Inductive Bio
@inductive_bio
Followers
284
Following
27
Media
3
Statuses
25
Inductive Bio accelerates compound optimization with state-of-the-art ADMET AI models and generative chemistry. https://t.co/L9IB7tkEd9
Joined December 2023
Big news: Inductive has raised a $25M Series A to democratize AI that transforms small molecule drug discovery. Our Compass platform, powered by our pre-competitive data consortium, predicts ADMET properties before synthesis - helping find higher quality drugs for patients,
inductive.bio
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
1
4
27
Can AI fix one of drug discovery’s biggest bottlenecks? At Inductive Bio, we think so, by making ADMET optimization faster and smarter. In this new @DrugTargetRev feature, our CEO Josh Haimson shares how:
drugtargetreview.com
Discover the role of AI in overcoming the challenges of ADMET in drug discovery, streamlining the development of new therapies.
0
1
1
We’re thrilled to announce that our latest generation of Beacon-1 ADMET models secured first place in the recent @Polaris_HQ blinded prediction challenge focused on ADMET properties in a real ASAP discovery antiviral program. Read about our lessons learned:
inductive.bio
Following our competition win, we explored what the competition results tell us about the state of ML for drug discovery
0
1
3
The rapid rise of AI in drug discovery brings both new opportunities and new challenges to navigate. We’ll be exploring these topics at two sessions at @ACS Spring 2025 this year. Looking to see a demo of Inductive Bio’s latest at #ACS? https://t.co/jjxOBFqdVx
0
2
3
Switching from SMILES to IUPAC reduces invalid molecules generated by LLMs by >90%. Want to know why? Catch up on our blog now: https://t.co/wLVx7rZOQw
#GenerativeChemistry #DrugDiscovery #AI #ML
inductive.bio
We explore how changing molecular notation from SMILES to IUPAC can dramatically improve the quality of analogs generated by LLMs, offering insight into how these models are trained and how we should...
0
0
1
LLMs’ impact in generative chemistry has been limited to date. We show that a slight change in how you ask the question, simply by switching the input from SMILES to IUPAC, can reduce invalid molecules by >90%. Learn more: https://t.co/wLVx7rZh0Y
#GenerativeChemistry #AI #ML
inductive.bio
We explore how changing molecular notation from SMILES to IUPAC can dramatically improve the quality of analogs generated by LLMs, offering insight into how these models are trained and how we should...
0
1
3
Join us at #ACSFall 2024! Our own Josh Haimson will be host "Sifting Reality from Hype - AI & ML in Drug Discovery" on Aug 20 with experts from Eli Lilly, Atavistik Bio, & Sanofi. Looking to meet with our team while at #ACS?
inductive.bio
Get in touch with our team to learn more about how we can help accelerate your drug discovery journey. We're here to answer your questions and provide expert support.
0
0
5
Guidelines for best practices when using #ML for #ADME drug optimization from @inductive_bio & @nestedtx including a successful case study! #ACSMedChemLett
https://t.co/ZR7F4eIU3Z
pubs.acs.org
Optimization of the ADME properties and pharmacokinetic (PK) profile of compounds is one of the critical activities in any medicinal chemistry campaign to discover a future clinical candidate....
0
6
6
Tired of the local vs. global property-prediction model debate? Why not both? Our blog dives into this debate and provides evidence that a combined global+local approach performs the best. Learn more: https://t.co/QI66EH8k8R
#DrugDiscovery #ML #ADME #Biotech
inductive.bio
A long-standing debate in cheminformatics is whether global property-prediction models perform better or worse than local QSAR models. We describe a result from our publication with Nested Therapeu...
0
2
5
High value AI application: Predicting properties of new drug candidates. Congrats to the Nested Tx and Inductive Bio teams on this successful collaboration showing how new AI models can predict ADME properties and accelerate small molecule drug discovery.
2
11
49
Thrilled to announce that our work with @nestedtx in drug optimization is now published! 🧬Our ML models helped overcome critical ADME issues to advance Nested’s program. Full story: https://t.co/Uob4kFErp7
#DrugDiscovery #ML #ADME #Biotech
inductive.bio
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...
0
4
11
Our latest blog post on Alpha Fold 3 explores how AF3 small-molecule docking compares to existing techniques and shows that the story is more nuanced than headlines suggest. https://t.co/Y1djsj3epX
0
6
13
Our journey is just beginning! DM us if you’d like to be involved either as a partner or as a member of our team.
0
0
4
We are collaborating with multiple therapeutics companies to validate and deploy our technology, including Denali Therapeutics (NASDAQ:DNLI), who have integrated our models into their small molecule drug design platform to support rapid, data-driven decision making.
1
0
7
To do all of this, we’ve brought together an incredibly talented team with deep experience, both in building innovative machine learning products and in bringing drugs into the clinic. This team has what it takes to build ML tools that are actually impactful on drug programs.
1
0
5
Our software provides real-time predictions as compounds are drawn, providing a data-driven input to decisions and acting as an experienced collaborator in the design process.
1
0
4
But models aren’t impactful if no one uses them. So we’ve invested in building easy-to-use chemistry design software that makes ML accessible to every scientist on the drug discovery team.
1
0
5
We leverage state-of-the-art deep learning techniques and then build custom architectures on top that are adapted to the unique needs of real-world heterogeneous ADMET data.
1
0
3
To do so, we are building the most comprehensive and best-curated commercially-available dataset to map the drivers of small-molecule ADMET. On top of this data, we are building machine learning models that can be used for decision making in real drug programs.
1
0
3
But rather than keeping these capabilities confined to a single biopharma company, we wanted to democratize this toolkit for the entire industry.
1
0
3