News
September 17, 2026
Inductive Launches Beacon-2, Making Human Dose Computable for Chemists and AI agents Across Biopharma
Chemists can now estimate which compounds will have the best human dose before making them in the lab.
.svg)
Chemists can now estimate which compounds will have the best human dose before making them in the lab.
NEW YORK—September 17, 2026 —Inductive launched Beacon-2 today, a system that predicts the efficacious human dose of a small molecule directly from its chemical structure.
Dose is the number that decides whether a compound can become a drug. It accounts for both how potent a molecule is and what the body does to it. A drug that works at a lower dose also carries less risk of off-target toxicity.
Beacon-2 predicts the properties that determine dose (absorption, distribution, metabolism, excretion, and toxicity) and estimates potency, then combines them through mechanistic models of pharmacokinetics. The ADMET models underneath it have won three consecutive OpenADMET blind challenges, beating more than 750 competitors from leading AI and pharma companies.
A technical post published today covers how Beacon-2 works and validates its projections across 20 real-world drug programs and 325 publicly available compounds from the ExpansionRx OpenADMET competition.
To test how Beacon-2 impacts agentic design workflows, Inductive gave its medicinal chemistry agent Indy a recently disclosed SARS-CoV-2 compound for optimization. Over 5 autonomous design cycles, Indy improved predicted human dose by 17x, which can be the difference between a drug program that gets killed and one that makes it to clinical trials.
"Chemists have always had to balance a dozen separate properties against each other to decide whether a compound is worth making," said Josh Haimson, co-founder and CEO of Inductive. "Dose is what those properties all add up to. Computing it from structure changes which compounds a team decides to make and helps them identify the highest quality compounds faster."
Beacon-2 is available to partners through Compass, where it is already running on live drug discovery programs.
About Inductive
Inductive is a chemical intelligence organization that embeds into drug programs and deploys frontier AI across experiment design and physical execution. Their chemical intelligence models, lab robotics, and expert chemists reason together about which experiments are scientifically valuable and which can be executed in the physical world, improving with every experiment. Inductive's models have placed first in three consecutive blind AI drug discovery benchmarks and support over 100 discovery programs with leading biopharma partners. For more information, please visit www.inductive.bio.
- QC analytical reports (1H/13C/19F/2D NMR, chiral SFC)
- Propose, visualize, and triage forward and retrosyntheses
- Monitor the synthesis queue and flag stalled targets
- QC assay data as it lands and flag suspicious results
- Prioritize repeats and nominate compounds for downstream assays
- Analyze SAR and identify data gaps
- Evaluate IVIVC and suggest diagnostic experiments
- Design, enumerate, and triage analogs
- Launch and analyze physics-based workflows like docking and FEP
- Project human PK and efficacious dose
- Answer questions about a program’s history (what was learned and when)
- Track team progress against the target candidate profile
- Get new scientists up to speed on a program
- Make meeting-ready slides and figures
Prompt: I’m attaching two files with activity data, one with new data from today and one with historical data. Can you look through the new data and identify any QC issues that I should be aware of? Create a csv where every compound + assay run pair is labeled with any relevant issues.
Prompt: Do a nitrogen walk around the core of this molecule: O=C(NCC1=CC=C(C)C(F)=C1)C2=CC=C3C=C(N4[C@H](C)CCCC4)C=CN32
Prompt: Do an OH walk around this whole molecule: O=C(NCC1=CC=C(C)C(F)=C1)C2=CC=C3C=C(N4[C@H](C)CCCC4)C=CN32
Prompt: Replace the core of this molecule with this set of 5,6-ring systems (file attached): O=C(NCC1=CC=C(C)C(F)=C1)C2=CC=C3C=C(N4[C@H](C)CCCC4)C=CN32
[Related posts]
September 14, 2026
News
Inductive Bio launches Indy, an AI chemistry assistant, to double the capacity of every medicinal chemist
Indy is the world’s first medicinal chemistry agent. Indy outperforms Claude Opus 5 and GPT-5.6 Sol in head-to-head benchmarks that include QC’ing new assay data, analyzing SAR, and the design/triage of analogs.
June 30, 2026
News
Inductive Bio joins Anthropic’s Connector Ecosystem for Life Sciences, Surfacing State-of-the-Art ADMET Prediction to Drug Discovery Scientists through Claude
Inductive’s global ADMET prediction models are now available as a connector for Claude, enabling any drug discovery scientist working with Claude to access state-of-the-art predictive models directly in their existing workflow.
May 26, 2026
News
Ginkgo Datapoints, Tangible Scientific, and Inductive Bio Launch ADME-One™: a High-Throughput ADME Platform That Brings Pharmacokinetic Projection Earlier in Drug Discovery
New co-developed product delivers a complete Tier 1 ADME panel coupled with best-in-class AI-driven human pharmacokinetic (PK) projection and integrated compound management —enabling scientists to make lead-optimization-quality decisions starting in hit identification
December 8, 2025
News
Inductive Bio Announces an up to $21M Award to Develop AI Drug Toxicity Models that Improve Drug Safety Assessment with Leading Academic and Biopharmaceutical Organizations
Team to develop and validate computational models trained on data from organoids and advanced human model systems that will improve drug safety and reduce reliance on animal testing
August 20, 2025
News
Ginkgo Datapoints, Tangible Scientific, and Inductive Bio Partner to Deploy AI-driven Lab-in-the-loop Workflows Across the Biopharma Industry
This new partnership will streamline drug discovery with AI, faster ADME profiling, and automated compound management, helping scientists design better treatments with fewer resources.
May 8, 2025
News
Inductive Bio Raises $25M Series A to Transform Small Molecule Drug Discovery with Industry-Wide AI Platform
Funding will accelerate company’s work to democratize state-of-the-art AI models trained on a pre-competitive dataset to speed the successful development of life-saving therapies
March 14, 2025
News
Inductive Bio to Present at ACS Spring 2025 on the Future of AI in Drug Discovery
The rapid rise of AI in drug discovery brings both unprecedented opportunities and complex challenges. From accelerating the development of better therapies to navigating the proliferation of tools and technologies, the path forward requires clarity, precision, and innovation. For small biotech companies, this moment also raises a critical question: how can we stay competitive with limited resources?
September 29, 2024
News
Inductive Bio Announces Publication of Successful Drug Optimization Collaboration with Nested Therapeutics
Inductive Bio, a leader in leveraging machine learning (ML) to accelerate compound optimization for small molecule drug discovery, announces the publication of the approach and findings from their recent collaboration with Nested Therapeutics, a biotechnology company pioneering a next-generation precision medicine platform to address hard-to-treat cancers.
August 9, 2024
News
Inductive Bio to Host Panel on AI and ML in Drug Discovery at ACS Fall 2024
As artificial intelligence and machine learning continue to reshape the landscape of drug discovery, this panel will tackle one of the field’s most pressing questions: how do we separate real innovation from overpromised potential?
December 13, 2023
News
Inductive Bio Emerges from Stealth, Unveiling an ML Platform to Accelerate Compound Optimization in Drug Discovery
Inductive Bio emerged with $4.3M in a seed funding round co-led by a16z Bio + Health and Lux Capital, with participation from Character, Bessemer Venture Partners, Alleycorp, and others. Inductive's team has deep expertise building innovative ML products and bringing drugs into the clinic.