we generate data at scale to power your ML models
get access to our wet-lab generated proteome-wide small molecule binding data to launch your next discovery program. Get started by adding $ to your Wallet and get access to over >1K datasets and billions of data points, or generate your own data just as easily.
Identify therapeutic opportunities instantly for disease targets of interest
get access to massive datasets detailing proteome wide small molecule binding data all generated internally at Om
generate hundreds of millions of data points on what molecules bind your protein
programmatically query billions of protein and small molecule interaction data points, all generated internally at Om.
run interactive ML workflows, manage jobs, and explore molecular viewers inside the Models Hub.
Go from hypothesis to launching a discovery program, in weeks.
We're screening entire proteomes against billions of molecules ahead of time, so you don't have to.
No more waiting
to screen a protein from scratch
We leverage synthetic biology and pico-scale engineering to screen hundreds of proteins against billions of molecules.
384
proteins screened per week
No more waiting
for molecular starting points
We characterize millions of interactions at the pico-scale to identify what small molecules bind what proteins.
350M
molecules tested per protein
No more waiting
for data to make next decisions
Billions of data points per week can be used to train ML models, that can improve with each re-training.
>100B
data points per week
From idea to data to discovery, in weeks.
Follow these steps to move from signup to getting data to launch your program fast.
Create your Om account
Sign up to access the dashboard, invite teammates, and request an Om API key for programmatic usage.
Fund your wallet and set your budget
Add funds and set your budget cap so API requests, exports, and diligence jobs can settle automatically.
Pick the protein you want small molecule binders for
Use our `/v2/datasets/catalog` endpoint to pick the protein you want small molecule binders for, then enter how many binders and non-binders you want, train a model, and launch a program.
Access or generate as much data as you need
Launch data generation campaigns or use diligence API endpoints (synthesizeReport, deep-diligence, search, gather, or crawl) to refine your strategy.
Launch your discovery program in weeks
With data in hand, you can move straight into discovery without additional onboarding friction.
Explore the Om platform
Leverage our API endpoints plus the dashboard to accelerate research.
Launch the latest models with Hub, or use proprietary Om models to go faster
Use Wallet Credits to run structure prediction, docking, and design workflows in Hub, with access to the latest models alongside proprietary Om models built to accelerate discovery.
- Use one Wallet Credits balance across active Hub models for prediction, docking, and design workflows.
- Launch the latest models in one workspace, including proprietary Om models designed to help you move faster.
- Upload files when a workflow needs artifacts and keep every run organized in one Om account.
- Review completed runs and download outputs as soon as jobs finish.
- Move from model output to downstream research, scoring, and decision workflows without leaving Om.
Hub runs use Wallet Credits with fixed per-run pricing by model; see Pricing for current rates.
Access Hub
Browse datasets and jump into API workflows
Explore available protein targets in the dashboard, copy the canonical protein UUID, and pull binders/non-binders or exports programmatically.
- Browse protein targets with Om-provided metadata to help you rank-order and optimize your data selection for model training.
- Copy the canonical protein UUID for Om API / SDK workflows.
- Get data streamed in through `/v2/data-access/shards` when you want to pull larger datasets into your ML workflow.
Subscription-gated access by active license plan.
Access datasets
Data generation on demand - screen hundreds of millions of molecules against your protein of interest
Provide a protein sequence and our lab returns the full binder / non-binder landscape through the Om API—no additional work required. Pick the delivery model that fits your IP strategy.
- Exclusive ownership (live pricing/sequence): private dataset licensed to you in perpetuity.
- Open access datasets (live pricing/sequence): dataset can join the public library, and access is governed by your active dataset subscription.
- Screen entire panels or mutant variants to understand binding pockets across protein classes.
- Results land in the dashboard and Om API workspace with metadata, QC, and exportable reports in 4-6 weeks.
Per-sequence pricing varies; see Pricing for current rates or contact us for large batch discounts.
Request data generation
Turn target and market questions into evidence-backed briefs
Use Diligence to move from a therapeutic question to cited claims, competitive context, and structured reports your team can act on quickly.
- Research targets, competitors, modalities, and clinical programs with source-linked outputs your team can review.
- Generate evidence-backed claims for one target or thesis, then turn them into a structured diligence brief.
- Use one Diligence workspace for fast scans, deeper research, and follow-up questions as your strategy evolves.
- Share validated findings across discovery, business development, and investment workflows without leaving Om.
Diligence uses Wallet Credits with pay-as-you-go pricing; see Pricing for current rates.
Access Diligence
Ready to launch with Om?
Create an account to browse datasets, manage subscriptions, and start exporting datasets or diligence results through the Om API.
Need a custom agreement or dataset buyouts? Contact our team.
How do we do it? Pico-scale spatial manipulations to link what molecules bind what proteins in a library by library format.
- +Synthetic Biology
- +Molecular Encoding
- +Pico-Scale Engineering
- +AI
Our technology leverages synthetic biology, pico-scale engineering, materials science, and molecular encoding to screen thousands of proteins against billions of molecules in a single reaction. We are leveraging these datasets to train machine learning models to predict molecular interactions at scale.
LatestArticles
Data Data Everywhere
Explore datasets and stream in the data you need through the Om API with subscription-gated access.
May 1, 2025 · 5 min read
Read More
Who is Om?
Om was built to solve the data problem everyone shares in therapeutic discovery, so that we can find new medicines faster.
April 30, 2025 · 6 min read
Read More
Om Launches Diligence
Diligence pairs our proteome-scale research assistant with pay-as-you-go Om API workflows, so you can evaluate targets in the UI or programmatically.
April 30, 2025 · 6 min read
Read MoreDon't know where to get started?Use free diligence on emerging targets.
Use our free diligence tool on the latest emerging targets in need of a therapeutic.
ACCESS DILIGENCE