Our Platform,

Powered by AI


There are thousands of plants containing molecules with therapeutic potential. At Enveda, we built three core technologies that we collectively refer to as our platform. These technologies allow us to:

  • efficiently hypothesize about which plants might hold therapeutics for specific diseases
  • map the novel chemical space in plants of interest
  • rapidly identify the active molecules responsible for the bioactivities and explore novel chemical space around those active molecules for improved activity

how we do it

We Solve Fundamental Challenges in Natural Product Drug Discovery with Advanced Technologies


MOA-driven hypotheses

Integrates multiple data streams to nominate high-confidence therapeutic hypotheses, target candidates, and mechanisms of action.


Cloud-scale dereplication

Rapidly executes “cloud-scale” dereplication to identify novel scaffolds for actionable lead identification.


Bioactive Lead Identification

Deconvolutes bioactive lead molecules 100X faster than traditional methods and nominates high-value SAR directions.



Biological Knowledge Graph.

The BIOEDGE knowledge graph integrates humanity’s collective knowledge about plants, biology, and disease with the results of our high-throughput internal experiments. With machine learning and graph algorithms, the BIOEDGE knowledge graph allows us to generate mechanistically sound therapeutic hypotheses quickly and comprehensively. BIOEDGE motivates and prioritizes the experiments we perform in our labs. The results of those experiments, in turn, inform BIOEDGE.

Known compounds
Novel compounds discovered by NOMAD



Networking for Molecular Annotations & Discovery.

Re-discovery of known natural products from complex mixtures stymied natural product research. NOMAD continuously analyzes metabolomics data from our growing library across 1000s of plants against all known natural products to “dereplicate” known plant compounds and annotate novel chemistry from BIOEDGE nominated plants for downstream efforts.



Molecular Activity Informed Diversity Enhancement.

Identifying and isolating active compounds from plants was a slow, iterative and labor-intensive process. MAIDEN leverages proprietary algorithms linking metabolomics data to bioactivity measurements to transform this process from an open-ended endeavor that could take decades to a highly parallelized, deterministic process that can be accomplished in days. MAIDEN allows us to rapidly explore the therapeutic potential of millions of phytochemicals and nominate targeted exploration of nearby chemical space around target molecular scaffolds provided by nature for enhanced bioactivity and drug-like potential.

Bioactive compounds (large nodes)
Patentable semi-synthetic compounds

Our Dataset

We are building the largest integrated dataset of plant chemistry in the world, tailor-made for drug discovery. With metabolomics analyses of thousands of medicinally important plants linked to internally generated bioactivity measurements using cutting-edge algorithms, we’re uniquely positioned to scale the discovery of first-in-class small molecules for complex diseases. With every experiment, we learn something about both our unique library and disease biology that we reintroduce into our dataset to fine-tune our algorithms.
With every experiment, our dataset grows, and our platform gets smarter.

Change the Future
with Us!