Almost 20 years ago, the Shoichet group introduced the Similarity Ensemble Approach (SEA), which predicts biological relationships based on chemical similarity. The original paper is openly available, and the link is below. This approach is interesting because it can reveal previously unrecognized biological relationships among compounds. But it’s hard to implement with open-source tools alone, since the authors used the commercial MDL Drug Data Report (MDDR).

Ask questions about the molecule you drew: a prototype that combines a chemical structure editor with an LLM chat.

Required Skills: computational chemistry, molecular simulations, python, gaussian, gromacs, lammps, amber, orca, psi4, nwchem, rdkit, openbabel, cheminformatics, electronic structure methods, scientific software configuration, molecular dynamics, drug discovery, ai/ml-assisted chemistry workflows, quantitative analysis, analytical reasoning, scientific programming, written communication, verbal communication, documentation, problem-solving

핵심 요약 • Google DeepMind가 Antigravity용 Cheminformatics Skills를 소개한 글(2026년 11월 3일)입니다. 보통 며칠 걸리는 신약 설계 한 번의 반복을, 문헌 검색부터 거대고리 설계까지 약 한 시간 안에 이어 간 데모를 보여 줍니다. • 언어 모델은 작업 순서와 과학적 추론(reasoning)을 맡고, 분자 계산은 RDKit 같은 결정적 화학 도구가 맡는 분업 구조입니다. ChEMBL과 PubChem 커넥터가 데이터를 공급합니다. • 사례는 폐암 치료제 크리조티닙과 롤라티닙입니다. 에...

How a SMILES string becomes a molecular graph: the OpenSMILES grammar, parsing stages, and how RDKit, Open Babel and CDK do it

Burette is a macOS desktop app and Quick Look extension for molecular previews: Mol* 3D, xyzrender SVG, and RDKit grids. There is a review of Burette here it can be...

As readers may know, many open-source molecular generative models have become available recently.A few years ago, SMILES-based generative models were dominant, but diffusion-based models have recently become mainstream. Today, I would like to introduce EvoDiffMol, a new conditional diffusion-based generative model recently published in the Journal of Cheminformatics. The model can generate molecules in 3D, conditioned on user-specified target properties, for example user-specified scaffold, ADMET properties such as CYP, hERG, Caco-2 etc.

All 2.9 million ChEMBL 37 structures, four RDKit releases: 202 keys change in 2026.09, and an atom-order regression from 2026.03 remains. Scripts, molecule lists and a two-command check for your own set.

Compound triage for Claude Code: SMILES standardization, Lipinski/Veber/QED, PAINS & Brenk alerts (RDKit) - chdominguez/chemkit-lite

Validate and standardize SMILES, compute Lipinski/Veber/QED, flag PAINS and Brenk alerts, and get a pass/review/fail verdict per compound.

Compound triage for Claude Code: SMILES standardization, Lipinski/Veber/QED, PAINS & Brenk alerts (RDKit) - chdominguez/chemkit-lite

Contribute to iwatobipen/rdkit_conformer_test development by creating an account on GitHub.

Last week, I attended the 2026 RDKit UGM in person. It was really nice to meet other participants and have lots of discussions with them. All the oral presentations and poster presentations were great, and I was able to learn about a lot of cutting-edge work in cheminformatics. I learned about a new conformer generation method, implemented in the latest version of RDKit, during the "What's New" session.