Generative AI-Driven Optimization for Novel Multi-Target Drug Candidates
Develop an intelligent drug discovery platform capable of generating and optimizing novel small-molecule drug candidates for multi-target activity. This challenge involves leveraging advanced Generative AI and cheminformatics tools to predict binding affinities, assess drug-likeness, and evaluate ADMET profiles. Participants will build a sophisticated agent using Llama 3.1 405B via Groq and Semantic Kernel to orchestrate the design process. The platform will iteratively propose molecular modifications, predict their properties, and refine candidates based on specific therapeutic targets (e.g., GLP-1R, GIPR, GCGR). Experiment tracking will be managed with Weights & Biases, and external knowledge will be integrated using Tavily.
What you are building
The core problem, expected build, and operating context for this challenge.
Develop an intelligent drug discovery platform capable of generating and optimizing novel small-molecule drug candidates for multi-target activity. This challenge involves leveraging advanced Generative AI and cheminformatics tools to predict binding affinities, assess drug-likeness, and evaluate ADMET profiles. Participants will build a sophisticated agent using Llama 3.1 405B via Groq and Semantic Kernel to orchestrate the design process. The platform will iteratively propose molecular modifications, predict their properties, and refine candidates based on specific therapeutic targets (e.g., GLP-1R, GIPR, GCGR). Experiment tracking will be managed with Weights & Biases, and external knowledge will be integrated using Tavily.
Shared data for this challenge
Review public datasets and any private uploads tied to your build.
What you should walk away with
Master prompt engineering techniques for Llama 3.1 405B (via Groq) to generate novel molecular scaffolds and specific functional group modifications.
Implement a Semantic Kernel planner to chain together Gen AI calls, cheminformatics tools (e.g., RDKit for descriptors), and molecular simulation software for property prediction.
Design and execute virtual screening workflows using tools like AutoDock Vina, PyRx, or custom QSAR models to predict binding affinity to specified protein targets (e.g., GLP-1R, GIPR, GCGR).
Build a feedback loop within Semantic Kernel to iteratively refine generated molecules based on predicted properties (e.g., improved binding, reduced toxicity, Lipinski's rule compliance).
Optimize drug candidates for a set of desirable properties including target selectivity, drug-likeness (e.g., Lipinski's rules), and ADMET (Absorption, Distribution, Metabolism, Excretion, Toxicity) profiles using a multi-objective approach.
Deploy Weights & Biases to manage and track generated molecules, their predicted properties, and optimization history, enabling comprehensive experiment tracking and comparison.
Integrate external knowledge bases and scientific literature search capabilities (e.g., ChEMBL, DrugBank via Tavily API) to provide context and validate generated structures and design choices.
[ok] Wrote CHALLENGE.md
[ok] Wrote .versalist.json
[ok] Wrote eval/examples.json
Requires VERSALIST_API_KEY. Works with any MCP-aware editor.
DocsAI Research & Mentorship
Participation status
You haven't started this challenge yet
Operating window
Key dates and the organization behind this challenge.
Find another challenge
Jump to a random challenge when you want a fresh benchmark or a different problem space.