Foundation and multimodal models are rapidly becoming a core methodology in molecular informatics, particularly for drug discovery, by leveraging large‐scale pretraining across sequences, graphs, 3D structures, and text. This mini‐review provides practical guidance on when these models help, how to choose representations and data, and how to design pretraining and adaptation pipelines for real‐world use. We clarify what qualifies as a foundation model in chemistry; compare chemical language models, graph‐based architectures, and 3D equivariant networks; review multimodal strategies that connect molecules with proteins, pockets, and natural language; and summarize diffusion‐based generative modeling. We also emphasize rigorous evaluation, discussing realistic splitting protocols, distribution shift, activity cliffs, uncertainty calibration, and conformal prediction in the context of widely used benchmarks.
Rastogi et al. evaluated fine-tuned transfer-learning architectures for brain tumor classification using MRI, reporting the best performance with Xception on a Kaggle-sourced dataset of tumor and non-tumor images