papers-for-molecular-design-using-DL

Why we included this project

Compiling a reading list in this field is mostly a matter of knowing where the important work lands, and this index does that legwork for you. It gathers papers on deep learning and generative models for molecular and material design, arranged by the method in play and the task being solved, so someone hunting for diffusion-based conformation generation or transformer-based de novo design can find it without combing through years of arXiv postings. The sections are fine-grained: fragment-based, scaffold-based, structure-based, pharmacophore-based, and text-driven generation each get their own place, along with the datasets, benchmarks, and drug-likeness metrics used to judge results. A dedicated reviews section helps you get the lay of the land before committing to an approach, and the list is still being updated. For researchers choosing a baseline or placing their own work, it is a structured starting point worth bookmarking.