Overview Fine-tune a Small Language Model (SLM) like Amazon Nova Micro (via Amazon SageMaker AI) for drug discovery — identify therapeutic targets and predict molecular properties with higher accuracy than what's possible with frontier-scale models, and at lower costs. Your fine-tuned SLM can either integrate multi-modal data to discover disease-specific targets, or predict molecular properties like permeability given a molecule's SMILES string — the same categories that determine whether a drug candidate survives to the clinic. This follows the same approach used by Insilico Medicine (TargetPro) and Nimbus Therapeutics (Novus model) on AWS: supervised fine-tuning on thousands of labeled multi-modal data, then iterating on prompts, data mixing, and training strategy to push accuracy higher. You can team up with others to prepare training data, configure fine-tuning jobs on SageMaker AI, and submit predictions to an automated evaluation pipeline that scores against experimental measurements in real time. Sample datasets like TargetBench and ChEMBL in JSONL Q&A pairs will be provided, and you can bring your own datasets as well. The team with the most accurate predictions wins up to $5K in AWS credits. Agenda 9:00 AM – 9:30 AM | Breakfast & Networking Grab coffee and breakfast, meet fellow builders, founders, and Amazonians. Setup AWS Workshop Studio environment plus Amazon Quick Desktop, and a walkthrough of the day's format. 9:30 AM – 11:30 AM | Build Starts Hands-on build sprint: use Amazon Quick to prepare datasets for model fine tuning; take advantage of serverless model fine tuning capability on Amazon SageMaker AI to develop your customized model. Deploy your best model to Amazon Bedrock. Use Amazon Quick Desktop as your scientific workbench to interact with your own model for competitive intelligent analysis. 11:30 AM – 12:00 PM | Leaderboard Showcase Submit your customized model on pre-built leaderboard — we will evaluate the model capability against certain tasks. Winners are rewarded with AWS credits and invited to showcase your models to AWS leadership. What You'll Walk Away With - A fine-tuned model you built, hands-on experience with Amazon SageMaker AI, and potential prizes up to $5K in AWS credits. Prizes Category: Target Identification - 1st Place: $3,000 in AWS Promotional Credits + AWS AI League Championship invitation - 2nd Place: $2,000 in AWS Promotional Credits - 3rd Place: $500 in AWS Promotional Credits Category: Molecular Property Prediction - 1st Place: $3,000 in AWS Promotional Credits + AWS AI League Championship invitation - 2nd Place: $2,000 in AWS Promotional Credits - 3rd Place: $500 in AWS Promotional Credits Full contest terms and conditions: https://pages.awscloud.com/rs/112-TZM-766/images/BostonAIWeek_Contest%20Terms%20and%20Conditions%20%28Life%20Science%20R%26D%20Hackathon%29.pdf

AWS AI League: Drug Discovery Challenge

About

Host

Location