Discussed on Hacker News

[ASAP] MotifLeadDB: A Hierarchical Structural Data Set for Congeneric Ligand Binding Activity Change

[ASAP] Machine Learning-Based Soft Voting Ensemble Model for the Prediction of Oral Drug-Likeness of Chemical Structures

ChemCanvas

Changes in the system prompt between Claude Opus 4.6 and 4.7

Covered by Alex Hyett

[ASAP] De Novo Molecular Design via Shape-Constrained Diffusion Models

[ASAP] Struct2Query: Structure-Guided Virtual Screening via Composite-Molecule ROCS Queries Derived from Protein Pocket Similarity

BiScale-GTR: Fragment-Aware Graph Transformers for Multi-Scale Molecular Representation Learning

ChatGPT voice mode is a weaker model

Predicting Activity Cliffs for Autonomous Medicinal Chemistry

Use transformer model for Lead optimization #journal #memo

[ASAP] COFFEE-PRESC: A Fast Prescreening Method Using Compound Retrieval by Pairwise Positional Relationship of Representative Fragments

Amazon revamps S3 cloud storage for the AI era, removing a key barrier for apps and agents

vijayvkrishnan/openmix: Open-source framework for computational formulation science from ingredient validation to autonomous mixture optimization. The missing infrastructure layer between single-molecule tools (RDKit) and real-world formulation.

Discussed on Hacker News

Scientists assess AI tools reshaping labs and drug discovery

Rules and Gates

MolDA: Molecular Understanding and Generation via Large Language Diffusion Model

Fine-tuning DeepSeek-OCR-2 for Molecular Structure Recognition

kurt.thorn's Likes

Databricks launches AiChemy multi-agent AI for drug discovery

How Claude Code Builds a System Prompt

[ASAP] MotifLeadDB: A Hierarchical Structural Data Set for Congeneric Ligand Binding Activity Change

[ASAP] Machine Learning-Based Soft Voting Ensemble Model for the Prediction of Oral Drug-Likeness of Chemical Structures

ChemCanvas

Changes in the system prompt between Claude Opus 4.6 and 4.7

[ASAP] De Novo Molecular Design via Shape-Constrained Diffusion Models

[ASAP] Struct2Query: Structure-Guided Virtual Screening via Composite-Molecule ROCS Queries Derived from Protein Pocket Similarity

BiScale-GTR: Fragment-Aware Graph Transformers for Multi-Scale Molecular Representation Learning

ChatGPT voice mode is a weaker model

Predicting Activity Cliffs for Autonomous Medicinal Chemistry

Use transformer model for Lead optimization #journal #memo

[ASAP] COFFEE-PRESC: A Fast Prescreening Method Using Compound Retrieval by Pairwise Positional Relationship of Representative Fragments

Amazon revamps S3 cloud storage for the AI era, removing a key barrier for apps and agents

vijayvkrishnan/openmix: Open-source framework for computational formulation science from ingredient validation to autonomous mixture optimization. The missing infrastructure layer between single-molecule tools (RDKit) and real-world formulation.

Scientists assess AI tools reshaping labs and drug discovery

Rules and Gates

MolDA: Molecular Understanding and Generation via Large Language Diffusion Model

Fine-tuning DeepSeek-OCR-2 for Molecular Structure Recognition

DrugPlayGround: Benchmarking Large Language Models and Embeddings for Drug Discovery