Updates

Highlights from the 2026 Datapoints Summit: AI x Tech in Drug Discovery

Highlights from our September 16 summit in Boston on AI and drug discovery, plus on-demand recordings of every talk and panel.

Ginkgo Datapoints and Apheris Welcome AbbVie, argenx, Lundbeck, and Takeda as Founding Members of the Antibody Developability Consortium

The Antibody Developability Consortium has launched with founding members AbbVie, argenx, Lundbeck, and Takeda. Together they are building the field's largest standardized antibody developability dataset: 10,000 antibodies plus a foundation model, delivered through Apheris' federated infrastructure.

VCPI Opens Up: All Datasets Now Immediately Available to Every Registered User

Every Virtual Cell Pharmacology Initiative dataset, existing and future, is now available to all registered users the moment it drops: more than 14,000 compounds across three releases, open under CC BY 4.0.

Ginkgo Datapoints Partners with Lilly TuneLab to Close the Gap between AI Models and Lab Data

Ginkgo Datapoints will provide small molecule (ADME) and antibody developability data generation services to biotech companies in Lilly TuneLab, with ML-ready results that plug straight into TuneLab's predictive models.

Ginkgo Bioworks to Build an Autonomous Lab at Novo's New U.S. R&D Site in Waltham

Novo has selected Ginkgo to build an autonomous lab powered by its Reconfigurable Automation Cart (RAC) architecture at Novo's new R&D site in Waltham, Massachusetts. This is the same automation that powers Datapoints.

GDPa5: Predicting VHH-Fc Developability from Large-Scale IgG Data

GDPa5 is a public, 160-member VHH-Fc developability dataset profiled across 10 assays. Models trained on 559 IgGs predict VHH-Fc developability better than models trained on VHH-Fc data alone.

Bispecific Antibody Developability: Design Rules and a Public 160-Member Dataset

We profiled 160 bispecific antibodies and their 65 parental arms across 10 developability assays on PROPHET-Ab, and released the dataset publicly alongside a bioRxiv preprint.

Ginkgo Datapoints, Tangible Scientific, and Inductive Bio Launch ADME-One™

ADME-One™ pairs a complete high-throughput Tier 1 ADME panel with AI-driven human PK projection and integrated compound management, so teams can make lead-optimization-quality decisions as early as hit identification.

# VCPI Launches First Open-Source Transcriptomics Dataset: Profiling 2,200+ Compounds in THP-1 Cells to Power AI Drug Discovery

Ginkgo X Phylo: Biomni Democratizes Rapid Interpretation of Complex Transcriptomic and Cell Painting Data

Ginkgo Datapoints partnered with Phylo’s Biomni Lab platform to explore what happens when high-quality functional genomics datasets, like our GDPx series, meet natural language-powered AI analysis. What once took weeks of manual bioinformatics with multiple scientific specialists, Biomni Lab completed in just hours. It was able to interpret complex transcriptomic and Cell Painting data and generate publication-ready insights and data visualizations. Read more about our results.

Forget “More Data” for Virtual Cells — We Need Better Data. Introducing VCPI

‘More is better’ has become the reigning mantra in AI research. But for AI drug discovery, it’s better data that will move the needle. We’ve launched the Virtual Cell Pharmacology Initiative (VCPI) to build that better data in a first-of-its-kind community-led effort. We’re using DRUG-seq: high-throughput, arrayed screening, backed by $1B in automation and a standardized cell line. Even better, we’re gifting 100,000 compounds of high-quality RNA profiling data and asking the community to choose the compounds. Inside: our mission to build the future of Virtual Cells — and transform bio-AI — together.

Releasing the GDPsm1 ADME Dataset

GDPsm1 profiles a 320-compound subset of the Library of Pharmacologically Active Compounds (LOPAC 1280) across key Tier 1 ADME assays

Making Lab-in-the-Loop Drug Discovery Accessible Across the Industry

Drug discovery is no longer confined to one lab bench or one building—it’s a global logistics challenge that often slows down innovation. Ginkgo Datapoints, Inductive Bio, and Tangible Scientific are changing that. Together, we’re connecting AI-driven design, streamlined compound management, and rapid experimental profiling into one lab-in-the-loop workflow—helping scientists iterate faster, cut costs, and focus on what matters most: discovering new treatments for patients.

Introducing ADME Built for Modern Discovery

Empower your decision-making with fast, AI-compatible, cost-effective ADME at scale

Releasing the GDPx3 Cell Painting Dataset

Ginkgo Datapoints has unveiled GDPx3, the third installment in its functional genomics dataset series

PROPHET-Ab: A Data Platform for Antibody Developability

Optimized and Automated Antibody Developability Assays: Now Available from Ginkgo Datapoints

Releasing the GDPx2 DRUG-seq Dataset

GDPx2 Transcriptomic Dataset Released

High-Throughput Data at New Scales: How to get our industry over the hump of antibody developability

High throughput service for faster, smarter, more effective biologics

Generating Open-Source AI-Ready Protein Expression Datasets with Align to Innovate

Partnership with Align to Innovate to Develop AI-Ready Dataset

Launching Ginkgo Datapoints: Transforming AI Model Training in Biology

New service from Ginkgo Bioworks aims to accelerate the next era of drug discovery

Introducing Ginkgo’s Model API: A Programmable Interface for Ginkgo’s AI Research

Ginkgo Bioworks, in partnership with Google Cloud, has launched a public API that gives machine learning scientists access to its biological AI models, starting with its first protein language model: AA-0.

Google and Ginkgo: Foundry-Scale Data Meets AI

New partnership with Google Cloud to build a generative AI platform for engineering biology