Contact Us

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

Posted on May 8, 2024August 2, 2024 by Anonymous
FEB 2, 2022

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

Speaker:

Matt Repasky
Senior Vice President

Abstract:

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. Ultra-large, on-demand synthesizable libraries from vendors have enabled ~100x expansion of purchasable compound space, now billions of compounds, while DNA encoded libraries (DEL) can be even larger. In order to screen these much larger chemical spaces in the billions of compounds, results of two machine learning enabled approaches are described that make it easy and cost effective to find novel hits through virtual and DEL screens of billion compound plus libraries. DNA encoded libraries (DEL) enable screening billions of synthesized compounds but are limited due to high rates of experimental false negatives and positives. Employing machine learning trained to experimental DEL results we demonstrate significantly reduced false negative rates while identifying byproducts in a more favorable property space. To enable efficient, extrapolative chemical space exploration with an accurate docking scoring function, we have developed an active learning-based method employing AutoQSAR/DC machine learning and Glide SP docking as the learner. Results from Active Learning Glide screening of 100 million to billion compound screens show increased chemical diversity and GlideScore of hits relative to brute force screening of subsets of the libraries. Results and costs from these two new methods suggest billion compound library screens could replace smaller, traditional screens commonly employed today.

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

Posted on May 2, 2024November 6, 2025 by Anonymous
MAY 29, 2024

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

Our world is evolving rapidly and with it comes a wide range of challenges, including the need for sustainable and energy-efficient solutions, advanced electronic devices, and durable, lightweight materials for transportation, aerospace, and construction. Traditional methods for materials discovery or selection are no longer viable for keeping pace with demands. 

In this talk, we will introduce a modern approach to materials R&D using a digital chemistry platform for in silico analysis, optimization, and discovery. The platform enables materials design at-scale across a wide range of applications, including organic electronics, catalysis, energy capture and storage, polymeric materials, consumer packaged goods, pharmaceutical formulation and delivery, and thin film processing. 

By combining both physics-based modeling approaches (e.g. DFT, molecular dynamics, coarse-graining) and machine learning, researchers can easily incorporate in silico methods into their day-to-day workflows to expedite R&D timelines. Moreover, automated solutions enable scaling from simple molecular property predictions on a local device to high-throughput calculations on the cloud.

We will present real-world case studies that were performed by both experienced modelers as well as novice experimentalists who are new to digital chemistry approaches. 

 

Key Learning Objectives:

  • Learn to leverage data from physics-based simulations and machine learning to accelerate materials R&D
  • Hear practical case studies and customer stories across materials industries including organic electronics, catalysis, energy capture and storage, polymeric materials, consumer packaged goods, pharmaceutical formulation and delivery, and thin film processing
  • Identify key areas in your R&D where physics-based simulation and machine learning can provide value

Michael Rauch, Ph.D.

Associate Director

Michael Rauch is an Associate Director at Schrödinger specializing in materials science and education. Michael earned his Ph.D. from Columbia University in synthetic organometallic chemistry as an NSF Graduate Research Fellow before pursuing a postdoctoral role in organic chemistry at the Weizmann Institute of Science as a Zuckerman Postdoctoral Scholar. Michael is particularly interested in green, sustainable chemistry and transforming the way that synthetic chemists utilize molecular modeling via practical education.

Data-driven materials innovation: Where machine learning meets physics

Posted on October 10, 2023November 6, 2025 by Anonymous
OCT 10, 2023

Data-driven materials innovation: Where machine learning meets physics

Abstract:

The surge of machine learning (ML) in materials science and chemistry has been driven by advancements in deep learning methodologies. While many industrial scientists aspire to transition to a data-centric and AI-guided design paradigm, companies often deal with limited datasets and complex materials that require customised featurisation techniques. Moreover, commonly used ML techniques often grapple with issues of explainability and extrapolation into unexplored chemical spaces.

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. We highlight how this synergistic approach can transform materials innovation across a wide-range of technology verticals. Specifically, we will highlight case studies in the following areas:

  • Using molecular dynamics simulations to generate descriptors that enhance the accuracy of ML models for viscosity predictions
  • Developing explainable ML models to predict the ionic conductivity of Li-ion battery electrolytes
  • Augmenting the performance of ML models for predicting properties such as absorption and emission wavelengths, fluorescence lifetime, and extinction coefficients of organic electronics using descriptors rooted in density functional theory

This integrated approach signifies a new frontier in materials science and chemistry, combining the strengths of ML and physics-informed methods.

Anand Chandrasekaran

Senior Principal Scientist

Machine learning force fields for improved materials modeling

Posted on August 18, 2023November 10, 2025 by Anonymous

Machine learning force fields for improved materials modeling

Machine learning force fields (MLFFs), also known as machine learning interatomic potentials, represent an intermediate between classical force fields and density functional theory (DFT), maintaining the linear scaling of the former while approaching the accuracy of the latter. Beyond the balance of accuracy and efficiency/cost, MLFFs are enabling new scientific insights by making large-scale and longtime scale simulations feasible for reactive systems. This opens the door to modeling complex materials systems that were previously computationally prohibitive with traditional quantum methods.

Message Passing Network with Iterative Charge Equilibration (MPNICE) is an MLFF architecture developed by Schrödinger for which multiple pretrained models spanning 89 elements are available, and which explicitly incorporates equilibrated atomic charges and long range electrostatics.1 This technological advancement has removed the drawback of previous MLFFs that were limited by the number of unique atomic elements they could model. Furthermore, inclusion of atomic charges and electrostatics through charge equilibration has enabled representation of multiple charge states, ionic systems, and electronic response properties, while simultaneously improving accuracy. In addition to MPNICE, the Schrӧdinger suite also allows users to utilize the Universal Models for Atoms (UMA),2 developed at Meta. This suite of models offers very high accuracy, includes a model that yields good performance for reaction barrier heights for finite systems, and covers the majority of the periodic table.

By integrating state-of-the-art MLFF methods with high-performance OPLS4 or OPLS5 force fields, as well as advanced DFT and molecular dynamics (MD) engines, Schrödinger offers a uniquely powerful platform for materials simulation — positioning us as the leading partner in advanced MLFF technologies. In this application note, we present case studies from materials-intensive industries, including batteries and catalysis.

Benefits of MLFF

Near DFT-level accuracy with orders of magnitude reduction in computational time
Option for GPU accelerated molecular dynamics with Desmond
Large chemical space spanning 89 elements
Specialized force fields for organic, inorganic, and hybrid materials
Figure 1: Illustrative examples of Schrödinger’s MLFF workflow and its applications *Datasets references: Nature Machine Intelligence 2023, 5, 1031–1041; arXiv:2410.12771

Diverse applications of MLFF 

Batteries:

  • Calculate bulk and transport properties, such as diffusion, viscosity, and conductivity of liquid electrolytes
  • Simulate Li-ion diffusion in solid-state electrolytes and cathode coating materials
  • Model electrolyte reactivity and SEI formation

OLED materials:

  • Simulate molecular packing and thin-film morphology
  • Investigate doping, host-guest, and interlayer interactions
  • Link device properties to the static and dynamic disorder of molecular systems
  • Facilitate thermomechanical property prediction
  • Model charge and exciton transport

Crystal structure prediction:

  • Rank order organic crystal structures

Adsorption on surfaces:

  • Study reactivity of multiple adsorbates in extended models of complex surfaces

Reactivity in molecules and solid-state:

  • Investigate reaction pathways and transition states
  • Expedite catalyst design
  • Optimize chemical reactions

Polymers:

  • Evaluate polymer dynamical properties
  • Investigate solid polymer electrolytes

Read the full white paper

Download white paper

References

  1. Efficient long-range machine learning force fields for liquid and materials properties.

    Weber JL, et al. arXiv:2505.06462. 1 Aug 2025.

  2. UMA: A Family of Universal Models for Atoms.

    Wood BM, et al. arXiv:2506.23971. 30 June 2025. 

  3. Synthesis of lithium aluminate for application in radiation dosimetry.

    Ha, NTT, et al. Materials Letters. 2020, 267, 127506. 

  4. Ultrathin lithium-ion conducting coatings for increased interfacial stability in high voltage lithium-ion batteries.

    Park, JS, et al. Chemistry of Materials. 2014, 26, 3128–3134.

Software and services to meet your organizational needs

Software Platform

Deploy digital materials discovery workflows with a comprehensive and user-friendly platform grounded in physics-based molecular modeling, machine learning, and team collaboration.

Research Services

Leverage Schrödinger’s expert computational scientists to assist at key stages in your materials discovery and development process.

Support & Training

Access expert support, educational materials, and training resources designed for both novice and experienced users.