We introduce ChemPro, a progressive benchmark with 4100 natural language question-answer pairs in Chemistry, across 4 coherent sections of difficulty designed to assess the proficiency of Large Language Models (LLMs) in a broad spectrum of general chemistry topics. We include Multiple Choice Questions and Numerical Questions spread across fine-grained information recall, long-horizon reasoning, multi-concept questions, problem-solving with nuanced articulation, and straightforward questions in a balanced ratio, effectively covering Bio-Chemistry, Inorganic-Chemistry, Organic-Chemistry and Physical-Chemistry. ChemPro is carefully designed analogous to a student's academic evaluation for basic to high-school chemistry. A gradual increase in the question difficulty rigorously tests the ability of LLMs to progress from solving basic problems to solving more sophisticated challenges. We evaluate 45+7 state-of-the-art LLMs, spanning both open-source and proprietary variants, and our analysis reveals that while LLMs perform well on basic chemistry questions, their accuracy declines with different types and levels of complexity. These findings highlight the critical limitations of LLMs in
Activity cliff prediction - identifying positions where small structural changes cause large potency shifts - has been a persistent challenge in computational medicinal chemistry. This work focuses on a parsimonious definition: which small modifications, at which positions, confer the highest probability of an outcome change. Position-level sensitivity is calculated using 25 million matched molecular pairs from 50 ChEMBL targets across six protein families, revealing that two questions have fundamentally different answers. "Which positions vary most?" is answered by scaffold size alone (NDCG@3 = 0.966), requiring no machine learning. "Which are true activity cliffs?" - where small modifications cause disproportionately large effects, as captured by SALI normalization - requires an 11-feature model with 3D pharmacophore context (NDCG@3 = 0.910 vs. 0.839 random), generalizing across all six protein families, novel scaffolds (0.913), and temporal splits (0.878). The model identifies the cliff-prone position first 53% of the time (vs. 27% random - 2x lift), reducing positions a chemist must explore from 3.1 to 2.1 - a 31% reduction in first-round experiments. Predicting which modificat
Matched molecular pairs (MMPs) capture the local chemical edits that medicinal chemists routinely use to design analogs, but existing ML approaches either operate at the whole-molecule level with limited edit controllability or learn MMP-style edits from restricted settings and small models. We propose a variable-to-variable formulation of analog generation and train a foundation model on large-scale MMP transformations (MMPTs) to generate diverse variables conditioned on an input variable. To enable practical control, we develop prompting mechanisms that let the users specify preferred transformation patterns during generation. We further introduce MMPT-RAG, a retrieval-augmented framework that uses external reference analogs as contextual guidance to steer generation and generalize from project-specific series. Experiments on general chemical corpora and patent-specific datasets demonstrate improved diversity, novelty, and controllability, and show that our method recovers realistic analog structures in practical discovery scenarios.
To enhance large language models (LLMs) for chemistry problem solving, several LLM-based agents augmented with tools have been proposed, such as ChemCrow and Coscientist. However, their evaluations are narrow in scope, leaving a large gap in understanding the benefits of tools across diverse chemistry tasks. To bridge this gap, we develop ChemToolAgent, an enhanced chemistry agent over ChemCrow, and conduct a comprehensive evaluation of its performance on both specialized chemistry tasks and general chemistry questions. Surprisingly, ChemToolAgent does not consistently outperform its base LLMs without tools. Our error analysis with a chemistry expert suggests that: For specialized chemistry tasks, such as synthesis prediction, we should augment agents with specialized tools; however, for general chemistry questions like those in exams, agents' ability to reason correctly with chemistry knowledge matters more, and tool augmentation does not always help.
The spatial distribution of the chemical reservoirs in protoplanetary disks is key to elucidate the composition of planets, especially habitable ones. However, the partitioning of the main elements among the refractory and volatile phases is still elusive. Key parameters such as the carbon-to-oxygen C/O elemental ratio and the ionization fraction remain poorly constrained, with the latter potentially orders of magnitude lower than in the interstellar medium. Moreover, the thermal structure of the gas is also poorly known, despite its deep influence on gas-phase chemistry. In this context, ortho-to-para ratios could provide selective and sensitive probes. Recent ALMA observations have measured the spatially resolved column density of ortho-and para-H2CO in the transition disk orbiting TW Hya and derived the radial profile of the ortho-to-para ratio. Yet, current disk models do not include the nuclear-spin-resolved chemistry required to interpret these observations. The present work aims to fill this gap, by combining a parametric disk physical model of TW Hya with the UGAN network, updated to include a comprehensive description of the nuclear-spin-resolved chemistry of formaldehyde.
Large language models (LLM) have achieved impressive progress across a broad range of general-purpose tasks, but their effectiveness in chemistry remains limited due to scarce domain-specific datasets and the demand for precise symbolic and structural reasoning. Here we introduce ECNU-ChemGPT(name after East China Normal University), a chemistry-specialized LLM engineered for deep chemical knowledge understanding and accurate retrosynthetic route planning. Our approach is distinguished by four key strategies: structured prompt-based knowledge distillation from authoritative chemistry textbooks to construct a high-quality question-answering dataset; domain-specific prompt engineering using curated chemical keywords, combined with LLMs APIs for data derivation and knowledge distillation; large-scale fine-tuning on a meticulously cleaned and enriched Pistachio reaction dataset to enhance retrosynthesis prediction accuracy; and integration of BrainGPT, a dynamic multi-model scheduling framework that enables task-specific invocation of multiple specialized models trained for diverse chemistry-related tasks. ECNU-ChemGPT exhibits superior performance on chemistry question-answering and r
Medicinal plants have been a key component in producing traditional and modern medicines, especially in the field of Ayurveda, an ancient Indian medical system. Producing these medicines and collecting and extracting the right plant is a crucial step due to the visually similar nature of some plants. The extraction of these plants from nonmedicinal plants requires human expert intervention. To solve the issue of accurate plant identification and reduce the need for a human expert in the collection process; employing computer vision methods will be efficient and beneficial. In this paper, we have proposed a model that solves such issues. The proposed model is a custom convolutional neural network (CNN) architecture with 6 convolution layers, max-pooling layers, and dense layers. The model was tested on three different datasets named Indian Medicinal Leaves Image Dataset,MED117 Medicinal Plant Leaf Dataset, and the self-curated dataset by the authors. The proposed model achieved respective accuracies of 99.5%, 98.4%, and 99.7% using various optimizers including Adam, RMSprop, and SGD with momentum.
Accelerated materials discovery is critical for addressing global challenges. However, developing new laboratory workflows relies heavily on real-world experimental trials, and this can hinder scalability because of the need for numerous physical make-and-test iterations. Here we present MATTERIX, a multiscale, graphics processing unit-accelerated robotic simulation framework designed to create high-fidelity digital twins of chemistry laboratories, thus accelerating workflow development. This multiscale digital twin simulates robotic physical manipulation, powder and liquid dynamics, device functionalities, heat transfer and basic chemical reaction kinetics. This is enabled by integrating realistic physics simulation and photorealistic rendering with a modular graphics processing unit-accelerated semantics engine, which models logical states and continuous behaviors to simulate chemistry workflows across different levels of abstraction. MATTERIX streamlines the creation of digital twin environments through open-source asset libraries and interfaces, while enabling flexible workflow design via hierarchical plan definition and a modular skill library that incorporates learning-based
Multimodal scientific reasoning remains a significant challenge for large language models (LLMs), particularly in chemistry, where problem-solving relies on symbolic diagrams, molecular structures, and structured visual data. Here, we systematically evaluate 40 proprietary and open-source multimodal LLMs, including GPT-5, o3, Gemini-2.5-Pro, and Qwen2.5-VL, on a curated benchmark of Olympiad-style chemistry questions drawn from over two decades of U.S. National Chemistry Olympiad (USNCO) exams. These questions require integrated visual and textual reasoning across diverse modalities. We find that many models struggle with modality fusion, where in some cases, removing the image even improves accuracy, indicating misalignment in vision-language integration. Chain-of-Thought prompting consistently enhances both accuracy and visual grounding, as demonstrated through ablation studies and occlusion-based interpretability. Our results reveal critical limitations in the scientific reasoning abilities of current MLLMs, providing actionable strategies for developing more robust and interpretable multimodal systems in chemistry. This work provides a timely benchmark for measuring progress in
While drug discovery is vital for human health, the process remains inefficient. Medicinal chemists must navigate a vast protein space to identify target proteins that meet three criteria: physical and functional interactions, therapeutic impact, and docking potential. Prior approaches have provided fragmented support for each criterion, limiting the generation of promising hypotheses for wet-lab experiments. We present HAPPIER, an AI-powered tool that supports hypothesis generation with integrated multi-criteria support for target identification. HAPPIER enables medicinal chemists to 1) efficiently explore and verify proteins in a single integrated graph component showing multi-criteria satisfaction and 2) validate AI suggestions with domain knowledge. These capabilities facilitate iterative cycles of divergent and convergent thinking, essential for hypothesis generation. We evaluated HAPPIER with ten medicinal chemists, finding that it increased the number of high-confidence hypotheses and support for the iterative cycle, and further demonstrated the relationship between engaging in such cycles and confidence in outputs.
The hydration of magnesium oxide (MgO) to magnesium hydroxide (Mg(OH)$_2$) is a fundamental solid-surface chemical reaction with significant implications for materials science. Yet its molecular-level mechanism from water adsorption to Mg(OH)$_2$ nucleation and growth remains elusive due to its complex and multi-step nature. Here, we elucidate the molecular process of MgO hydration based on structures of the MgO/water interface obtained by a combined computational chemistry approach of potential-scaling molecular dynamics simulations and first-principles calculations without any a priori assumptions about reaction pathways. The result shows that the Mg$^{2+}$ dissolution follows the dissociative water adsorption. We find that this initial dissolution can proceed exothermically even from the defect-free surface with an average activation barrier of $\sim$12 kcal/mol. This exothermicity depends crucially on the stabilization of the resulting surface vacancy, achieved by proton adsorption onto neighboring surface oxygen atoms. Further Mg$^{2+}$ dissolution then occurs in correlation with proton penetration into the solid. Moreover, we find that the Mg(OH)$_2$ nucleation and growth pro
Efficient chemical kinetic model inference and application in combustion are challenging due to large ODE systems and widely separated time scales. Machine learning techniques have been proposed to streamline these models, though strong nonlinearity and numerical stiffness combined with noisy data sources make their application challenging. Here, we introduce ChemKANs, a novel neural network framework with applications both in model inference and simulation acceleration for combustion chemistry. ChemKAN's novel structure augments the generic Kolmogorov Arnold Network Ordinary Differential Equations (KAN-ODEs) with knowledge of the information flow through the relevant kinetic and thermodynamic laws. This chemistry-specific structure combined with the expressivity and rapid neural scaling of the underlying KAN-ODE algorithm instills in ChemKANs a strong inductive bias, streamlined training, and higher accuracy predictions compared to standard benchmarks, while facilitating parameter sparsity through shared information across all inputs and outputs. In a model inference investigation, we benchmark the robustness of ChemKANs to sparse data containing up to 15% added noise, and superfl
Stratospheric aerosol injection (SAI) has been proposed as a geoengineering strategy to mitigate global warming by increasing Earth's albedo. Silica-based materials, such as diamond-doped silica aerogels, have shown promising optical properties, but their impact on stratospheric chemistry, ozone one in particular, remains largely unknown. Here, we present first-principles molecular dynamics (MD) simulations of the heterogeneous reaction between hydrogen chloride ($\mathrm{HCl}$) and chlorine nitrate ($\mathrm{ClONO_2}$), two main reservoirs of stratospheric chlorine and nitrogen species, on a dry, hydroxylated $α$-quartz silica interface. Our results reveal a barrierless reaction pathway toward the formation of chlorine gas ($\mathrm{Cl}_2$), a major contributor to stratospheric ozone loss. We design a heterogeneous kinetic model informed by our MD simulation and available experimental data: despite the barrierless formation of $\mathrm{Cl_2}$, the higher surface affinities and partial pressures of $\mathrm{HNO_3}$ and $\mathrm{HCl}$ compared to those of $\mathrm{ClONO_2}$ result in a negligible reaction probability, $γ_\mathrm{ClONO_2}$, upon chlorine nitrate collision with the si
Cyanopolyynes, a family of nitrogen containing carbon chains, are common in the interstellar medium and possibly form the backbone of species relevant to prebiotic chemistry. Following their gas phase formation, they are expected to freeze out on ice grains in cold interstellar regions. In this work we present the hydrogenation reaction network of isolated HC_{3}N, the smallest cyanopolyyne, that consists over-a-barrier radical-neutral reactions and barrierless radical-radical reactions. We employ density functional theory, coupled cluster and multiconfigurational methods to obtain activation and reaction energies for the hydrogenation network of HC_{3}N. This work explores the reaction network of the isolated molecule and constitutes a preview on the reactions occurring on the ice grain surface. We find that the reactions where the hydrogen atom adds to the carbon chain at carbon atom opposite of the cyano-group give the lowest and most narrow barriers. Subsequent hydrogenation leads to the astrochemically relevant vinyl cyanide and ethyl cyanide. Alternatively, the cyano-group can hydrogenate via radical-radical reactions, leading to the fully saturated propylamine. These results
Three-body recombination, or ternary association, is a termolecular reaction in which three particles collide, forming a bound state between two, whereas the third escapes freely. Three-body recombination reactions play a significant role in many systems relevant to physics and chemistry. In particular, they are relevant in cold and ultracold chemistry, quantum gases, astrochemistry, atmospheric physics, physical chemistry, and plasma physics. As a result, three-body recombination has been the subject of extensive work during the last 50 years, although primarily from an experimental perspective. Indeed, a general theory for three-body recombination remains elusive despite the available experimental information. Our group recently developed a direct approach based on classical trajectory calculations in hyperspherical coordinates for three-body recombination to amend this situation, leading to a first principle explanation of ion-atom-atom and atom-atom-atom three-body recombination processes. This review aims to summarize our findings on three-body recombination reactions and identify the remaining challenges in the field.
In this work, the teaching content of a theoretical-chemistry (TC) course is reformed, establishing a theoretical contents from micro- to macro-system, and comprehensively introducing the theory of chemical reaction to undergraduate students in chemistry. In order to develop such TC course based on the general physical-chemistry course, we focus on the last-mile problem between the physics and chemistry courses to train the critical thinking of undergraduate students in chemistry. To clearly show this, a reduction scheme of polymer molecular dynamics was discussed as an example, which shows a different theoretical content in polymer chemistry. Moreover, we propose a series of experiences and dependent measures that can provide information regarding students' levels of knowledge and understanding. This assessment quiz was designed to test students on the fundamental concepts and applications of TC, such as dynamics, statistical ensemble, kinetics, and so on. From the actual teaching for 36 students, it was found that these students performed significantly improvement from the present TC content. Further analysis of each individual question revealed that approximately two-third of th
We present two open-source implementations of the Locally Optimal Block Preconditioned Conjugate Gradient (LOBPCG) algorithm to find a few eigenvalues and eigenvectors of large, possibly sparse matrices. We then test LOBPCG for various quantum chemistry problems, encompassing medium to large, dense to sparse, wellbehaved to ill-conditioned ones, where the standard method typically used is Davidson's diagonalization. Numerical tests show that, while Davidson's method remains the best choice for most applications in quantum chemistry, LOBPCG represents a competitive alternative, especially when memory is an issue, and can even outperform Davidson for ill-conditioned, non diagonally dominant problems.
Plasma Assisted Combustion (PAC) is a promising technology to enhance the combustion of lean mixtures prone to instabilities and flame blow-off. Although many PAC experiments demonstrated combustion enhancement, several studies report an increase in NOx emissions. The aim of this study is to determine the kinetic pathways leading to NOx formation in the second stage of a sequential combustor assisted by Nanosecond Repetitively Pulsed Discharges (NRPDs). For this purpose, Large Eddy Simulation (LES) associated with an accurate description of the combustion/NOx chemistry and a phenomenological model of the plasma kinetics is used. Detailed kinetics 0-Dimensional reactors complement the study. First, the LES setup is validated by comparison with experiments. Then, the NOx chemistry is analyzed. For the conditions of operation studied, it is shown that the production of atomic nitrogen in the plasma by direct electron impact on nitrogen molecules increases the formation of NO. Then, the NO molecules are transported through the turbulent flame without being strongly affected. This study illustrates the need to limit the diatomic nitrogen dissociation process in order to mitigate harmful
Medicinal plants are increasingly recognized worldwide as an alternative source of efficacious and inexpensive medications to synthetic chemo-therapeutic compound. Rapid declining wild stocks of medicinal plants accompanied by adulteration and species substitutions reduce their efficacy, quality and safety. Consequently, the low accessibility to and non-affordability of orthodox medicine costs by rural dwellers to be healthy and economically productive further threaten their life expectancy. Finding comprehensive information on medicinal plants of conservation concern at a global level has been difficult. This has created a gap between computing technologies' promises and expectations in the healing process under complementary and alternative medicine. This paper presents the design and implementation of a Multimedia-based Medicinal Plants Sustainability Management System addressing these concerns. Medicinal plants' details for designing the system were collected through semi-structured interviews and databases. Unified Modelling Language, Microsoft-Visual-Studio.Net, C#3.0, Microsoft-Jet-Engine4.0, MySQL, Loquendo Multilingual Text-to-Speech Software, YouTube, and VLC Media Player
During this era of new drug designing, medicinal plants had become a very interesting object of further research. Pharmacology screening of active compound of medicinal plants would be time consuming and costly. Molecular docking is one of the in silico method which is more efficient compare to in vitro or in vivo method for its capability of finding the active compound in medicinal plants. In this method, three-dimensional structure becomes very important in the molecular docking methods, so we need a database that provides information on three-dimensional structures of chemical compounds from medicinal plants in Indonesia. Therefore, this study will prepare a database which provides information of the three dimensional structures of chemical compounds of medicinal plants. The database will be prepared by using MySQL format and is designed to be placed in http://herbaldb.farmasi.ui.ac.id website so that eventually this database can be accessed quickly and easily by users via the Internet.