Skip to main content

Creating a workstation

info

To use SSH to connect to workstations, before creating workstations, upload your SSH public key to your account.

Follow these steps to create a workstation:

  1. Navigate to the workstations overview page.
  2. Click the "+ Create" button at the top-right of the overview page.
  3. Follow the on-screen instructions to enter a name, select the software blueprint, and configure the hardware blueprint for your workstation.
  4. Review the cost for the workstation.
  5. Click the "Create" button.
  6. Our OS will create and start your workstation. Within 2-4 minutes, your workstation will be running and ready.

Selecting a software blueprint​

The software blueprint defines the initial software configuration for the workstation. Several software blueprints for common tasks in computational biology, machine learning, and simulation are available. Please see the workstation software blueprints page in the catalog for more information about the available blueprints.

info

Blueprints with many pre-installed tools, such as the "Metagenomics, microbiome and microbial genetics" blueprint, take additional time to start up.

info

Need additional software? The Deep Origin OS is fully customizable. Contact customer support to discuss creating a custom software blueprint.

Selecting a hardware blueprint​

The hardware blueprint defines the hardware that is available to your workstation. The following selections are available:

  • Compute cluster
    • The compute cluster defines where your workstation is provisioned. You can choose from Deep Origin's AWS regions, or use your own AWS account. More information is available here.
  • Central processing power (vCPU)
    • The processing power defines your workstation's capacity to process data and run code. One vCPU is equal to one thread of a CPU core.
  • Accelerated processing power (NVIDIA GPU)
    • The accelerated processing power defines your ability to train and use machine learning models, like AlphaFold and DeepVariant. Choose a larger GPU to train and deploy larger models. See the hardware blueprints page for advice on choosing the right GPU size.
  • Memory
    • Defines how much information your workstation can store for immediate processing.
    • Three options are available, with different amounts of RAM per vCPU.
      • Small memory: Provides 2 GB RAM per vCPU.
      • Medium memory: Provides 4 GB RAM per vCPU.
      • Large memory: Provides 8 GB RAM per vCPU.
  • High-performance persistent local storage
    • The persistent local storage defines how much information your workstation can persist across sessions of your workstation. The storage will be mounted to the home directory (/home/bench-user/) of the workstation. In addition, users can mount shared storage drives to the workstations and access managed data from workstations.

You can change the hardware blueprint of a workstation after it is created. See the hardware blueprints page for more information.

Choosing the appropriate hardware blueprint for your workstation​

Choosing the appropriate hardware for a workstation can be challenging. We recommend striking a balance between power and price. If the workstation is underpowered, you won't have enough resources to do your work. If the workstation is overpowered, you'll pay for more resources than you need.

Need help?

Contact customer support for advice on the hardware capacity of workstations.

Configuring idle workstations to automatically stop and terminate​

Auto-stopping and auto-termination are in beta

Idle auto-stopping and auto-termination are new features. Please report errors and share feedback to customer support.

Auto-stopping and auto-termination are automatically enabled for free accounts

To disable auto-stopping and auto-termination, contact customer support to upgrade your account.

Workstations can be configured to automatically stop after they've have been idle and automatically terminate after they've been stopped. These features can help you manage your costs. For example, you can start a pipeline in a workstation with a large amount of resources, know that the workstation will stop 30 minutes after the pipeline has completed, and know that the workstation will terminate 30 minutes after the workstation has stopped.

When idle auto-stopping is enabled, workstations are stopped once their average CPU usage falls below 0.25 vCPU for the chosen duration and their network usage has been minimal. When idle auto-termination is enabled, workstations are terminated once they've been stopped for the chosen duration. Shortly before workstations are stopped and terminated, notifications are posted to the workstations overview page.

To disable auto-stopping and auto-termination, toggle these options when you create and edit workstations.

Replicating the configuration of an existing workstation​

To help users create workstations, the configuration of an existing workstation can be used as a starting point for a new workstation.

  1. Navigate to the workstations overview page.
  2. Select the workstation you wish to replicate.
  3. Click the actions menu (three dots) at the right of the workstation.
  4. In the actions menu, click the "Replicate" option.
  5. In the wizard that opens, optionally, edit the configuration for your new workstation.
  6. Click the "Create" button.
info

Any software or data that you added to your existing workstation while it was running will not be replicated to your new workstation.