Getting started with Cradle

Overview

Learn how to get started with Cradle, from creating your first project and designing new sequences to receiving the generated sequences and planning your next steps.

Using Cradle

1

Setting up your account

Once you receive an invitation to Cradle, you can log in using Single Sign-On (SSO) with your organization's email address.

2

Creating your project

To set up a project, click on the + New Project button. You will be asked to create a project name and paste your Project base sequence.

Your Project base sequence is the protein sequence that you start the project with. This may be a wild-type sequence that is found in nature or a previously engineered sequence.

Learn more in Workspace and projects.

3

Adding assays

After adding the project base sequence, specify the assays you will measure and aim to improve.

Learn more in Assays.

4

Importing data

If you have existing experimental data from the lab for your project base sequence, upload it to the platform. Cradle's models improve if they are trained on high-quality data specific to the protein you want to optimize.

Learn more in Importing data.

5

Setting objectives

Based on the specified assays and uploaded data, add the experimental objectives you want to achieve. You can set one primary and multiple constraint objectives.

Learn more in Objectives.

6

Running a benchmark

After uploading your data and setting objectives, you can run a data benchmark to evaluate how well your data suits Cradle's machine learning models. This benchmark helps assess how impactful your data will be for a design round with Cradle.

Learn more in Data benchmark.

7

Generating sequences

After setting up your project, configure the design of new protein sequences by specifying the number of sequences you aim to test in the lab, the number of mutations allowed, and blocked positions (those that should not be mutated).

Based on your data and design configuration, Cradle's models will generate a set of sequences for you to test in the lab. You can view the proposed sequences and their mutations in the Generation Report.

Learn more in Sequence generation.

8

Testing in the lab

Test the sequences in your lab or through an outsourced service (not provided by Cradle). After testing, upload the results to the Cradle platform. This data will further improve your Cradle machine learning models so the models are able to generate better sequences in the next round.

At this point, you will have completed an experimental round with Cradle! You can now set up a new experimental round based on the learnings from the previous round and continue optimizing your protein.