The Tool Desk
Outbyte PC Repair FREEClear out junk files and repair common Windows errorsFree Scan →Outbyte Driver Updater FREEFix the driver behind crashes, sound loss and screen glitchesFind Drivers →Some links on this page are affiliate links: if you buy through them we may earn a commission, at no extra cost to you.
Absci and Memorial Sloan Kettering Cancer Center announced a research collaboration on August 12, 2024, to pursue up to six antibody-based cancer therapeutics using generative AI and laboratory testing. The announcement described an early drug-discovery objective—not six completed medicines, a clinical treatment, an approved therapy, or evidence that patients can receive an AI-created cancer drug.
What Absci and MSK announced
Absci, a biotechnology company headquartered in Vancouver, Washington, said it would work with Memorial Sloan Kettering Cancer Center (MSK) to pursue as many as six novel cancer therapeutics. The reported plan was for MSK to contribute oncology expertise and identify promising cancer targets, while Absci used generative-AI design tools and wet-lab capabilities to develop and test antibody candidates.
The organizations reportedly began discussions at the January 2024 J.P. Morgan Healthcare Conference in San Francisco. The collaboration was presented both as a therapeutic-development effort and as a way to explore how AI might improve oncology drug discovery. Contemporary reports from GeekWire and Life Science Washington did not establish the identity of the targets, candidates, cancer types, timeline, or financial terms.
What’s actually slowing this PC down?
Pick the symptom - the matching free tool is one click away.
What “generative AI” means here
This is not primarily a chatbot or patient-advice application. In drug discovery, generative models can propose biological molecules—such as antibody or protein sequences—based on desired characteristics. Those characteristics may include:
#1 Best Overall
- Binding to a selected cancer-related target.
- Specificity and affinity.
- Stability and manufacturability.
- Compatibility with an antibody format.
- Lower potential immunogenicity.
- Activity against a particular disease mechanism.
An AI-generated sequence is a hypothesis, not a medicine. The proposed molecule must be produced and tested experimentally. Successful candidates then require further pharmacology, toxicology, manufacturing work, regulatory review, and clinical testing.
The drug-discovery path
The partnership can be understood as a series of increasingly difficult gates:
- Target selection: Researchers identify a protein or biological mechanism worth attacking.
- Molecule generation: AI proposes antibody designs intended to interact with that target.
- Laboratory testing: Scientists test whether the candidates bind and function as predicted.
- Optimization: Designs are revised using experimental results.
- Preclinical development: Researchers assess pharmacology, toxicity, dosing, manufacturing, and formulation.
- Clinical development: A candidate is tested in people, beginning with safety-focused studies and later efficacy trials.
- Approval: Regulators evaluate evidence of quality, safety, efficacy, and manufacturing controls.
Absci’s proposed contribution is important because it combines computational design with wet-lab experimentation. In principle, the workflow can generate candidates, test them, feed the results back into the models, and repeat the process. That may expand the design space and improve iteration speed, but the announcement did not demonstrate a specific time saving for this collaboration.
Why the antibodies matter
Antibodies can be designed to bind tumor-associated antigens, block growth or survival signals, recruit immune cells, alter the tumor microenvironment, or deliver a therapeutic payload. Their complexity also creates substantial development risks.
An antibody that binds a target may still fail to block the relevant pathway, reach a tumor at a useful concentration, work across genetically different tumors, avoid healthy tissue, or produce meaningful patient benefit. Generative AI may help search and optimize designs; it cannot by itself validate the underlying cancer biology.
Why MSK’s role matters
MSK contributes capabilities that a general-purpose AI platform does not automatically possess: disease-specific oncology knowledge, cancer biology, physician-scientists, translational research infrastructure, and experience identifying clinically relevant targets.
MSK’s broader commercialization ecosystem includes licensing, sponsored research, venture creation, therapeutics, antibodies, diagnostics, data, and AI partnerships. Its partnering program and Office of Entrepreneurship and Commercialization illustrate why successful AI drug discovery is not just a model problem. It also requires biological validation, clinical insight, capital, manufacturing, regulatory planning, and patient testing.
Outdated Drivers Are Slowing You Down
One free scan finds every outdated or missing driver and matches the right update for your exact hardware.Free scan · exact hardware matchWindows Errors? Fix Them Before They Spread
Repair common Windows errors and clear accumulated junk for a smoother, more stable PC - no reinstall needed.Free scan · no reinstallWhat the announcement did not prove
“Up to six therapeutics” was a development goal. It should not be read as six completed drugs or six clinical programs. In the sources reviewed through August 16, 2026, the following were not verified for the specific Absci–MSK collaboration:
- A named clinical candidate.
- A disclosed antibody sequence, target, or cancer indication.
- A registered human clinical trial.
- Public clinical efficacy results.
- FDA approval or other marketing authorization.
- An investigational-new-drug-enabling package.
- Development milestones, project deadlines, or success criteria.
- Upfront payments, milestones, royalties, equity, or other financial terms.
- Which organization would hold development or commercialization rights.
This does not prove that the work was terminated. It means the public material available for this article does not establish that the project has reached those milestones.
Best Value
Why AI does not equal an “AI cancer cure”
Cancer is not one disease with one target. Tumors can differ between patients and within the same patient, develop resistance, and share important biology with healthy tissue. The main failure points include:
- Target failure: The target may not be sufficiently important to tumor survival or may also be present in healthy tissue.
- Design failure: The molecule may not bind or function as predicted.
- Assay failure: Cell or animal models may not reflect human disease.
- Safety failure: The antibody may produce off-target effects, immunogenicity, or dose-limiting toxicity.
- Developability failure: The molecule may be unstable, difficult to formulate, or expensive to manufacture.
- Clinical failure: A candidate may be safe but ineffective in patients.
- Commercial failure: Even an effective drug must compete on outcomes, safety, cost, dosing, and access.
“AI-generated” is not a regulatory shortcut or a special approval category. Regulators assess the resulting product under the applicable standards for quality, safety, efficacy, and manufacturing.
What investors and business readers should watch
The commercial opportunity is potentially significant, but the announcement alone does not establish a clinical asset, near-term revenue, or a probability of approval. The most meaningful future signals would be:
- Named targets, candidates, and cancer populations.
- Peer-reviewed or conference-reported preclinical data.
- Patent filings that identify relevant candidates or targets.
- A registered clinical trial.
- An announcement describing regulatory-enabling work or an investigational-new-drug submission.
- Phase 1 safety data and later evidence of efficacy in a defined patient population.
- Disclosed licensing, milestone, funding, or commercialization arrangements.
For enterprise buyers, the relevant commercial models are negotiated biotech partnerships, wet-lab research services, licensing, sponsored research, and specialized AI or cloud infrastructure—not a consumer subscription or an immediately available cancer product. Absci’s platform is positioned for biopharmaceutical collaboration, while cloud providers such as AWS provide computing and development infrastructure rather than a validated oncology therapy.
Related MSK AI activity is not the same project
MSK later announced a separate February 2025 collaboration with AWS involving AI, high-performance computing, deidentified clinical and genomic data, and AI-enabled cancer research. That initiative provides context about MSK’s wider AI ecosystem, but it is not evidence that the Absci collaboration advanced. It should not be treated as an update to the Absci agreement. See MSK’s AWS announcement for the separate project.
Patient takeaway
This partnership does not identify a cancer treatment currently available to patients. Patients and families should not seek an experimental therapy, change treatment, or pay a company based solely on an AI claim or a research-partnership announcement. Any investigational treatment must be evaluated through appropriate clinical and regulatory channels with qualified medical professionals.
Recommended Free Tools
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
