From 157ad7b1debb733dfaf2ee58f78bce86ec79673a Mon Sep 17 00:00:00 2001 From: Rishiraj Chandra Date: Fri, 13 Dec 2024 16:07:07 -0500 Subject: [PATCH 1/3] Changed title of Streamlit app --- streamlitapp/app.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/streamlitapp/app.py b/streamlitapp/app.py index c74d5db..93b10f2 100644 --- a/streamlitapp/app.py +++ b/streamlitapp/app.py @@ -427,7 +427,7 @@ def response_generator(): st.success(f"Selected actions: {', '.join(selected_actions)}") # Main content -st.title("Clinical Trial Agent") +st.title("Biomarker Research Agent") col1, col2 = st.columns([6, 1]) with col2: @@ -526,4 +526,4 @@ def response_generator(): image_placeholder.error(error_msg) # Add assistant response to chat history - #st.session_state.messages.append({"role": "assistant", "content": response}) \ No newline at end of file + #st.session_state.messages.append({"role": "assistant", "content": response}) From 0625e3ab77a9a2081c2c42d0892afff1f3c02f04 Mon Sep 17 00:00:00 2001 From: Rishiraj Chandra Date: Fri, 13 Dec 2024 17:13:03 -0500 Subject: [PATCH 2/3] Specified environment --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index bf1dd54..c30fcb3 100644 --- a/README.md +++ b/README.md @@ -8,7 +8,7 @@ https://aws.amazon.com/blogs/machine-learning/accelerate-analysis-and-discovery- Multi-Agents Update: - A Jupyter notebook located in this repository has been developed to walk users through creating these agents - Users deploy AWS CloudFormation infrastructure to their AWS account as before -- This agent deployment notebook is meant to be run in a SageMaker Notebook environment +- This agent deployment notebook is meant to be run in a SageMaker Studio environment - Users follow the instructions within the notebook step-by-step to interactively create agents Now follow the step-by-step instructions below to deploy these Bedrock Agents @@ -17,7 +17,7 @@ Step 1: Navigate to the agents/ folder in this repository and download the files Step 2: Click the 'Launch Stack' button located in the [Deployment](#deployment) section to deploy the AWS infrastructure needed to support the agents -Step 3: Create a SageMaker Notebook in your AWS account and upload the agent/ files there +Step 3: Go to a SageMaker Studio JupyterLab environment in your AWS account and upload the agent/ files there, use the Python 3 (ipykernel) Step 4: Follow the step-by-step instructions shown in deploy_agents.ipynb to deploy agents From dad48e6572b3322aa6d822a86a409fb0edfe3b0a Mon Sep 17 00:00:00 2001 From: Rishiraj Chandra Date: Fri, 13 Dec 2024 17:33:17 -0500 Subject: [PATCH 3/3] Included instruction to change template parameter for multi-agent --- README.md | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index c30fcb3..9bab052 100644 --- a/README.md +++ b/README.md @@ -17,9 +17,11 @@ Step 1: Navigate to the agents/ folder in this repository and download the files Step 2: Click the 'Launch Stack' button located in the [Deployment](#deployment) section to deploy the AWS infrastructure needed to support the agents -Step 3: Go to a SageMaker Studio JupyterLab environment in your AWS account and upload the agent/ files there, use the Python 3 (ipykernel) +Step 3: When deploying this template make sure to change the 'GitBranch' parameter to the value 'multi-agent-collaboration' before clicking 'Submit' -Step 4: Follow the step-by-step instructions shown in deploy_agents.ipynb to deploy agents +Step 4: Go to a SageMaker Studio JupyterLab environment in your AWS account and upload the agent/ files there, use the Python 3 (ipykernel) + +Step 5: Follow the step-by-step instructions shown in deploy_agents.ipynb to deploy agents ## Overview The success rate for Phase I oncology clinical trials is significantly low. According to a study published in Nature Reviews Drug Discovery, the overall success rate for oncology drugs from Phase I to approval is around 5%, indicating a high failure rate of approximately 95%.