 1.6 QSAR and related procedures for prescreening and predicting potential endocrine-active compounds

2004 ◽  
Vol 76 (10) ◽  
pp. 1927-1931
Author(s):  
T. Fujita
Keyword(s):  
In Silico ◽  
Model Building ◽  
Quantitative Structure Activity Relationship ◽  
Quantitative Prediction ◽  
Quantitative Structure ◽  
Activity Data ◽  
Endocrine Activity ◽  
The Past ◽  
Structure Activity ◽  
Computer Aided

This workshop has been organized to cover various quantitative structure-activity relationship (QSAR) and computer aided procedures currently carried out for the prediction of the endocrine activity of unknown compounds. Each of the procedures has own scope as well as limitations. It seems inappropriate to consider that a single quantitative prediction model derived from each of these procedures could solve the entire issue. Because the model building is highly dependent on the data/knowledge about endocrine activity of a large number of existing compounds accumulated to date and the data/knowledge are growing constantly, the model has a destiny to be amended “forever ”as the structure-activity data of newly synthesized compounds are accumulated. The skepticism about in silico and QSAR procedures put forward in the past is likely to be cleared at least to some extent if not entirely by participating in this workshop.

Sign in / Sign up

Export Citation Format

Share Document