Efficient Long-Range Machine Learning Force Fields for Liquid and Materials Properties
Advancing efficiency in deep-blue OLEDs: Exploring a machine learning–driven multiresonance TADF molecular design
Band Gap and Reorganization Energy Prediction of Conducting Polymers by the Integration of Machine Learning and Density Functional Theory
Screening Antioxidant Ingredients Using Quantum Mechanics and Machine Learning
Accurate hydration free energy calculations for diverse organic molecules with a machine learning force field
Advancing battery materials innovation using charge-aware machine learning force fields
OCT 29, 2025
Advancing battery materials innovation using charge-aware machine learning force fields
Batteries are fundamental technology – powering everything from our personal electronics to electric vehicles, as well as large-scale grid storage systems for renewable energy integration. However, current battery technologies, primarily lithium-ion batteries, face significant limitations in performance, safety, cost, and reliance on scarce materials like cobalt. Therefore, innovation in battery materials is the key to unlocking the next generation of energy storage.
In this webinar, we will demonstrate how Schrödinger is utilizing an integrated computational approach combining physics-based molecular modeling with machine learning force fields (MLFFs) to address key challenges in battery materials design. We will introduce Schrödinger’s latest advancements in MLFFs, featuring charge recursive neural networks (QRNN) and the recently released Message Passing Network with Iterative Charge Equilibration (MPNICE) architectures, which incorporate explicit electrostatics for accurate charge representations.
Moreover, we will showcase several industry-relevant case studies highlighting the application of MLFFs to precisely model the structure and properties of electrolyte materials (liquid, polymer, and inorganic solid-state electrolytes), cathode coatings, and electrode materials. We will also explore how MLFFs facilitate large-scale simulations, allowing scientists to investigate the impact of defects and heterogeneities on crucial properties like Li-ion transport, paving the way for the efficient design of next-generation battery materials and chemistries.
Webinar Highlights:
- How Schrödinger combines physics-based modeling with machine learning force fields to drive battery materials discovery
- Schrödinger’s latest MLFF technologies, including QRNN and MPNICE
- Real-world case studies modeling electrolytes, cathode coatings, and electrode materials
- How MLFFs facilitate large-scale simulations, such as the investigation of Li-ion transport
Our Speaker
Garvit Agarwal
Principal Scientist, Schrödinger
Garvit Agarwal, Principal Scientist and Scientific Lead for Energy Storage at Schrödinger, works to extend and apply molecular modeling tools for the accelerated discovery of next-generation clean energy technologies. Garvit obtained his Ph.D. in Materials Science and Engineering from the University of Connecticut. He worked as a post-doctoral researcher in the Materials Science Division at Argonne National Laboratory prior to joining the Materials Science team at Schrödinger.
Machine Learning Force Fields
Advancing machine learning force fields for materials science applications 最新機能 MPNICEのご紹介
Advancing machine learning force fields for materials science applications
最新機能 MPNICEのご紹介
機械学習力場（MLFFs：Machine Learning Force Fields）は、「機械学習原子間ポテンシャル」とも呼ばれ、多様な化学系に対するコスト効率の高い原子レベルのシミュレーションを実現するための重要なツールとして登場しており、しばしば密度汎関数理論（DFT）に匹敵する精度を、はるかに低い計算コストで達成しています。
近年のメッセージパッシングネットワークの進歩により、従来のMLFFが抱えていた「対応できる元素の種類に制限がある」という課題が克服されました。さらに、電荷平衡法を用いた原子電荷および静電相互作用の導入により、複数の電荷状態、イオン系、電子応答特性の精密な再現が可能となり、長距離相互作用を明示的に考慮することで、さらに高い精度を実現しています。
本ウェビナーでは、シュレーディンガーが開発した最先端のMLFFアーキテクチャ「MPNICE（Message Passing Network with Iterative Charge Equilibration）」をご紹介します。MPNICEは、正確な電荷表現のために明示的な静電気を組み込んでいます。周期表全体（89元素）を網羅する材料を対象に学習させた事前学習済みモデル群も提供しています。
MPNICEは高いスループット性能を重視しており、従来の手法では実現困難だった長時間・大規模な原子レベルのシミュレーションを、高精度を維持しながら可能にします。
ウェビナーでは、材料設計においてより大規模かつ複雑なシミュレーションを可能にするMLFF搭載ツール群の概要を紹介し、産業応用に即した事例を交えて解説します。
ハイライト：
- MPNICEの概要：原子の部分電荷や長距離相互作用を取り入れながら、同等精度のモデルよりも1桁高速な計算を実現する、メッセージパッシング型機械学習力場（MLFF）アーキテクチャ
- MPNICEの最新応用例の紹介：産業界のニーズに対応するために、有機材料、無機材料、そして有機・無機ハイブリッド材料に対する汎用モデルとして活用された事例を紹介
Our Speaker
Jack Weber
Senior Scientist, Schrödinger
コロンビア大学で化学物理学の博士号を取得。博士課程では、先端的な計算手法を駆使し、化学および材料科学における基礎的課題に取り組み、遷移金属錯体のような強相関系に対応するための電子構造計算手法（ab initio法）の改良や、三重項－三重項消滅（TTA）型アップコンバージョン光触媒の設計などを行いました。 現在は、創薬および材料科学分野における応用を目的とした機械学習力場（MLFF）の開発に取り組んでいます。
Machine Learning Force Field
Advancing machine learning force fields for materials science applications
AUG 6, 2025
Advancing machine learning force fields for materials science applications
Machine learning force fields (MLFFs), also referred to as machine learning interatomic potentials, have emerged as a critical tool for the cost-efficient atomistic simulations of diverse chemical systems, often achieving density functional theory (DFT) accuracy at a fraction of the cost. Recent advances in message passing networks have 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 approaches have enabled accurate representations of multiple charge states, ionic systems, and electronic response properties, while simultaneously improving accuracy using explicit long-range interactions.
In this webinar, we will introduce Schrödinger’s state-of-the-art MLFF architecture, called Message Passing Network with Iterative Charge Equilibration (MPNICE), which incorporates explicit electrostatics for accurate charge representations. We present a family of pre-trained models trained on materials covering the entire periodic table (89 elements). MPNICE prioritizes efficient throughput, enabling atomistic simulations at length and time scales that were previously inaccessible without sacrificing accuracy. We will outline available tools in the Schrödinger suite that incorporate MLFFs to enable larger and more complex simulations for materials design, providing industry relevant examples throughout.
Highlights:
- Overview of MPNICE – a message passing MLFF architecture that includes atomic partial charges and long-range interactions, while maintaining speeds an order of magnitude faster than comparable models
- Highlights of recent applications of MPNICE, including general organic, inorganic, and hybrid (organic and inorganic) models to address industry relevant needs
Our Speaker
Jack Weber
Senior Scientist, Schrödinger
Jack Weber is a Senior Scientist at Schrödinger, where he develops machine learning force fields (MLFFs) for applications in drug discovery and materials science. Jack received his PhD in Chemical Physics in 2023 from Columbia University, advised by Professors Richard Friesner and David Reichman. In his doctoral research, he used advanced computational methods to investigate fundamental problems in chemistry and materials science, including improving ab-initio methods in electronic structure to treat strongly correlated systems.
Leveraging machine learning applications combined with physics-based modeling for drug discovery
OCT 4, 2023
Leveraging machine learning applications combined with physics-based modeling for drug discovery
Abstract:
Machine learning strategies in drug discovery are becoming increasingly popular and can be used in various areas. In the Schrödinger Suite DeepAutoQSAR serves as the main tool for training machine learning models to predict activity, ADMET, and other compound properties. In order to leverage both the proven accuracy and wide applicability domain of physics-based computational models, such as QM and FEP, together with the speed and scale of machine learning, we have combined our physics-based modeling technologies with an active learning framework. This framework can effectively speed up virtual screening methods such as in Active Learning -Glide, Active Learning-FEP, and Active Learning-ABFEP, or to improve the accuracy and applicability domain of models such as pKa prediction in Epik and machine learned force fields such as QRNN. We will also discuss how to utilize machine learning protein structure prediction methods to enable new targets for structure-based drug design.
Speaker:
Dr. Marton Vass, Principal Scientist II, Schrödinger