ProtoMI is a literature‑driven framework that learns structural priors from 126 reported boron‑containing electrolyte additives and applies them to screen 179,977 unlabeled candidates. Using graph contrastive learning, it identifies seven interpretable prototypes and adapts them through semi‑supervised contrastive learning, achieving enrichment factors of 9.2–45.6 while evaluating less than 2% of the candidate space. The method led to the discovery of four commercially accessible additives, including TNDB, which improves high‑temperature LiFePO4||graphite cycling by 34.93% and forms protective interphases that suppress solvent decomposition and Fe deposition.
arXiv:2607. 25597v1 Announce Type: new Abstract: The reactivity of lithium-metal electrolytes arises from the interplay of molecular functional groups, Li$^+$ solvation, and salt-anion participation.
The paper presents a hierarchical deep‑learning framework that integrates compositional, structural, and transport models to screen solid‑state electrolytes. Four modules—L‑G‑DCNN, DenseGNN, MatterSim, and DeePMD—coordinate to evaluate thermodynamics, multi‑property performance, and kinetic transport, outperforming existing methods. Applied to over 30 million candidates, the workflow identifies 97 high‑performance materials, mainly halides, and links Li⁺ jump‑network connectivity to ionic conductivity while highlighting limits for oxide electrolytes.
The paper introduces EMolStudio, a density‑matrix‑centered AI platform that predicts and analyzes electronic structure for electrolyte molecules in lithium batteries. It integrates molecular functionalization, explicit Li⁺ first‑shell assembly, density‑matrix prediction, and electronic‑structure parsing, enabling systematic study of 163,655 functionalized molecules and 22,500 first‑shell clusters across four lithium salts. The analysis reveals that functional groups and anion identity distinctly influence frontier orbital energies, electrostatic potential, and Li⁺‑donor contacts, with LiTDI anchoring the highest occupied orbital on the anion.
arXiv:2607. 02212v1 Announce Type: cross Abstract: Aqueous solubility is a key property in early-stage drug discovery, but most predictive models merge physicochemical descriptors and molecular graph information into a single representation, obscuring whether a prediction is driven by global chemistry, molecular structure, or both.
arXiv:2609.37384v1 Announce Type: new Abstract: Molecular representation learning is central to computer-aided drug discovery. Molecular graphs, SMILES strings, and 3D conformations provide complemen...
arXiv:2606. 24983v1 Announce Type: cross Abstract: Implicit solvent machine learning potentials (MLPs) offer a powerful route to bridging the gap between accuracy and efficiency in molecular simulations.
arXiv:2607. 23886v1 Announce Type: cross Abstract: X-ray absorption spectroscopy (XAS) is central to understanding the local electronic and atomic structure of materials, yet most published spectra remain inaccessible to data-driven analysis because they are embedded in figures and described through fragmented textual context in the literature.
arXiv:2607. 07708v1 Announce Type: cross Abstract: Structure-property relationships are foundational to biology, chemistry and materials science, where function, reactivity and physical response emerge from spatial, chemical and periodic organization.
arXiv:2608.30636v1 Announce Type: new Abstract: Optimizing absorption, distribution, metabolism, and excretion (ADME) is an important part of small molecule drug discovery. Many machine learning mode...
arXiv:2607. 08003v1 Announce Type: cross Abstract: Catalysts are essential for sustainable chemical manufacturing, yet discovering novel architectures remains a bottleneck dominated by trial-and-error experimentation and computationally intensive screening.
Nuclear Magnetic Resonance (NMR) spectroscopy is the gold standard for molecular structure elucidation, yet interpreting complex spectra for unknown molecules remains a bottleneck reliant on human expertise. While artificial intelligence has advanced this field, current methods face a critical trade-off: database retrieval cannot identify novel scaffolds, while de novo molecular structure elucidation models operate as black boxes, lacking the atom-level interpretability required for rigorous scientific validation.
Monroe is a new molecular foundation model that improves upon existing models by pre‑training on over 81 million molecules from the PM6 quantum chemistry dataset, enhancing stereochemistry representation, and introducing novel training losses such as conformer denoising and embedding decorrelation. It also incorporates a prior‑data‑fitted model (TabPFN) for downstream in‑context prediction and demonstrates superior performance on Polaris benchmarks and activity cliff tests. Ablation studies show that the PFN‑based downstream approach can upgrade other models, producing state‑of‑the‑art variants MiniMol_PFN and CheMeleon_PFN.