Periodic Reporting for period 1 - Eco-CosmePharm (Computational 'eco-toxicity' assessment of pharmaceutical and cosmetics materials, an approach towards a green and sustainable environment)
Reporting period: 2019-09-16 to 2021-09-15
There are varieties of materials utilized or produced in the pharmaceutical industry, but the materials that have a huge impact on the environment are the solvents and the end-products. The pharmaceutical products are released in the environment during manufacturing, usage, and disposal. Some are adsorbed to the soils and get deposited, while most are water-soluble and have low volatility, and thus are transported to water compartments in the environment. The main purpose of any pharmaceutical drug/medicine is to ‘stimulate desirable’ or ‘inhibit undesirable’ physiological responses in humans. However, such potent pharmaceutical products including solvents used, are highly capable to show unforeseen adverse effects to non-target ecological species when released in the environment. Another major concern is that these chemicals unintentionally released in the water, although in low concentrations, might pose a high risk to human health after ingestion of contaminated drinking water over a long period, or even there is an adequate risk of contamination via the food chain.
The main objective is to identify and reduce the impact of potentially hazardous pharmaceuticals, cosmetics, and solvents on the aquatic environment. The toxicity-related properties that will be studied include acute and chronic toxicity, biodegradation, and bioaccumulation. The research methodology to perform toxicity assessment will majorly involve Quantitative Structure-Toxicity Relationship (QSTR), which employs several machine learning approaches for understanding the structural features responsible for aquatic toxicity.
Conclusion of the actions: We have developed a multi-tasking QSTR model to predict the acute and chronic toxicity of pharmaceuticals and cosmetics. Moreover, we have also developed a multi-tasking QSAR model employing random forest technique to predict the bioaccumulation and a classification-based QSAR model employing linear discriminant analysis technique to predict the biodegradation status of chemicals of our interest. The knowledge gained from the QSAR studies helped us in classifying existing marketed pharmaceuticals and cosmetics into toxic and non-toxic groups. Further, we have also performed the experimental validation of the developed models and the results are encouraging. Interestingly, this project also resulted in the development of highly user-friendly AI-based software tools ‘ProtoML-Basic’ and ‘ProtoML-Mixture’ for efficiently executing several QSAR and machine learning tasks. In the near future, the study will surely help us in screening or designing novel analogs of selected toxic chemicals or to identify alternative chemicals that might show similar desirable physicochemical properties with less or no eco-toxicity.
The main objective is to identify and reduce the impact of potentially hazardous pharmaceuticals, cosmetics, and solvents on the aquatic environment. The toxicity-related properties that will be studied include acute and chronic toxicity, biodegradation, and bioaccumulation. The research methodology to perform toxicity assessment will majorly involve Quantitative Structure-Toxicity Relationship (QSTR), which employs several machine learning approaches for understanding the structural features responsible for aquatic toxicity.
Conclusion of the actions: We have developed a multi-tasking QSTR model to predict the acute and chronic toxicity of pharmaceuticals and cosmetics. Moreover, we have also developed a multi-tasking QSAR model employing random forest technique to predict the bioaccumulation and a classification-based QSAR model employing linear discriminant analysis technique to predict the biodegradation status of chemicals of our interest. The knowledge gained from the QSAR studies helped us in classifying existing marketed pharmaceuticals and cosmetics into toxic and non-toxic groups. Further, we have also performed the experimental validation of the developed models and the results are encouraging. Interestingly, this project also resulted in the development of highly user-friendly AI-based software tools ‘ProtoML-Basic’ and ‘ProtoML-Mixture’ for efficiently executing several QSAR and machine learning tasks. In the near future, the study will surely help us in screening or designing novel analogs of selected toxic chemicals or to identify alternative chemicals that might show similar desirable physicochemical properties with less or no eco-toxicity.
The work was executed via. 6 work packages. In the first work package (WP1) the two key tasks were executed: 1) Literature survey and collection of the available experimental data representing acute and chronic aquatic toxicity, biodegradation, and bioaccumulation, 2) Chemical and biological data curation of the collected data.
In the second work package, the first task was initially planned to develop new descriptors specific for studying salts, organo-metallic, inorganics, and mixture. However, based on the literature survey we realized that much of the work is already going on with the development of descriptors for the mentioned types of chemicals, and thus we planned to perform a study to evaluate the applicability and efficiency of typically used descriptors as well as new descriptors recommended for handling such chemicals. Thus, as a case study, we have developed a generalized nanoQSAR model for predicting cytotoxicity and genotoxicity of metal oxides nanoparticles (published here DOI: 10.4018/IJQSPR.20201001.oa2). The next task was the development of the QSAR methodology for mixtures. There were two key areas where we can contribute to this topic, i.e. first to compile the information and design a rational methodology, and second to move one step ahead and develop a user-friendly software platform ‘ProtoML-Mixture’ to execute the designed methodology for handling mixtures. To demonstrate the capabilities of the developed software ‘ProtoML-Mixture’ we have performed a case study, where we have developed a multi-tasking QSTR model for predicting the ecotoxicity of deep eutectic solvents (DESs).
In the third work package, we have developed an artificial intelligence (AI) based 'Proto-ML' software to develop and validate the regression and classification-based QSAR models. It has a lot of functionalities that will help users to develop robust models and it works like a workflow, which makes it highly user-friendly. It comprises several essential nodes starting from reading and confirming the input data, data pre-treatment, data set splitting, machine learning (ML) technique node comprising several feature selection methods, ML techniques, as well as, options to set validation parameters, graphs/plots, and applicability domain determination method and finally output data node. In the fourth work package, we have developed several QSTR/QSAR models including multi-tasking that assisted us to screen potential pharmaceuticals and/or cosmetics that may show aquatic toxicity. Thus, first, we have developed requisite QSTR models to predict the acute and chronic toxicity of pharmaceuticals and cosmetics, as well as, to predict the biodegradation and bioaccumulation status. Later, these models were ultimately utilized in screening marketed pharmaceuticals and cosmetics to identify potential chemicals that can be harmful to aquatic life. On screening 8282 chemicals, we have selected 55 chemicals from different toxicity categories for experimental validation of the developed models. The toxicity studies on Daphnia magna were performed in Xenobiotics S.L. (secondment 1), while studies on Oncorhynchus mykiss were performed in INIA, Madrid (secondment 2). We have disseminated the progress and results of the project in about 10 scientific events including conferences, workshops, etc., and promoted in social media.
In the second work package, the first task was initially planned to develop new descriptors specific for studying salts, organo-metallic, inorganics, and mixture. However, based on the literature survey we realized that much of the work is already going on with the development of descriptors for the mentioned types of chemicals, and thus we planned to perform a study to evaluate the applicability and efficiency of typically used descriptors as well as new descriptors recommended for handling such chemicals. Thus, as a case study, we have developed a generalized nanoQSAR model for predicting cytotoxicity and genotoxicity of metal oxides nanoparticles (published here DOI: 10.4018/IJQSPR.20201001.oa2). The next task was the development of the QSAR methodology for mixtures. There were two key areas where we can contribute to this topic, i.e. first to compile the information and design a rational methodology, and second to move one step ahead and develop a user-friendly software platform ‘ProtoML-Mixture’ to execute the designed methodology for handling mixtures. To demonstrate the capabilities of the developed software ‘ProtoML-Mixture’ we have performed a case study, where we have developed a multi-tasking QSTR model for predicting the ecotoxicity of deep eutectic solvents (DESs).
In the third work package, we have developed an artificial intelligence (AI) based 'Proto-ML' software to develop and validate the regression and classification-based QSAR models. It has a lot of functionalities that will help users to develop robust models and it works like a workflow, which makes it highly user-friendly. It comprises several essential nodes starting from reading and confirming the input data, data pre-treatment, data set splitting, machine learning (ML) technique node comprising several feature selection methods, ML techniques, as well as, options to set validation parameters, graphs/plots, and applicability domain determination method and finally output data node. In the fourth work package, we have developed several QSTR/QSAR models including multi-tasking that assisted us to screen potential pharmaceuticals and/or cosmetics that may show aquatic toxicity. Thus, first, we have developed requisite QSTR models to predict the acute and chronic toxicity of pharmaceuticals and cosmetics, as well as, to predict the biodegradation and bioaccumulation status. Later, these models were ultimately utilized in screening marketed pharmaceuticals and cosmetics to identify potential chemicals that can be harmful to aquatic life. On screening 8282 chemicals, we have selected 55 chemicals from different toxicity categories for experimental validation of the developed models. The toxicity studies on Daphnia magna were performed in Xenobiotics S.L. (secondment 1), while studies on Oncorhynchus mykiss were performed in INIA, Madrid (secondment 2). We have disseminated the progress and results of the project in about 10 scientific events including conferences, workshops, etc., and promoted in social media.
The research methodology to perform toxicity assessment majorly involves QSAR including multi-tasking QSAR. Multi-tasking QSAR/QSTR models developed in this project are really unique since these models have capabilities to capture and provide much more information if compared to typical QSAR/QSTR models. The key feature of a multi-tasking model is that it not only identifies the relationship between the structural features and the toxicity of our interest but also captures the changes in the toxicity due to variation in the experimental conditions. These models were ultimately utilized in screening marketed pharmaceuticals and cosmetics to identify potential chemicals that can be harmful to aquatic life and some of them were experimentally validated. The original and validated ecotoxicity models developed in this project will be implemented in the ProtoPred tool (developed in our company) and will be made available for end-users of cosmetics or pharmaceuticals.
This project also resulted in highly user-friendly software tools ‘ProtoML-Basic’ and ‘ProtoML-Mixture’ for efficiently executing several QSAR and machine learning tasks. The software tools will be freely available upon registration and we are expecting that these software tools will be very useful for students, researchers, as well as, industry people.
This project also resulted in highly user-friendly software tools ‘ProtoML-Basic’ and ‘ProtoML-Mixture’ for efficiently executing several QSAR and machine learning tasks. The software tools will be freely available upon registration and we are expecting that these software tools will be very useful for students, researchers, as well as, industry people.