Large perturbation datasets to power your AI models
We generate large perturbation datasets to power your AI models of cell and disease biology for use in target identification, target validation, and drug discovery.
How It Works
Our functional genomics product addresses key problems you face when training AI models for early drug discovery: data availability, quality, and uniformity. We generate large, high fidelity transcriptomic and phenotypic datasets in the disease context of your choice.
We introduce genetic and chemical perturbations in major cell types and provide you with your readouts of choice. Our highly automated workflow means you get data back in as little as 3 weeks.
Select from a range of perturbations and readout types.
Designed with your needs in mind.
Flexibility and Customization
Choose from:
- Cell types (bring your own or choose from onboarded cell types)
- Compound library
- Data readouts
End-to-End
We handle both perturbation and readouts. Tell us what you need, and we will deliver the data.
Scale
10,000s of in vitro chemical and genetic perturbations in each cell type.
Speed
We deliver data in as little as 3 weeks.
Attractive Deal Terms
Fee-for-service only: no royalties, no milestones. And you own the data, always. Our version of an easy button.
Interact with a sample dataset
To provide an example of our workflows and data packets, we ran a functional genomics screen for you to download, review, and analyze.
The Library of Pharmacologically Active Compounds (LOPAC 1280), containing 1,264 compounds, was tested at two concentrations (100 nM and 1000 nM) using four technical replicates in A549 cells (a human lung carcinoma epithelial cell line). We used plates in a 384 well format, which were sequenced using Ginkgo’s custom DRUG-seq pipeline. The downloadable dataset includes a subset of 20 compounds from the larger screen.
Sample Data
Download the sample dataset.
Submit the form to access the sample dataset (3MB) including a:
- Compressed dataset (metadata + raw UMI counts)
- Short report detailing the workflow and data and a link to the full dataset.
"*" indicates required fields
By clicking this link and accessing the dataset included therein (the “data”) you acknowledge and agree that: (1) the data is solely owned by ginkgo bioworks, inc. and/or its affiliates and/or representatives (collectively, “ginkgo”) and you are not granted any license thereto except solely as necessary for the limited purpose of determining whether to pursue a data generation agreement with ginkgo (“the Purpose”) and for no other purpose; (2) you may not copy, modify, sell, lease, or distribute the data (except as necessary for the Purpose); (3) in no event will ginkgo be liable to you or any third party for any consequential, special, indirect, incidental, punitive or exemplary damages, costs, expenses or losses (including lost profits) (collectively, “damages”), regardless of the form of action or the basis for such claim or liability arising in any way from your access to or use of the data; and (4) ginkgo does not make any representations, warranties or guarantees of any kind with respect to the data, either express or implied, including any warranty of quality, merchantability, or fitness for a particular use or purpose or any warranty as to non-infringement of any intellectual property rights of third parties.