All Schrödinger offices worldwide will be closed for the week of August 17-21 as part of a company-wide initiative to rest and recharge. Please expect limited responses during this time. Scientific and Technical Support team members will be available to answer emergency support issues only.

Battery materials

Battery_Course_Hero

Battery materials


Molecular and periodic quantum mechanics, all-atom molecular dynamics, and machine learning for studying battery materials and their properties under various conditions

Details
Available Languages
Chinese, English, Japanese, Korean
Duration
6 weeks / ~25 hours to complete
Level
Introductory
Cost
$600 for non-student users
$160 for student / post-doc
Course Timeframe
When registering for the course, you will be able to choose your preferred start and end date. Within those dates, you will have asynchronous access to the course to work on your preferred schedule

Overview

Computational molecular modeling tools have proven effective in materials science research and development. Chemists, physicists and engineers working in materials science will increasingly encounter molecular modeling throughout their careers, making it critical to have a foundational understanding of the cutting edge tools and methods. These courses are ideal for those who wish to develop professionally and expand their CV by earning certification and a badge.

These computational chemistry courses offer an effective and efficient approach to learn practical computational chemistry for materials science:

  • Work hands-on with Schrödinger’s industry-leading Materials Science Maestro software
  • Jump start your research program by learning methods that can be directly applied to ongoing projects
  • Learn topics ranging from density functional theory (DFT) to molecular dynamics to machine learning for materials design
  • Perform a completely independent case study to demonstrate mastery of the course content
  • Benefit from review and feedback from Schrödinger Education Team experts for course assignments and course-related queries
  • Work on the course materials on your own schedule whenever convenient for you

 

This course comes with access to a web-based version of Schrödinger software with the necessary licenses and compute resources for the course:

Requirements
  • A computer with reliable high speed internet access (8 Mbps or better)
  • A mouse and/or external monitor (recommended but not required)
  • Working knowledge of general chemistry
Certification
  • A certificate signed by the Schrödinger course lead
  • A badge that can be posted to social media, such as LinkedIn
background pattern

What you will learn

MS Maestro interface

Learn how to use an industry-leading interface for materials science modeling. No coding or scripting required to run modeling workflows

Quantum mechanics

Learn to apply molecular & periodic density functional theory (DFT) for automated property prediction for organic & inorganic molecules

Molecular dynamics

Learn to leverage all-atom MD simulations for simulating device layers & electrolyte properties

Machine learning

Learn to apply machine learning for rapid & accurate property prediction of battery-relevant organic molecules

Modules

Module 1
2 Hours

Introduction to materials modeling

Video
Video

Introduction to materials modeling & this online course

Video Tutorial
Video tutorial

Introduction to materials science (MS) Maestro

Video
Video

Introduction to modeling for batteries

End checkpoint
Honor code agreement and checkpoint
Module 2
7 Hours + Compute Time

Molecular & periodic quantum mechanics

Video
Video

Introduction to molecular & periodic quantum mechanics (mQM & pQM)

Tutorial
Tutorials
  • Quantum mechanical workflows & properties: Part 1
  • Quantum mechanical workflows & properties: Part 2
  • Bond and ligand dissociation energy
  • Nanoreactor
  • Building bulk crystals and calculating properties
  • Calculating intercalation and voltage curves
  • Lithium ion migration barrier (NEB)
End checkpoint
End of module checkpoint
Module 3
6 Hours + Compute Time

All-atom molecular dynamics

Video
Video

Introducing to molecular dynamics (MD)

Tutorial
Tutorials
  • Disordered system building & MD multistage workflows
  • Building, equilibrating & analyzing polymers
  • Diffusion
  • Polymer electrolyte analysis
  • Liquid electrolyte properties: Part 1
  • Liquid electrolyte properties: Part 2
  • Solid electrolyte interphase builder
End checkpoint
End of module checkpoint
Module 4
3 Hours + Compute Time

Machine learning

Video
Video

Introduction to machine learning (ML)

Tutorial
Tutorials
  • Machine learning property prediction
  • Machine learning for materials science
  • Machine learning for ionic conductivity
  • Molecular dynamics descriptors for machine learning
  • Machine learning for formulations
End checkpoint
End of module checkpoint
Module 5
3 Hours + Compute Time

Guided case study

Tutorial
Case Studies
  • EC decomposition on a Li (001) surface
  • Ab initio molecular dynamics simulations of Li-ion diffusion in solid-state electrolytes
End checkpoint
End of module checkpoint
Module 6
4 Hours + Compute Time

Independent case study

Assignment
Assignment

Modifying battery electrolyte components

Course completion
Course completion & certification
Self-paced video lessons on materials modeling

Self-paced video lessons on materials modeling

Videos on practical theory break down complex scientific concepts (e.g. Molecular Quantum Mechanics)

Videos on practical theory break down complex scientific concepts (e.g. Molecular Quantum Mechanics)

Access cloud-based computing resources to perform calculations yourself

Access cloud-based computing resources to perform calculations yourself

Hands-on step-by-step tutorials (e.g. Pharmaceutical Formulations course, pKa prediction)

Hands-on step-by-step tutorials (e.g. Pharmaceutical Formulations course, pKa prediction)

Hands-on modeling in the web-based graphical user interface (e.g. Polymeric Materials course, Diffusion tutorial)

Hands-on modeling in the web-based graphical user interface (e.g. Polymeric Materials course, Diffusion tutorial)

Videos on practical theory break down complex scientific concepts (e.g. Molecular Dynamics)

Videos on practical theory break down complex scientific concepts (e.g. Molecular Dynamics)

On-demand video lessons on materials modeling

On-demand video lessons on materials modeling

Access cloud-based computing resources to perform calculations yourself

Access cloud-based computing resources to perform calculations yourself

Perform case studies with expert feedback (e.g. Organic Electronic Course, Independent Case Study)

Perform case studies with expert feedback (e.g. Organic Electronic Course, Independent Case Study)

Video on practical theory break down complex scientific concepts (e.g. Machine Learning for Chemistry)

Video on practical theory break down complex scientific concepts (e.g. Machine Learning for Chemistry)

Videos on practical theory break down complex scientific concepts (e.g. Periodic Quantum Mechanics)

Videos on practical theory break down complex scientific concepts (e.g. Periodic Quantum Mechanics)

Videos on practical theory break down complex scientific concepts (e.g. Coarse-Graining)

Videos on practical theory break down complex scientific concepts (e.g. Coarse-Graining)

Self-paced video lessons on materials modeling
Videos on practical theory break down complex scientific concepts (e.g. Molecular Quantum Mechanics)
Access cloud-based computing resources to perform calculations yourself
Hands-on step-by-step tutorials (e.g. Pharmaceutical Formulations course, pKa prediction)
Hands-on modeling in the web-based graphical user interface (e.g. Polymeric Materials course, Diffusion tutorial)
Videos on practical theory break down complex scientific concepts (e.g. Molecular Dynamics)
On-demand video lessons on materials modeling
Access cloud-based computing resources to perform calculations yourself
Perform case studies with expert feedback (e.g. Organic Electronic Course, Independent Case Study)
Video on practical theory break down complex scientific concepts (e.g. Machine Learning for Chemistry)
Videos on practical theory break down complex scientific concepts (e.g. Periodic Quantum Mechanics)
Videos on practical theory break down complex scientific concepts (e.g. Coarse-Graining)

Need help obtaining funding for a Schrödinger Online Course?

We proudly support the next generation of scientists and are committed to providing opportunities to those with limited resources. Learn about your funding options for our online certification courses as a student, post-doc, or industry scientist and enroll today!

What our alumni say

“Clear instructions with a well-designed interface allowed me to run some of my own first molecular dynamics simulations. The information from the course felt much more secure than the information from YouTube because I knew it was developed by experts”
Graduate Student
“The course let me talk confidentially about molecular modeling and what it can do. For me, this was a nice experience which left me with many ideas for applying molecular modeling in the research area of our department, not only for me but also for my colleagues.”
Graduate Student
“As always, the course is very well designed. Formulation is quite outside my comfort zone in terms of theory and modeling but this course provided me with knowledge of evaluating what modeling can facilitate in the real world. Really great design and education process.”
Senior DirectorTherapeutic Protein Design

Show off your newly acquired skills with a course badge and certificate

When you complete a course with us in molecular modeling and are ready to share what you learned with your colleagues and employers, you can share your certificate and badge on your LinkedIn profile.

Frequently asked questions

How much do the online courses cost?

Pricing varies by each course and by the participant type. For students wishing to take these courses, we offer a student price of $150 for introductory courses, $305 for the Materials Science bundle, and $870 for advanced courses. For commercial participants, the course price is $575 for introductory courses and $1435 for advanced courses and bundles.

When does the course start?

The courses run on sessions, which range from 3-6 week periods during which the course and access to software are available to participants. You can find the course session and start dates on each course page.

What time are the lectures?

Once the course session begins, all lectures are asynchronous and you can view the self-paced videos, tutorials, and assignments at your convenience.

How could I pay for this course?

Interested participants can pay for the course by completing their registration and using the credit card portal for an instant sign up. Please note that a credit card is required as we do not accept debit cards. Additionally, we can provide a purchase order upon request, please email online-learning@schrodinger.com if you are interested in this option. If you have any questions regarding how to pay for the course, please visit our funding options page.

Are there any scholarship opportunities available for students?

Schrödinger is committed to supporting students with limited resources. Schrödinger’s mission is to improve human health and quality of life by transforming the way therapeutics and materials are discovered. Schrödinger proudly supports the next generation of scientists. We have created a scholarship program that is open to full-time students or post-docs to students who can demonstrate financial need, and have a statement of support from the academic advisor. Please complete the application form if you qualify for our scholarship program!

Will material still be available after a course ends?

While access to the software will end when the course closes, some of the material within the course (slides, papers, and tutorials) are available for download so that you can refer back to it after the course. Other materials, such as videos, quizzes, and access to the software, will only be available for the duration of the course.

Do I need access to the software to be able to do the course? Do I have to purchase the software separately?

For the duration of the course, you will have access to a web-based version of Maestro, Bioluminate, Materials Science Maestro and/or LiveDesign (depending on the course). You do not have to separately purchase access to any software. While access to the software will end when the course closes, some of the material within the course (slides, papers, and tutorials) are available for download so that you can refer back to it after the course. Other materials, such as videos, quizzes, and access to the software, will only be available for the duration of the course. Please note that Schrödinger software is only to be used for course-related purposes.

Related Courses

Online certification course: Level-up your skill set in catalysis modeling Materials Science Materials Science
Homogeneous catalysis & reactivity

Molecular quantum mechanics and machine learning approaches for studying reactivity and mechanism at the molecular level

Molecular modeling for materials science applications: course bundle Materials Science Materials Science
Course bundle

Access all materials science courses with a single, discounted registration

Molecular modeling for materials science applications: Polymeric materials course Materials Science Materials Science
Polymeric materials

All-atom molecular dynamics and machine learning approaches for studying polymeric materials and their properties under various conditions

Supporting Associations

nanoHUB

Beyond the Lab: Unleashing the Potential of In Silico Modeling in Drug Product Formulation

SEPT 14, 2023

Beyond the Lab: Unleashing the Potential of In Silico Modeling in Drug Product Formulation

Speaker

John Shelley
Fellow

Abstract

In this webinar, we will explore Schrödinger’s leading molecular modeling and machine learning platform, including workflows for:

  • Drug product characterization: Predicting stability & reactivity, solubility, solid form characterization, and crystal polymorphs
  • Drug formulation: Modeling drug-excipient interactions and predicting complex thermodynamic and mechanical formulation properties

You will learn how digital chemistry tools facilitate rapid screening of formulation parameters, aiding in the identification of optimal drug delivery systems, excipient selection, and dosage forms. Following the webinar, a panel of Schrödinger researchers and scientists will be available to answer questions.

Whether you are a pharmaceutical scientist, researcher, or computational chemist, this webinar offers an opportunity to stay ahead of the curve and explore the potential of in silico drug formulation to optimize drug development, reduce costs, and accelerate time to market.

DeepAutoQSAR

DeepAutoQSAR

Automated, scalable solution for the training and application of predictive machine learning models

DeepAutoQSAR

Create high-performing machine learning models using state-of-the-art methods

DeepAutoQSAR is a machine learning (ML) solution that allows users to predict molecular properties based on chemical structure. The automated supervised learning pipeline enables both novice and experienced users to train and inference best-in-class quantitative structure activity/property relationship (QSAR/QSPR) models.

Key Capabilities

Streamline model building with fully automated workflows

Automatically compute descriptors and fingerprints, create models with multiple machine learning architectures, and evaluate model performance.

Customize models to your project with unique project-specific descriptors

Provide your own descriptors in CSV format to be used in addition to or instead of those generated by DeepAutoQSAR for a wide range of applications beyond small molecules, such as polymers, organic electronics, catalysis, and more.

Ensure model optimization using best practices

Employ QSAR/QSPR best practices to minimize the likelihood of overfitting or misrepresenting a model’s performance while ensuring maximum predictive model performance.

Understand the domain of applicability using model confidence estimates

DeepAutoQSAR provides uncertainty estimates alongside model predictions to help determine how much confidence should be placed on predictions generated for candidate molecules which may lie beyond the model’s training set.

Visualize and analyze results to gain further insights 

Visualize color-coded atomic contributions towards target property facilitating ideation of novel chemistry. Visualize and analyze DeepAutoQSAR metrics reports and plots in Maestro to enable further experiments — quickly learn what model architectures are most effective and how models generalize on holdout sets.  

Scalable training to support small or large datasets

Use classical ML methods like boosted trees on smaller datasets while also supporting the largest scale QSAR/QSPR models using graph neural networks and other modern deep learning approaches.

Case studies & webinars

Discover how Schrödinger technology is being used to solve real-world research challenges.

Materials Science Webinar

Accelerating OLED innovation with multi-scale, multi-physics simulations

Join us to explore how integrated digital workflows drive the design of next-generation, high-performance OLEDs.

Materials Science Webinar

Electrodes, electrolytes & interfaces: Harnessing molecular simulation and machine learning for rapid advancements in battery materials development

In this webinar, we demonstrate the application of automated solutions for accurate prediction of electrode materials.

Materials Science Webinar

Schrödinger Materials Science Seminar Japan 2024 

《無料Webセミナー》材料開発向けシミュレーション・ソフトウェアおよびマテリアルズ・インフォマティクスの活用事例を紹介。

Materials Science Webinar

Taking experimentation digital: Materials innovation using atomistic simulation and machine learning at-scale

In this webinar, we introduce a modern approach to materials R&D using a digital chemistry platform for in silico analysis, optimization and discovery.

Materials Science Webinar

In silico materials development: Integrating atomistic simulation into academic chemistry and engineering labs

In this webinar, we explore Schrödinger’s leading physics-based and machine learning computational technologies and provide a comprehensive introduction to the capabilities of computational modeling in chemistry, materials science, and engineering.

Materials Science Webinar

Data-driven materials innovation: Where machine learning meets physics

In this webinar, we demonstrate how Schrödinger’s tools can help overcome these common challenges by using a combination of physics-based simulation data, enterprise informatics, and chemistry-informed ML.

Materials Science Webinar

Cutting-Edge Cosmetics: Innovating for Sustainability with Machine Learning & Molecular Simulations

In this webinar, we explore the challenges chemists face, and how new approaches can help find solutions quicker.

Materials Science Case Study

De novo design of hole-conducting molecules for organic electronics

Materials Science Webinar

Battery Tech – Leveraging Atomic Scale Modeling for Design and Discovery of Next-Generation Battery Materials

In this webinar, we present an advanced digital chemistry platform for developing next-generation battery materials with improved properties.

Materials Science Webinar

Chinese: 利用原子尺度建模设计和发现下一代电池材料 | Leveraging Atomic Scale Modeling for Design and Discovery of Next-Generation Battery Materials

This webinar discussed how to drive the development of novel battery materials with molecular simulations.

Documentation & Tutorials

Get answers to common questions and learn best practices for using Schrödinger’s software.

Materials Science Tutorial

De Novo Design of Novel Compounds with REINVENT

Learn to train a generative ML model with REINVENT to design new compounds with property constraints.

Materials Science Documentation

DeepAutoQSAR

Predict molecular properties based on chemical structure using machine learning (ML).

Materials Science Documentation

Materials Science Panel Explorer

Quickly learn which Schrödinger tools are the best fit for your research.

Related Products

Learn more about the related computational technologies available to progress your research projects.

Virtual Cluster

Secure, scalable environment for running simulations on the cloud

Active Learning Applications

Accelerate discovery with machine learning

FEP+

High-performance free energy calculations for drug discovery

Glide

Industry-leading ligand-receptor docking solution

De Novo Design Workflow

Fully-integrated, cloud-based design system for ultra-large scale chemical space exploration and refinement

Jaguar

Quantum mechanics solution for rapid and accurate prediction of molecular structures and properties

LiveDesign

Your complete digital molecular design lab

MS Informatics

Automated machine learning tools for materials science applications

Quantum ESPRESSO Interface

Integrated graphical user interface for nanoscale quantum mechanical simulations

Publications

Browse the list of peer-reviewed publications using Schrödinger technology in related application areas.

Materials Science Publication

Band Gap and Reorganization Energy Prediction of Conducting Polymers by the Integration of Machine Learning and Density Functional Theory

Materials Science Publication

A machine learning approach for in silico prediction of the photovoltaic properties of perovskite solar cells based on dopant-free hole-transport materials

Materials Science Publication

Machine learning-based design of pincer catalysts for polymerization reaction

Materials Science Publication

Development of Scalable and Generalizable Machine Learned Force Field for Polymers

Life Science Publication

Pathfinder-Driven Chemical Space Exploration and Multiparameter Optimization in Tandem with Glide/IFD and QSAR-Based Active Learning Approach to Prioritize Design Ideas for FEP+ Calculations of SARS-CoV-2 PLpro Inhibitors

Materials Science Publication

Benchmarking Machine Learning Descriptors for Crystals

Materials Science Publication

Machine Learning for the Design of Novel OLED Materials

Life Science Publication

A Descriptor Set for Quantitative Structure-Property Relationship Prediction in Biologics

Materials Science Publication

Active Learning Accelerates Design and Optimization of Hole-Transporting Materials for Organic Electronics

Materials Science Publication

Design of organic electronic materials with a goal-directed generative model powered by deep neural networks and high-throughput molecular simulations

Training & Resources

Online certification courses

Level up your skill set with hands-on, online molecular modeling courses. These self-paced courses cover a range of scientific topics and include access to Schrödinger software and support.

Tutorials

Learn how to deploy the technology and best practices of Schrödinger software for your project success. Find training resources, tutorials, quick start guides, videos, and more.

DeepAutoQSAR

DeepAutoQSAR

Automated, scalable solution for the training and application of predictive machine learning models

DeepAutoQSAR

Create high-performing machine learning models using state-of-the-art methods

DeepAutoQSAR is a machine learning (ML) solution that allows users to predict molecular properties based on chemical structure. The automated, supervised learning pipeline enables both novice and experienced users to train and inference best-in-class quantitative structure activity/property relationship (QSAR/QSPR) models.

Key Capabilities

Streamline model building with fully automated workflows

Automatically compute descriptors and fingerprints, create models with multiple machine learning architectures, and evaluate model performance.

Customize models to your project with unique project-specific descriptors

Provide your own descriptors in CSV format to be used in addition to or instead of those generated by DeepAutoQSAR for a wide range of applications beyond small molecules, such as polymers, organic electronics, catalysis, and more.

Ensure model optimization using best practices

Employ QSAR/QSPR best practices to minimize the likelihood of overfitting or misrepresenting a model’s performance while ensuring maximum predictive model performance.

Understand the domain of applicability using model confidence estimates

DeepAutoQSAR provides uncertainty estimates alongside model predictions to help determine how much confidence should be placed on predictions generated for candidate molecules which may lie beyond the model’s training set.

Visualize and analyze results to gain further insights 

Visualize color-coded atomic contributions towards target property facilitating ideation of novel chemistry. Visualize and analyze DeepAutoQSAR metrics reports and plots in Maestro to enable further experiments — quickly learn what model architectures are most effective and how models generalize on holdout sets. 

Scalable training to support small or large datasets

Use classical ML methods like boosted trees on smaller datasets while also supporting the largest scale QSAR/QSPR models using graph neural networks and other modern deep learning approaches.  

Case studies & webinars

Discover how Schrödinger technology is being used to solve real-world research challenges.

Life Science Webinar

Leveraging machine learning applications combined with physics-based modeling for drug discovery

Machine learning strategies in drug discovery are becoming increasingly popular and can be used in various areas.

Life Science Case Study

High precision, computationally-guided discovery of highly selective Wee1 inhibitors for the treatment of solid tumors

Life Science Case Study

Hit to lead design of novel d-amino-acid oxidase inhibitors using a comprehensive digital chemistry strategy

Life Science Webinar

Trends in modern hit discovery: How your ultra-large screens can benefit from machine learning

While traditional structure-based virtual screening has been successful in finding diverse hits to advance projects there is significant room for improvement of hit rates, diversity of hit chemotypes, available IP space explored, and the potency of unoptimized hits.

Life Science Webinar

Aggregation scoring and liability prediction using Schrödinger’s Biologics Suite

Documentation & Tutorials

Get answers to common questions and learn best practices for using Schrödinger’s software.

Life Science Tutorial

Learning Path: Cyclic Peptide Modeling

A structured overview of tools and workflows for cyclic peptides in drug discovery.

Life Science Documentation

DeepAutoQSAR

Predict molecular properties based on chemical structure using machine learning (ML).

Life Science Documentation

Learning Path: Virtual Screening

A structured overview of how to construct a virtual screening pipeline.

Life Science Tutorial

Training and Evaluating ADMET Models with DeepAutoQSAR

Build and test two models for predicting aqueous solubility using a large dataset.

Related Products

Learn more about the related computational technologies available to progress your research projects.

Virtual Cluster

Secure, scalable environment for running simulations on the cloud

Active Learning Applications

Accelerate discovery with machine learning

FEP+

High-performance free energy calculations for drug discovery

Glide

Industry-leading ligand-receptor docking solution

De Novo Design Workflow

Fully-integrated, cloud-based design system for ultra-large scale chemical space exploration and refinement

Jaguar

Quantum mechanics solution for rapid and accurate prediction of molecular structures and properties

LiveDesign

Your complete digital molecular design lab

MS Informatics

Automated machine learning tools for materials science applications

Quantum ESPRESSO Interface

Integrated graphical user interface for nanoscale quantum mechanical simulations

Publications

Browse the list of peer-reviewed publications using Schrödinger technology in related application areas.

Materials Science Publication

Band Gap and Reorganization Energy Prediction of Conducting Polymers by the Integration of Machine Learning and Density Functional Theory

Materials Science Publication

A machine learning approach for in silico prediction of the photovoltaic properties of perovskite solar cells based on dopant-free hole-transport materials

Materials Science Publication

Machine learning-based design of pincer catalysts for polymerization reaction

Materials Science Publication

Development of Scalable and Generalizable Machine Learned Force Field for Polymers

Life Science Publication

Pathfinder-Driven Chemical Space Exploration and Multiparameter Optimization in Tandem with Glide/IFD and QSAR-Based Active Learning Approach to Prioritize Design Ideas for FEP+ Calculations of SARS-CoV-2 PLpro Inhibitors

Materials Science Publication

Benchmarking Machine Learning Descriptors for Crystals

Materials Science Publication

Machine Learning for the Design of Novel OLED Materials

Life Science Publication

A Descriptor Set for Quantitative Structure-Property Relationship Prediction in Biologics

Materials Science Publication

Active Learning Accelerates Design and Optimization of Hole-Transporting Materials for Organic Electronics

Materials Science Publication

Design of organic electronic materials with a goal-directed generative model powered by deep neural networks and high-throughput molecular simulations

Training & Resources

Online certification courses

Level up your skill set with hands-on, online molecular modeling courses. These self-paced courses cover a range of scientific topics and include access to Schrödinger software and support.

Tutorials

Learn how to deploy the technology and best practices of Schrödinger software for your project success. Find training resources, tutorials, quick start guides, videos, and more.

Computational drug design and chemo-informatics: a hands-on course at the University of Antwerp

Computational drug design and chemo-informatics: a hands-on course at the University of Antwerp

The University of Antwerp is the third-largest university in the Dutch-speaking region of Belgium, with over 20,000 students annually. Within the Biochemistry and Biotechnology curriculum, students have the option to take a three-ECTS course on computational drug design and chemo-informatics. The course is organized in a modular fashion and covers both theoretical and practical sessions.

During the theoretical sessions, students learn about chemo-informatics and virtual screening, which includes concepts such as chemical fingerprints, molecular similarity, clustering, machine learning models, and virtual screening performance metrics. The course also covers molecular docking and pharmacophore searching. The concepts covered in the theoretical sessions are then put into practice in a series of hands-on sessions.

For the chemo-informatics tasks, the students use Google Colab with RDKit as a chemo-informatics toolkit, while for the pharmacophore and docking-related aspects, they use Maestro, Phase, and Glide. These tools are made available through the “Teaching with Schrödinger” web-based virtual workstations, which allows students to access them from anywhere at any time. Finally, using an internally-developed virtual reality system, the students can graphically study the non-bonded interactions between ligand and protein.

At the start of the course, a drug design project is defined based on ongoing research programs in the Faculty. The goal of the project is to identify a limited number of commercially-available compounds (5-10) that are subsequently purchased and biochemically characterized for their inhibitory properties. The students complete the program with a written report, which serves as the basis for the oral examination at the end.

Our Speaker

Prof. Hans De Winter

Professor, University of Antwerp

Hans De Winter was appointed in 2013 as a professor of Computational Drug Design at the University of Antwerp (Belgium) after a long career in industry, first as a senior scientist at Johnson & Johnson in Beerse, Belgium, and subsequently as a co-founder and CSO of Silicos NV. He holds a PhD from the University of Leuven (Belgium) and completed post-doctoral stays at the Victorian College of Pharmacy (Australia) and the Rega Institute in Leuven (Belgium) before starting his career as a scientist in the pharmaceutical industry. Despite his elaborated industrial background during a period of more than 20 years, he has over 60 scientific publications and is listed as inventor on eight granted patents. Hans’ research interests are mainly situated in the field of computational medicinal chemistry and cheminformatics.

Molecular Modelling to Support Drug Formulation for Small Molecule and Biologic Drugs

JUN 28, 2022

Molecular Modelling to Support Drug Formulation for Small Molecule and Biologic Drugs

Speaker

John C. Shelley
Fellow

Abstract

  • Complementary use of machine learning and physics-based modeling contribute to the drug development and formulation process
  • Molecular modelling provides a basic understanding of the structure and behaviour of drugs as formulated that compliments experimental data and informs decision making in drug formulation
  • API and excipient physical and chemical property prediction for small molecule drug formulations
  • Characterization of drug-drug and drug-excipient association including drug-polymer interactions in small molecule and biologics formulations
  • Provide structural insights into concentrated protein solutions and predict viscosity, aggregation, and the effect of excipients

A chemist’s view on R&D digitalization

MAY 11, 2021

A chemist’s view on R&D digitalization

Speaker:
Dr. Laura Scarbath-Evers, Senior Scientist

Abstract:
How the integration of machine learning with physics based modelling and enterprise informatics transforms materials discovery.

Global challenges, like a clean energy future or circular economy, have increased the demand for new materials. Typically, the performance of materials depends on a multitude of parameters which makes traditional research approaches, relying on experiments solely, slow, inefficient, and prohibitively expensive. Data driven approaches can significantly speed up the discovery process and shorten the time from idea to market.

In this presentation, we will illustrate how the integration of Schrödinger’s machine learning technologies with physics based modelling can be utilized to predict properties of new materials. Use cases from important materials science areas, like polymers and opto-electronic materials, will illustrate how data generated from experiment as well as physics-based modelling can be used to build machine learning models to predict physical properties and even suggest new compounds. Finally, we demonstrate how the integration of machine learning approaches into collaborative design schemes can maximize their usability and accessibility to non-expert users.

25th EuroQSAR

Conference

25th EuroQSAR

CalendarDate & Time
  • September 27th – October 1st, 2026
LocationLocation
  • Perugia, Italy

Schrödinger is excited to be participating in the 25th European Symposium on Quantitative Structure-Activity Relationship conference taking place on September 27th – October 1st in Perugia, Italy. Join us for a presentation by Dr. Giulia D’Arrigo, Senior Scientist II, Applications Science at Schrödinger, titled “Mitigating Off-Target Liabilities Using Physics-Based Simulations.”

icon time SEPT 30 | 11:50 AM
Mitigating Off-Target Liabilities Using Physics-Based Simulations

Speaker:
Dr. Giulia D’Arrigo, Senior Scientist II, Applications Science, Schrödinger

Abstract:
By one estimate, unmanaged toxicity is responsible for roughly 30%[1] of all drug discovery project failures. The adoption of experimental screening panels has contributed to the overall improved safety profile of drugs on the market. However, the high cost and latency associated with performing these screens mean that such panels are run later in the pre-clinical discovery process and cannot be effectively incorporated into hit finding and lead-optimization stages of the project. To meet the demand for off-target screening during the design process, many teams deploy digital toxicology screening in the form of ligand-based machine learning models. These models, which are fast and inexpensive to operate are typically limited by poor generalizability to ligand matter dissimilar from the data used to train the models and lack the protein context to help designers rationally dial out liabilities. Here we present a novel in silico, physics-based approach that constructs a full 3D, atomistic representation of the ligand interacting with the off-target using induced-fit docking and molecular dynamics simulations and leverages free energy calculations to model off-target binding affinity. This workflow has been applied to a wide range of targets across different protein classes (kinases, hERG or CYPs).[2] Recently this has been extended to nuclear receptor RXRɑ and retrospectively validated with literature data.

19th German Conference on Cheminformatics 2026

Conference

19th German Conference on Cheminformatics 2026

CalendarDate & Time
  • November 8th-11th, 2026
LocationLocation
  • Bad Soden, Germany

Schrödinger is excited to be participating in the 19th German Conference on Cheminformatics 2026 taking place on November 8th – 11th in Bad Soden, Germany. Join us for a presentation by Daniel Cappel, Senior Principal Scientist, Applications Science at Schrödinger, titled “Mitigating off-target liabilities using physics-based simulations.”

icon time NOV 9 | 10:40 AM
Mitigating off-target liabilities using physics-based simulations

Speaker:
Daniel Cappel, Senior Principal Scientist, Applications Science, Schrödinger

Abstract:
By one estimate, unmanaged toxicity is responsible for roughly 30%[1] of all drug discovery project failures. The adoption of experimental screening panels has contributed to the overall improved safety profile of drugs on the market. However, the high cost and latency associated with performing these screens mean that such panels are run later in the pre-clinical discovery process and cannot be effectively incorporated into hit finding and lead-optimization stages of the project. To meet the demand for off-target screening during the design process, many teams deploy digital toxicology screening in the form of ligand-based machine learning models. These models, which are fast and inexpensive to operate are typically limited by poor generalizability to ligand matter dissimilar from the data used to train the models and lack the protein context to help designers rationally dial out liabilities.

Here we present a novel in-silico, physics-based approach that constructs a full 3D, atomistic representation of the ligand interacting with the off-target using induced-fit docking and molecular dynamics simulations and leverages free energy calculations to model off-target binding affinity. This workflow has been applied to a wide range of targets across different protein classes (kinases, hERG or CYPs).[2] Recently this has been extended to nuclear receptor RXRɑ and retrospectively validated with literature data.

Release 2026-3

Library Background

Release Notes

Release 2026-3

Small Molecule Drug Discovery

Platform Environment

Maestro Graphical Interface

  • Added nonstandard nucleotide support: Right-click any DNA or RNA residue to mutate it to a nonstandard nucleotide via a searchable panel with 2D structure preview
  • New GPCR Workspace Preset for annotated G protein-coupled receptor visualization
  • Revamped surface management including comparison of multiple surfaces in the surface toggle: Select multiple surfaces to see a sortable, side-by-side comparison of Area, Isovalue, Sigma, and more in the Info tab. The panel can now be undocked and floated freely
  • Simplified Maestro to LiveDesign export for Biologics: Redesigned the Generic Entity export panel (“Biologics/Others”) with two clear workflows, Register New Entities (with HELM-based deduplication) or Append 3D Data to Existing Entities
  • Streamlined ability to “Load Selection” for Workspace Interactions: Select atoms in the Workspace, click “Load Selection” in the Interactions dropdown to instantly display their interactions without manually configuring “Other” definitions
  • Standalone Map Import in Get PDB: Diffraction data and EM maps are now imported as standalone entries grouped alongside their structures in the Project Table
  • New “Other Modalities” Task Tool category with “Degraders” and “Macrocycles” subcategories, grouping specialized panels for easier discoverability
  • More intuitive clipping plane zoom controls: The clipping plane view now zooms with the Workspace by default, and new right-click menu options let you toggle clipping plane behavior without navigating to Preferences
  • Redesigned Preferences Directories page: Cleaner layout with Browse buttons, clearer terminology, automatic detection of SCHRODINGER_TEMP_PROJECT overrides, and Windows-only sections hidden on Mac/Linux
  • “Check for update” option added to the Help menu
  • Dramatic improvements in the MSV pairwise sequence alignment

Target Validation & Structure Enablement

Protein Preparation

  • Annotate GPCRs automatically during structure preparation
  • Selenomethionines are now converted to methionines by default during preparation
  • Command-line options overhauled for greater simplicity and to match the Maestro interface’s defaults
  • Disable/Hide unusable options in Academic Maestro
  • Removed the -noimpref flag from CLI consistent with deprecation of the impref minimization scheme
  • Warn users if sidechain atoms could not be rebuilt with the new sidechain rebuilding method

Cofolding

  • Maestro panel automatically evaluates and corrects ligand bond orders in prepared models
  • Removed confidence based trimming of residues in post-processing
  • Full multiple sequence alignment used to construct homology models viewable in the MSV

Predictive Tox Panel

  • Added thirteen new GPCR targets to panel, 5HT1B, 5HT2B, 5HT2C, ACM4, ADA2A, ADRB1, ADRB2, APJ, DRD3, OX2R, DRD2, ADORA1 and CNR2
  • Added five new bromodomain targets to panel, BRD2 BD1, BRD2 BD2, BRD4, BD1, BRD4 BD2, and CBP
  • Added three new nuclear receptor targets to panel, RXRa, AR, ER Beta
  • All panel targets supported in both Predictive Tox and Predictive Tox SAR Panels

Binding Site & Structure Analysis

Binding Site Characterization

  • First release of Rapid Binding Site Similarity (RBSS)
    • Compute binding site similarities for a protein against all binding sites in the PDB in seconds
    • Compute binding site similarities for a protein against user-provided libraries of binding sites
    • Uses coarsened molecular interaction fields (MIFs) computed on a grid to represent the preference for different functional groups to occupy locations on a grid including, aromatic, hydrophobic, h-bond acceptor, h-bond donor, and positive and negative charges

Desmond Molecular Dynamics

  • Speed simulations up to ~66% with support to adjust Hydrogen Mass Repartitioning (HMR)
  • Seven new mixed lipid bilayers are now supported by the System Builder

Mixed Solvent MD (MxMD)

  • Specify probe target concentration in the input to simulations (command line only)

Hit Identification & Virtual Screening

Active Learning Applications

  • Automatically generate the group dG prediction for multi-state protomer groups after including all protonation states of the selected ligands
  • Specify the number of lambda windows separately for charged and uncharged ligands for ABFEP and final rescore ABFEP steps
  • Apply positional restraints in AL-ABFEP simulations
  • AL-FEP+ enriched substructures in the report file now exclude the common core
  • AL-ABFEP extends the final rescore ligands instead of running them from scratch to save computation time when ABFEP is run on GraphDB

Docking

  • Glide uses ZMQ job distribution (-mq option) by default for faster wall clock turnaround of docking jobs with multiple subjobs through better subjob scheduling

Lead Optimization

RetroSynth

  • New combined Maestro RetroSynth setup and analysis panel: Perform and analyze retrosynthesis routes generated by RetroSynth in Maestro or LiveDesign

FEP+

  • New ABFEP scanning mode: Perform calculations up to 5x faster with slight loss of accuracy using half lambda windows, 2 ns simulation times, and a truncated receptor
  • New Interaction Energy plot fragment decomposition feature: Get a richer understanding of how specific compound fragments interact with the receptor
  • Support added for seven new mixed lipid bilayers
  • Create “write” submission commands from Maestro interface to Web Services
  • PoseBuilder can now generate covalent protein-ligand complex poses ready for covalent FEP+ from command line or in LiveDesign

Protein FEP

  • Compute pH-dependent affinities directly from the Maestro interface
  • Perform FEP Residue Scanning (FRS) at large scale : New workflow that splits mutations into multiple batches and automatically runs them in parallel before merging results into a single out.fmp file

E-sol

  • New panel to setup, execute, and analyze predictions if experimental Efflux ratio data is available

FEP+ Protocol Builder

  • Unified Panels that can set up and analyze FEP+ Protocol Builder jobs
  • Explore different membrane types as a new parameter
  • Command line ‘-prepare’ mode that generates protocols without submitting them

Quantum Mechanics

  • Predict compound atropisomerism and analyze key rotational barriers with a new Maestro panel
  • Provide an at-a-glance view into the simulation settings and results of an AutoTS calculation in an automatically generated html report

Spectroscopy

  • 13C NMR heavy-atom corrections for C-F are now supported

Semi-Empirical Quantum Mechanics

  • g-xTB can be invoked from Jaguar after installation by the user (must activate the XTB_GXTB feature flag)

Macrocycles

  • New macrocycle docking panel for launching MacroDock jobs
  • New sampling options in the Prime macrocycle sampling panel
  • Improved macrocycle conformer generation for Glide and IFD-MD docking for ring systems that contain certain nitrogen chemistries
  • More thorough sampling of complex multicycles such as vancomycin in Prime macrocycle sampling (Prime-MCS)
  • Prime macrocycle sampling (Prime-MCS) conformers are now all automatically aligned to a single reference frame
  • Macrocycle docking workflow (MacroDock) is ~2.5x faster than reported in the original publication, reducing the median CPU runtime to under 1 hour per compound while maintaining a success rate of ~80%
  • Macrocycle docking workflow (MacroDock) now supports docking with experimental density maps
  • New script for batch docking into the same ligand site (macrocycle_batch_docking.py)

Drug Formulations

Crystal Structure Prediction

  • Full release of Crystal Structure Prediction supporting salts, solvates, and co-crystals for confident form selection in solid-state development: Computationally screen at scale to identify the most stable, manufacturable crystal form before committing to experiments and secure your formulation strategy

Docs Content

  • Learning Paths have been completely redesigned for improved usability

Education Content

  • New Learning Path: Cyclic Peptide Modeling
  • New Tutorial: Handling Non-standard Amino Acids
  • New Tutorial: Modeling Blood-Brain Barrier Penetration Using E-sol
  • Redesigned Tutorial: A Chemist’s Guide to Maestro
  • Updated Tutorial: Evaluating Large Ligand Libraries with Active Learning Glide
  • Updated Tutorial: Introduction to Performing Metadynamics Simulations with Desmond
  • New Interactive Mini-tutorial: Rapid Binding Site Similarity Search (embedded in the Panel Help)

Biologics Drug Discovery

  • Simple, high-throughput creation of a nonstandard nucleotide library for use in Maestro for DNA/RNA/oliogo design
  • New output files from PIPER enables streamlined analysis of docked poses reducing post-processing effort

Materials Science

GUI for Quantum ESPRESSO

Product: Quantum ESPRESSO (QE) Interface

  • Support for dipole correction setup from the input *.cfg file (command line)
  • Option to visualize reaction profile as a function of NEB inter-image distance
  • Multi-threaded MLFF calculations for NEB calculations (command line)
  • GPU support for NEB calculations with MLFF (command line)

Microkinetics

Product: MS Microkinetics

  • (+MKM_ELECTROCATALYSIS) Support for multistage workflow for electrocatalysis

Active Learning Optoelectronics

Product: Active Learning Optoelectronics

  • Active Learning Optoelectronics: Access to ML property prediction models
  • Active Learning Optoelectronics: Access to AutoQSAR/DeepAutoQSAR models

Reactivity

Product: MS Reactivity

  • Nanoreactor: Option to adjust biasing potential
  • Nanoreactor: Simplified UI for improved user experience
  • Nanoreactor: Improved settings for enhanced reaction discovery
  • Nanoreactor: AutoTS transition state frequencies reported in the output
  • Reaction Network Profiler: Prevention of atom clashes during input preparation

Reactive Interface Simulator

Product: MS RIS

  • Solid Electrolyte Interphase: Improved support for ions with zeroth order bonds

Advanced Force Field Applications

Product: MS FF Applications

  • MLFF Fine-tuning: Solution to fine-tune MPNICE MLFF models and use them through in Schrödinger Suite
  • MLFF Calculations: Support for vibrations and phonon calculations

Transport Calculations via MD simulations

Product: MS Transport

  • Ionic Conductivity: Option to apply linear response theory for predictions
  • Thin Plane Shear: Improved definition of plane for shear

Coarse-Grained (CG) Molecular Dynamics

Product: MS CG

  • Backmapping: Tool to map coarse-grained systems to atomic representations
  • CG FF Assignment: Support for encrypted force field files
  • CG FF Builder: Improved selection of data for plotting in viewer
  • CG FF Builder: Improved fitting of valence terms
  • Coarse-Grained Mapping: Generation of Martini FF file for selected structures
  • Visualization of CG protein backbone as tube in the workspace

Materials Informatics

Product: MS Informatics

  • MPNICE Embeddings: Machine learning with MPNICE embeddings as descriptor

Layered Device ML

Product: MS Layered Device ML

  • OLED Device ML: Option to use pre-trained ML model output as descriptors for new models
  • OLED Device ML: Support for tandem OLED devices
  • OLED Device ML: Visualization of feature importance from the viewer panel

Denovo ML

Product: MS Denovo ML

  • REINVENT: Updated job submission protocol for improved speed

MS Maestro Builders and Tools

  • Agentic Workflow: (+MATSCI_AGENTIC_WF) Language-model-based solution to create custom Meta Workflows
  • Crystal Structure Prediction: Support for salts and solvents
  • Free Volume Analysis: Reduced memory use for the analysis
  • Import Slabs: Addition of 25 pre-built slab models
  • Interface Builder: Model builder for bulk interfaces and grain boundaries
  • Structured Liquid: Redesigned UI for improved user experience
  • Sugar Builder: (+NEW_SUGAR_BUILDER_PANEL) Option to build with glycosylation patterns

Classical Mechanics

  • Droplet Contact Angle: Support for MLFF
  • Electrolyte Analysis: Option to merge neighboring ion clusters for analysis
  • Evaporation: Speedup of up to an order of magnitude for coarse-grained systems
  • Support for TIP4P water model with OPLS_2005
  • MD Multistage: (+MULTISTAGE_MD_CONCATENATE) Option to concatenate Brownie stage with other stages
  • Polymer Crosslink: Reduced memory use of free volume analysis
  • Thermophysical Properties: Reduced use of disk space

Quantum Mechanics

  • Optoelectronic Film Properties: Option to set T1 geometry from DFT or TDDFT
  • Optoelectronic Film Properties: Speed up for ISC/RISC reorg energy calculation
  • Reaction Network Viewer: Single output for multiple rxn networks (command line)
  • Reaction Network Viewer: Option to view structures in the workspace
  • Reaction Network Viewer: Option to save reaction network images

Education Content

  • New Tutorial: MLFF Fine-Tuning
  • New Tutorial: Building Epitaxial Interfaces
  • New Tutorial: Protein Characterization: Part 2
  • New Tutorial: Machine Learning with MPNICE Embedding
  • New Tutorial: Crystal Structure Prediction: Part 2
  • Updated Tutorial: Optoelectronics Active Learning
  • Updated Tutorial: Ionic Conductivity
  • Updated Tutorial: Liquid Electrolyte Properties: Part 2
  • Updated Tutorial: Automated Dissipative Particle Dynamics (DPD) Parameterization
  • Updated Tutorial: Nanoemulsions with Automated DPD Parameterization
  • New Quick Reference Sheet: Coarse-Grained Backmapping

Education Content

Life Science

  • New Learning Path: Cyclic Peptide Modeling
  • New Tutorial: Handling Non-standard Amino Acids
  • New Tutorial: Modeling Blood-Brain Barrier Penetration Using E-sol
  • Redesigned Tutorial: A Chemist’s Guide to Maestro
  • Updated Tutorial: Evaluating Large Ligand Libraries with Active Learning Glide
  • Updated Tutorial: Introduction to Performing Metadynamics Simulations with Desmond
  • New Interactive Mini-tutorial: Rapid Binding Site Similarity Search (embedded in the Panel Help)

Materials Science

  • New Tutorial: MLFF Fine-Tuning
  • New Tutorial: Building Epitaxial Interfaces
  • New Tutorial: Protein Characterization: Part 2
  • New Tutorial: Machine Learning with MPNICE Embedding
  • New Tutorial: Crystal Structure Prediction: Part 2
  • Updated Tutorial: Optoelectronics Active Learning
  • Updated Tutorial: Ionic Conductivity
  • Updated Tutorial: Liquid Electrolyte Properties: Part 2
  • Updated Tutorial: Automated Dissipative Particle Dynamics (DPD) Parameterization
  • Updated Tutorial: Nanoemulsions with Automated DPD Parameterization
  • New Quick Reference Sheet: Coarse-Grained Backmapping

LiveDesign

What’s New in 2026-3

  • Biologics

    • Design new Antibody-Drug Conjugates: create ADC entities in the Entity Builder using four new templates supporting monospecific and bispecific antibodies, with separate or combined linker and payload components.

    • Multi-point and combinatorial residue substitution: choose Single Point, Multi-point, or Combinatorial mutation type to enumerate all combinations across multiple positions in a single run, with up to 10,000 unique combinations per request; progress notifications link directly to newly inserted rows.

    • Monomer Database Viewer: browse, search across name, symbol, and other fields, sort, filter, and manage monomers in a dedicated viewer supporting libraries of 30,000 or more monomers, with alias support for HELM strings and validation on batch upload

    • Subsequence search across adjoining annotated regions: search for sequences spanning region boundaries — such as a CDR3 and FR4 junction — by selecting multiple structural annotations in Advanced Search and enabling “Search across boundaries.”

    • Import 3D structure data from Maestro: export 3D data from Maestro directly to generic entities and biologics, with options to create a new 3D column, append to an existing column, or overwrite existing data.

    • Sequence Viewer: filter to constant domains and hinge regions: show only CH1, CH2, CH3, CL, or hinge region residues for faster antibody developability and manufacturability checks; CDR regions are now shown by default for antibody entities.

    • Sequence Viewer: alignment with standard and custom substitution matrices: choose from BLOSUM62, PAM250, BLOSUM45, BLOSUM80, or GONNET, upload a custom CSV matrix, or align by residue number using Kabat or other antibody numbering schemes.

  • Project Scaffolds

    • Apply project-level scaffolds in the R-group decomposition panel alongside LiveReport-specific scaffolds, with project scaffolds given preferential compound matching; publishing an updated scaffold list automatically syncs changes and recalculates R-group decomposition across all open LiveReports.

    • Manage project scaffolds from a new Project Administration tab in the Project Dashboard; renaming a scaffold is immediately reflected in R-group decomposition results across all open LiveReports.

  • Forms: Multi-Entity Matrix Widget: view compound structures and data side-by-side in a transposed table format, with structures as columns and properties as rows, and add custom labels for each row.

  • Project Dashboard: filter the Activity stream by specific published comment columns or by users in the project; access the Dashboard directly from the LiveDesign header by clicking the LiveDesign logo.

  • Plots

    • 2D Heatmap (Beta): visualize data across two categorical dimensions with aggregation modes (Mean, Median, Min, Max, or Count) and support for MPO and other advanced coloring rules.

    • Date-based grouping in Box Plots, Scatter, and Line charts: group date-type X-axes by Day, Week, Month, Quarter, or Year to view trends over time, with an option to display data aggregated or unaggregated per time bin.

  • SAR Analysis: option to remove entity structure coloring: toggle “Show Structure Coloring” off in the compound column menu to remove R-group decomposition color overlays while preserving scaffold alignment; the toggle is per-LiveReport and session-only, and a server property controls the default state for all users.

  • System Health Tool (Beta): monitor LiveDesign system health from a centralized dashboard showing model task queue depth, LiveReport execution queue metrics, task engine status by queue type (Sync, Async, Fast, and Realtime), and JVM heap usage, with icons and tooltips on each metric tile.

  • UX Improvements

    • Recalculate Failed Only: the model column menu now includes a “Recalculate Failed Only” option to rerun only cells with failed results, without filtering the LiveReport first.

    • Adding a compound via the design sketcher now selects the newly added row, consistent with search-by-ID and advanced search.

    • Admin users can configure a server property to allow regular users to apply templates to LiveReports they do not own or that already contain data.

    • The Visualize panel tab now includes a Close All option for open plots and tools; right-clicking a plot tab shows context menu options to open, pop out, or close it without switching to the tab first.

    • Renaming a plot now opens an in-app dialog instead of a browser popup, and hovering over a plot tab shows the full plot name in a tooltip.

    • Plot legends repositioned from their default location now appear correctly in exported PNG and SVG files.

    • Residue-level sync selection between the Sequence Viewer and 3D Visualizer is now enabled by default.

    • The property column dropdown in the Generic Entity import dialog now includes a search field to quickly locate columns by name.

What’s Been Fixed

Advanced Search

  • Advanced Search: changing AND/OR logic operators in the complex view would be ignored during the subsequent search, and now correctly reflects the updated logic.

  • Advanced Search: entering an invalid sequence in a subsequence query would silently search using the previously entered valid sequence, and now correctly disables the search button when the sequence format is invalid.

  • Advanced Search with child entity queries would return parent entities whose only matching child was archived, and now correctly excludes archived child entities from search matching.

  • Dragging and dropping a structure into the filter panel would load the structure in the sketcher but leave the ‘Add’ button disabled, requiring a manual edit before the filter could be applied; the ‘Add’ button is now enabled as soon as a structure is loaded.

  • Substructure searches in Advanced Search would return the same entities regardless of which dataset was selected, and now correctly filter results to the chosen dataset.

  • The Structural Annotation and Numbering Scheme dropdowns in Advanced Search would appear misaligned and incorrectly sized in complex view, and now display with consistent alignment in both simple and complex view.

  • Deleting a query group that contained sub-queries in Advanced Search would throw an error and cause subsequent queries to fail; query groups with sub-queries can now be deleted without errors.

  • Advanced search by ID would return entities that matched the All IDs column, and now correctly returns only entities where the ID matches the ID column.

  • Advanced search queries would get stuck in a permanent error state when changes were made concurrently, forcing users to start over in a new LiveReport, and now handle concurrent updates without getting stuck.

  • The ‘Presence in LiveReport’ advanced search condition would expose Global Project LiveReports to users in Hyper Restricted Projects via the ‘Shared with Me’ option, and now only shows LiveReports within the restricted project.

Filters

  • A deleted condition in the complex filter panel would reappear after a browser refresh when the filter expression contained a validation error, and now deleted conditions are correctly persisted. Invalid filter expressions also now show a friendly error message instead of repeatedly showing a loading state.

Authentication

  • During SSO login, users would be redirected back to the login page and need to click the ‘Login with SSO‘ button a second time to successfully sign in, and now log in on the first attempt.

  • Users on servers with the refresh token filter enabled would receive 401 errors on login or be frequently logged out, and can now log in and maintain sessions reliably.

  • Multiple users starting sessions concurrently would receive 502 errors, and now start sessions reliably even under high concurrent load.

  • When LiveDesign attempted to refresh a user access token and the authentication service was temporarily unreachable, the timeout was treated as an authentication failure and the user was logged out; LiveDesign now retries the token refresh request over a short window before treating the disruption as a failure, so brief authentication service unavailability no longer causes unexpected session termination.

Biologics

  • In Entity Builder, using ‘Get from Selection’ on a Monospecific Antibody in a LiveReport would show an entity type mismatch error, and now correctly populates the selection.

  • In the Monomer Database viewer, clicking a monomer row after applying a filter would display the details of a different monomer; the correct monomer details are now shown when clicking a filtered row.

  • Copying a monomer SMILES from the Monomer Database tooltip would include extra whitespace that caused SMILES filter searches to return no results; copying SMILES from the tooltip now correctly returns matching monomers when used as a filter.

  • Editing a reactant in the Reaction Enumeration sketcher would change Enhanced Stereo labels to Absolute (R or S) labels; Enhanced Stereo labels are now preserved when structures are edited and re-opened in the sketcher.

  • The monomer storage tool is now consistently named Monomer Database throughout the interface.

Freeform Columns

  • Bulk copying values into a Freeform column would cause the LiveReport to show a white screen until the browser was refreshed, and now applies the copied values correctly without a page reload.

  • The Freeform column audit trail tooltip would display values from a previously hovered cell when a network error occurred; the audit trail now always shows the correct content for the currently hovered cell.

  • Double-clicking OK when saving a comment in a Freeform Comment column would create two duplicate comment entries, and now correctly creates only one.

  • Deleted Freeform Comment columns would still show an Edit Column option in the column menu and allow editing column details, and now deleted columns are correctly view-only.

  • The Comments Panel would show ‘No entities selected’ when entities were selected but the LiveReport had no Freeform Comment columns, and now correctly indicates that no comment cells are selected.

Forms View

  • In Forms View, clicking an entity in the parent widget would require a second click before the child widget updated with the drilled-down entity; the child widget now updates on the first click.

  • Forms matrix widget labels now correctly save all rich text formatting including font size, font color, italic, underline, strikethrough, and horizontal alignment.

  • Switching between spreadsheet and Forms view in large LiveReports is now faster.

  • Kanban tiles would not have a drop zone for dragging to a new vertical or swimlane when the vertical column was not displayed on the tile; drag and drop now works regardless of which columns are shown on the tile.

  • Kanban tiles in Forms View now correctly display biologic entity images instead of showing a blank cell.

  • Global form layout templates could be overwritten, renamed, or deleted from non-Global projects, and now global templates are protected from modification outside the Global project.

LiveReport

  • LiveReports containing date columns with many empty cells would take an unusually long time to load due to slow date parsing; loading performance for these LiveReports is now significantly faster.

  • LiveReports containing multiple real generic entities that share a virtual entity would fail to load, and now calculate correctly.

  • Duplicating a LiveReport with hundreds of columns and unpublished Freeform columns would take over a minute, and now completes in seconds.

  • Limited assay columns would lose their reference to the parent assay column and become impossible to publish, and now correctly retain that reference.

  • Limited assay columns in a batch group would fail to ungroup via the Column Ungroup option or the Data & Columns tree Ungroup option, and now ungroup correctly through both methods.

  • Running a model on parent entities that have child entities would cause the child entities to appear as separate rows in the LiveReport, and now only the parent entities are affected.

  • Copying cell values from a LiveReport with frozen rows would add extra blank lines to the clipboard equal to the number of frozen rows; cell values now copy without extra blank lines.

  • The vertical scrollbar handle in the LiveReport spreadsheet would lag behind the cursor when dragging quickly, preventing users from reaching the bottom of large LiveReports, and now scrolls smoothly and responsively.

  • The Show Hidden Rows dialog would display an incorrect entity alias when multiple ID column aliases existed, and now shows the correct ID column alias.

  • Clicking OK in the project picker after searching for a project by name would fail to switch to that project, and now correctly navigates to the selected project.

  • Clicking the Assay Viewer link in an assay data tooltip would fail to open the tool and could leave it inaccessible until the page was refreshed, and now the Assay Viewer opens correctly from the tooltip.

  • Files with underscores in their names were not searchable in the Manage Files dialog, and now appear correctly in search results.

  • Adding a design from the sketcher to a LiveReport could take more than 20 seconds and sometimes fail entirely, and now is added immediately.

Models

  • Models using the {ORIG-SDF-FILE} macro in their protocol commands would fail to generate the required input file when run against Generic Entity rows, and now correctly produce the input file for all entity types.

  • Model result cells would sporadically show as failed even when the model had completed with data, requiring a manual model rerun to display the results; cells now correctly show model results without needing a rerun.

  • Click-to-run models would fail to submit when a dependent model was triggered simultaneously, and now correctly submit their tasks.

  • Empty input cells passed to parameterized models would inconsistently appear as ‘[]’ instead of an empty string in the model’s CSV input, and now consistently use an empty string.

Admin Panel

  • On Admin Panel deployments with a large number of parameterized models, the model list page would stretch horizontally to render all pagination page numbers in a single row, making the layout difficult to use; the pagination control now displays a condensed set of links, keeping the table compact regardless of model count.

  • Users with the LiveDesign User role were unable to open the Tasks dialog on deployments with a large number of unrestricted projects (~250 or more); the request line size limit has been increased to allow the task page to load on deployments with 400+ unrestricted projects.

  • Users with the UserAdmin role would fail to save edits to project properties, including project description, Therapeutic Area, and Group permissions; UserAdmin users can now edit and save project settings as expected.

  • Admin Panel actions on the Projects and Groups pages would return 403 CSRF token errors when the same user performed edits simultaneously from multiple browsers or tabs; this issue has been resolved.

  • The LiveDesign logo in the Admin Panel header would become distorted when the browser window was resized to a smaller width; the logo now displays correctly at all viewport sizes.

Project Dashboard

  • Entity and R-group structure images on plot axes were not visible when plots were added to the Project Dashboard; plots on the Project Dashboard now correctly display structure images on their axes.

  • Plots with entity or R-group images on the axes would display all compound images grouped into one when added to the Project Dashboard; compound images on dashboard plot axes are now grouped and displayed individually.

  • Pinned tooltips on Project Dashboard plot widgets would disappear when clicking a different data point, and now remain visible.

  • Radar plots are now excluded from the Project Dashboard, where they could not display data because they depend on user selection; a message indicates that radar plots are not supported on the Dashboard.

Plots

  • 3D scatter plots would fail to render after a library upgrade; 3D scatter plots now display correctly across all column types, aggregation modes, and views.

  • Hovering over data points on scatter or line plots with aggregation mode applied would not show a tooltip, and now correctly displays aggregated value information on hover.

  • Exporting plots containing entity or R-group column axes to SVG or PNG would produce files without the structure images; exported plot files now correctly display entity and R-group images.

  • Chart legends would be cut off when exporting plots as SVG or PNG, and now appear fully visible in the exported file.

  • Holding and dragging the mouse to select compounds in a 1D heatmap would not select entities within the drag area, and now correctly selects all entities in the selection region.

  • Compound images shown along a plot axis would expand downward and get cut off by the docked tooltip, and now display correctly above the tooltip.

  • The plot options ‘more’ button would get cut off with certain browser or OS scaling settings or when long column names were selected, and now remains fully visible in all configurations.

  • The Rename dialog for plots now displays the current plot name alongside a field for the new name, with the dialog title updated to use standard capitalization.

  • The 1D heatmap would inconsistently display entity identifiers instead of the configured corporate ID, and now consistently shows the correct ID column identifier.

  • The visualization panel would go blank and become unresponsive for viewer-access users when clicking a dropdown on any plot or the 3D Visualizer, and now correctly displays the dropdown options.

  • The Plot Options modal could be dragged so far up the screen that its title bar and close button were hidden behind the browser’s address bar; the modal now stays within the visible viewport.

Sequence Viewer

  • Selecting an entity from the LiveReport grid would not load it into the Sequence Viewer when in Forms View, and now correctly loads the selected entity.

  • In the Sequence Viewer, residue conservation values shown in tooltips would change when switching the residue display format between FASTA and Monomer-DB, and now conservation values remain consistent regardless of the display format selected.

  • The Sequence Viewer alignment dropdown option was incorrectly labeled ‘By Numbering Residue’ and has been corrected to ‘By Residue Number.’

  • Sequence Viewer data column values would become hidden when scrolling horizontally past the sequence canvas, and now remain visible throughout horizontal scrolling.

  • Sequence Viewer: non-natural monomers (X) in the Logo plot would be colored using the active color scheme, and now correctly use their assigned natural analog color or a neutral gray.

  • Sequence monomer fonts in the Sequence Viewer would change when applying ‘Differing Residues’ coloring in Firefox, and now remain consistent regardless of coloring mode or selection state.

  • The ‘Processing X Sequences’ notification in the Sequence Viewer would count all loaded sequences rather than only the visible ones, and now correctly reflects only the visible sequence count.

  • Clicking on annotation dropdown labels such as CDR1, CDR2, and CDR3 in the Sequence Viewer would not open the dropdown, and now correctly opens it.

  • CDR filtering in the Sequence Viewer would only work for the first two chains of a multi-chain antibody, and now works correctly for antibodies with any number of heavy and light chains.

  • Residues matching the reference sequence would stop displaying as dots when CDR filtering was applied, and now display consistently as dots regardless of filtering.

3D Visualizer

  • In the 3D Visualizer, loading a saved scene would not re-orient the structure to the captured view, and saving subsequent new scenes would also fail; saved scenes now correctly restore the saved orientation.

  • The Residue Type color scheme in the 3D Visualizer now correctly colors unknown and non-natural amino acid residues with a distinct default color.

  • 3D Visualizer: selecting multiple residues one by one on the canvas would only reflect the first selection in the Hierarchy panel, and now all selected residues are highlighted correctly.

  • 3D Visualizer: entity checkboxes in the Content panel now work independently when the same attachment is loaded in multiple cells.

  • 3D Visualizer: adding non-polar hydrogens to a ligand would cause atom labels to change color, and now labels retain their correct color.

  • In the 3D Visualizer, entering measurement mode while structure alignment was active would disable all selection types; the measurement tool is now automatically disabled when structure alignment is in progress.

  • Residue labels in the 3D Visualizer would disappear when switching background colors, and now remain visible after background color changes.

  • 3D Visualizer: exporting a structure to .mae or .maegz would include previously removed atom labels, and now only the currently visible labels appear in the exported file.

  • The Numbering Scheme dropdown in the 3D Visualizer’s Hierarchy tab would truncate ‘Enhanced Chothia’ and not show the full name, and now correctly displays all numbering scheme names in full.

  • In the 3D Visualizer, labels applied to binding site residues would be removed when a ligand was toggled off and back on, and now labels are correctly restored on all residues after toggling.

  • Residue labels in the 3D Visualizer would turn white when changing style presets on a black background, and now retain their correct color.

  • 3D Visualizer now loads structures faster by requesting compressed attachment data from the server and caching structures across the browser session.

  • In the 3D Visualizer structure alignment panel, pressing the Back button in custom atom selection mode would clear the reference selection on the canvas, and now correctly restores the previous selection.

  • The ‘Carbons Only’ checkbox in the 3D Visualizer’s canvas override color panel would appear enlarged with missing padding, and now displays at the correct size.

Ligand Designer

  • Ligand Designer: overlay structures were editable and allowed atoms to be selected and modified, and now remain non-editable as intended.

  • Ligand minimization would silently succeed for structures with invalid bond orders, and now correctly reports a failure for structures that cannot be processed.

MMP

  • The View button for a proposed compound in the MMP analysis panel would not scroll to and highlight that compound in the LiveReport; the button now correctly brings the compound into focus.

  • The MMP delta plot X-axis would start at zero instead of the first transformation ID, and now correctly starts at 1.

SAR Analysis

  • Saving R-groups to a new LiveReport after R-group decomposition would produce an empty LiveReport when aromatized structures were generated, and now correctly saves all R-groups.

Enumeration

  • Reaction enumeration would occasionally fail with no products appearing in the target LiveReport and no indication of what went wrong; the failure now surfaces a descriptive error message.

Export

  • Exporting a LiveReport containing limited assay columns would omit the ‘(Limited)’ suffix from column names in SDF, PPTX, and XLS exports, and now correctly includes the suffix to match the display in the LiveReport grid.

  • Exporting a LiveReport containing generic entities to XLS or XLS Aligned format in row-per-pose mode would fail with an error, and now exports successfully.

Training & Resources

Online Certification Courses

Level up your skill set with hands-on, online molecular modeling courses. These self-paced courses cover a range of scientific topics and include access to Schrödinger software and support.

Tutorials

Learn how to deploy the technology and best practices of Schrödinger software for your project success. Find training resources, tutorials, quick start guides, videos, and more.

Other Resources

Practical Materials Informatics: Designing Molecules, Formulations, and Devices

Practical Materials Informatics: Designing Molecules, Formulations, and Devices

Practical Materials Informatics: Designing Molecules, Formulations, and Devices


Learn how to apply informatics tools to design molecules, formulations, and devices for materials science applications

Details
Available Languages
Chinese, English, Japanese, Korean
Duration
4 weeks / ~15 hours to complete
Level
Introductory
Cost
$600 for non-student users
$160 for student / post-doc
Course Timeframe
When registering for the course, you will be able to choose your preferred start and end date. Within those dates, you will have asynchronous access to the course to work on your preferred schedule

Overview

Materials informatics brings machine learning to every stage of materials and device design, from predicting a single molecule’s properties to optimizing multi-component formulations to guiding device-level performance. This course teaches you to build and apply Machine Learning (ML) models using Schrödinger’s Materials Science Maestro (MS Maestro) interface, with no coding required.

You’ll work hands-on with real property-prediction datasets spanning small organic and organometallic molecules, ionic liquids, catalysts, polymers, inorganic solids, and formulated products. Then, you will extend that workflow to device design. By the end of the course, you will independently build, evaluate and apply ML models for a real-world design problem.

This materials informatics course offers an effective and efficient approach to learn practical data-driven workflows for materials science:

  • Work hands-on with Schrödinger’s industry-leading MS Maestro software
  • Jump start your research program by learning methods that can be directly applied to ongoing projects
  • Perform a completely independent case study to demonstrate mastery of the course content
  • Benefit from review and feedback from Schrödinger Education Team experts for course assignments and course-related queries
  • Work on the course materials on your own schedule whenever convenient for you

 

This course comes with access to a web-based version of Schrödinger software with the necessary licenses and compute resources for the course:

Requirements
  • Working knowledge of general chemistry
  • No coding or machine learning background required – all workflows are conducted through the MS Maestro graphical interface
  • A computer with reliable high speed internet access (8 Mbps or better)
  • A mouse and/or external monitor (recommended but not required)
Certification
  • A certificate signed by the Schrödinger course lead
  • A badge that can be posted to social media, such as LinkedIn
background pattern

What you will learn

The basics of materials informatics & the MS Maestro interface

Learn the basics of materials informatics and how to use an industry-leading interface for data-driven materials science modeling. No coding or scripting required to run modeling workflows

Molecule-to-material property prediction

Learn how to build, train, validate, and apply models for structure-property relationships across diverse chemistries and applications

Formulation informatics

Learn how to build, train, validate and apply models for formulation-property relationships of multi-component mixtures across diverse chemistries and applications

Device-level informatics

Learn how to build, train, validate and apply models for device-property relationships of layered devices with a focus on organic light-emitting diodes (OLEDs) devices

Modules

Module 1
2 Hours

Introduction to materials informatics

Video
Video

Introduction to materials informatics

Video Tutorial
Video tutorial

Introduction to materials science (MS) Maestro

End checkpoint
Honor code agreement and checkpoint
Module 2
4 Hours + Compute Time

Predicting properties: From molecules to materials

Video
Video

Introduction to structure-property relationships

Tutorial
Tutorials
  • Machine learning property prediction
  • Machine learning for singlet-triplet-gap of TADF molecules
  • Machine learning for ionic conductivity of ionic liquids
  • Machine learning for glass transition temperature of polymers
  • Machine learning for bulk modulus of inorganic solids
  • Machine learning for sweetness of small organic molecules
  • Machine learning for reaction rate constants of homogeneous catalysts
  • Machine learning for viscosity of organic liquids
End checkpoint
End of module checkpoint
Module 3
4 Hours + Compute Time

Formulation informatics & design

Video
Video

Introduction to formulation machine learning

Tutorial
Tutorials
  • Formulation ML for compressive strength of concrete geopolymers
  • Formulation ML for glass transition temperature of copolymers
  • Formulation ML for motor octane number of oil and gas hydrocarbons
  • Formulation ML for selectivity of heterogeneous catalysts in methanol dehydrogenation
  • Formulation ML for temperature-dependent drug solubility
  • Formulation ML for temperature-dependent solvent viscosity
  • Formulation ML for viscosity of shampoo
End checkpoint
End of module checkpoint
Module 4
2 Hours + Compute Time

Device-level informatics: OLED applications

Video
Video

Introduction to machine learning for OLED devices

Tutorial
Tutorials
  • Machine learning for OLED device design
  • Optoelectronics device designer
End checkpoint
End of module checkpoint
Module 5
3 Hours + Compute Time

Independent case study

Assignment
Assignment A

Developing a QSAR model for aqueous solubility

Assignment
Assignment B

Optimizing the solubility and cost of drug-solvent formulations

Assignment
Assignment C

Designing an OLED device with a target emission color

End checkpoint
End of module checkpoint
Self-paced video lessons on materials modeling

Self-paced video lessons on materials modeling

Videos on practical theory break down complex scientific concepts (e.g. Molecular Quantum Mechanics)

Videos on practical theory break down complex scientific concepts (e.g. Molecular Quantum Mechanics)

Access cloud-based computing resources to perform calculations yourself

Access cloud-based computing resources to perform calculations yourself

Hands-on step-by-step tutorials (e.g. Pharmaceutical Formulations course, pKa prediction)

Hands-on step-by-step tutorials (e.g. Pharmaceutical Formulations course, pKa prediction)

Hands-on modeling in the web-based graphical user interface (e.g. Polymeric Materials course, Diffusion tutorial)

Hands-on modeling in the web-based graphical user interface (e.g. Polymeric Materials course, Diffusion tutorial)

Videos on practical theory break down complex scientific concepts (e.g. Molecular Dynamics)

Videos on practical theory break down complex scientific concepts (e.g. Molecular Dynamics)

On-demand video lessons on materials modeling

On-demand video lessons on materials modeling

Access cloud-based computing resources to perform calculations yourself

Access cloud-based computing resources to perform calculations yourself

Perform case studies with expert feedback (e.g. Organic Electronic Course, Independent Case Study)

Perform case studies with expert feedback (e.g. Organic Electronic Course, Independent Case Study)

Video on practical theory break down complex scientific concepts (e.g. Machine Learning for Chemistry)

Video on practical theory break down complex scientific concepts (e.g. Machine Learning for Chemistry)

Videos on practical theory break down complex scientific concepts (e.g. Periodic Quantum Mechanics)

Videos on practical theory break down complex scientific concepts (e.g. Periodic Quantum Mechanics)

Videos on practical theory break down complex scientific concepts (e.g. Coarse-Graining)

Videos on practical theory break down complex scientific concepts (e.g. Coarse-Graining)

Self-paced video lessons on materials modeling
Videos on practical theory break down complex scientific concepts (e.g. Molecular Quantum Mechanics)
Access cloud-based computing resources to perform calculations yourself
Hands-on step-by-step tutorials (e.g. Pharmaceutical Formulations course, pKa prediction)
Hands-on modeling in the web-based graphical user interface (e.g. Polymeric Materials course, Diffusion tutorial)
Videos on practical theory break down complex scientific concepts (e.g. Molecular Dynamics)
On-demand video lessons on materials modeling
Access cloud-based computing resources to perform calculations yourself
Perform case studies with expert feedback (e.g. Organic Electronic Course, Independent Case Study)
Video on practical theory break down complex scientific concepts (e.g. Machine Learning for Chemistry)
Videos on practical theory break down complex scientific concepts (e.g. Periodic Quantum Mechanics)
Videos on practical theory break down complex scientific concepts (e.g. Coarse-Graining)

Need help obtaining funding for a Schrödinger Online Course?

We proudly support the next generation of scientists and are committed to providing opportunities to those with limited resources. Learn about your funding options for our online certification courses as a student, post-doc, or industry scientist and enroll today!

Show off your newly acquired skills with a course badge and certificate

When you complete a course with us in molecular modeling and are ready to share what you learned with your colleagues and employers, you can share your certificate and badge on your LinkedIn profile.

Frequently asked questions

How much does the Practical Materials Informatics: Designing Molecules, Formulations, and Devices online course cost?

Pricing varies by each course and by the participant type. For students wishing to take this, we offer a student price of $160, and $600 for non-students.

What time are the lectures?

Once the course session begins, all lectures are asynchronous and you can view the self-paced videos, tutorials, and assignments at your convenience. When registering for the course you will select the start and end date. Within those dates, you will have asynchronous, on-demand access to the course material and virtual workstation to work on the course when it best suits your schedule.

How could I pay for this course?

Interested participants can pay for the course by completing their registration and using the credit card portal for an instant sign up. Please note that a credit card is required as we do not accept debit cards. Additionally, we can provide a purchase order upon request, please email online-learning@schrodinger.com if you are interested in this option. If you have any questions regarding how to pay for the course, please visit our funding options page.

Are there any scholarship opportunities available for students?

Schrödinger is committed to supporting students with limited resources. Schrödinger’s mission is to improve human health and quality of life by transforming the way therapeutics and materials are discovered. Schrödinger proudly supports the next generation of scientists. We have created a scholarship program that is open to full-time students or post-docs to students who can demonstrate financial need, and have a statement of support from the academic advisor. Please complete the application form if you qualify for our scholarship program!

Will material still be available after a course ends?

While access to the software will end when the course closes, some of the material within the course (slides, papers, and tutorials) are available for download so that you can refer back to it after the course. Other materials, such as videos, quizzes, and access to the software, will only be available for the duration of the course.

Related Courses

Molecular Modeling for Materials Science: Pharmaceutical Formulations Materials Science Materials Science
Pharmaceutical formulations

Molecular and periodic quantum mechanics, all atom molecular dynamics, and coarse-grained approaches for studying active pharmaceutical ingredients and their formulations

Molecular modeling for materials science applications: Polymeric materials course Materials Science Materials Science
Polymeric materials

All-atom molecular dynamics and machine learning approaches for studying polymeric materials and their properties under various conditions

Online certification course: Level-up your skill set in catalysis modeling Materials Science Materials Science
Homogeneous catalysis & reactivity

Molecular quantum mechanics and machine learning approaches for studying reactivity and mechanism at the molecular level

Supporting Associations

nanoHUB

EUROTOX 2026

EUROTOX 2026

CalendarDate & Time
  • September 13th-16th, 2026
LocationLocation
  • Vienna, Austria

Schrödinger is excited to be participating in the EUROTOX 2026 conference taking place on September 13th – 16th in Vienna, Austria. Join us for an e-poster presentation by Tatjana Braun, Senior Principal Scientist at Schrödinger, titled “Predictive Toxicology: Accelerating Off-Target Liability Mitigation through Physics-Based Cloud Workflows.” Stop by booth #88 to speak with Schrödinger scientists.

icon time
Predictive Toxicology: Accelerating Off-Target Liability Mitigation through Physics-Based Cloud Workflows

Speaker:
Tatjana Braun, Senior Principal Scientist, Schrödinger

Abstract:
Unmanaged toxicity accounts for approximately 30%1 of drug discovery project failures. While the adoption of experimental screening panels has improved the safety profiles of drugs entering the market, the high cost and significant latency of these screens often delay their implementation until the later stages of pre-clinical discovery. Consequently, they cannot be effectively integrated into the hit-finding and lead-optimization phases. To address the need for early off-target screening, many teams utilize digital toxicology models based on ligand-based machine learning. Although these models are fast and cost-effective, they are frequently limited by poor generalizability to novel ligand structures and lack the necessary protein context to help designers rationally mitigate liabilities.

We present a novel, physics-based in-silico solution for identifying and mitigating off-target liabilities. This approach constructs a detailed 3D atomistic representation of the ligand-target interaction and utilizes free energy calculations to model off-target binding. Molecules can be assessed against individual targets or a screening panel of representative targets, with all calculations performed in the cloud to eliminate local hardware requirements. This workflow has been successfully applied to diverse protein classes. Here, we share both retrospective validation from literature and prospective applications in drug discovery projects, highlighting how this workflow effectively helped resolve toxicity-related liabilities in CYP3A4 and hERG across our internal pipeline.