This workshop covers searching and analysis of structural data in PSILO®, and organization of structural families in MOE-Project. Participants will learn to consolidate macromolecular and protein-ligand structural data, generate and navigate advanced queries, and streamline analysis with 3D contact and protein pocket similarity searches. The session also covers organizing structure-based drug design projects, aligning protein families, configuring MOE-Project databases, and using Protein-Ligand Interaction Fingerprints (PLIF) analysis to compare ligand binding modes. Attendees will gain practical skills for efficient structural data mining and project management.

This workshop focuses on methods for analyzing and optimizing peptide-protein interactions in the binding site. Participants will learn peptide-protein structure preparation, peptide sequence optimization using both natural and non-natural amino acids, and perform conformational analysis. Peptide-protein docking will be demonstrated, along with tools for analyzing protein-ligand interactions to assess contact points. Advanced conformational searching techniques using distance restraints will also be described.

This workshop provides an overview of SVL capabilities and its application within MOE. Participants will be introduced to the essentials of the SVL scripting language, including its use in automating tasks, customizing workflows, and enhancing MOE functionalities for specific research needs.

This workshop focuses on structure-based antibody design. Topics such as protein-protein interaction analysis, in silico protein engineering, affinity modeling, and antibody homology modeling will be covered. Participants will explore an antibody-antigen co-crystallized complex by generating and examining molecular surfaces and visualizing protein-protein contacts in 3D. Antibody properties will be evaluated using specialized protein property descriptors and protein patch analysis. The session will also cover the application of protein engineering tools for affinity and property optimization in the context of antibody developability. Additionally, participants will learn to optimize antibody homology models, including identifying glycosylation sites and their selective modification using a specialized MOE Project antibody database. The full workflow for high-throughput antibody homology modeling, from sequence to structure to property calculations for developability analysis, will be demonstrated.

This workshop explores advanced structure-based drug design (SBDD) workflows used in drug discovery projects. Participants will learn about key topics, including pharmacophore query generation, protein-ligand docking, scaffold replacement, and R-group screening. The session will cover the application of pharmacophore searching in drug design, as well as methods for querying 3D project databases. Additionally, participants will generate and analyze protein-ligand interaction fingerprints (PLIF) to support their design strategies.

The course covers essential in silico methods needed for guiding drug discovery projects in the absence of a protein structure. SAR Analysis through R-group profiling and matched molecular pairs (MMP) analysis using MOEsaic to determine relationships among a chemical series are examined. Molecular descriptor calculations and their application for determining property correlations are described. Molecular alignments and conformational analyses of a congeneric series are explored to assess the impact of ligand substituents. An approach for developing pharmacophore queries is discussed. Management and manipulation of MOE databases are also covered.

This workshop covers essential methods for aligning protein sequences, superposing structures, loop modeling, building fusion protein models, and conducting protein-protein docking. Participants will learn techniques for grafting and refining antibody CDR loops, as well as using a knowledge-based approach to scFv fusion protein modeling with the Linker Modeler application. The session will also cover protein-protein docking of an antibody to an antigen and epitope mapping. Finally, the workshop will guide participants through a complete workflow for generating a QSAR model to predict and analyze protein/biologics solubility.

This workshop explores the suite of MOE applications for small-molecule virtual screening. Participants will learn to prepare small-molecule databases for screening, filter databases using substructure matching and property values, and build QSAR/QSPR models and fingerprint similarity models as screening filters. The session will cover creating and searching pharmacophore queries and performing small-molecule docking. A complete virtual screening workflow will be presented, including the creation of de novo structures using MOE’s Scaffold Replacement and Medchem transformation tools.

This workshop describes cheminformatics methods for managing and analyzing datasets of small molecules, as well as generating quantitative structure-activity relationship (QSAR) models. Participants will learn how to import data, prepare MOE databases, calculate molecular descriptors, and analyze trends using sorting, coloring, and plotting tools. Advanced database filtering, data clustering, and diverse subset selection techniques will also be explored. The workshop will include sessions on developing both linear regression and binary QSAR models. Finally, data mining of large compound libraries will be demonstrated using substructure and molecular fingerprint similarity searching.

As the field of biologics moves toward in silico binder discovery, the integration of structural visualization/analysis tools and next-generation AI/ML technologies is paramount within the biologics drug discovery workflow. To democratize access to structural analysis tools, we have implemented comprehensive training in Molecular Operating Environment (MOE) for individual scientists. This training empowers researchers to leverage structural analysis and visualization across various aspects of biologics discovery, including antibody and VHH humanization, liability correction, affinity maturation, antigen design, and complex format engineering. In this presentation, I will highlight a case study that demonstrates the application of AI/ML-driven protein engineering techniques to design soluble G protein-coupled receptors (GPCRs), thereby facilitating biologics discovery. This case study illustrates the potential of integrating advanced computational methods with structural biology to accelerate the development of innovative therapeutics.

Over the past decade, technological advancements in Cryo Electron Microscopy (CryoEM) leading to “resolution revolution”, has displayed great potential to visualize molecular mechanisms of pathogenic infections, cancer development and other intracellular processes at atomic detail. From resolving the precise architecture of viruses, to rapid high-resolution epitope mapping of glycosylated antigens on viruses, cancer, and immune cells, CryoEM structure-based design is accelerating the development of next generation therapeutics. Our structure biology and protein design team utilizes integrated structure biology methods, which combine experimental structure determination by X-ray crystallography and artificial intelligence enhanced cryoEM, with the power of predictive modeling by Alphafold2, for rapid determination of high-resolution three-dimensional (3D) structures. The 3D structures of antigen-antibody(Ab)/NANOBODY® VHH (Nb) complexes are routinely used to deliver critical epitope-paratope information, mechanism of action, and to re-design molecules with enhanced therapeutic properties.

Examples (from masked targets) to decipher cryoEM structures of glycosylated antigen-Fab/Nb complexes using automated and unsupervised data collection and processing protocols at in-house microscope in Cambridge crossing (CX) will be discussed. This data combined with AI/ML methods is utilized for HT 3D structure interpretation from intermediate resolution maps for structure-based variant design and engineering of desired properties like pH dependent binding and affinity tuning.

Antibody-drug conjugates (ADCs) constitute a rising class of medicines that combine the selectivity of antibodies with the cytotoxicity of drug payloads to yield highly targeted and potent therapeutics. Owing to the need to chemically modify antibody residues for the attachment of the drug payload and their more complex structure compared to either component alone, ADCs can present additional challenges related to stability of the final drug product. This talk explores the use of high-throughput experimental screens and computational techniques to understand the conformational and colloidal behavior of an IgG1-based ADC, representing the first reported example of tuning the biophysical properties (e.g. melting temperature, aggregation temperature, diffusion interaction parameter) of a monomethyl auristatin F-based ADC by screening a large formulation library. The ADC, which exhibits high opalescence and strong attractive protein-protein interactions, is transformed into a more stable structure by experimentally traversing a library of more than ~100 different formulation conditions. A significant reduction in turbidity and diffusion interaction parameter is observed by varying solution attributes such as pH and ionic strength. Molecular modeling simulations rationalized these changes and pointed to the presence of attractive electrostatic interactions between ADC molecules under specific solution conditions (low pH and low ionic strength) facilitated by the drug payload and histidine residues. Experimental characterization of the ADC’s structure using techniques such as circular dichroism, size-exclusion chromatography, and peptide mapping further corroborated the computational results. Taken together, we envision that the studies and findings presented here will be applicable across a wide scope of ADCs towards enhancing their stability, therapeutic efficacy, and ultimate prospects for developability.

The engineering of pH-sensitive therapeutic antibodies, particularly for improving effectiveness and specificity in acidic solid-tumor microenvironments, has recently gained traction. While there is a justified need for pH-dependent immunotherapies, current engineering techniques are tedious and laborious, requiring repeated rounds of experiments under different pH conditions. Inexpensive computational techniques to predict the effectiveness of His pH-switches require antibody-antigen complex structures, but these are lacking in most cases. To circumvent these requirements, we introduce a sequence-based in silico method for predicting His mutations in the variable region of antibodies, which could lead to pH-biased antigen binding. This method, called Sequence-based Identification of pH-sensitive Antibody Binding (SIpHAB), was trained on 3D-structure-based calculations of 3,490 antibody-antigen complexes with solved experimental structures. SIpHAB was parametrized to enhance preferential binding either toward or against the acidic pH, for selective targeting of solid tumors or for antigen release in the endosome, respectively. Applications to nine antibody-antigen systems with previously reported binding preferences at different pHs demonstrated the utility and enrichment capabilities of this high-throughput computational tool. SIpHAB, which only requires knowledge of the antibody primary amino-acid sequence, could enable a more efficient triage of pH-sensitive antibody candidates than could be achieved conventionally. An online webserver for running SipHAB is available freely at https://mm.nrc-cnrc.gc.ca/software/siphab/runner/.

Predicting potential liabilities, aggregation, viscosity etc. is of importance in monoclonal antibody development. Computational property prediction methods are routinely used in the selection and optimization of candidate antibodies. High quality property prediction involves prediction of ensembles of 3D structures at specified pH to reduce sensitivity to single conformational states.

We present 3dpredict/Ab which calculates ensemble-based predictions of antibody developability descriptors and putative liabilities. 3dpredict/Ab allows for out-of-the-box SaaS automation and integration of such complex simulations of hundreds or thousands of sequences.

Antibody humanization and optimization remain critical steps in the development of therapeutic biologics, requiring a balance between reducing immunogenicity and preserving or enhancing function. This presentation provides a comparative analysis of Molecular Operating Environment (MOE) 2022 and 2024 releases for antibody engineering, with a focus on how improvements accelerate workflow performance using real-world multispecific antibody case studies.

In addition, we will showcase practical tips for integrating bio_MOE, CCG’s biology-oriented interface, to streamline humanization, paratope/canonical residue analysis, developability assessments, and in silico QC. Custom workflows using 3D pI, solvent-accessible hydrophobicity, and PTM risk assessment will be demonstrated for both single-domain and multi-chain antibody constructs. The talk will conclude with recommendations on how to combine MOE’s updated property descriptors to triage and optimize humanized antibody candidates for developability including manufacturing, distribution, and efficacy.

This session will provide a comprehensive and practical guide to making the most of the platform’s evolving capabilities.

Human papillomavirus (HPV) is the primary driver of cervical, head and neck, and anal cancers through its ability to hijack the cellular E3-ligase E6AP and promote degradation of the tumor suppressor protein p53. This mechanism, mediated by the HPV E6 protein, has been recognized for decades but has remained difficult to therapeutically target.

We recently determined the high-resolution (~3.3 Å) cryo-electron microscopy structure of the full-length HPV16 E6:E6AP:p53 complex, uncovering an unexpectedly high affinity interaction and large surface interface between HPV16 E6 and E6AP, far beyond the canonical E6AP LXXLL motif. This provided new structural insights and identified critical, previously unknown interfaces essential for complex stability.

In parallel, we developed peptide discovery strategies, including Reversibly Reactive Affinity Selection–Mass Spectrometry (ReAct-ASMS) coupled with rational design of covalent peptide inhibitors or "reactides". Through these studies we identified and optimized covalent peptides targeting a critical cysteine residue within HPV16 E6, effectively disrupting its interaction with E6AP.

Together, our integrated structural, computational, and chemical biology approaches provide a deeper understanding of HPV-driven carcinogenesis, and importantly, establish a foundation for the development of selective covalent targeted strategies to inhibit HPV-driven cancers.

The gene editing field has seen significant progress recently with two FDA approvals for gene editing using ex vivo approaches. However, in vivo delivery of gene editing therapies remains attractive, as in vivo treatment offers an opportunity to make these life-changing treatments accessible to many more patients. Using computational and wet lab approaches, Orna has identified a suite of class 2 type V endonucleases that can be leveraged for in vivo gene editing therapies. The natural editing rates of these enzymes were found to be low, so to improve editing outcomes, Orna has taken a multi-pronged approach in which both the type V protein, as well as its RNA guide, were engineered. Using a tertiary model of our lead Cas protein, which included both a gRNA and a template DNA, we identified sites predicted to enhance protein-nucleic acid interactions but also predicted to be tolerated by the Cas protein fold. Next, we sought to enhance the stability of our guide by incorporating gRNA backbone modifications at positions on the guide gRNA predicted to stabilize the gRNA backbone without compromising key binding interactions with the Cas protein. By combining the novel gRNA modifications with protein Cas engineering, we achieved editing rates above 80% in primary cells, comparable to published rates for well-characterized type V enzymes.

The growing popularity of siRNA based therapies has highlighted a critical need for new enzymatic approaches for synthesis. The current state of the art for the synthesis of siRNA is using phosphramidite chemistry. Here we report on the use of a biological means to replace decades old chemistry with a new innovative approach. The dsRNA ligase is one of a suite of engineered enzymes being developed for a new process. RNA ligases are critical in the synthesis of elongated targets from smaller fragments. The successful use of an ML algorithm was implemented to predict the ideal junctions for assembling siRNA targets with high precision and accuracy.

Modeling nucleic acids, particularly RNA, presents challenges due to their dynamic nature, with biologically relevant conformations often differing significantly between unbound and bound states. This variability complicates predictions in silico, making efficient conformational sampling crucial. In this presentation, we investigate the efficacy of the LowModeMD method for enhancing conformational sampling in DNA and RNA systems compared to traditional molecular dynamics approaches.

By focusing on low-frequency vibrational modes, LowModeMD enables rapid exploration of conformational space, facilitating the identification of biologically relevant structures. Coupling conformational states with protonation states provide deeper insights into biological mechanisms. We demonstrate the utility of LowModeMD in analyzing bulged residues, sampling bound conformations in tetraloops from unbound states, and assessing tertiary structure stability across varying pH levels.

Predicting human clearance with high accuracy from in silico-derived parameters alone is highly desirable, as it is fast, saves in vitro resources, and is animal-sparing. Random forest (RF) models were generated based on 1340 compounds with human intravenous pharmacokinetic (PK) data, the largest data set publicly available today. The talk highlights ways to assess the general applicability of the developed RF models and shows the difficulty of obtaining useful, broadly applicable models for human clearance. The use of a conformal prediction formalism to derive confidence intervals and assess model applicability is demonstrated. Renally cleared compounds could be identified through an in silico classification model and were found to be better predicted than compounds cleared through other mechanisms. It is hypothesized that this is because renal clearance is mechanistically less complex than e.g. metabolic clearance. The developed RF models compared similar to models derived from scaling human hepatocytes or preclinical in vivo data. The results were generated with the help of KNIME workflows that included MOE nodes, e.g. for descriptor calculations.

Ensuring pollinator safety is a critical aspect of developing sustainable crop protection products. Research efforts have advanced both the understanding of pollinator toxicity and the development of new approach methodologies in toxicity testing. Within the agricultural and chemical industries, prioritizing pollinator safety remains a key objective in the development of predictive tools. Among these, computational models such as quantitative structure–activity relationships (QSARs) play a valuable role in predicting chemical toxicity. This study utilizes bee toxicity data to develop artificial neural network classification models for predicting acute toxicity in honey bees. A dataset of 1,542 compounds was used to train the models, with the best-performing model achieving sensitivity and specificity values of 0.90 and 0.91, respectively. These in silico models support the discovery of next-generation crop protection products by facilitating the early identification of candidates with high safety margins for pollinators. By integrating these tools into the early discovery stage, researchers can screen and select molecules with favorable sustainability profiles before in vivo testing.

Drug discovery is a multi-parameter optimization challenge where in vitro toxicology assays are often employed to screen initial candidates and guide the discovery efforts towards a safer chemical space. In this iterative design-make-test cycle, medicinal chemists require feedback on the structural features causing specific toxicity signals to iteratively design out these features.

Machine learning models and docking are commonly used to aid medicinal chemists in making informed decisions. However, machine learning models often fail to guide chemistry design and pinpoint the structural features responsible for toxicology signals. Additionally, in the absence of crystal structures of similar chemical series, docking produces poses and scores that are often unreliable for guiding further design. Docking against numerous off-targets responsible for toxicity is also time-consuming.

To address these challenges, we propose a pharmacophore-based platform designed to flag and filter compounds that medicinal chemists propose to synthesize. This platform aims to create alerts for obvious pharmacophores responsible for particular off-target effects, thereby enhancing the efficiency and safety of the drug discovery process. In the initial version, we selected several off-targets based on the availability of structures, including GPCRs (preferably agonists, antagonists, and inverse agonists), kinases, enzymes, and off-targets without available structures. We plan to expand and improve on this platform in the future.

Structural information of drug targets has proven to be an asset to drug discovery projects. MOE provides a broad platform for disseminating structural information and project data enabling transforming the data into knowledge to move the project forward. Understanding and quantifying protein-ligand interactions is a valuable consideration in molecular design. Assessing the electrostatic match between compounds and binding pockets provides important insights into why compounds bind. In this presentation I will discuss a case study, where we use MOE project and electrostatic complementary at various stages of a project in medicinal chemistry.

Structure determination is essential to a mechanistic understanding of diseases and the development of novel therapeutics. Machine-learning-based structure prediction methods have made significant advancements by computationally predicting protein and bioassembly structures from sequences and molecular topology alone. Despite substantial progress in the field, challenges remain to deliver structure prediction models to real-world drug discovery. Here, we present NeuralPLexer3 -- a physics-inspired flow-based generative model that achieves state-of-the-art prediction accuracy on key biomolecular interaction types and improves training and sampling efficiency compared to its predecessors and alternative methodologies. Examined through newly developed benchmarking strategies, NeuralPLexer3 excels in vital areas that are crucial to structure-based drug design, such as physical validity and ligand-induced conformational changes.

DNA-encoded libraries (DEL) screening has historically been used to identify hits from libraries of hundreds of billions of diverse molecules. X-Chem's approach to DEL produces data that facilitates not just hit identification, but structure-function mapping. Pharmacophores are widely used in early drug discovery, capturing key molecular features responsible for ligand binding and guiding the identification of new therapeutic candidates. In this work, we present a novel computational workflow designed to generate pharmacophores from DEL screening data. Current workflows typically yield top hits from clusters of DEL compounds grouped into “families”, which leaves the breadth of the data underutilized. In this new methodology, each DEL family, and combinations of families, can be used as a whole, representing an ensemble of chemical matter indicative of binding, and it optionally incorporates ligand activity and inactive molecules. Our platform offers a promising framework for translating DEL screening results into pharmacophores, enabling more efficient hit identification and better utilization of the wealth of DEL data in post-validation medicinal chemistry design. In this presentation we also present case studies for this novel technology.