Virtual Toxicity panels focussed on interpretable machine learning models that can guide medicinal chemists to identify critical substructures that are assocaited with toxicities.
Accelerating lead optimisation with active learning by exploiting MMPA based ...Ed Griffen
Presented at the 15th GCC - German Conference on Cheminformatics November 2019
We combine regression forest machine learning with our MMPA based generative methods to deliver an active learning system to accelerate lead optimisation. In the process we identify permutative MMPA as a method to leverage SAR information from small data sets.
Published by MedChemica Ltd
Emerging Challenges for Artificial Intelligence in Medicinal ChemistryEd Griffen
Presentation by Dr Ed Griffen of MedChemica Ltd, at The IBSA Conference "How Artificial Intelligence Can Change the Pharmaceutical Landscape“ - LUGANO, October 9th 2019.
This document discusses how bioinformatics tools can be used in drug design. It describes several approaches: chemical modification of existing drugs, receptor-based design by determining receptor structures, and ligand-based design using known active ligands. It also discusses identifying disease targets, refining drug structures, detecting drug binding sites using protein modeling, and rational drug design techniques like virtual screening. QSAR methods relate compound structures to activities, while molecular modeling and docking simulate drug-receptor interactions to aid design. Informatics plays a key role in storing and analyzing the large amounts of data generated.
MOLECULAR DOCKING AND RELATED DRUG DESIGN ACHIEVEMENTS santosh Kumbhar
Molecular docking is a computational method used in structure-based drug design to predict how biological macromolecules interact with other molecules. It attempts to predict the preferred orientation of one molecule to another when bound to each other to form a stable complex. Docking is useful for predicting the binding orientation of small molecule drug candidates to their protein targets in order to predict their interaction and to design effective inhibitors. There are various types of docking software available that implement different algorithms to predict the binding orientation and affinity between molecules rapidly and accurately to help identify potential lead compounds for drug development. Molecular docking has contributed to the discovery of several new drug classes and is playing an increasingly important role in modern computer-aided drug design and virtual
Connecting Metabolomic Data with ContextDmitry Grapov
The document summarizes Dmitry Grapov's presentation on connecting metabolomic data with context. It discusses using network mapping and multivariate tools to analyze metabolomic data by generating connections between metabolites based on biochemical, chemical, and empirical relationships. These connections can help identify relationships between experimental observations and link the known with unknown. The presentation also provides examples of projects applying these techniques to analyze data from various disease studies involving changes in lipids, proteins, and small molecule metabolites.
Qsar studies on gallic acid derivatives and molecular docking studies of bace...bioejjournal
It is reported that Alzheimer disease is linked with hypertension, diabetes type 2 and high cholesterolemia. The underlying genetic cause relating these diseases are not well studied clinically. But it has been widely
accepted that beta secretase (BACE1) is the main culprit of causing Alzheimer disease. This enzyme comes under peptidase A1 family. In the present work, ligand based and structure based drug designing have been reported. QSAR studies were done using 21 gallic acid derivatives dataset to develop good predictive
model in order to predict biological activity and certain descriptors was reported to further enhance the
analgesic activity of gallic acid derivatives. Molecular docking studies were performed in order to find
structure based drug design. Two natural gallic acid derivative have been repoted as a potent inhibitor to beta secretase enzyme.
Qsar Studies on Gallic Acid Derivatives and Molecular Docking Studies of Bace...bioejjournal
It is reported that Alzheimer disease is linked with hypertension, diabetes type 2 and high cholesterolemia. The underlying genetic cause relating these diseases are not well studied clinically. But it has been widely accepted that beta secretase (BACE1) is the main culprit of causing Alzheimer disease. This enzyme comes under peptidase A1 family. In the present work, ligand based and structure based drug designing have been
reported. QSAR studies were done using 21 gallic acid derivatives dataset to develop good predictive model in order to predict biological activity and certain descriptors was reported to further enhance the analgesic activity of gallic acid derivatives. Molecular docking studies were performed in order to find
structure based drug design. Two natural gallic acid derivative have been repoted as a potent inhibitor to beta secretase enzyme.
Accelerating lead optimisation with active learning by exploiting MMPA based ...Ed Griffen
Presented at the 15th GCC - German Conference on Cheminformatics November 2019
We combine regression forest machine learning with our MMPA based generative methods to deliver an active learning system to accelerate lead optimisation. In the process we identify permutative MMPA as a method to leverage SAR information from small data sets.
Published by MedChemica Ltd
Emerging Challenges for Artificial Intelligence in Medicinal ChemistryEd Griffen
Presentation by Dr Ed Griffen of MedChemica Ltd, at The IBSA Conference "How Artificial Intelligence Can Change the Pharmaceutical Landscape“ - LUGANO, October 9th 2019.
This document discusses how bioinformatics tools can be used in drug design. It describes several approaches: chemical modification of existing drugs, receptor-based design by determining receptor structures, and ligand-based design using known active ligands. It also discusses identifying disease targets, refining drug structures, detecting drug binding sites using protein modeling, and rational drug design techniques like virtual screening. QSAR methods relate compound structures to activities, while molecular modeling and docking simulate drug-receptor interactions to aid design. Informatics plays a key role in storing and analyzing the large amounts of data generated.
MOLECULAR DOCKING AND RELATED DRUG DESIGN ACHIEVEMENTS santosh Kumbhar
Molecular docking is a computational method used in structure-based drug design to predict how biological macromolecules interact with other molecules. It attempts to predict the preferred orientation of one molecule to another when bound to each other to form a stable complex. Docking is useful for predicting the binding orientation of small molecule drug candidates to their protein targets in order to predict their interaction and to design effective inhibitors. There are various types of docking software available that implement different algorithms to predict the binding orientation and affinity between molecules rapidly and accurately to help identify potential lead compounds for drug development. Molecular docking has contributed to the discovery of several new drug classes and is playing an increasingly important role in modern computer-aided drug design and virtual
Connecting Metabolomic Data with ContextDmitry Grapov
The document summarizes Dmitry Grapov's presentation on connecting metabolomic data with context. It discusses using network mapping and multivariate tools to analyze metabolomic data by generating connections between metabolites based on biochemical, chemical, and empirical relationships. These connections can help identify relationships between experimental observations and link the known with unknown. The presentation also provides examples of projects applying these techniques to analyze data from various disease studies involving changes in lipids, proteins, and small molecule metabolites.
Qsar studies on gallic acid derivatives and molecular docking studies of bace...bioejjournal
It is reported that Alzheimer disease is linked with hypertension, diabetes type 2 and high cholesterolemia. The underlying genetic cause relating these diseases are not well studied clinically. But it has been widely
accepted that beta secretase (BACE1) is the main culprit of causing Alzheimer disease. This enzyme comes under peptidase A1 family. In the present work, ligand based and structure based drug designing have been reported. QSAR studies were done using 21 gallic acid derivatives dataset to develop good predictive
model in order to predict biological activity and certain descriptors was reported to further enhance the
analgesic activity of gallic acid derivatives. Molecular docking studies were performed in order to find
structure based drug design. Two natural gallic acid derivative have been repoted as a potent inhibitor to beta secretase enzyme.
Qsar Studies on Gallic Acid Derivatives and Molecular Docking Studies of Bace...bioejjournal
It is reported that Alzheimer disease is linked with hypertension, diabetes type 2 and high cholesterolemia. The underlying genetic cause relating these diseases are not well studied clinically. But it has been widely accepted that beta secretase (BACE1) is the main culprit of causing Alzheimer disease. This enzyme comes under peptidase A1 family. In the present work, ligand based and structure based drug designing have been
reported. QSAR studies were done using 21 gallic acid derivatives dataset to develop good predictive model in order to predict biological activity and certain descriptors was reported to further enhance the analgesic activity of gallic acid derivatives. Molecular docking studies were performed in order to find
structure based drug design. Two natural gallic acid derivative have been repoted as a potent inhibitor to beta secretase enzyme.
This document discusses molecular docking, which is a computational method used in structure-based drug design to predict the preferred orientation of molecules when bound to their protein targets to form stable complexes. It begins by introducing drug discovery and computational chemistry approaches. It then defines molecular docking and describes different docking types and software. Applications of docking in modern drug discovery are presented, along with case studies and achievements that have resulted in new drug classes. The document concludes that docking contributes promisingly to drug discovery by aiding in target identification and lead optimization.
Fragment-based drug design (FBDD) is an approach to drug discovery that starts with small molecular fragments rather than whole compounds. It identifies fragments that bind to the target protein and then elaborates on those fragments or fuses them together to create lead-like drug molecules. FBDD has advantages over high-throughput screening in that it focuses on developing "lead-like" compounds that are more likely to be optimized into drug candidates. The key steps involve screening a fragment library against the target, elaborating initial fragment hits, and traditional lead optimization methods to generate drug-like molecules.
1) The document discusses strategies for designing targeted arrays to screen nuclear receptor ligands, including defining nuclear receptor chemical space and using x-ray crystallography data to assess potential ligands.
2) Virtual arrays are generated and analyzed using shape and pharmacophore matching tools like ROCS to prioritize arrays based on similarity to known receptor ligands.
3) Limitations of the current approach include using a single protein structure, not accounting for flexibility, and limitations of computational docking. Advancing the methods could improve array design for orphan receptors.
This document describes molecular docking of ligands to the anaplastic lymphoma kinase protein using Autodock Tools. It discusses docking methodology including scoring functions, genetic algorithms, and the Autodock software. The document then outlines the steps taken to dock four ligands (loratinib, ceritinib, crizotinib, alectinib) to the protein, including preparing files and running Autodock. It analyzes and compares the binding energies of the different ligand-protein complexes and visualizes the results, finding that loratinib had the strongest binding to the protein.
Molecular docking involves binding a small ligand molecule to a larger target molecule to form a stable complex. Docking software simulates this binding process and calculates the energy of interactions between the ligand and target in different orientations. The best fitting ligand orientation is one that provides structural and chemical stability to the complex. Molecular docking and computer-aided drug design are used to identify chemical compounds that can interact with and inhibit or activate protein targets, with the goal of developing new drug candidates.
This document discusses chemoinformatics and its role in distance education. It defines chemoinformatics as the application of informatics methods to solve chemical problems, involving the design, creation, organization, management, analysis and use of chemical information. The document then outlines proposed courses for a distance learning program in chemoinformatics, including introductory courses covering fundamental concepts as well as more advanced topics involving programming, databases, and molecular modeling. It concludes by discussing how chemoinformatics can help improve distance education programs in chemistry fields.
Molecular docking is a method for predicting how two molecules, such as a ligand and its protein target, will interact and fit together in three dimensions. Docking has become an important tool in drug discovery for identifying potential binding conformations between drug candidates and protein targets. The key steps in a typical docking workflow involve selecting the receptor and ligand molecules, then using software to computationally predict the orientation of binding and evaluate the fit through scoring functions. Popular molecular docking software packages include AutoDock, GOLD, and Glide. Applications of docking include virtual screening in drug discovery and lead optimization.
A lecture on molecular docking that I give for master students at University Paris Diderot.
Warning: this presentation has numerous animations which are not included in the slideshare document.
https://florentbarbault.wordpress.com/
The document discusses docking, which predicts the optimal binding configuration between two molecules by optimizing their orientation and interaction energy. It describes protein-protein docking where both molecules are rigid, and protein-ligand docking where the ligand is flexible but the protein is rigid. It also discusses the AutoDock software, which uses grids and heuristic search algorithms like genetic algorithms to model docking. It provides examples of docking interleukin-10 to an alkaloid ligand, and nuclear factor kappa-B to a ligand. The document advises considering compounds with binding energies close to or better than a positive control as potential hits.
Structure based drug design- kiranmayiKiranmayiKnv
This presentation helps in detail learning about the structure based drug design. It includes types of structure based drug design and detailed study of docking, de novo drug design.
Domainex has contributed to three clinical candidates through its drug discovery programs for clients. It uses a variety of technologies like combinatorial domain hunting, LeadBuilder for virtual screening, and integrated medicinal and computational chemistry. Domainex has a highly experienced team of drug discovery scientists and has successfully delivered ion-channel blockers, kinase inhibitors, and anti-thrombotics into clinical trials for clients. It provides concise drug discovery services from hit identification to candidate selection through its expertise in computational chemistry, library synthesis, and medicinal chemistry.
Molecular docking is a computer modeling technique used to predict the preferred orientation of one molecule to another when bound to form a stable complex. It involves fitting potential drug molecules into the active site of a protein receptor in order to identify which molecules may bind strongly. There are different approaches to molecular docking including rigid docking which treats molecules as rigid bodies, and flexible docking which accounts for conformational changes in ligands. The goal of docking is to find binding orientations that minimize the total energy of the system and maximize intermolecular interactions in order to predict effective drug candidates.
Fragment-based drug design (FBDD) uses small molecular fragments that bind weakly to a target protein's binding site. These fragments can then be grown, merged, or linked to improve binding affinity. FBDD provides starting points for challenging targets like protein-protein interactions. It increases the use of biophysics to characterize compound binding. FBDD also gives small research groups access to tools for identifying chemical probes of biological systems.
Structure based computer aided drug designThanh Truong
The document discusses structure-based computer-aided drug design. It describes the drug discovery process and challenges involved in predicting how small molecules bind to protein targets. Key steps in molecular docking include describing the receptor and ligand, sampling possible binding configurations, and scoring the interactions to estimate binding affinity. Genetic and simulated annealing algorithms are commonly used to sample configurations. The accuracy of docking depends on factors like receptor and ligand flexibility.
Molecular docking is a computational method that predicts the preferred orientation of one molecule to another when bound and forming a stable complex. It involves finding the best match between two molecules and can be used for drug design and development by predicting the binding affinity between potential drug candidates and their protein targets. Common molecular docking approaches include shape complementarity, which describes interacting molecules as complementary surfaces, and simulation methods, which simulate the actual docking process and calculate interaction energies between molecules. Popular molecular docking software includes AutoDock, FlexX, and GOLD.
Docking is a method that predicts the preferred orientation of one molecule binding to another to form a stable complex with minimum energy. It is important for rational drug design, as the results can be used to design inhibitors for target proteins and new drugs. Docking is key to structure-based drug design for lead generation and optimization. Factors like intramolecular and intermolecular forces influence docking. There are rigid and flexible docking methods. Molecular docking has been successfully used in drug discovery for HIV, influenza, and other diseases.
Computer-aided drug design (CADD) is a widely used technology using computational tools and resources for the storage, management, analysis and modeling of compounds. It relies on digital repositories for study of designing compounds with physicochemical characteristics, predicting whether a given molecule will be combined with the target, and if so how strongly. Computer based methods can help us to search new hits in drug discovery, screen many irrelevant compounds at the same time and study the structure-activity relationship of drug molecules.
Stable Drug Designing by Minimizing Drug Protein Interaction Energy Using PSO csandit
1. The document proposes using a particle swarm optimization (PSO) algorithm to design stable drug molecules that minimize interaction energy with target proteins.
2. In the algorithm, drugs are represented as variable-length trees containing functional groups, and PSO is used to optimize van der Waals and electrostatic interaction energies.
3. Results show that PSO performs better than previous fixed-length tree methods at designing drugs that stably bind to active sites of human rhinovirus, malaria, and HIV proteins.
The document discusses computational models that have been and can be used for predicting human toxicities. It provides examples of models that have been developed for predicting various physicochemical properties, interactions with proteins, and toxicity outcomes like mutagenicity, environmental toxicity, and drug-induced liver injury. It also outlines future areas that could be modeled, like mixtures and more specific protein targets. The key enablers of these models are increased computing power and data availability from literature and open sources.
Finland Helsinki Drug Research slides 2011Sean Ekins
This document summarizes the application and future of ADME/Tox (Absorption, Distribution, Metabolism, Excretion and Toxicology) models. It discusses how combining in silico, in vitro and in vivo data can help evaluate these properties earlier in drug discovery. It also outlines how crowdsourcing and increased data and model sharing can help advance the field. Finally, it provides examples of Bayesian machine learning models that have been developed to predict various ADME/Tox endpoints.
This document discusses molecular docking, which is a computational method used in structure-based drug design to predict the preferred orientation of molecules when bound to their protein targets to form stable complexes. It begins by introducing drug discovery and computational chemistry approaches. It then defines molecular docking and describes different docking types and software. Applications of docking in modern drug discovery are presented, along with case studies and achievements that have resulted in new drug classes. The document concludes that docking contributes promisingly to drug discovery by aiding in target identification and lead optimization.
Fragment-based drug design (FBDD) is an approach to drug discovery that starts with small molecular fragments rather than whole compounds. It identifies fragments that bind to the target protein and then elaborates on those fragments or fuses them together to create lead-like drug molecules. FBDD has advantages over high-throughput screening in that it focuses on developing "lead-like" compounds that are more likely to be optimized into drug candidates. The key steps involve screening a fragment library against the target, elaborating initial fragment hits, and traditional lead optimization methods to generate drug-like molecules.
1) The document discusses strategies for designing targeted arrays to screen nuclear receptor ligands, including defining nuclear receptor chemical space and using x-ray crystallography data to assess potential ligands.
2) Virtual arrays are generated and analyzed using shape and pharmacophore matching tools like ROCS to prioritize arrays based on similarity to known receptor ligands.
3) Limitations of the current approach include using a single protein structure, not accounting for flexibility, and limitations of computational docking. Advancing the methods could improve array design for orphan receptors.
This document describes molecular docking of ligands to the anaplastic lymphoma kinase protein using Autodock Tools. It discusses docking methodology including scoring functions, genetic algorithms, and the Autodock software. The document then outlines the steps taken to dock four ligands (loratinib, ceritinib, crizotinib, alectinib) to the protein, including preparing files and running Autodock. It analyzes and compares the binding energies of the different ligand-protein complexes and visualizes the results, finding that loratinib had the strongest binding to the protein.
Molecular docking involves binding a small ligand molecule to a larger target molecule to form a stable complex. Docking software simulates this binding process and calculates the energy of interactions between the ligand and target in different orientations. The best fitting ligand orientation is one that provides structural and chemical stability to the complex. Molecular docking and computer-aided drug design are used to identify chemical compounds that can interact with and inhibit or activate protein targets, with the goal of developing new drug candidates.
This document discusses chemoinformatics and its role in distance education. It defines chemoinformatics as the application of informatics methods to solve chemical problems, involving the design, creation, organization, management, analysis and use of chemical information. The document then outlines proposed courses for a distance learning program in chemoinformatics, including introductory courses covering fundamental concepts as well as more advanced topics involving programming, databases, and molecular modeling. It concludes by discussing how chemoinformatics can help improve distance education programs in chemistry fields.
Molecular docking is a method for predicting how two molecules, such as a ligand and its protein target, will interact and fit together in three dimensions. Docking has become an important tool in drug discovery for identifying potential binding conformations between drug candidates and protein targets. The key steps in a typical docking workflow involve selecting the receptor and ligand molecules, then using software to computationally predict the orientation of binding and evaluate the fit through scoring functions. Popular molecular docking software packages include AutoDock, GOLD, and Glide. Applications of docking include virtual screening in drug discovery and lead optimization.
A lecture on molecular docking that I give for master students at University Paris Diderot.
Warning: this presentation has numerous animations which are not included in the slideshare document.
https://florentbarbault.wordpress.com/
The document discusses docking, which predicts the optimal binding configuration between two molecules by optimizing their orientation and interaction energy. It describes protein-protein docking where both molecules are rigid, and protein-ligand docking where the ligand is flexible but the protein is rigid. It also discusses the AutoDock software, which uses grids and heuristic search algorithms like genetic algorithms to model docking. It provides examples of docking interleukin-10 to an alkaloid ligand, and nuclear factor kappa-B to a ligand. The document advises considering compounds with binding energies close to or better than a positive control as potential hits.
Structure based drug design- kiranmayiKiranmayiKnv
This presentation helps in detail learning about the structure based drug design. It includes types of structure based drug design and detailed study of docking, de novo drug design.
Domainex has contributed to three clinical candidates through its drug discovery programs for clients. It uses a variety of technologies like combinatorial domain hunting, LeadBuilder for virtual screening, and integrated medicinal and computational chemistry. Domainex has a highly experienced team of drug discovery scientists and has successfully delivered ion-channel blockers, kinase inhibitors, and anti-thrombotics into clinical trials for clients. It provides concise drug discovery services from hit identification to candidate selection through its expertise in computational chemistry, library synthesis, and medicinal chemistry.
Molecular docking is a computer modeling technique used to predict the preferred orientation of one molecule to another when bound to form a stable complex. It involves fitting potential drug molecules into the active site of a protein receptor in order to identify which molecules may bind strongly. There are different approaches to molecular docking including rigid docking which treats molecules as rigid bodies, and flexible docking which accounts for conformational changes in ligands. The goal of docking is to find binding orientations that minimize the total energy of the system and maximize intermolecular interactions in order to predict effective drug candidates.
Fragment-based drug design (FBDD) uses small molecular fragments that bind weakly to a target protein's binding site. These fragments can then be grown, merged, or linked to improve binding affinity. FBDD provides starting points for challenging targets like protein-protein interactions. It increases the use of biophysics to characterize compound binding. FBDD also gives small research groups access to tools for identifying chemical probes of biological systems.
Structure based computer aided drug designThanh Truong
The document discusses structure-based computer-aided drug design. It describes the drug discovery process and challenges involved in predicting how small molecules bind to protein targets. Key steps in molecular docking include describing the receptor and ligand, sampling possible binding configurations, and scoring the interactions to estimate binding affinity. Genetic and simulated annealing algorithms are commonly used to sample configurations. The accuracy of docking depends on factors like receptor and ligand flexibility.
Molecular docking is a computational method that predicts the preferred orientation of one molecule to another when bound and forming a stable complex. It involves finding the best match between two molecules and can be used for drug design and development by predicting the binding affinity between potential drug candidates and their protein targets. Common molecular docking approaches include shape complementarity, which describes interacting molecules as complementary surfaces, and simulation methods, which simulate the actual docking process and calculate interaction energies between molecules. Popular molecular docking software includes AutoDock, FlexX, and GOLD.
Docking is a method that predicts the preferred orientation of one molecule binding to another to form a stable complex with minimum energy. It is important for rational drug design, as the results can be used to design inhibitors for target proteins and new drugs. Docking is key to structure-based drug design for lead generation and optimization. Factors like intramolecular and intermolecular forces influence docking. There are rigid and flexible docking methods. Molecular docking has been successfully used in drug discovery for HIV, influenza, and other diseases.
Computer-aided drug design (CADD) is a widely used technology using computational tools and resources for the storage, management, analysis and modeling of compounds. It relies on digital repositories for study of designing compounds with physicochemical characteristics, predicting whether a given molecule will be combined with the target, and if so how strongly. Computer based methods can help us to search new hits in drug discovery, screen many irrelevant compounds at the same time and study the structure-activity relationship of drug molecules.
Stable Drug Designing by Minimizing Drug Protein Interaction Energy Using PSO csandit
1. The document proposes using a particle swarm optimization (PSO) algorithm to design stable drug molecules that minimize interaction energy with target proteins.
2. In the algorithm, drugs are represented as variable-length trees containing functional groups, and PSO is used to optimize van der Waals and electrostatic interaction energies.
3. Results show that PSO performs better than previous fixed-length tree methods at designing drugs that stably bind to active sites of human rhinovirus, malaria, and HIV proteins.
The document discusses computational models that have been and can be used for predicting human toxicities. It provides examples of models that have been developed for predicting various physicochemical properties, interactions with proteins, and toxicity outcomes like mutagenicity, environmental toxicity, and drug-induced liver injury. It also outlines future areas that could be modeled, like mixtures and more specific protein targets. The key enablers of these models are increased computing power and data availability from literature and open sources.
Finland Helsinki Drug Research slides 2011Sean Ekins
This document summarizes the application and future of ADME/Tox (Absorption, Distribution, Metabolism, Excretion and Toxicology) models. It discusses how combining in silico, in vitro and in vivo data can help evaluate these properties earlier in drug discovery. It also outlines how crowdsourcing and increased data and model sharing can help advance the field. Finally, it provides examples of Bayesian machine learning models that have been developed to predict various ADME/Tox endpoints.
Nc state lecture v2 Computational ToxicologySean Ekins
The document discusses computational approaches to modeling various aspects of toxicology, including physicochemical properties, quantitative structure-activity relationships, and interactions with proteins and pathways involved in toxicity. It provides examples of modeling properties like solubility and lipophilicity, as well as targets like cytochrome P450 enzymes and the pregnane X receptor. Statistical methodologies for building predictive models are also reviewed. The future of crowdsourced drug discovery is briefly mentioned.
Sortase A Inhibition By Ugi Products (Complex)Andrew Lang
D. Bulger et al. sought to identify inhibitors of the bacterial enzyme Sortase A using a combination of computational docking and multi-component Ugi reactions. They expressed and purified Sortase A and developed a colorimetric assay to detect its inhibition. Computational docking was used to select Ugi products more likely to inhibit Sortase A, and NMR spectroscopy approximated solubilities to identify products that would precipitate and be easier to purify. Several Ugi reactions were carried out and their products will be tested in the colorimetric assay to identify potential Sortase A inhibitors. Future work will optimize reactions, docking, solubility predictions, and assays to further drug discovery efforts targeting this important bacterial enzyme.
Accelerating multiple medicinal chemistry projects using Artificial Intellige...Al Dossetter
The technical methods and results of Matched Molecular Pair Analysis (MMPA) applied from a small, individual assay scale through large pharma scale, to multiple pharma data sharing scale have been published and reviewed. The drive behind these efforts has been to derive a medicinal chemistry knowledge base (i.e. definitive textbook) that can be applied to drug discovery projects. The aim is to greatly decrease the time in lead identification and optimization by the synthesis of fewer compounds. Such a system suggests compound designs to expert chemists to triage; such a process is Artificial Intelligence (AI). Given this context, how does this work on projects? How do the chemists make decisions? What are the results? The talk will answer these questions through project examples where MMPA has been applied and how this led to drug candidates. The projects disclosed are from multiple organisations and describe Cathepsin K inhibitors, Glucokinase Inhibitors, 11β-Hydroxysteroid Dehydrogenase Type I Inhibitors (11β-HSD1), Ghrelin inverse antagonists and Tubulin Polymerization inhibitors. An overview of MMPA will be presented and each project will be briefly described with a focus on how the chemists used MMPA to understand SAR and design compounds. The impact of project progress to CD will be quantified.
The Karolinska Institute (KI) is the largest centre for medical education and research in Sweden and the home of the Nobel Prize in Physiology or Medicine.
KI consists of 22 departments and 600 research groups dedicated to improving human health through research and higher education.
The role of the Kohonen/Grafström team has been to guide the application, analysis, interpretation and storage of so called “omics” technology-derived data within the service-oriented subproject “ToxBank”.
COMPUTER AIDED DRUG DESIGN BYJayant_Nimkar78JAYANTNIMKAR
This document discusses computer aided drug design (CADD). It begins with a brief history of drug design from the 19th century to modern computational methods. It then covers the introduction, context, benefits and limitations of CADD. The main benefits are cost savings compared to traditional experimentation and the ability to screen large libraries of compounds more quickly. Limitations include lack of quality data and challenges with modeling complex targets. The document outlines the main stages of the CADD process and concludes that while computational, it still requires experimental validation and has helped reduce drug development costs.
COMPUTER AISES DRUG DESIGN .BY JAYA NT NIMKAR78JAYANTNIMKAR
This document discusses computer aided drug design (CADD). It begins with a brief history of drug design from the 19th century to modern computational methods. It then covers the introduction, context, benefits and limitations of CADD. The main benefits are cost savings compared to traditional experimentation and the ability to screen large libraries of compounds more quickly. Limitations include lack of quality data and challenges with modeling complex targets. The document outlines the main stages of the CADD process and concludes that while computational, it still requires experimental validation and has helped reduce drug development costs.
Development and sharing of ADME/Tox and Drug Discovery Machine learning modelsSean Ekins
This document discusses the development and sharing of machine learning models for ADME/Tox prediction and drug discovery. It notes that while ADME/Tox modeling began over 15 years ago with small datasets, modern models have much larger training data and address more properties. The opportunity to get pharmaceutical companies to use open-source tools and algorithms to build and share precompetitive models is described. Examples of published models for various properties like CYP inhibition and P-gp efflux built using open descriptors and algorithms are provided. The export of models from the Collaborative Drug Discovery platform and their use in mobile apps is also covered.
This document discusses computer assisted drug discovery (CADD) in plant pathology. It begins by outlining problems faced by plant protectionists like pathogen variability and pesticide resistance that necessitate new targeted approaches. The key stages of CADD are then described, including identifying suitable drug targets in plant pathogens, generating 3D structures through homology modeling or crystallography, molecular docking to screen compounds, and ligand-based approaches like pharmacophore modeling and QSAR when no target structure is available. Case studies applying these CADD methods to discover treatments for various fungal and bacterial diseases are also mentioned. The document concludes by noting potential challenges in applying CADD for plant pathogens.
The Utility of H/DX-MS in Biopharmaceutical Comparability StudiesAbhijeet Lokras
A presentation based on the research of Engen et al, which compares the utility of Hydrogen-Deuterium Exchange MS in Biopharmaceutics. HDX-MS is briefly introduced and some concepts are explained.
An Actionable Annotation Scoring Framework For Gas Chromatography - High Reso...Nicole Heredia
1. The document proposes an actionable annotation scoring framework for gas chromatography-high resolution mass spectrometry (GC-HRMS) to standardize the reporting of confidence levels in chemical identifications.
2. The framework adapts an existing scoring schema for liquid chromatography-mass spectrometry to the evidence provided by common GC-HRMS workflows, including retention time, ionization patterns, accurate mass, isotopic patterns, and database matches.
3. Validation using spiked standards in plasma and air samples showed a 12% false positive rate for annotations assigned a confidence level of 2 when isomers are excluded, demonstrating the framework's ability to reliably communicate identification confidence.
Talk at Yale University April 26th 2011: Applying Computational Modelsfor To...Sean Ekins
The document discusses applying computational models to problems in toxicology, drug discovery, and beyond. It summarizes recent work using machine learning models and other in silico techniques to predict drug-induced liver injury (DILI) and interactions with transporters like hOCTN2. Models were able to classify compounds as DILI-positive or negative with over 75% accuracy when tested on external datasets. The techniques discussed could help prioritize compounds for further testing and filter libraries to avoid reactive or toxic features.
This document describes computational techniques used to design novel competitive inhibitors of the E. coli 5'-methylthioadenosine/S-adenosylhomocysteine nucleosidase (MTN) enzyme. It utilized core hopping to generate 10,000 structures by varying the core while keeping functional groups constant. Docking and binding energies were calculated for subsets of compounds down to the top 8 ligands. Results show several compounds have more favorable predicted binding than the control TDI inhibitor, warranting further optimization and testing of lead compounds.
Genotoxic impurities are potentially harmful compounds that must be strictly controlled in pharmaceuticals. They can cause mutations in DNA that may lead to cancer. Guidelines classify genotoxic impurities into five categories based on their mutagenic and carcinogenic potential to determine appropriate testing and control strategies. Analytical methods for detecting genotoxic impurities at the parts-per-million level or lower require sensitive techniques like mass spectrometry and NMR due to the stringent limits for these compounds.
Process Impurities: Don’t Let PEI or HCP Derail Your BioTherapyMilliporeSigma
View our webinar here: https://bit.ly/2lKNdWX
Many different impurities are present in or generated during biotherapy manufacturing. This webinar will address how process contaminates can arise from raw input materials, occur as residual processing agents, or form as reaction by-products. We will review strategies within product characterization to de-risk the manufacturing process, including the use of routine and high complexity assays; and the recommended testing to meet regulatory requirements for clinical submission. Learn methods to avoid costly pitfalls and implement procedures to expedite product quality decisions at critical junctures in your development plan. We will discuss two types of therapies:
Cell & Gene Therapies
Polyethylenimine (PEI) is a transfection agent used in nearly all cell and gene therapy products. We will review the regulations and the liquid chromatography with charged aerosol detection (LC-CAD) methodology to demonstrate PEI removal during the production process.
Monoclonal Antibodies (mAb) and Cell & Gene Therapies
During mAb manufacturing and inherent to Cell & Gene Therapies, a significant proportion of process impurities arise from the host cell used to express the drug. Host cell protein (HCP) impurities, present at PPM-levels, are a major immunogenicity risk because they can elicit an unpredictable immune response in patients. We will review why their complex and diverse nature makes them challenging to monitor, and theho best practices, specifically HCP identification by mass spectrometry, for detection.
Learning points:
1. Accurate detection and characterization of residual PEI in cell and gene therapy products
2. Effective detection and characterization of residual host cell proteins (HCP) in mAbs
3. Available technology and assays for quantifying process impurities
4. Current regulatory requirements for detecting, quantifying, and removing process impurities during biotherapy manufacturing
Process Impurities: Don’t Let PEI or HCP Derail Your BioTherapyMerck Life Sciences
View our webinar here: https://bit.ly/2lKNdWX
Many different impurities are present in or generated during biotherapy manufacturing. This webinar will address how process contaminates can arise from raw input materials, occur as residual processing agents, or form as reaction by-products. We will review strategies within product characterization to de-risk the manufacturing process, including the use of routine and high complexity assays; and the recommended testing to meet regulatory requirements for clinical submission. Learn methods to avoid costly pitfalls and implement procedures to expedite product quality decisions at critical junctures in your development plan. We will discuss two types of therapies:
Cell & Gene Therapies
Polyethylenimine (PEI) is a transfection agent used in nearly all cell and gene therapy products. We will review the regulations and the liquid chromatography with charged aerosol detection (LC-CAD) methodology to demonstrate PEI removal during the production process.
Monoclonal Antibodies (mAb) and Cell & Gene Therapies
During mAb manufacturing and inherent to Cell & Gene Therapies, a significant proportion of process impurities arise from the host cell used to express the drug. Host cell protein (HCP) impurities, present at PPM-levels, are a major immunogenicity risk because they can elicit an unpredictable immune response in patients. We will review why their complex and diverse nature makes them challenging to monitor, and theho best practices, specifically HCP identification by mass spectrometry, for detection.
Learning points:
1. Accurate detection and characterization of residual PEI in cell and gene therapy products
2. Effective detection and characterization of residual host cell proteins (HCP) in mAbs
3. Available technology and assays for quantifying process impurities
4. Current regulatory requirements for detecting, quantifying, and removing process impurities during biotherapy manufacturing
Next Generation Epigenetic Profiling for Environmental Health Sciences
The document discusses next generation epigenetic profiling technologies and their applications in environmental health sciences. It provides an overview of epigenetics and biology, next generation epigenetic profiling technologies like methylation arrays and sequencing, and applications in areas like nutrition, circadian rhythms, temperature stress, and small molecules. The technologies allow genome-wide analysis of epigenetic marks at higher resolution and lower cost than previous methods. This enables studying how environmental exposures may influence human health by altering epigenetic regulation of genes.
Gregg Kamilar is an experienced drug discovery chemist with over 20 years of experience in medicinal chemistry, small molecule design and synthesis. He has worked at major pharmaceutical companies including Pfizer, Vertex, and NPS Pharmaceuticals designing and synthesizing novel compounds for drug development. He has experience across many areas of medicinal chemistry including structure based drug design, heterocyclic and nucleotide synthesis, compound purification and characterization.
The document discusses various strategies for targeting protein-protein interactions (PPIs) for drug development, including small molecule inhibitors, peptides, and allosteric modulation. PPIs are important for many cellular pathways but have been challenging to target with drugs. Examples are given of peptides being developed into peptidomimetics to inhibit PPIs like integrins. Fragment-based approaches and structure-based design have also produced PPI inhibitors for targets like interleukin-2 receptor. Covalent modifiers and stabilizing allosteric sites are additional strategies discussed.
Similar to Griffen MedChemica Virtual Tox Panel (20)
MedChemica Levinthal Lecture at Openeye CUP XX 2020Ed Griffen
This document summarizes a lecture on improving medicinal and computational medicinal chemistry. It discusses defining clear target product profiles through collaboration between medicinal chemists and other experts. Navigating medicinal chemistry projects requires estimating the predicted therapeutic dose of compounds. The document outlines tactics for exploring a compound's structure-activity relationship, including introducing and modifying chiral centers. It also describes how mining past medicinal chemistry data can provide rules for modifying compounds to improve properties like solubility while maintaining potency.
Presented at Artificial Intelligence and Machine Learning for Advanced Drug Discovery & Development 2019 on 28th May 2019 by Dr Ed Griffen of MedChemica Ltd
SCI What can Big Data do for Chemistry 2017 MedChemicaEd Griffen
This document discusses how advanced analytics and big data techniques can be applied in the chemistry industry. It provides examples of how matched molecular pair analysis has been used to extract statistically valid structure-activity relationships from large datasets and summarize them in the form of transformation rules. These rules have helped suggest new molecules, explore structure-activity relationships, identify exceptional structure-property relationships, and enable the rapid optimization of drug candidates. The document argues that combining data from multiple sources yields more comprehensive rules and that interfaces must be designed with the intended users in mind.
Lecture given by Ed Griffen UKQSAR meeting Sept 2017. Covers material from work in our paper http://pubs.acs.org/doi/10.1021/acs.jmedchem.7b00935 background discussed in https://www.linkedin.com/pulse/first-draft-medicinal-chemistry-admet-encyclopedia-ed-griffen/
ESR spectroscopy in liquid food and beverages.pptxPRIYANKA PATEL
With increasing population, people need to rely on packaged food stuffs. Packaging of food materials requires the preservation of food. There are various methods for the treatment of food to preserve them and irradiation treatment of food is one of them. It is the most common and the most harmless method for the food preservation as it does not alter the necessary micronutrients of food materials. Although irradiated food doesn’t cause any harm to the human health but still the quality assessment of food is required to provide consumers with necessary information about the food. ESR spectroscopy is the most sophisticated way to investigate the quality of the food and the free radicals induced during the processing of the food. ESR spin trapping technique is useful for the detection of highly unstable radicals in the food. The antioxidant capability of liquid food and beverages in mainly performed by spin trapping technique.
ESPP presentation to EU Waste Water Network, 4th June 2024 “EU policies driving nutrient removal and recycling
and the revised UWWTD (Urban Waste Water Treatment Directive)”
Phenomics assisted breeding in crop improvementIshaGoswami9
As the population is increasing and will reach about 9 billion upto 2050. Also due to climate change, it is difficult to meet the food requirement of such a large population. Facing the challenges presented by resource shortages, climate
change, and increasing global population, crop yield and quality need to be improved in a sustainable way over the coming decades. Genetic improvement by breeding is the best way to increase crop productivity. With the rapid progression of functional
genomics, an increasing number of crop genomes have been sequenced and dozens of genes influencing key agronomic traits have been identified. However, current genome sequence information has not been adequately exploited for understanding
the complex characteristics of multiple gene, owing to a lack of crop phenotypic data. Efficient, automatic, and accurate technologies and platforms that can capture phenotypic data that can
be linked to genomics information for crop improvement at all growth stages have become as important as genotyping. Thus,
high-throughput phenotyping has become the major bottleneck restricting crop breeding. Plant phenomics has been defined as the high-throughput, accurate acquisition and analysis of multi-dimensional phenotypes
during crop growing stages at the organism level, including the cell, tissue, organ, individual plant, plot, and field levels. With the rapid development of novel sensors, imaging technology,
and analysis methods, numerous infrastructure platforms have been developed for phenotyping.
The technology uses reclaimed CO₂ as the dyeing medium in a closed loop process. When pressurized, CO₂ becomes supercritical (SC-CO₂). In this state CO₂ has a very high solvent power, allowing the dye to dissolve easily.
Unlocking the mysteries of reproduction: Exploring fecundity and gonadosomati...AbdullaAlAsif1
The pygmy halfbeak Dermogenys colletei, is known for its viviparous nature, this presents an intriguing case of relatively low fecundity, raising questions about potential compensatory reproductive strategies employed by this species. Our study delves into the examination of fecundity and the Gonadosomatic Index (GSI) in the Pygmy Halfbeak, D. colletei (Meisner, 2001), an intriguing viviparous fish indigenous to Sarawak, Borneo. We hypothesize that the Pygmy halfbeak, D. colletei, may exhibit unique reproductive adaptations to offset its low fecundity, thus enhancing its survival and fitness. To address this, we conducted a comprehensive study utilizing 28 mature female specimens of D. colletei, carefully measuring fecundity and GSI to shed light on the reproductive adaptations of this species. Our findings reveal that D. colletei indeed exhibits low fecundity, with a mean of 16.76 ± 2.01, and a mean GSI of 12.83 ± 1.27, providing crucial insights into the reproductive mechanisms at play in this species. These results underscore the existence of unique reproductive strategies in D. colletei, enabling its adaptation and persistence in Borneo's diverse aquatic ecosystems, and call for further ecological research to elucidate these mechanisms. This study lends to a better understanding of viviparous fish in Borneo and contributes to the broader field of aquatic ecology, enhancing our knowledge of species adaptations to unique ecological challenges.
The binding of cosmological structures by massless topological defectsSérgio Sacani
Assuming spherical symmetry and weak field, it is shown that if one solves the Poisson equation or the Einstein field
equations sourced by a topological defect, i.e. a singularity of a very specific form, the result is a localized gravitational
field capable of driving flat rotation (i.e. Keplerian circular orbits at a constant speed for all radii) of test masses on a thin
spherical shell without any underlying mass. Moreover, a large-scale structure which exploits this solution by assembling
concentrically a number of such topological defects can establish a flat stellar or galactic rotation curve, and can also deflect
light in the same manner as an equipotential (isothermal) sphere. Thus, the need for dark matter or modified gravity theory is
mitigated, at least in part.
hematic appreciation test is a psychological assessment tool used to measure an individual's appreciation and understanding of specific themes or topics. This test helps to evaluate an individual's ability to connect different ideas and concepts within a given theme, as well as their overall comprehension and interpretation skills. The results of the test can provide valuable insights into an individual's cognitive abilities, creativity, and critical thinking skills
THEMATIC APPERCEPTION TEST(TAT) cognitive abilities, creativity, and critic...
Griffen MedChemica Virtual Tox Panel
1. Bowes J., et al. Reducing safety-related drug attrition: the use of in vitro pharmacological profiling.
Nature Reviews Drug Discovery 2012;11:909–22.
Number in training set 4585 3106 2457
Median difference with/without feature (DpIC50) 0.35 -0.1 0
Cohan’s d 0.4 -0.26 0.02
Explainable AI
MedChemica
Virtual Toxicity Panel Screens to aid the Medicinal Chemist
A. G. Dossetter•, E. Griffen•, A. Leach•+, A. Lin‡, J. Stacey†, L. Reid§, S. Montague•.
•Medchemica Ltd, Macclesfield, UK, + Pharmacy and Biomolecular Sciences, Liverpool John Moores University, †Information School, University of Sheffield,
‡Laboratory of Chemoinformatics, Faculty of Chemistry, University of Strasbourg,
§Bioinformatics Institute (A*STAR), 30 Biopolis Street, Matrix, Singapore 138671
Problem
Unforeseen toxicity via secondary pharmacology is a significant risk and when encountered late in a
discovery project’s life creates major issues and may even terminate it.
Chemists need to be alerted to potential risks but to be influenced they must be able to audit the reasons
and evidence for the alerts.
Solution
Build transparent models of critical toxicity targets
and communicate results in chemical structures
rather than just numbers. This is an example of
‘Explainable AI’ for chemists
contact@medchemica.com
Learning
• Models must be transparent and show structures to influence chemists
• Random Forest models with the correct descriptors can be used to show important features as pharmacophores and the evidence supporting them
• Error models can given a measure of confidence to predictions beyond use of an RMSE.
Chemists won’t make decisions without understanding
Language of medicinal chemists = structures / clear pharmacophores
Machine Learning method Description
MMPA transformations Example pairs
kNN + Morgan fp Structures of Nearest Neighbours
Random Forest + pharmacophore fp Compound highlighted with
important features
Graph analytics Connections between
compound families
Graph Convolutional Neural
Network (GCNN)
Graph node feature importance
– a work in progress
Aspects of Models
Pay attention to Feature Engineering
Clear definitions enables identifying key features
Transparency
Scientific
Sense
Consistency
Parsimony
Applicability
Performance
Modeler’s
domain
Chemist’s
domain
Interpretable
Failure cost high
Immature science
Highly skilled, critical users
Business-2-Business
Transparent and auditable
Black Box
Failure cost is low
Real time response critical
Interactive = self correcting
Business-2-consumer
User agnostic of process
Trying to explain black box models, rather than creating models that are
interpretable in the first place, is likely to perpetuate bad practice and can
potentially cause great harm to society. The way forward is to design
models that are inherently interpretable.
- Cynthia Rudin Nature Machine Intelligence (2019), 206–215.
Approach Application
Advanced Pharmacophore Features
Feature Definition
Basic Group Atom or group most likely protonated at pH 7.4
Acidic Group Atom or group most likely deprotonated at pH 7.4,
includes N and C acids
Acceptor Definitions derived from Taylor & Cosgrove
Donor Definitions derived from Taylor & Cosgrove
Hydrophobic C4 or greater cyclic or acyclic alkyl group
Aromatic Attachment connection of any group to an aromatic atom excluding
connections within rings
Aliphatic Attachment connection of any atom to an aliphatic group not in a ring.
Halo F,Cl, Br, I
Gobbi, A.; Poppinger, D. Biotechnology and Bioengineering 1998, 61 (1), 47–54.
Reutlinger, M.; Koch, C. P.; Reker, D.; Todoroff, N.; Schneider, P.; Rodrigues, T.; Schneider, G. Mol. Inf. 2013, 32 (2), 133–138.
Taylor, R.; Cole, J. C.; Cosgrove, D. A.; Gardiner, E. J.; Gillet, V. J.; Korb, O. J Comput Aided Mol Des 2012, 26 (4), 451–472.
Acid & Base definitions are SMARTS including C, N, heteroaromatic acids, bases excluding weak aniline bases, including amidines, guanidine’s - MedChemica
definitions.
Simple
H bond
acceptor
base
acid
Precise
Diclofenac
(1973)
Sulfadiazine
(1941)
Pharmacophore Pairs
• Feature 1 – topological distance - Feature 2
• Engineered for chemical relevance – pairs can
be superimposed or directly linked, e.g.
enables a group to be both a hydrogen bond
acceptor and a base
• Used as unfolded 280 bit fingerprints
• A bit identifies a pharmacophore pair e.g. :
Aromatic - 3 bonds - Base
• Random Forest feature importance and Cohan’s d for effect size allow identification of critical features in models
• Highlight atoms by S Feature Importance coloured by direction of Cohan’s d
• Show statistics on the effect and variance of each feature
• Drill back to precise features and original compounds with data supporting that feature – complete transparency
Cardiac toxicity and Seizure are key toxicological risks
Cardiac
hERG ion channel inhibitor
NaV 1.5 channel inhibitor
Ca L type channel inhibitor
Ca T-type channel inhibitor
PDE 3A inhibitor
Seizure
Dopamine D1 receptor ant/ag
Dopamine D2 receptor ant/ag
Cannabinoid CB1 receptor ant/ag
Acetylcholine a1b2 receptor
agonist / antagonists
µ opioid agonist / antagonists
k opioid agonist
d opioid agonist/ antagonists
Muscarinic M1 receptor ant/ag
Muscarinic M2 receptor ant/ag
Seizure
5HT 1A receptor antagonists
5HT 1B receptor antagonists
5HT receptor antagonists 2A
GABA a1 antagonist
NMDA-NR1 agonist
5HT Transporter inhibitor
Dopamine Transporter inhib
Noradrenaline Transporter inh
Acetylcholine esterase
inhibitor
Monoamine oxidase inhibitor
PDE 4D inhibitor
Model ‘quality’, Error models and Domain of applicability
• Build models with 10 fold CV – report CV-Pearson’s R2 and CV RMSE
• Build a Random Forest error model to generate predicted error for each compound
• Error model can be used to flag compounds out of Domain of Applicability
hERG n=5968, RMSE = 0.16, CV Pearson’s R2 = 0.27
CHEMBL12713 sertindole,
prediction pIC50 7.8 [7.1 – 8.4], actual 8.2
.
Predictions and Transparency
Medicinal Chemistry
Seizure Models – RF and kNN
Dopamine
Transporter
Norepinephrine
Transporter
5HT1a
receptor
GABA-A
receptor
d Opioid
receptor
MAO-A
inhibitor
AChE
inhibitor
Training set
size
1712 1757 400 1526 1070 1684 3283
CV-R2 0.28 0.23 0.37 0.24 0.28 0.21 0.32
RMSE 0.13 0.18 0.21 0.29 0.18 0.29 0.16
Best Random Forest based models for seizure endpoints,
All the seizure data sets delivered kNN models based on Morgan fingerprints
hERG Example