By comparing embeddings from zero-shot and finetuned CLMs combined with molecular physicochemical properties, this lightweight adaptation retains performance efficiency while reducing over-parameterization.
Abstract
Chemical language models (CLMs) like ChemBERTa and Molformer enable compound property prediction, but their computational demands limit adoption in resource-constrained settings. We integrate Low-Rank Adapters (LoRA) with CLMs to significantly reduce trainable parameters required for finetuning. Results: We observe 3–5% area under the receiver operating curve (AUC) improvement across classification tasks for molecule toxicity, blood-brain barrier permeability, and flavor prediction over Molformer-XL. Our approach achieves Matthews correlation coefficient (MCC) scores of 0.80–0.90 across three tasks while reducing model parameters by 75–95%. By comparing embeddings from zero-shot and finetuned CLMs combined with molecular physicochemical properties, we attain optimal performance across four datasets. This lightweight adaptation retains performance efficiency while reducing over-parameterization.
The experiments show that existing molecular LLMs and strong proprietary models such as GPT-5.2 and Gemini-3-Flash show limited reliability in substituent contribution prediction, and training on MolSC substantially improves this ability and achieves strong performance across diverse downstream molecular tasks.
Hyuntae Park, Sooyeon Kim, J. Park et al.· 0 citations
The accuracy, generalizability, data scalability, and ease of use of this work demonstrate that FuelProp-LM can serve as a practical and flexible tool for fuel property prediction and play a significant role in future AI-assisted fuel design.
Chen-Yue Tao, Cheng-Cheng Liu, Chen-Xuan Li et al.· ENGINEERING Energy· 0 citations
Monroe is presented, a new MFM with several innovations over the existing state of the art: increased scale allowing pre-training on over 81 million molecules from the PM6 quantum chemistry dataset; improved graph representation of stereochemistry; improved training losses including conformer denoising and embedding de...
Błażej Banaszewski, Andrew W. Fitzgibbon· 1 citation
CoMPASS is presented, a retrieval-calibrated framework for small-large model collaboration that retains a graph attention network as the predictive anchor, retrieves locally relevant training molecules, provides attention-grounded evidence to an LLM, and converts its proposal into a bounded correction through an agreem...
Wen-Tao Li, Jiang-Jie Qiu, Yi-Jun Li et al.· 0 citations
The results show that explicit molecular comparisons can strengthen tabular in-context learning for structural generalization while keeping the molecular encoder and pretrained model weights fixed.
Jin-Mo Lee, Dooho Lee, Minho Jeong et al.· 0 citations
Visualization and prototype preference analyses indicate that PACL separates structurally similar molecules with different functional properties more clearly in task-aligned representation spaces, supporting adaptive substructure contrastive learning and task-specific semantic alignment as an effective strategy for mul...
Jie-Zhou Chen, Ping-Yu Wang, Lin-Bo Qing et al.· Journal of Computer-Aided Mo...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
