惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

有赞技术团队
有赞技术团队
cs.CV updates on arXiv.org
cs.CV updates on arXiv.org
P
Palo Alto Networks Blog
C
Cisco Blogs
The Hacker News
The Hacker News
T
Threatpost
S
Schneier on Security
K
Kaspersky official blog
Spread Privacy
Spread Privacy
博客园_首页
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
NISL@THU
NISL@THU
量子位
cs.CL updates on arXiv.org
cs.CL updates on arXiv.org
Google DeepMind News
Google DeepMind News
Security Latest
Security Latest
博客园 - 司徒正美
云风的 BLOG
云风的 BLOG
博客园 - 叶小钗
H
Hackread – Cybersecurity News, Data Breaches, AI and More
N
News and Events Feed by Topic
爱范儿
爱范儿
P
Proofpoint News Feed
C
CERT Recently Published Vulnerability Notes
Project Zero
Project Zero
Application and Cybersecurity Blog
Application and Cybersecurity Blog
Cisco Talos Blog
Cisco Talos Blog
GbyAI
GbyAI
cs.AI updates on arXiv.org
cs.AI updates on arXiv.org
Apple Machine Learning Research
Apple Machine Learning Research
T
Tenable Blog
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
V
Vulnerabilities – Threatpost
Forbes - Security
Forbes - Security
博客园 - 三生石上(FineUI控件)
C
Cyber Attacks, Cyber Crime and Cyber Security
N
News and Events Feed by Topic
V
V2EX
Webroot Blog
Webroot Blog
The Register - Security
The Register - Security
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
阮一峰的网络日志
阮一峰的网络日志
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
Blog — PlanetScale
Blog — PlanetScale
M
MIT News - Artificial intelligence
Scott Helme
Scott Helme
Simon Willison's Weblog
Simon Willison's Weblog
L
LangChain Blog
W
WeLiveSecurity
Cloudbric
Cloudbric

AWS for Industries

Dynamic Inbound Routing for BYOIP Workloads Using Amazon VPC Route Server | Amazon Web Services How Autel Transformed Charging Station Management with AI Agents on AWS | Amazon Web Services How Danone Simplified Kubernetes at Scale with Amazon EKS Auto Mode | Amazon Web Services Build a Multi-Agent Assessment Workbench with Amazon Bedrock AgentCore | Amazon Web Services Sovereign by design: How AWS helps Nigeria’s financial services industry protect data and drive innovation | Amazon Web Services Scaling ML in production: how BBVA accelerated delivery with MLOps | Amazon Web Services Inside BBVA’s MLOps transformation: from data platform to scalable ML on AWS | Amazon Web Services Blazing a Trail: How Peloton Rebuilt the SDLC for the Agentic Era with Amazon Bedrock | Amazon Web Services Accelerate RISC-V Software Development Before Silicon: Virtual Prototyping with MachineWare’s SIM-V on AWS | Amazon Web Services How retailers deliver hyper-personalization in-store with Personalisation Hub, UST, and AWS | Amazon Web Services Deploy diagnostic-quality imaging globally with MedDream and AWS HealthImaging | Amazon Web Services Coins in Motion: Building agentic blockchain payments for in-vehicle experiences | Amazon Web Services Reduce P&ID analysis time by 80% with hybrid AI maintenance planning | Amazon Web Services Deploying industrial AI on AWS: Building the autonomous factory | Amazon Web Services How Atlantic Health cut legal document search time by 42% with Amazon Bedrock metadata filtering | Amazon Web Services Edge-to-Cloud Architecture for Real-Time Surgical Intelligence with AWS and NVIDIA | Amazon Web Services Reimagining B-Pillar DFMEA: Why Ontology-Grounded AI Is the Future of Automotive Engineering | Amazon Web Services Transforming energy trading by managing complexity and driving growth with Cloud ETRM | Amazon Web Services How Multi-Agent AI Turns Supply Chain Data into Decisions and Actions | Amazon Web Services ​​​Deploy Agentic Bidding Without Sacrificing Speed: ARTF Containers with NVIDIA GPU Acceleration on AWS​​ | Amazon Web Services Next-generation programmatic advertising: How AWS RTB Fabric redefines the game | Amazon Web Services Flexible Telecom AI Workload Deployment Across AWS Hybrid Cloud | Amazon Web Services Building a HIPAA-ready generative AI architecture for healthcare on AWS | Amazon Web Services Highlights from the 2026 AWS Life Sciences Symposium: MedTech Track | Amazon Web Services Multi-Agent Systems for Financial Services on Amazon EKS and AgentCore | Amazon Web Services How AI can help developers migrate embedded codebases between Arm SoCs | Amazon Web Services From Connected to Resilient: Cloud-Native Payment Connectivity on AWS | Amazon Web Services Ultra-low-latency cross-Region crypto trading with Avelacom and AWS | Amazon Web Services Build an AI-powered 5G Signaling Trace Analyzer Using Amazon Bedrock | Amazon Web Services Medical Legal Regulatory Review Orchestration with AI Agents on AWS | Amazon Web Services AWS showcases the agentic AI future of advertising and entertainment at Cannes Lions 2026 | Amazon Web Services The Road to 180M GRefs/s: Sizing Epic on AWS with R8ib and Enhanced EBS | Amazon Web Services BridgeWise builds responsible AI in FSI with Amazon Bedrock | Amazon Web Services Rethink Everything: Highlights from the 2026 AWS Financial Services Symposium | Amazon Web Services Improving Defect Analysis and Quality Control with AI Diagnostics | Amazon Web Services Building a cloud-based EV charging monitoring platform with real-time AI analytics | Amazon Web Services Introducing the AWS guide to the ECB Guide on outsourcing cloud services to cloud service providers | Amazon Web Services How a Luxury Retailer Accelerates Customer Experience with Amazon CloudFront | Amazon Web Services The Art of the Possible: Building an Intelligent Wealth Management Platform – Part 1 | Amazon Web Services How We Built Healthcare AI You Can Trust: The Science Behind Amazon Connect Health | Amazon Web Services How Everllence Scaled P&ID Intelligence to Improve Plant Operations | Amazon Web Services Rivian accelerates production with second-generation AWS Outposts: Improving resiliency and reducing costs | Amazon Web Services AI-Driven Development Lifecycle for Financial Services | Amazon Web Services How Agentic AI and Digital Twins on AWS Drive Operational Excellence | Amazon Web Services Modernizing Core Banking Systems: A Strategic Guide for Financial Leaders | Amazon Web Services Highlights from the 2026 AWS Life Sciences Symposium: Research and Drug Discovery | Amazon Web Services Discount Tire Uses Cloud WAN and Buffer VPC to Create a Scalable Enterprise Network Centralized third-party connectivity in AWS: Architecture patterns for highly regulated environments | Amazon Web Services FHIR-powered Care Continuum on AWS HealthLake From code to chemistry: using Kiro to tackle ADME-Tox, a key drug discovery challenge | Amazon Web Services How Toyota securely deployed HiveMQ with mTLS on AWS to power Smart Manufacturing | Amazon Web Services From record to intelligence: How EMR systems on AWS become the foundation for generative AI in healthcare | Amazon Web Services How to Connect AWS HealthOmics to Public and Private Network Sources at Runtime | Amazon Web Services Accelerating Android Builds on AWS: From 3 Hours to Under 5 Minutes with SourceFS | Amazon Web Services Massive Parallel Processing of Financial Transactions with Amazon EKS and Amazon MSK | Amazon Web Services Submit up to 100,000 Bioinformatics Workflow Runs with a Single API Call in AWS HealthOmics | Amazon Web Services Energy HPC Orchestrator powers collaborative, scalable energy computing | Amazon Web Services Automate Investment Research Using Strands Agents on Bedrock AgentCore | Amazon Web Services How OCC Built a Governed Cloud Foundation and Then Stress-Tested It Executive Insights from the 2026 AWS Life Sciences Symposium How Carlsberg’s Traitomic business leveraged AWS HealthOmics to power genetic trait development | Amazon Web Services CME Group MDP multicast data access on AWS using Transit Gateway | Amazon Web Services How retailers solve the customer identity puzzle with Amperity and AWS | Amazon Web Services Exact Sciences Transforms Bioinformatics Infrastructure with AWS HealthOmics | Amazon Web Services Building a Serverless Supply Chain Management Solution for Automotive Customers with AWS AppSync and Amazon Aurora Serverless | Amazon Web Services Accelerating physical AI with AWS and NVIDIA: building production-ready applications with simulation and real-world learning | Amazon Web Services Modernizing life-saving workloads with AWS serverless | Amazon Web Services Transforming Industrial Operations: How AVEVA and AWS drive Cloud Innovation | Amazon Web Services Introducing Amazon Bio Discovery | Amazon Web Services Accelerate Project Delivery with AI-Native Execution System on Amazon Quick | Amazon Web Services Reinvent Telecom Mediation Systems with Amazon Bedrock AgentCore, Strands Agents, and the Model Context Protocol | Amazon Web Services AWS Cloud Connectivity Patterns for Financial Market Infrastructures | Amazon Web Services Event-Driven Digital Pathology: Governed Whole Slide Image Ingestion to Scalable Inference with Amazon SageMaker | Amazon Web Services How Telefonica Germany achieved a centralized tracing solution with VPC Traffic Mirroring | Amazon Web Services AWS Teams Up with Wingstop to Deliver Wings to Millions During March Hoops Tournament | Amazon Web Services How Amazon Connect Health brings agentic AI to the point of care | Amazon Web Services How Liftoff improved conversion performance and reduced infrastructure costs with Cortex using AWS Graviton | Amazon Web Services From Prompt to Pipeline: AI-Powered Bioinformatics Workflow Development with Kiro and AWS HealthOmics | Amazon Web Services Driving Intelligent Quality in the Software-Defined Vehicle Era | Amazon Web Services How Amazon Devices Eliminated Credential Risk to Scale AI across Engineering Tools | Amazon Web Services The Evolution of BMW Group’s 3D Streaming Experience | Amazon Web Services Build ChatGPT Apps with MCP Servers and AWS Infrastructure | Amazon Web Services
Closing the Loop with Amazon Bio Discovery’s Integrated Lab Partners | Amazon Web Services
Ryan Greene · 2026-05-07 · via AWS for Industries

Contract research organizations (CROs) play a critical role in drug discovery, providing the specialized laboratory services that translate computational designs into physical candidates. They enable researchers to access capabilities that for some teams would be impractical to build and maintain in-house, from DNA synthesis and protein expression to comprehensive biophysical characterization. Yet for many researchers, working with CROs remains harder than it should be. Finding the right partner with the right services for a specific project takes time and effort. Setting up new engagements involves manual coordination across procurement, contracting, and data exchange. And once results come back, the data often lives in separate systems from the computational tools used to design candidates, creating silos that slow down the iterative cycle between design and experimentation. According to David Younger, Co-Founder and CEO of A-Alpha Bio, in an interview with GEN Edge, the “fundamental gap” in AI-powered drug discovery is the lack of high-quality, experimental data at scale to evaluate protein design models. “The convergence of technology and life sciences isn’t just about faster compute or better algorithms,” Younger said. “It’s about connecting those advances to real-world, experimental observations.”

Amazon Bio Discovery is an AI-powered application designed to help scientists design and test new antibody drugs more quickly and confidently. It gives you access to 40+ AI biology models with AI-guided selection, plus agentic assistants that help design and configure experiments. It also connects you to a network of integrated contract research organization (CRO) partners, including Twist Bioscience and Ginkgo Bioworks, with A-Alpha Bio coming soon, who physically synthesize and test the most promising candidates. Lab results flow directly back into the application, improving the next round of design. This continuous workflow, known as “lab-in-the-loop,” turns drug discovery from a series of disconnected steps into a continuously accelerating learning cycle.

Figure 1: Amazon Bio Discovery's lab-in-the-loop workflow connecting computational design with integrated CRO partners

Figure 1: Amazon Bio Discovery’s lab-in-the-loop workflow connecting computational design with integrated CRO partners

In this post, we showcase our CRO launch partners and explain how integrating computational and wet-lab workflows in a single application is expanding lab-in-the-loop drug discovery to more researchers.

One Application for All Antibody Research Teams

Amazon Bio Discovery is built on the same AWS infrastructure trusted today by 19 of the top 20 global pharmaceutical companies to power their most sensitive research workloads. The application brings enterprise-grade privacy and security to every researcher, with complete data isolation and full customer ownership over all proprietary data and intellectual property. All proprietary models remain private and accessible only to you or your organization. If you discover a novel antibody using the application, the IP belongs to you.

The researchers who stand to benefit most from integrated CRO services are the ones who previously couldn’t access them independently. Academic labs, non-profit research institutions, early-stage biotechs, and smaller teams often lack the procurement resources, volume commitments, or even awareness of which CRO partner offers the right services for their research needs. These teams do critical work across oncology, rare disease, and infectious disease research, but frequently lack the infrastructure and lab resources that larger organizations have. For larger pharmaceutical and biotech organizations, integrated CRO access offers a way to complement existing in-house lab capabilities, giving research teams the ability to run additional characterization campaigns without having to make tradeoffs with other programs using internal lab capacity.

Amazon Bio Discovery gives these researchers a direct line to trusted CROs with transparent pricing and turnaround times visible before they submit an order. And with a free academic tier, researchers at universities, medical centers, and non-profit research institutes can design candidates using state-of-the-art AI models and send them to our CRO partners without worrying about first securing compute resources.

For CRO partners, Amazon Bio Discovery opens access to potentially tens of thousands of new researchers who previously had no practical path to their services. The ability to batch orders together through the application, with streamlined legal and payment processes, makes it practical for CRO partners to serve smaller research teams that would otherwise fall below minimum engagement thresholds. For CROs with established relationships with large research customers, those partnerships continue as they always have. Amazon Bio Discovery offers the added option of centralizing data integration across computational and wet-lab workflows in a single application, creating a connected feedback loop between design and experimentation.

See It in Action

The CRO network is designed to give you more choice and transparency while removing the operational friction that slows down the lab-in-the-loop discovery cycle. For computational biologists, this means you can rapidly iterate on model predictions by sending candidates to wet-lab CRO partners and using returning experimental data to improve accuracy with each cycle. For bench scientists, it means you can validate candidates through integrated CRO partners and get experimental data returned directly into the same environment where you designed them for additional analysis.

Analyze and select candidates. After computationally generating hundreds of thousands of candidates, Amazon Bio Discovery helps you identify the most promising ones for experimental validation. Using multi-property optimization, AI-guided ranking, and liability assessment, you can filter and prioritize candidates based on predicted binding affinity, developability, thermostability, and other key properties. The result is a focused shortlist of high-confidence candidates ready for wet-lab testing.

screenshot of AI-recommended candidates

Figure 2: Review AI-recommended candidates filtered by multi-property optimization and liability assessment

Submit candidates to a CRO partner. Once you have identified your top candidates, you browse available CRO services within the application. Each partner lists available assays, pricing, estimated turnaround times, and supported antibody formats. You can compare options across CRO partners side by side, giving you the transparency to choose the best option for your project. With a few clicks, you send selected candidates directly to the CRO partner through an integrated workflow. No manual data exports, no separate systems, no email chains. Only the specific candidate sequences you select are transmitted to the CRO partner. The CRO partner does not have access to your projects, experiments, or any other data.

screenshot of validated candidates

Figure 3: Send validated candidates directly to an integrated CRO partner with assay details, cost estimates, and turnaround times

Receive results and close the loop. When the lab completes its work, results flow back into your Amazon Bio Discovery environment automatically. The data can then be used for analysis and comparison against computational predictions. Results stay within your account. You can use returning lab data to refine your AI models, improving prediction accuracy for the next cycle. Over time, this feedback loop produces increasingly high-confidence candidates, reducing the number of experimental iterations needed to identify a viable therapeutic lead.

Meet the CRO Partners

Each Amazon Bio Discovery CRO partner brings distinct capabilities to the lab-in-the-loop workflow. Below, we highlight what each partner offers and the benefits for researchers. Across all partners, you retain full ownership of the data generated through these services.

Twist Bioscience
Twist Bioscience brings high-throughput antibody production and characterization services to Amazon Bio Discovery. Twist’s offering spans DNA synthesis through expression to a comprehensive panel of biophysical assays, including binding affinity, developability, thermostability, and functional characterization. Twist supports multiple antibody formats including full-length IgG, VHH, scFv, bispecifics, and Fab, with flexible expression scales from microgram to milligram quantities.

Twist was the wet-lab CRO partner behind two early validations of Amazon Bio Discovery: the Memorial Sloan Kettering Cancer Center collaboration, where nearly 300,000 novel antibody candidates were designed and the top 100,000 sent to Twist for synthesis and testing in weeks versus up to a year using traditional methods, and the Antibody Developability Benchmark developed jointly with Johns Hopkins University.

“At Twist, integrating this end-to-end wet-lab workflow within a single provider empowers Amazon Bio Discovery customers by avoiding delays and data silos often created when outsourcing different stages of validation to multiple vendors. This consolidation ensures a seamless transition from digital design to physical results, maximizing the efficiency of the ‘lab-in-the-loop’ cycle and providing researchers with a more reliable path to high-confidence candidates,” said Emily M. Leproust, CEO and co-founder of Twist Bioscience.

Ginkgo Bioworks
Through its Datapoints business, Ginkgo Bioworks brings large-scale antibody developability characterization services to Amazon Bio Discovery. Ginkgo offers wet-lab capabilities spanning DNA synthesis, antibody expression and purification, and a comprehensive panel of developability assays, including target binding, aggregation, thermostability, self-association, polyreactivity, and hydrophobicity.

Ginkgo’s services are designed for flexibility and scale. You can run characterization campaigns ranging from 20 to 5,000+ antibodies per batch across a panel of up to 14 assays. The service supports a broad range of antibody formats including IgGs, ADCs, Fc-fusions, VHH, Fab, scFv, multispecifics, and minibinders. For researchers running large characterization campaigns, Ginkgo offers volume discounts to help maximize the scope of testing within budget constraints. Smaller pilot campaigns are also available for teams looking to validate specific candidates before scaling up.

“Amazon Bio Discovery brings bio-AI and lab-in-the-loop capabilities to any team, at any scale. Researchers can access models and submit antibody designs directly to Ginkgo’s automated wet labs— getting validated data back fast, and iterating from there. We built the infrastructure to match the fast pace and confidence modern drug discovery demands” said John Androsavich, GM of Ginkgo Datapoints.

A-Alpha Bio (Coming Soon)
A-Alpha Bio generates high-quality, quantitative protein-protein affinity data through its high-throughput AlphaSeq platform. Researchers can quickly measure on- and off-target affinities for their in silico designs at scale, enabling broader screening to identify diverse candidate binders for any downstream application.

“With the AlphaSeq integration, Amazon customers can experimentally test their binder designs by the hundreds or thousands, which is essential for modern design pipelines with single-digit-percent success rates for the easiest targets,” says David Younger, Co-Founder and CEO of A-Alpha Bio. “This partnership with Amazon extends access to AlphaSeq beyond large pharmaceutical companies to academic labs and early-stage biotechs. Improving access to abundant and high-quality data is how we can move the needle on bringing new medicines to patients faster.”

Get Started

The CRO partners integrated into Amazon Bio Discovery today represent the beginning of a growing lab-in-the-loop ecosystem. We plan to expand the network of integrated partners across new modalities and service types, always with the same principle: making high-quality laboratory services accessible to every researcher, regardless of your organization’s size or resources.

To get started with Amazon Bio Discovery and explore integrated CRO partner services, sign up for a free trial and design your first antibody molecule through a free digital course today.