Amazon Sagemaker
Amazon SageMaker is a fully-managed platform that enables developers and data scientists to quickly and easily build, train, and deploy machine learning models at any scale. With Amazon SageMaker, all the barriers and complexity that typically slow down developers who want to use machine learning are removed. The service includes models that can be used together or independently to build, train, and deploy your machine learning models.
Product Overview
The Neopoly Formulation Algorithm trains a Hierarchical Graph Network (HGN) within a joint embedding predictive architecture to learn molecular representations that contain structural information. Its training trajectory is guided by causal representation learning to ensure that the representation for each chemical in a formulation can be used to build a structural causal model for the formulation. The causal mechanisms between representations, ratios, and properties are governed by functional equations so you can predict your formulation properties and optimize its chemical constituents and ratios.
Key Data
Version
By
Categories
Type
Algorithm
Highlights
Deploy the HGN encoder model to embed each chemical in your formulation into a representation of fixed dimensionality.
Deploy the structural causal model to predict the properties of your formulation given the chemical constituents and their ratios.
Optimize your formulation by simulating results with different chemical constituents and ratios.
Not quite sure what you’re looking for? AWS Marketplace can help you find the right solution for your use case. Contact us
Pricing Information
Use this tool to estimate the software and infrastructure costs based your configuration choices. Your usage and costs might be different from this estimate. They will be reflected on your monthly AWS billing reports.
Estimating your costs
Choose your region and launch option to see the pricing details. Then, modify the estimated price by choosing different instance types.
Version
Region
Software Pricing
Algorithm Training$0.00/hr
running on ml.r5.8xlarge
Model Realtime Inference$0.00/hr
running on ml.r7i.8xlarge
Model Batch Transform$0.00/hr
running on ml.r7i.8xlarge
Infrastructure PricingWith Amazon SageMaker, you pay only for what you use. Training and inference is billed by the second, with no minimum fees and no upfront commitments. Pricing within Amazon SageMaker is broken down by on-demand ML instances, ML storage, and fees for data processing in notebooks and inference instances.
Learn more about SageMaker pricing
With Amazon SageMaker, you pay only for what you use. Training and inference is billed by the second, with no minimum fees and no upfront commitments. Pricing within Amazon SageMaker is broken down by on-demand ML instances, ML storage, and fees for data processing in notebooks and inference instances.
Learn more about SageMaker pricing
SageMaker Algorithm Training$2.419/host/hr
running on ml.r5.8xlarge
SageMaker Realtime Inference$2.54/host/hr
running on ml.r7i.8xlarge
SageMaker Batch Transform$2.54/host/hr
running on ml.r7i.8xlarge
Algorithm Training
For algorithm training in Amazon SageMaker, the software is priced based on hourly pricing that can vary by instance type. Additional infrastructure cost, taxes or fees may apply.InstanceType | Algorithm/hr | |
|---|---|---|
ml.p3.8xlarge | $0.00 | |
ml.m5.4xlarge | $0.00 | |
ml.r5.8xlarge Vendor Recommended | $0.00 | |
ml.p2.8xlarge | $0.00 |
Usage Information
Training
Step 1: Prepare the "training/" data directory
data/
training/
smiles_train.csv
raw/
sedds.csvStep 2: Preprocess raw dataset in the command line
python finetune_utils.pyStep 3: Check the created "processed/" data directory
data/
training/
processed/
geometric_data_processed.pt
geometric_data_processed_cosolvent.pt
geometric_data_processed_surfactant.pt
geometric_data_processed_oil.pt
pre_filter.pt
pre_transform.ptChannel specification
Fields marked with * are required
training
*This channel includes raw and processed data
Input modes: File
Content types: text/csv
Compression types: None
Hyperparameters
Fields marked with * are required
epochs
Number of training epochs
Type: Integer
Tunable: No
t_0
Number of epochs before scheduler restart
Type: Integer
Tunable: No
t_mult
Multiplier to lengthen scheduler restarts
Type: Integer
Tunable: No
batch_size
Batch size to train end-2-end
Type: Integer
Tunable: No
finetune_batch_size
Batch size to train end-2-end
Type: Integer
Tunable: No
structure_lr
Learning rate to train structure
Type: Continuous
Tunable: No
property_lr
Learning rate to train property
Type: Continuous
Tunable: No
alpha
Alpha parameter for multi-objective Chebyshev scalarization
Type: Continuous
Tunable: No
edge_threshold
Weight threshold to learn causal edges
Type: Continuous
Tunable: No
Model input and output details
Input
Summary
Prepare "transform/" data directory for inferencing
data/
training/
transform/
transform_test.csvInput MIME type
text/csvSample input data
Output
Summary
The Neopoly Formulation model will output the predicted size of the API drug given the chemical constituents and ratios in your formulation.
Output MIME type
text/csvSample output data
Sample notebook
Additional Resources
End User License Agreement
By subscribing to this product you agree to terms and conditions outlined in the product End user License Agreement (EULA)
Support Information
Neopoly Formulation
Customize the Neopoly algorithm for your use case; reach out to us at hello@neopolyai.com
AWS Infrastructure
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Learn MoreRefund Policy
This product is offered for free. If there are any questions, please contact us for further clarifications.
Customer Reviews
There are currently no reviews for this product.
View allWrite a review
Share your thoughts about this product.
Write a customer review