arXiv subjects

Valéry Weber

Publications and source records attributed to Valéry Weber.

8 recordsLinked to original sources

arXiv2026

MarkushGrapher-2: End-to-end Multimodal Recognition of Chemical Structures

Automatically extracting chemical structures from documents is essential for the large-scale analysis of the literature in chemistry. Automatic pipelines have been developed to recognize molecules represented either in figures or in text independently. However, methods for recognizing chemical structures from multimodal descriptions (Markush structures) lag behind in precision and cannot be used for automatic large-scale processing. In this work, we present MarkushGrapher-2, an end-to-end approach for the multimodal recognition of chemical structures in documents. First, our method employs a dedicated OCR model to extract text from chemical images. Second, the text, image, and layout information are jointly encoded through a Vision-Text-Layout encoder and an Optical Chemical Structure Recognition vision encoder. Finally, the resulting encodings are effectively fused through a two-stage training strategy and used to auto-regressively generate a representation of the Markush structure. To address the lack of training data, we introduce an automatic pipeline for constructing a large-scale dataset of real-world Markush structures. In addition, we present IP5-M, a large manually-annotated benchmark of real-world Markush structures, designed to advance research on this challenging task. Extensive experiments show that our approach substantially outperforms state-of-the-art models in multimodal Markush structure recognition, while maintaining strong performance in molecule structure recognition. Code, models, and datasets are released publicly.

cs.CV↗

arXiv2025

SubGrapher: Visual Fingerprinting of Chemical Structures

Automatic extraction of chemical structures from scientific literature plays a crucial role in accelerating research across fields ranging from drug discovery to materials science. Patent documents, in particular, contain molecular information in visual form, which is often inaccessible through traditional text-based searches. In this work, we introduce SubGrapher, a method for the visual fingerprinting of chemical structure images. Unlike conventional Optical Chemical Structure Recognition (OCSR) models that attempt to reconstruct full molecular graphs, SubGrapher focuses on extracting molecular fingerprints directly from chemical structure images. Using learning-based instance segmentation, SubGrapher identifies functional groups and carbon backbones, constructing a substructure-based fingerprint that enables chemical structure retrieval. Our approach is evaluated against state-of-the-art OCSR and fingerprinting methods, demonstrating superior retrieval performance and robustness across diverse molecular depictions. The dataset, models, and code are publicly available.

cs.CV↗

arXiv2025

MarkushGrapher: Joint Visual and Textual Recognition of Markush Structures

The automated analysis of chemical literature holds promise to accelerate discovery in fields such as material science and drug development. In particular, search capabilities for chemical structures and Markush structures (chemical structure templates) within patent documents are valuable, e.g., for prior-art search. Advancements have been made in the automatic extraction of chemical structures from text and images, yet the Markush structures remain largely unexplored due to their complex multi-modal nature. In this work, we present MarkushGrapher, a multi-modal approach for recognizing Markush structures in documents. Our method jointly encodes text, image, and layout information through a Vision-Text-Layout encoder and an Optical Chemical Structure Recognition vision encoder. These representations are merged and used to auto-regressively generate a sequential graph representation of the Markush structure along with a table defining its variable groups. To overcome the lack of real-world training data, we propose a synthetic data generation pipeline that produces a wide range of realistic Markush structures. Additionally, we present M2S, the first annotated benchmark of real-world Markush structures, to advance research on this challenging task. Extensive experiments demonstrate that our approach outperforms state-of-the-art chemistry-specific and general-purpose vision-language models in most evaluation settings. Code, models, and datasets will be available.

cs.CV↗

arXiv2020

CP2K: An Electronic Structure and Molecular Dynamics Software Package -- Quickstep: Efficient and Accurate Electronic Structure Calculations

CP2K is an open source electronic structure and molecular dynamics software package to perform atomistic simulations of solid-state, liquid, molecular and biological systems. It is especially aimed at massively-parallel and linear-scaling electronic structure methods and state-of-the-art ab-initio molecular dynamics simulations. Excellent performance for electronic structure calculations is achieved using novel algorithms implemented for modern high-performance computing systems. This review revisits the main capabilities of CP2k to perform efficient and accurate electronic structure simulations. The emphasis is put on density functional theory and multiple post-Hartree-Fock methods using the Gaussian and plane wave approach and its augmented all-electron extension.

physics.chem-ph↗

arXiv2019

Comparison of computational methods for the electrochemical stability window of solid-state electrolyte materials

Superior stability and safety are key promises attributed to all-solid-state batteries (ASSBs) containing solid-state electrolyte (SSE) compared to their conventional counterparts utilizing liquid electrolyte. To unleash the full potential of ASSBs, SSE materials that are stable when in contact with the low and high potential electrodes are required. The electrochemical stability window is conveniently used to assess the SSE-electrode interface stability. In the present work, we review the most important methods to compute the SSE stability window. Our analysis reveals that the stoichiometry stability method represents a bridge between HOMO-LUMO method and phase stability method (grand canonical phase diagram). Moreover, we provide computational implementations of these methods for SSE material screening. We compare their results for the relevant Li- and Na-SSE materials LGPS, LIPON, LLZO, LLTO, LATP, LISICON, and NASICON, and we discuss their relation to published experimental stability windows.

cond-mat.mtrl-sci↗

arXiv2013

Conditional solvation of isoleucine in model extended and helical peptides: context dependence of hydrophobic hydration and the failure of the group-transfer model

The hydration thermodynamics of the GXG tripeptide relative to the reference GGG is often used to define the conditional hydration contribution of X. This quantity or the hydration thermodynamics of a small molecule analog of the side-chain or some combination of such estimates, have anchored the interpretation of seminal experiments on protein stability and folding. We show that such procedures to model protein hydration have significant limitations. We study the conditional hydration thermodynamics of the isoleucine side-chain in an extended pentapeptide and in helical deca-peptides, using as appropriate an extended penta-glycine or appropriate helical deca-peptides as reference. Hydration of butane in the gauche conformation provides a small molecule reference for the side-chain. We use the quasichemical theory to parse the hydration thermodynamics into chemical, packing, and long-range interaction contributions. The chemical contribution reflects the contribution of solvent clustering within the defined inner-shell of the solute; the chemical contribution of g-butane is substantially more negative than the conditional chemical contribution of isoleucine. The packing contribution gives the work required to create a cavity in the solvent, a quantity of interest in understanding hydrophobic hydration. The packing contribution for g-butane substantially overestimates the conditional packing of isoleucine. The net of such compensating contributions still disagrees with the conditional free energy of isoleucine but by a lesser magnitude. The excess enthalpy and entropy of hydration of g-butane model are also more negative than the corresponding conditional quantities for the side-chain. The conditional solvation of isoleucine in GGIGG also proves unsatisfactory in describing the conditional solvation of isoleucine in the helical peptides.

physics.bio-ph↗

arXiv2010

Thermodynamics of water modeled using ab initio simulations

We regularize the potential distribution framework to calculate the excess free energy of liquid water simulated with the BLYP-D density functional. The calculated free energy is in fair agreement with experiments but the excess internal energy and hence also the excess entropy are not. Our work emphasizes the importance of thermodynamic characterization in assessing the quality of electron density functionals in describing liquid water and hydration phenomena.

physics.chem-ph↗

arXiv2004

Higher Order Response in ${\cal O}(N)$ by Perturbed Projection

Perturbed projection for linear scaling solution of the coupled-perturbed self-consistent-field equations [Weber, Niklasson and Challacombe, Phys. Rev.\ Lett. {\bf 92}, 193002 (2004)] is extended to the computation of higher order static response properties. Although generally applicable, perturbed projection is developed here in the context of the self-consistent first and second electric hyperpolarizabilities of three dimensional water clusters at the Hartree-Fock level of theory. Non-orthogonal, density matrix analogues of Wigner's $2n+1$ rule are given up to fourth order. Linear scaling and locality of the higher order response densities under perturbation by a global electric field are demonstrated.

cond-mat.mtrl-sci↗