Performance of (consensus) kNN QSAR for predicting estrogenic activity in a large diverse set of organic compounds

A novel method (in the context of quantitative structure–activity relationship (QSAR)) based on the k nearest neighbour (kNN) principle, has recently been introduced for the derivation of predictive structure–activity relationships. Its performance has been tested for estimating the estrogen binding affinity of a diverse set of 142 organic molecules. Highly predictive models have been obtained. Moreover, it has been demonstrated that consensus-type kNN QSAR models, derived from the arithmetic mean of individual QSAR models were statistically robust and provided more accurate predictions than the great majority of the individual QSAR models. Finally, the consensus QSAR method was tested with 3D QSAR and log?P data from a widely used steroid benchmark data set.     

Holographic QSAR of environmental estrogens

Environmental endocrine disrupting chemicals(EDCs) or environmental estrogens pose severe healthhazard to wildlife and humans. They are believed to bethe main cause of the weakening activity and secretionof sex hormone, sperm declination, abnormal repro-d…     

Performance of (consensus) kNN QSAR for predicting estrogenic activity in a large diverse set of organic compounds

A novel method (in the context of quantitative structure-activity relationship (QSAR)) based on the k nearest neighbour (kNN) principle, has recently been introduced for the derivation of predictive structure-activity relationships. Its performance has been tested for estimating the estrogen binding affinity of a diverse set of 142 organic molecules. Highly predictive models have been obtained. Moreover, it has been demonstrated that consensus-type kNN QSAR models, derived from the arithmetic mean of individual QSAR models were statistically robust and provided more accurate predictions than the great majority of the individual QSAR models. Finally, the consensus QSAR method was tested with 3D QSAR and log P data from a widely used steroid benchmark data set.     

Effects-based chemical category approach for prioritization of low affinity estrogenic chemicals

Regulatory agencies are charged with addressing the endocrine disrupting potential of large numbers of chemicals for which there is often little or no data on which to make decisions. Prioritizing the chemicals of greatest concern for further screening for potential hazard to humans and wildlife is an initial step in the process. This paper presents the collection of in vitro data using assays optimized to detect low affinity estrogen receptor (ER) binding chemicals and the use of that data to build effects-based chemical categories following QSAR approaches and principles pioneered by Gilman Veith and colleagues for application to environmental regulatory challenges. Effects-based chemical categories were built using these QSAR principles focused on the types of chemicals in the specific regulatory domain of concern, i.e. non-steroidal industrial chemicals, and based upon a mechanistic hypothesis of how these non-steroidal chemicals of seemingly dissimilar structure to 17ß-estradiol (E2) could interact with the ER via two distinct binding types. Chemicals were also tested to solubility thereby minimizing false negatives and providing confidence in determination of chemicals as inactive. The high-quality data collected in this manner were used to build an ER expert system for chemical prioritization described in a companion article in this journal.     

An integrated "4-phase" approach for setting endocrine disruption screening priorities--phase I and II predictions of estrogen receptor binding affinity

Recent legislation mandates the US Environmental Protection Agency (EPA) to develop a screening and testing program for potential endocrine disrupting chemicals (EDCs), of which xenoestrogens figure prominently. Under the legislation, a large number of chemicals will undergo various in vitro and in vivo assays for their potential estrogenicity, as well as other hormonal activities. There is a crucial need for priority setting before this strategy can be effectively implemented. Here we report an integrated computational approach to priority setting using estrogen receptor (ER) binding as an example. This approach rationally integrates different predictive computational models into a "Four-Phase" scheme so that it can effectively identify potential estrogenic EDCs based on their predicted ER relative binding affinity (RBA). The system has been validated using an in-house ER binding assay dataset for 232 chemicals that was designed to have both broad structural diversity and a wide range of binding affinities. When applied to 58,000 chemicals identified by Walker et al. as candidates for endocrine disruption screening, some 9100 chemicals were predicted to bind to ER. Of these, only 3600 were expected to bind to ER at RBA values up to 100,000-fold less than that of 17 g -estradiol. The method ruled out 83% of the chemicals as non-binders with a very low rate of false negatives. We believe that the same integrated scheme will be equally applicable to endpoints of other endocrine disrupting mechanisms, e.g. androgen receptor binding.     

Homology model of the rainbow trout estrogen receptor (rtERα) and docking of endocrine disrupting chemicals (EDCs)‖

A model for rainbow trout (Oncorhynchus mykiss) estrogen receptor (rtERα) was built by homology with the human estrogen receptor (hERα). A high level of sequence conservation between the two receptors was found with 64% and 80% of identity and similarity, respectively. Selected endocrine disrupting chemicals were docked into the ligand binding domain (LBD) of rtERα and the corresponding free binding energies Δ(ΔG_bind) values were calculated. A Quantitative Structure-Activity Relationship (QSAR) model between the relative binding affinity data and the Δ(ΔG_bind) values was derived in order to predict which further organic pollutants are likely to bind to rtERα.

     

An integrated "4-phase" approach for setting endocrine disruption screening priorities--phase I and II predictions of estrogen receptor binding affinity

Recent legislation mandates the US Environmental Protection Agency (EPA) to develop a screening and testing program for potential endocrine disrupting chemicals (EDCs), of which xenoestrogens figure prominently. Under the legislation, a large number of chemicals will undergo various in vitro and in vivo assays for their potential estrogenicity, as well as other hormonal activities. There is a crucial need for priority setting before this strategy can be effectively implemented. Here we report an integrated computational approach to priority setting using estrogen receptor (ER) binding as an example. This approach rationally integrates different predictive computational models into a "Four-Phase" scheme so that it can effectively identify potential estrogenic EDCs based on their predicted ER relative binding affinity (RBA). The system has been validated using an in-house ER binding assay dataset for 232 chemicals that was designed to have both broad structural diversity and a wide range of binding affinities. When applied to 58,000 chemicals identified by Walker et al. as candidates for endocrine disruption screening, some 9100 chemicals were predicted to bind to ER. Of these, only 3600 were expected to bind to ER at RBA values up to 100,000-fold less than that of 17beta-estradiol. The method ruled out 83% of the chemicals as non-binders with a very low rate of false negatives. We believe that the same integrated scheme will be equally applicable to endpoints of other endocrine disrupting mechanisms, e.g. androgen receptor binding.