The basics of what we’re building and why.

We turn insect behavior into training data to prevent disease and protect crops with a community of crop, global health, and machine learning scientists.

When a mosquito lands on a human, it can mean malaria. When an insect lands on a crop, it can mean eating, egg-laying, and lost food.

Changing these decisions means understanding the living animal. Which compounds change its behavior? Under what conditions? And does that change translate into protection for people and crops?

Our tools are not keeping pace. Insects evolve faster than the insecticide industry can formulate. We need an approach built around changing their decision to land.

Changing trillions of those decisions is a technically more challenging approach. But answering it could be one of humanity’s most important achievements. We think this is one of the most important technical and moral challenges of our time.

We are living through rapid gains in machine intelligence, yet malaria is resurgent and insects continue to reduce global crop yields.

Taking advantage of those gains means removing a bottleneck to real-world progress: behavioral data. The opportunity is to bring increasingly capable models together with a scientific community committed to running the experiments those models need.

Decades can pass with little progress, then months can produce decades’ worth of progress. The acceleration of machine intelligence, together with the global scientific community’s commitment to generating the data needed to unlock its potential, gives us a rare opportunity to make significant progress in the near-term.

AI can read everything humanity has written about mosquitoes and other insects and still cannot know how an untested compound will change a decision of this living animal. We have to run the experiments.

We are building a standardized database capturing insect responses to thousands of chemical compounds. Those responses become training data for predictive models. Each experiment, whether a compound works or fails, adds evidence that helps us decide what to test next.

To accelerate the answer means more openness and rapid sharing. It means an effort with the ambition of the Human Genome Project, with thousands of scientists generating behavioral data that becomes training data for increasingly capable predictive models.

Laboratories bring different expertise, insect populations, and field conditions. Sharing their work allows each experiment to inform the next, across the network. We want a community of researchers pointed in the same direction, with the same intention, with the same mission.

Compound identities and basic repellency data on those compounds are released publicly each quarter, so researchers, companies, and other organizations can build on those findings. Public release of anything else requires separate written permission from Monarch and the contributing institutions.

Organizations can then pursue the work needed to turn promising compounds into effective products: developing formulations, testing safety and performance in the field, obtaining regulatory approvals, and manufacturing and distributing them.

Like the Human Genome Project, our aim is to create a shared scientific foundation that enables many organizations to develop useful applications. We think this gives effective solutions a better chance of reaching the people and farmers who need them.

This requires an array of disciplines, from machine learning and computer vision to chemical ecology, insect biology, and insect neuroscience.

University laboratories, research institutes, and qualified independent researchers can contribute their assays, expertise, and field validation. Your group might screen compounds, investigate how they change behavior, test model predictions, or study their performance in the field. We would work together to define the experiments and the support needed to run them.

Every participating group receives the full shared dataset and ranked actives, including results from other laboratories. Shared materials include behavioral measurements, experimental metadata, and video recordings.

Accepted laboratories also receive compounds, standardized assay materials, and shared protocols. Only compound identities and basic repellency data on those compounds are released publicly each quarter. Other research data is shared within the network; public release requires separate written permission from Monarch and the contributing institutions.

We are also open to funding a student or postdoctoral researcher working on an agreed collaboration. That support is considered case by case.

Please request access here, choosing disease prevention for mosquito research or crop protection for agricultural insect research. If your lab is accepted, we'll follow-up with onboarding instructions.

The application includes a required checkbox accepting the Memorandum of Understanding and confirming that you are authorized to accept it for the applicant. No separate signature document is required.

Tell us what your laboratory works on, the questions you want to answer, and how you think you could contribute. We will follow up to discuss the work and the support it would require.

All labs run a fixed protocol on the same assay, pair every treated run with a same-day solvent control, and test a shared compound panel at the same concentrations.

We will report the following metrics to assess data reliability:

• Inter-assay correlation (r)
• Hit re-test rate
• Inter-lab variance (CV)
• z-score

According to the CDC, Anopheles mosquitoes generally remain within 1.2 miles (2 km) of their larval habitats. We aim to use this local movement pattern to design repellent coverage that takes neighboring communities into account. Field testing is needed to determine whether that coverage protects people without increasing biting in nearby unprotected areas.

Sources on mosquito movement: CDC’s Anopheles guide and a mark-release-recapture study.

• Inter-lab reproducibility of the contact/non-contact assay across geographies and mosquito strains.
• Cross-genus concordance of landing inhibition between Aedes aegypti and Anopheles gambiae.
• Benchmarking in-silico repellency predictions against prospective assay outcomes.
• Structure–activity relationships in a new scaffold class identified through the open atlas.
• Mode-of-action studies linking repellent chemistry to mosquito odorant receptor interactions.

Public release of Program findings beyond the quarterly compound identities and basic repellency data requires separate written permission from Monarch and the contributing institutions.

• Inter-lab reproducibility of the contact/non-contact assay across geographies and fly populations.
• Context dependency of repellency across fruit and host volatiles: raspberry, strawberry, blueberry, and cherry.
• Benchmarking in-silico repellency predictions against prospective assay outcomes.
• Structure–activity relationships in a new scaffold class identified through the open atlas.
• Mode-of-action studies linking repellent chemistry to Drosophila odorant receptor interactions.

Public release of Program findings beyond the quarterly compound identities and basic repellency data requires separate written permission from Monarch and the contributing institutions.