MolMetaLM: a Physicochemical Knowledge-Guided Molecular Meta Language Model
Most current molecular language models transfer the masked language model or image-text generation model from natural language processing to molecular field. However, molecules are not solely characterized by atom/bond symbols; they encapsulate important physical/chemical properties. Moreover, normal language models bring grammar rules that are irrelevant for understanding molecules. In this study, we propose a novel physicochemical knowledge-guided molecular meta language framework MolMetaLM. We design a molecule-specialized meta language paradigm, formatted as multiple <S,P,O> (subject, predicate, object) knowledge triples sharing the same S (i.e., molecule) to enhance learning the semantic relationships between physicochemical knowledge and molecules. By introducing different molecular knowledge and noises, the meta language paradigm generates tens of thousands of pretraining tasks. By recovering the token/sequence/order-level noises, MolMetaLM exhibits proficiency in large-scale benchmark evaluations involving property prediction, molecule generation, conformation inference, and molecular optimization. Through MolMetaLM, we offer a new insight for designing language models.
Code (1)
Tasks
Language ModelingLanguage ModellingProperty PredictionText GenerationSimilar Papers 제목 키워드 기반
Vertex-Edge Weighted Molecular Graphs: A study on topological indices and their relevance to physicochemical properties of drugs in use cancer treatment
Quantitative Structure-Property Relationship (QSPR) analysis plays a crucial role in predicting physicochemical properties and biological activities of pharmaceutical compounds, aiding in drug design and optimization. Th…
Drug DesignPhenoMoler: Phenotype-Guided Molecular Optimization via Chemistry Large Language Model
Current molecular generative models primarily focus on improving drug-target binding affinity and specificity, often neglecting the system-level phenotypic effects elicited by compounds. Transcriptional profiles, as mole…
Beyond Chemical Language: A Multimodal Approach to Enhance Molecular Property Prediction
We present a novel multimodal language model approach for predicting molecular properties by combining chemical language representation with physicochemical features. Our approach, MULTIMODAL-MOLFORMER, utilizes a causal…
feature selectionLanguage ModelingLanguage ModellingMolecular Property Prediction+1GLACIER: A Multimodal Student-Teacher Foundation Model for Molecular Property Prediction
Deep learning models facilitate the discovery of molecules with tailored properties among billions of candidate compounds. However, the computational burden to develop and deploy state-of-the-art models continuously incr…
Molecular Property PredictionComputational EfficiencyContrastive LearningFP-GNN: a versatile deep learning architecture for enhanced molecular property prediction
Deep learning is an important method for molecular design and exhibits considerable ability to predict molecular properties, including physicochemical, bioactive, and ADME/T (absorption, distribution, metabolism, excreti…
Deep LearningMolecular Property PredictionProperty Prediction