Publications & Presentations

In this section we post selections of work that the Optibrium team and others have presented or published. 

Transferable machine learning interatomic potential for bond dissociation energy prediction of drug-like molecules

This paper describes a new machine learning method which increases the computational efficiency of predicting Cytochrome P450 sites of metabolism. Read More

Predicting routes of Phase I and II metabolism based on quantum mechanics and machine learning

This paper describes a new method to determine the most likely experimentally-observed routes of metabolism and metabolites based on our WhichP450, regioselectivity and new WhichEnzyme model. Read More

Predicting Regioselectivity of Cytosolic SULT Metabolism for Drugs

This paper describes a model to predict whether a particular site on a molecule will be metabolised by cytosolic sulfotransferase enzymes (SULTs). Read More

Predicting Reactivity to Drug Metabolism: Beyond CYPs

This poster describes new models to predict whether a particular site on a molecule will be metabolised by key enzymes involved in phase I and II metabolism, including aldehyde oxidases (AOs), flavin-containing monooxygenases (FMOs) and uridine 5′-diphospho-glucuronosyl-transferases (UGTs). Read More

Application of the Alchemite deep-learning methodology to categorical modelling of PK endpoints – ACS National Meeting, 2023

Presentation slides on the Application of the Alchemite deep-learning methodology to categorical modelling of PK endpoints.Charlotte ... Read More

Reaction Based Enumeration: Lessons learned in designing a workflow that chemists want to use – ACS National Meeting, 2023

Presentation slides on Reaction based enumeration: Lessons learned in designing a workflow that chemists want to use.Tamsin Mansley ... Read More

A Distributional Model of Bound Ligand Conformational Strain: From Small Molecules up to Large Peptidic Macrocycles

In this J. Med. Chem. article, written in collaboration with Merck, our xGen method is validated on a set of ~3000 protein-ligand complexes. With this distributional model, strain estimates are consistently lower and better correlated with ligand efficiency than when using classically-modelled ligand coordinates. Read More

Predicting Regioselectivity of AO, CYP, FMO and UGT Metabolism Using Quantum Mechanical Simulations and Machine Learning

This paper describes the prediction of the regioselectivity of metabolism by AOs, FMOs and UGTs for humans and CYPs for three preclinical species. The research extends from previous work developing the StarDrop™ P450 module. Visit the P450 webpage to discover how StarDrop can help you model metabolism. Read More

Prediction of In Vivo Pharmacokinetic Parameters and Time–Exposure Curves in Rats Using Machine Learning from the Chemical Structure

This article is a collaboration with Intellegens, the University of Cambridge and AstraZeneca. It provides a proof-of-concept study in which Cerella™ is used to predict rat in vivo pharmacokinetic (PK) parameters and concentration–time PK profiles. Read More

Imputation of sensory properties using deep learning – ACS Spring 22

Presentation slides on the imputation of sensory properties. Dmitriy Chekmarev (IFF) and Samar Mahmoud (Optibrium) gave this talk on ... Read More

Synergy and Complementarity between Focused Machine Learning and Physics-Based Simulation in Affinity Prediction

This article, in collaboration with Stephen Johnson at BMS, demonstrates how the QuanSA method is complementary to FEP+, demonstrating improvements in ranking and pKi when a combined approach is used for affinity prediction. Read More

Experimental Validation of Predictive Models in a Series of Novel Antimalarials

This article outlines an open drug discovery competition. Optibrium, in collaboration with Intellegens, developed potential anti-malarials by combining our Cerella™ technology and StarDrop™ drug discovery software. We achieved second place with a compound flagged by Cerella. An unusual compound structure, our entry would not have been considered by human scientists alone. Read More

Imputation of Sensory Properties Using Deep Learning

In this article, the team applies Cerella™'s deep learning imputation methods to physicochemical and sensory data. They compare the results with those from traditional QSAR models, demonstrating significantly improved accuracy using Cerella's methods. Read More

Deep Imputation on Large-Scale Drug Discovery Data

This article outlines the deep learning imputation methods underpinning our Cerella platform, applied to large data sets. It demonstrates significant improvements over commonplace quantitative structure-activity relationship (QSAR) machine learning models Read More

Conformational Strain of Macrocyclic Peptides in Ligand–Receptor Complexes Based on Advanced Refinement of Bound-State Conformers

In collaboration with Merck, we show how the xGen method can be used to refine bound-state conformations of macrocyclic peptide cocrystal structures by building conformational ensembles that are low-energy and fit experimental electron density, providing better guidance for ligand design. Read More

XGen: Real-Space Fitting of Complex Ligand Conformational Ensembles to X‐ray Electron Density Maps

This J. Med. Chem. article is the first report of our xGen methodology, developed in collaboration with Merck. It enables X-ray density ligand fitting and refinement that is suitable for a wide variety of small-molecule ligands, including macrocycles. Read More

Predicting Reactivity to Drug Metabolism: Beyond P450s – Modelling FMOs and UGTs

In this work, the team builds models to calculate the activation energy of the rate-limiting steps for FMO oxidation and UGT glucuronidation at potential sites of metabolism on a compound, validated with experimental data. Read More

Practical Applications of Deep Learning to Impute Heterogeneous Drug Discovery Data

This paper describes Alchemite™, the cutting-edge deep learning method underpinning our Cerella platform, and its success in making predictions even faced with sparse, noisy data. Read More

Structure-Based and Ligand-Based Virtual Screening on DUD-E+: Performance Dependence on Approximations to the Binding-Pocket

Using the DUD-E+ benchmark, we explore the impact of using a single protein pocket or ligand for virtual screening compared with using ensembles of alternative pockets, ligands, and sets thereof. A hybrid approach combining ensemble docking with eSim-based screening produced the best and most consistent performance. Read More

Predicting pKa Using a Combination of Quantum Mechanical and Machine Learning Methods

This study aimed to create a model to predict the propensity of a molecule to lose or gain a proton in water, using a semi-empirical quantum mechanics (QM) approach combined with machine learning (ML). Read More

Electrostatic-field and surface-shape similarity for virtual screening and pose prediction

In collaboration with BMS, we introduce the eSim method for rapid computation of 3D molecular similarity. It combines electrostatic field comparison with comparison of molecular surface-shape and directional hydrogen-bonding preferences. Read More

Practical Applications of Deep Learning to Imputation of Drug Discovery Data

Presented by Ben Irwin, on 28 August 2019 at the ACS National Meeting and Exposition in San Diego, USA Presentation Overview Problems ... Read More

N- and S-Oxidation Model of the Flavin-containing Monooxygenases

This poster was presented at the Eighth Joint Sheffield Conference on Chemoinformatics; 17-19 June 2019 Peter Walton, Mario Öeren, ... Read More

Complex macrocycle exploration: Parallel, heuristic, and constraint-based conformer generation using ForceGen

This study, in collaboration with Merck, demonstrates the application of ForceGen, particularly to a large benchmarking set of macrocycles, generating fast, accurate conformers. Read More

Imputation of Assay Bioactivity Data using Deep Learning

In this study, the team applied a deep learning neural network (the foundations of our Cerella platform) to impute assay pIC50 values. It was shown to outperform other approaches such as traditional QSAR models, and provide predictions with excellent accuracy. Read More

Bigfoot, the Loch Ness Monster, and Halogen Bonds

At the 2018 Streamlining Drug Discovery Symposium in San Diego, David Lawson treated us to this illuminating presentation entitled ... Read More

A Novel Scoring Profile for the Design of Antibacterials Active Against Gram-Negative Bacteria

At the 2nd SCI/RSC Symposium on Antimicrobial Drug Discovery, 12-13 November 2018, Bailey Montefiore, Optibrium - Franca Klingler, ... Read More

Imputation of Protein Activity Data Using Deep Learning

At the US Symposia, Streamlining Drug Discovery 2018 in Cambridge MA, Matthew Segall from Optibrium and Tom Whitehead from Intellegens ... Read More

WaterSwap to Assess Target Druggability

At the 2018 Streamlining Drug Discovery Symposium in San Diego and San Francisco, Adam Kallel gave an insightful presentation on ... Read More

Using AI to Improve the Safety of New Drug Candidates

On 18 October 2018, at the Streamlining Drug Discovery Symposium in Cambridge MA, Nigel Greene gave this fascinating presentation on ... Read More

Hydrogen Bonding: Ab Initio Accuracy From Fast Interatomic Gaussian Approximation Potentials

Mario Öeren gave this presentation at the ACS Fall 2018 National Meeting & Exposition held in Boston, USA. Abstract Non-covalent, ... Read More

Quantitative Surface Field Analysis: Learning Causal Models to Predict Ligand Binding Affinity and Pose

This article introduces our QuanSA method for inducing physically meaningful field-based models of ligand binding pockets based on structure-activity data alone. Read More

Library Design for Collaborative Drug Discovery: Expanding Druggable Chemogenomic Space

Dr Kazuyoshi Ikeda, Keio University, gave this presentation at the "Streamlining Drug Discovery" symposium held in Tokyo, Japan on 5 ... Read More

Robotic Drug Discovery: An Automated Design and Synthesis System to Boost SAR Investigations

Dr Tsukasa Ishihara, National Institute of Advanced Industrial Science and Technology (AIST), gave this presentation at the ... Read More

Genetic Toxicology: Progress on International Test Guidelines and New Methods

Dr Yan Chang, National Shanghai Center for New Drug Safety Evaluation and Research, gave this presentation at the "Streamlining Drug ... Read More

Theoretical Studies of G-Protein-Coupled Receptors

Dr Xianqiang Sun, Guangzhou Medical University/ Wuxi Apptec, gave this presentation at the "Streamlining Drug Discovery" symposium ... Read More

In Silico Approaches in Genetic Toxicology: Progress and Future

Dr Masamitsu Honma, National Institute of Health Science, gave this presentation at the "Streamlining Drug Discovery" symposium held ... Read More

A Practical View of Structure Activity Relationship (SAR) Analysis in Novartis Shanghai

Dr Zhengtian Yu and Dr Sean Xiao, Novartis, gave this presentation at the "Streamlining Drug Discovery" symposium held in Shanghai, ... Read More

Poster: Intuitive Workflow to Enumerate and Explore Large Virtual Libraries

This poster by Matthew D Segall, Aishling Cooke, James Chisholm, Edmund Champness, Peter Hunt and Tamsin Mansley was presented at the ... Read More

Translating Methods from Pharma to Fragrances and Flavours

Tamsin Mansley gave this presentation at the ACS National Spring Meeting 2018 in New Orleans. Abstract The pharma sector has generated ... Read More

Deep Learning and Chemistry

At our 2018 Drug Discovery Consultants' Day, Professor Bobby Glen of the University of Cambridge gave an excellent overview of ... Read More

Imputation of Protein Activity Data using Deep Learning Presentation 2

At Optibrium's 2018 Drug Discovery Consultants' Day, Dr Gareth Conduit from University of Cambridge and Intellegens Ltd. described ... Read More

Pistoia Alliance AI/Deep Learning Projects and Community

At our Drug Discovery Consultants' Day in March 2018, Nick Lynch gave an overview of the Pistoia Alliances' projects and community on ... Read More

WhichP450: a multi-class categorical model

This paper describes the underlying methods and validation of a model predicting the most likely Cytochrome P450 isoforms responsible for metabolism of a compound. The model makes up part of StarDrop's P450 module. Read More

Poster: Closing the loop between synthesis and design: Balancing optimisation of potency with selectivity

This poster by Peter Hunt, Tamsin Mansley, Edmund Champness, Nicholas Foster & Matthew Segall was presented at the ACS Fall 2017 ... Read More

Integrated Cheminformatics to Guide Drug Discovery

Ed Champness gave this presentation at the ACS Fall 2017 National Meeting & Exposition held in Washington DC, USA. Abstract A ... Read More

Poster: Supporting Compound Optimisation in Not-for-Profit and Academic Research

This poster by Matthew Segall1, Tamsin Mansley1, Peter Hunt1, Kelly Chibale2, Tanya Paquet2, James Duffy3 was presented at the RSC ... Read More

Improved quantum mechanical model of P450-mediated aromatic oxidation

Rasmus Leth gave this presentation at the ACS Fall 2017 National Meeting & Exposition held in Washington DC, USA. Abstract The ... Read More

Continuing the public benefit of the Carcinogenic Potency Database (CPDB)

Dr Nik Marchetti, Lhasa Ltd, gave this presentation at "Streamlining Drug Discovery" symposium held in Cambridge UK on 18 May ... Read More

Docking – old hat or hats off

Dr Christian Lemmen, BioSolveIT, gave this presentation at the "Streamlining Drug Discovery" symposiums held in San Diego, CA, USA on ... Read More

Resolving the question of on- or off-target toxicity – a case study

Dr Joachim Rudolph, Genentech, gave this presentation at "Streamlining Drug Discovery" symposium held in San Diego, AA, USA on 21 ... Read More

Lead Identification: Where Science Meets Art

Dr Mehran Jalaie, Pfizer, gave this presentation at "Streamlining Drug Discovery" symposium held in San Diego, CA, USA on 21 April ... Read More

Data visualization: Saying it all in a bite-sized chunk

Ed Champness gave this presentation at the ACS Spring 2017 National Meeting & Exposition held in San Diego, USA. Abstract We often ... Read More

Confidently Targeting High Quality Hits from High-Throughput Screening

Matt Segall gave this presentation at the ACS Spring 2017 National Meeting & Exposition held in San Diego, USA. Abstract When ... Read More

Poster: 3D Modelling for the Masses: A Universal Interface for Easy Access to Expertly Prepared 3D Models

This poster by Fayzan Ahmed, Tamsin Mansley, Chris Leeding, Edmund Champness, Peter Hunt & Matthew Segall was presented at the ACS ... Read More

Combining quantum and QSAR methods for prediction of acid dissociation constants

Layla Hosseini-Gerami1,2, Rasmus Leth1, Peter Hunt1, Matthew Segall1. 1 Optibrium Limited, Cambridge, UK2 University of Leeds, Leeds, ... Read More

ForceGen 3D structure and conformer generation: From small lead-like molecules to macrocyclic drugs

Here, we introduce the ForceGen method for 3D structure generation and conformational elaboration, which does not rely on distance geometry, precalculated molecular templates, or stochastic sampling. Read More

Poster: BSEP, MRP, AND DILI… Just a bad hand at Scrabble?

This poster was presented by Nick Foster at the 11th International ISSX Meeting, Busan, Korea in June 2016 Abstract Cholestatic ... Read More

Practical Applications of Matched Series Analysis

This paper explores applications of Matched Series Analysis within StarDrop's Nova module to SAR transfer, binding mode suggestion, and data point validation. Read More

Avoiding Missed Opportunities by Analysing the Sensitivity of our Decisions

This peer-reviewed article describes how identifying sensitive criteria can highlight new avenues for exploration, and assist us in avoiding missed opportunities. Read More

Predicting interactions of compounds and metabolites with toxicity-associated targets

Peter Hunt gave this presentation at the ACS Fall 2016 National Meeting & Exposition held in Philadelphia, USA. Abstract We ... Read More

Predicting Regioselectivity and Lability of P450 Metabolism

This article describes the underlying methods, validation and example applications of the most recent models of Cytochrome P450 ... Read More

Medicinal Chemistry is an art, when you don’t understand the data

Dr Jeremy Edmunds, Abbvie, gave this presentation at "Streamlining Drug Discovery and Development" held in Cambridge, MA, USA on 11 ... Read More

TB Alliance Drug Discovery and Development: Harnessing Global Resources to Address a Global Disease

Dr Chris Cooper, TB Alliance, gave this presentation at "Streamlining Drug Discovery and Development" held in San Francisco, CA, USA ... Read More

Structure Guided Design and Optimization of Selective Kinase Inhibitors from Fragment Starting Points

Dr Steve Woodhead, Takeda, gave this presentation at "Streamlining Drug Discovery and Development" held in San Francisco, CA, USA on ... Read More

Cheminformatics from the end-user perspective: Past, present and future

Dr Paul Greenspan, Takeda, gave this presentation at "Streamlining Drug Discovery and Development" held in Cambridge, MA, USA on 11 ... Read More

User-friendly Database Querying for Decision-Making in Drug Discovery

This poster was presented by Chris Leeding, Ed Champness, Chris Mills*, Andrew Lemon*, Ashley Fenwick$ and Matt Segall at BioIT World ... Read More

Bridging the dimensions: Seamless integration of 3D structure-based design and 2D structure-activity relationships to guide medicinal chemistry

Matt Segall gave this presentation at the ACS Spring National Meeting & Exposition held in San Diego, USA on 13 March ... Read More

Gaussian processes: We demand rigorously defined areas of uncertainty and doubt

Ed Champness gave this presentation at the ACS Spring National Meeting & Exposition held in San Diego, USA on 16th April ... Read More

Closing the Loop Between Synthesis and Design

Tamsin Mansley gave this presentation at the ACS Spring National Meeting & Exposition held in San Diego, USA on 13th March ... Read More

Extrapolative prediction using physically-based QSAR

This study demonstrates the application of the Surflex-QMOD method for 3D-QSAR on a large, diverse public data set, showcasing recent algorithmic and workflow enhancements to improve the generated models. Read More

When Two are not Enough: Lead optimisation beyond matched pairs

This article, co-authored with Noel O'Boyle and Roger Sayle of Optibrium NextMove Software, was published in Drug Discovery World. It ... Read More

Data visualization: New directions or just familiar routes?

Ed Champness gave this presentation at the ACS Fall 2015 National Meeting & Exposition held in Boston, USA on 19th August ... Read More

Modeling ABC transporters as potential DILI targets

Matt Segall gave this presentation at the ACS Fall 2015 National Meeting & Exposition held in Boston, USA on 16th August ... Read More

Webinar: Quantum mechanical models of P450 metabolism

Read the presentation "Quantum mechanical models of P450 metabolism to guide optimization of metabolic stability" from the Webinar on ... Read More

Knowledge-Guided Docking: Accurate Prospective Prediction of Bound Configurations of Novel Ligands using Surflex-Dock

This study presents a new benchmarking data set for assessing pose prediction using molecular docking called PINC. It also presents new approaches within Surflex Dock that use structural information known prior to a particular cutoff-date to make predictions on ligands whose bounds structures were determined later, showing excellent results. Read More

The Challenges of Making Decisions Using Uncertain Data

This paper discusses the challenges of using uncertain experimental data to make confident decisions on the selection of compounds. Read More

Analyzing Selectivity Through Multi-dimensional Activity Cliff Analysis

Dr Tim Cheeseright, Cresset, gave this presentation at the "Guiding Optimal Compound Design and Development Symposium" held in ... Read More

Understanding Compound Quality

Dr Paul Leeson, Paul Leeson Consulting Ltd, gave this presentation at the "Guiding Optimal Compound Design and Development Symposium" ... Read More

Predicting Adverse Drug Reactions: What Works and What Doesn’t

Dr Nigel Green, Pfizer, gave this presentation at the "Guiding Optimal Compound Design and Development Symposium" held in Cambridge, ... Read More

Modeling of Chemical and Physical Stability of Pharmaceuticals

Dr Yuriy Abramov, Pfizer, gave this presentation at the "Guiding Optimal Compound Design and Development Symposium" held in Cambridge, ... Read More

Predicting Metabolites – Enhancing an Expert System with Machine Learning

Dr Christopher Barber, Lhasa Limited, gave this presentation at the "Guiding Optimal Compound Design and Development Symposium" held ... Read More

Development of a Drug Discovery Simulation Laboratory Exercise in the Pharmaceutical Sciences Graduate Program Curriculum

Dr Chase Smith, Massachusetts College of Pharmacy and Health Sciences, gave this presentation at the "Guiding Optimal Compound Design ... Read More

Improving the Plausibility of Success in Drug Discovery with the Use of Inefficient Metrics

Dr Mike Shultz,Novartis, gave this presentation at the "Guiding Optimal Compound Design and Development Symposium" held in Cambridge, ... Read More

Practical Application of Multi-Parameter Optimization to Guide Successful Drug Discovery

Dr Matt Segall, Optibrium, gave this presentation at the "Guiding Optimal Compound Design and Development Symposium" held in ... Read More

Development of a Structure Generator to Explore a Target Area on Chemical Spaces

Dr Kimita Funatsu gave this presentation at the International Symposium on Compound Design Technologies held in Tokyo and Osaka, Japan ... Read More

Knowledge-based Small Molecule and Antibody Design Strategies

Mark Swindells gave this presentation at the International Symposium on Compound Design Technologies held in Tokyo and Osaka, Japan on ... Read More

Quantum mechanical models of P450 metabolism to guide optimization of metabolic stability Presentation

Matt gave this presentation at "Drug Discovery USA 2015 - Advances in Drug Discovery and Design" Abstract In this presentation we will ... Read More

Breaking Free from Chemical Spreadsheets

This article explores the benefits of a more intuitive and flexible approach to viewing and interacting with drug discovery data, the ... Read More

Poster: Predicting Regioselectivity and Lability of Cytochrome P450 Metabolism using Quantum Mechanical Simulations

Jon Tyzack presented this poster at the joint ISSX/JSSX North America meeting in October 2014. Abstract: Optibrium™, as part of the ... Read More

Beyond Matched Pairs

Noel O'Boyle of NextMove Software gave this presentation "Beyond Matched Pairs: Using matched series for activity prediction" at our ... Read More

Structure-based drug discovery in Shanghai Hengrui

Dr Qiyue (Jerry) Hu gave this presentation at the International Symposium on Compound Design Technologies held in Shanghai, China on ... Read More

Integrated predictive ADME tools for optimising exposure and safety in drug discovery and development

Dr Jianling Wang gave this presentation at the International Symposium on Compound Design Technologies held in Shanghai, China on 21 ... Read More

Chemical and Protein Structural Basis for Biological Crosstalk Between PPAR-alpha and COX Enzymes

Here we present an analysis of novel drug/target predictions, focusing on those that were not obvious based on known pharmacological crosstalk. We show how protein structural information can be exploited to bolster predictions of polypharmacology from ligand-based computations. Read More

Visualising Structured Compound Data in an Unstructured Way

This Poster was presented at the ACS Fall 2014 National Meeting & Exposition held in San Francisco, USA on 12th August ... Read More

Advances in Multi-parameter Optimisation Methods for de Novo Drug Design

This review article discusses recent developments in the methods and opinions around multi-parameter optimisation, focusing on applications to de novo drug design and illustrated with published examples. Read More

Predictive Application of Bioisostere Transformations to Identify Novel High Quality Compound Ideas

Ed Champness gave this presentation at the ACS Spring 2014 National Meeting & Exposition held in Dallas, USA on 17th March ... Read More

Advances in Multi-Parameter Optimisation: Targeting the ‘best’ profile for your project’s objectives

Ed Champness gave this presentation at the ACS Spring 2014 National Meeting & Exposition held in Dallas, USA on 16th March ... Read More

The Significance of Protein Structure Data Set Choices for in-silico Drug Discovery: Design of BACE1 Inhibitors

Dr Yoshio Hamada gave this presentation at the International Symposium on Compound Design Technologies held in Tokyo and Osaka, Japan ... Read More

New, Transparent, Statistical Approaches to Toxicity Prediction

Thierry Hanser gave this presentation at the International Symposium on Compound Design Technologies held in Tokyo and Osaka, Japan on ... Read More

Linear Expression by Representative Energy Terms: A Novel QSAR Procedure Using Theoretical Computations on Protein-Ligand Complexes

Dr Hiroshi Chuman gave this presentation at the International Symposium on Compound Design Technologies held in Tokyo and Osaka, Japan ... Read More

ChEMBL an Open Data Resource of Medicinal Chemistry and Patent Data

John Overington gave this presentation at the International Symposium on Compound Design Technologies held in Tokyo and Osaka, Japan ... Read More

Finding and Applying Multi-Parameter Rules to Guide Successful Drug Discovery

Matt Segall gave this presentation at the International Symposium on Compound Design Technologies held in Tokyo and Osaka, Japan on 19 ... Read More

Finding the Rules for Successful Drug Optimisation

In this drug optimisation article, coauthored with Pfizer we discuss new 'rule induction' methods. Read More

A structure-guided approach for protein pocket modeling and affinity prediction

We present a hybrid structure-guided strategy that combines molecular similarity, docking, and multiple-instance learning such that information from protein structures can be used to inform models of structure–activity relationships. Read More

Addressing Toxicity Risk when Designing and Selecting Compounds in Early Drug Discovery

In this article, we discuss the application of expert knowledge-based predictions of toxicity. We highlight how they can be used with MPO... Read More

Protein Function Annotation By Local Binding Site Surface Similarity

This study presents some updates to the Surflex-PSIM method, validated on apo/holo cognate protein pairs. The method now supports fully automatic binding site detection and is fast enough to screen comprehensive databases of protein binding sites. Read More

Implementation of multi-criteria decision making (MCDM) tools in early drug discovery processes

Marie Ledecq from UCB Pharma gave this presentation at the ACS National Spring Meeting 2013. Abstract The current trend in medicinal ... Read More

Exploring the chemical space of screening results

Ed Champness gave this presentation at the ACS National Spring Meeting 2013. Abstract When faced with the results from a screening ... Read More

Finding Multi-parameter Rules for Successful Optimization

Matt gave this presentation at the ACS National Spring Meeting 2013 in New Orleans. Abstract Multi-parameter optimization (MPO) is ... Read More

Protein-Protein Interactions and Inhibitors

Alan Naylor led a stimulating discussion on drug discovery targeting inhibition of protein-protein interactions at our 2012 Drug ... Read More

QSAR Modelling of HLM Stability

This talk was presented by Dr Alexey Zakharov at the American Chemical Society 2012 Fall Meeting in Philadelphia. Abstract The most ... Read More

Preprint: Considering the Impact of ‘Drug-like’ Properties on the Chance of Success

In the paper we review the strengths and weaknesses of these different definitions of 'drug-like' properties and measures of 'drug-likeness.' Read More

Iterative Refinement of a Binding Pocket Model: Active Computational Steering of Lead Optimization

This study demonstrates the application of Surflex-QMOD, a computational approach for binding affinity prediction, to an iterative, temporal lead optimisation exercise. Read More

Comprehensive comparison of automatically generated QSAR models of target potency

Matt gave this presentation at the ACS National Spring Meeting 2012. Abstract Automatic QSAR model building methods are now readily ... Read More

Can We Really Do Computer-aided Drug Design?

Matt gave this presentation at the ACS National Spring Meeting 2012. Abstract We will explore the accuracy of current computational ... Read More

Relative Drug Likelihood: Going Beyond Drug-Likeness

Matt gave this presentation at the ACS National Fall Meeting 2012. Abstract Many approaches have been used to characterise compounds ... Read More

Overcoming Psychological Barriers to Good Decision-making in Drug Discovery

Matt gave this presentation at the Keystone Symposium, Addressing the Challenges of Drug Discovery 2011. Abstract Better individual ... Read More

Does Your Model Weigh the Same as a Duck?

This article discusses some of the pitfalls of computer-aided drug design, such as confirmation bias, in the context of off-target predictive modeling, QSAR, molecular similarity computations, and docking. Examples are shown that avoid such problems. Read More

Chemical Structural Novelty: On-Targets and Off-Targets

This study presents s framework for combining multiple similarity computations, along with its systematic application to 358 drugs with overlapping pharmacology. Read More

Applying Med Chem Transformations and Multi-Parameter Optimisation

This article on applying med chem transformations and multi-parameter optimisation describes the concepts and algorithms underlying StarDrop’s Nova module.  Read More

Multi-parameter Optimisation in Drug Discovery

Matt Segall, Optibrium's CEO, gave a presentation on Multi-parameter Optimisation in Drug Discovery at ELRIG Drug Discovery.Abstract A ... Read More

Multi-Parameter Optimisation Review Article

In this review, we survey the range of methods used for MPO in drug discovery, compare their strengths and weaknesses and present some example applications. Read More

Guided Application of Med Chem Rules to Generate ‘Good’ Ideas

Matt gave this presentation at the ACS Spring meeting 2011 in Anaheim. Abstract Computational tools can guide the selection of high ... Read More

Making Priors a Priority Presentation

Matt gave this presentation at the ACS Spring meeting 2011 in Anaheim. Abstract When we build a predictive model of a drug property we ... Read More

Making Priors a Priority Publication

This article discusses the importance of ‘priors’ in assessing models in different contexts, covering a critical issue that the community needs to address address in order to use the predictive models that we build to the greatest effect. Read More

Poster: Guiding Focused Design of Potent Leads with Improved Metabolic Stability

Matt presented this poster at ISSX in September 2010. Abstract: A number of methods have been developed for the prediction of ... Read More

Poster: Predicting Regioselectivity and Lability of Cytochrome P450

Matt presented this poster at ISSX in October 2011. Abstract: Many computational methods have been developed that predict the ... Read More

Poster: Automatic Generation and Validation of QSAR Toxicity Models

Matt presented this poster at ISSX in October 2011. Abstract: Whether compounds are intended as drugs, cosmetics, agrochemicals or for ... Read More

Issues in the Interpretation, Understanding, and Use of Drug Discovery Data

Dr Terry Stouch gave this presentation as part of the first StarDrop User Group Meeting and Workshop at the ACS Fall meeting 2010 in ... Read More

Exploring Project Spaces to Quickly Identify High Quality Compounds

In this presentation Ed Champness demonstrates some of StarDrop's features for identifying and selecting compounds, using chemical ... Read More

Poster: Maximising compound value by making good decisions:

Matt presented this poster at MipTec in September 2010. Abstract: People are notoriously poor at making good decisions based on ... Read More

Medicinal chemists are people too: And that’s a problem

Dr Mikel Moyer gave this presentation as part of the first StarDrop User Group Meeting and Workshop at the ACS Fall meeting 2010 in ... Read More

In silico ADME/Tox: Why models fail: Why models work

Dr Terry Stouch, Consulting in Drug Discovery and Design Practice, Technologies, Process at Princeton, NJ and Duquesne University gave ... Read More

Overcoming psychological barriers to good discovery decisions

This article explores the psychological barriers and risks of cognitive biases to R&D decision-making. It contrasts current practice with the use of evidence-based medicine Read More

A rational approach to risk reduction

Dr Andrew Chadwick, Consultant (Life Sciences and Healthcare) at Tessella gave this presentation on "Rational Approach to Risk ... Read More

Gaussian Processes for Classification: QSAR Modeling of ADMET and Target Activity

In this study, the researchers look to solve classification quantitative structure−activity relationship (QSAR) modelling problems using Gaussian processes. Read More

Visual analyses for guiding compound selection and design

In this presentation Ed Champness considers the decision-making challenges faced by drug discovery scientists and presents some visual ... Read More

Poster: Comparison of Metasite and StarDrop Prediction of CYP3A4, CYP2C9 and CYP2D6

Young Shin and his colleagues at Genentech presented this poster at the ISSX North American Regional meeting in Baltimore, MD in ... Read More

Beyond Profiling: Using ADMET Models to Guide Decisions

Summary The main use of ADMET models, whether in silico or in vitro,tends to be molecule ‘profiling’; identifying compounds which are ... Read More

Automatic QSAR modeling of ADME properties: blood-brain barrier penetration and aqueous solubility

In this study, our researchers combined an automatic model generation process for building QSAR models with the Gaussian Processes machine learning method. Read More

ADMET Property Prediction: The State of the Art and Current Challenges

This article explores ADMET property prediction by QSAR methods. It covers statistical modelling techniques, molecular descriptors, data sets applications and challenges faced. Read More

Poster: Guiding the Decision-Making Process to Identify High Quality Compounds

Defining a property profile is subjective and often leads to lengthy, interdisciplinary discussions about the criteria and their ... Read More

Poster: Application of in Silico (ADMEnsa Interactive) and ADME/PK Assays in the Identification of New Chemical Entities (NCEs) for Pre-Clinical Evaluation

The current paradigm of  drug discovery utilising chemical library synthesis coupled with high throughput screening technologies often ... Read More

Predictive ADME Models in Drug Discovery: Can You Trust Them? Can You Afford Not To?

In this presentation, Alan Beresford discusses drug discovery and considers how ADME models fit into the process as a step necessary ... Read More

Gaussian Processes for Classification

O. Obrezanova and M. D. Segall, White Paper In this article, Olga describes how we extend the application of Gaussian Processes ... Read More

Automated QSAR Modelling to Guide Drug Design

In this presentation Olga Obrezanova describes  an automated process for building QSAR models (now available as part of StarDrop as ... Read More

Poster: Opening the ‘Black Box’: Interpreting in Silico Models to Guide Compound Design

In silico predictive models are now widely used to predict a range of molecular properties and help prioritise molecule for synthesis. ... Read More

Poster: Automated QSAR Modeling to Guide Drug Design

The rapid design-test-redesign cycles of modern drug discovery and the demand for fast model (re)building whenever data becomes ... Read More

The journey from Drug Discovery to Drug Design: How far have we travelled?

In this presentation, Matt Segall talks about the differences between "design" and "discovery" and considers two different analogies ... Read More

Gaussian Processes: a method for automatic modelling of ADME properties

In this presentation Olga Obrezanova talks about Gaussian Processes - a powerful computational method  for QSAR modelling. Olga starts ... Read More

Join The

Optibrium Community

Access a wealth of information on all of our products, learn more about our science and our wider community of collaborators.