Brett M. Savoie
YOU?
Author Swipe
View article: Generalized Molecular Property Imputation Using a Flexible Transformer Architecture
Generalized Molecular Property Imputation Using a Flexible Transformer Architecture Open
Chemical data is fundamentally sparse, with molecular structures serving as database keys for countless properties. Current machine learning methods map structures to properties with remarkable accuracy, yet they do not leverage available …
View article: Design of Hybrid Quasi-2D Perovskite Ligands to Improve Stability
Design of Hybrid Quasi-2D Perovskite Ligands to Improve Stability Open
Quasi-two-dimensional (Q2D) metal-halide perovskites hold great promise for optoelectronic applications through their unique ability to accommodate bulky organic ligands while maintaining structural flexibility, offering advantages over co…
View article: Reaction Database for Catalysis and Organometallics via Freely Available Supplementary Information
Reaction Database for Catalysis and Organometallics via Freely Available Supplementary Information Open
Chemical reaction databases have become core scientific infrastructure. Most prominent datasets focus on or- ganic reactions, or only include reactants and product rather than full reaction pathways, leaving organometallic chemistry partic…
View article: LLMs4All: A Review of Large Language Models Across Academic Disciplines
LLMs4All: A Review of Large Language Models Across Academic Disciplines Open
Cutting-edge Artificial Intelligence (AI) techniques keep reshaping our view of the world. For example, Large Language Models (LLMs) based applications such as ChatGPT have shown the capability of generating human-like conversation on exte…
View article: Escaping Vibrational Purgatory: Hybrid kMC/MD Algorithms for Atomistic Simulations of Slow Reaction Chemistry
Escaping Vibrational Purgatory: Hybrid kMC/MD Algorithms for Atomistic Simulations of Slow Reaction Chemistry Open
Atomistic simulations provide essential mechanistic insights into chemical processes, yet many important phenomena in chemistry and materials science occur on timescales that are inaccessible to molecular dynamics. Existing computational a…
View article: Fluoride Electrolyte Discovery via Reactivity Guided Genetic Algorithms
Fluoride Electrolyte Discovery via Reactivity Guided Genetic Algorithms Open
Fluoride-ion batteries (FIBs) present a promising alternative to lithium-ion technologies, offering superior theoretical energy densities and improved sustainability. However, fluoride's high reactivity rapidly degrades traditional organic…
View article: LLMs4All: A Review of Large Language Models Across Academic Disciplines
LLMs4All: A Review of Large Language Models Across Academic Disciplines Open
Cutting-edge Artificial Intelligence (AI) techniques keep reshaping our view of the world. For example, Large Language Models (LLMs) based applications such as ChatGPT have shown the capability of generating human-like conversation on exte…
View article: Force‐Induced Selective Carbon‐Carbon Bond Cleavage in Mechanoresponsive Topochemical Polymers
Force‐Induced Selective Carbon‐Carbon Bond Cleavage in Mechanoresponsive Topochemical Polymers Open
Mechanoresponsive polymeric materials that respond to mechanical deformation are highly valued for their potential in sensors, degradation studies, and optoelectronics. However, direct visualization and detection of these responses remain …
View article: AIMNet2-rxn: A Machine Learned Potential for Generalized Reaction Modeling on a Millions-of-Pathways Scale
AIMNet2-rxn: A Machine Learned Potential for Generalized Reaction Modeling on a Millions-of-Pathways Scale Open
Mechanistic modeling of chemical transformations offers a compelling basis for understanding reactivity and allows for prediction of reaction outcomes before attempting experiments. Despite progress in machine learned interatomic potential…
View article: Design Rules for Thermally Depolymerizable Polybutadienes
Design Rules for Thermally Depolymerizable Polybutadienes Open
The vast majority of commodity plastics are based on all-carbon backbones. This creates a baseline for processing and mechanical properties that has been difficult to emulate with recyclable polymers that are based on heteroatomic linkages…
View article: Data-driven Coarse-Graining with Simple Functional Forms
Data-driven Coarse-Graining with Simple Functional Forms Open
Deep neural networks have become popular model architectures for fitting coarse-grained molecular dynamics potentials (CGMD) owing to their ability to describe complex features and ease of training against large datasets. However, such arc…
View article: Reaction Exploration Reveals Strong Kinetic Filtering in Li-Ion Battery Electrolyte Degradation
Reaction Exploration Reveals Strong Kinetic Filtering in Li-Ion Battery Electrolyte Degradation Open
A solid electrolyte interphase (SEI) forms spontaneously during the first few recharging cycles of a lithium-ion battery (LIB) due to electrolyte degradation at the electrodes. The properties of the SEI critically affect the lifespan and s…
View article: More Bang for Your Bond: Small Molecule Kinetics as Predictors of Polymer Stability
More Bang for Your Bond: Small Molecule Kinetics as Predictors of Polymer Stability Open
Thermally stable polymers are essential for many high-performance applications, yet the traditional experimental methods for studying stability are material intensive while machine learning models remain limited by the scarcity of reliable…
View article: Stereoregular radical polymers enable selective spin transfer
Stereoregular radical polymers enable selective spin transfer Open
Spintronic devices are emerging as an approach to realize performance and energy efficiency beyond what is possible with traditional electronic devices. State-of-the-art metals and doped conjugated polymers used for spin manipulation suffe…
View article: More Bang for Your Bond: Small Molecule Kinetics as Predictors of Polymer Stability
More Bang for Your Bond: Small Molecule Kinetics as Predictors of Polymer Stability Open
Thermally stable polymers are essential for many high-performance applications, yet the traditional experimental methods for studying stability are material intensive while machine learning models remain limited by the scarcity of reliable…
View article: Kinetics Overcome Thermodynamics in Primitive Analogs of the Reverse Tricarboxylic Acid Cycle
Kinetics Overcome Thermodynamics in Primitive Analogs of the Reverse Tricarboxylic Acid Cycle Open
The reverse/reductive tricarboxylic acid (rTCA) cycle is a metabolic pathway that facilitates CO2 fixation in certain anaerobic bacteria and archaea. Its presence in phylogenetically ancient organisms has led to hypotheses about its role i…
View article: Graphically-Defined Model Reactions are Extensible, Accurate, and Systematically Improvable
Graphically-Defined Model Reactions are Extensible, Accurate, and Systematically Improvable Open
Achieving fast and accurate reaction prediction is central to a suite of chemical applications. Nevertheless, classic approaches based on templates or simple models are typically fast but with limited scope or accuracy, while the emerging …
View article: Scalable, biologically sourced depolymerizable polydienes with intrinsically weakened carbon–carbon bonds
Scalable, biologically sourced depolymerizable polydienes with intrinsically weakened carbon–carbon bonds Open
View article: Verdazyl radical polymers for advanced organic spintronics
Verdazyl radical polymers for advanced organic spintronics Open
Spin currents have long been suggested as a potential solution to addressing circuit miniaturization challenges in the semiconductor industry. While many semiconducting materials have been extensively explored for spintronic applications, …
View article: Spintronic Pathways in a Nonconjugated Radical Polymer Glass
Spintronic Pathways in a Nonconjugated Radical Polymer Glass Open
Radical chemistries have attracted burgeoning attention due to their intriguing technological applications in organic electronics, optoelectronics, and magneto‐responsive systems. However, the potential of these magnetically active glassy …
View article: Facilitating Ionic and Electronic Conduction in Radical Polymers through Controlled Assembly
Facilitating Ionic and Electronic Conduction in Radical Polymers through Controlled Assembly Open
The major objectives, research performed, and significant results associated with this effort agree with the originally proposed work. That is, we have made significant advances in terms of both the experimental and computational thrusts o…
View article: Selenium Dioxide Catalyzed Polymerization of N‐doped Poly(benzodifurandione) (n‐PBDF) and Its Derivatives
Selenium Dioxide Catalyzed Polymerization of N‐doped Poly(benzodifurandione) (n‐PBDF) and Its Derivatives Open
The recent discovery of highly conductive, solution‐processable, n‐doped poly(benzodifurandione) (n‐PBDF) marks a milestone in the development of conducting polymers. Currently, n‐PBDF is prepared by either duroquinone‐mediated or copper‐c…
View article: Selenium Dioxide Catalyzed Polymerization of N‐doped Poly(benzodifurandione) (n‐PBDF) and Its Derivatives
Selenium Dioxide Catalyzed Polymerization of N‐doped Poly(benzodifurandione) (n‐PBDF) and Its Derivatives Open
The recent discovery of highly conductive, solution‐processable, n‐doped poly(benzodifurandione) (n‐PBDF) marks a milestone in the development of conducting polymers. Currently, n‐PBDF is prepared by either duroquinone‐mediated or copper‐c…
View article: Large property models: a new generative machine-learning formulation for molecules
Large property models: a new generative machine-learning formulation for molecules Open
We have built the first transformers trained on the property-to-molecular-graph task, which we dub “large property models”. A key ingredient is supplementing these models during training with relatively basic but abundant chemical property…
View article: Two-dimensional-lattice-confined single-molecule-like aggregates
Two-dimensional-lattice-confined single-molecule-like aggregates Open
View article: Chemical Networks from Scratch with Reaction Prediction and Kinetics-Guided Exploration
Chemical Networks from Scratch with Reaction Prediction and Kinetics-Guided Exploration Open
Algorithmic reaction explorations based on transition state searches can now routinely predict relatively short reaction sequences involving small molecules. However, applying these algorithms to deeper chemical reaction network (CRN) expl…
View article: Large Property Models: A New Generative Paradigm for Molecules
Large Property Models: A New Generative Paradigm for Molecules Open
Generative models for the inverse design of molecules with particular properties have been heavily hyped but have yet to demonstrate significant gains over machine learning augmented expert intuition. A major challenge of such models is th…
View article: Deductive Machine Learning Challenges and Opportunities in Chemical Applications
Deductive Machine Learning Challenges and Opportunities in Chemical Applications Open
Contemporary machine learning algorithms have largely succeeded in automating the development of mathematical models from data. Although this is a striking accomplishment, it leaves unaddressed the multitude of scenarios, especially across…
View article: Organic Reactivity Made Easy and Accurate with Automated Multireference Calculations
Organic Reactivity Made Easy and Accurate with Automated Multireference Calculations Open
In organic reactivity studies, quantum chemical calculations play a pivotal role as the foundation of understanding and machine learning model development. While prevalent black-box methods like density functional theory (DFT) and coupled-…
View article: Reductive Doping Inhibits the Formation of Isomerization‐Derived Structural Defects in N‐doped Poly(benzodifurandione) (n‐PBDF)
Reductive Doping Inhibits the Formation of Isomerization‐Derived Structural Defects in N‐doped Poly(benzodifurandione) (n‐PBDF) Open
Recently, solution‐processable n‐doped poly(benzodifurandione) (n‐PBDF) has been made through in‐situ oxidative polymerization and reductive doping, which exhibited exceptionally high electrical conductivities and optical transparency. The…