Input
Target context defined by your team’s biological objective.
Pipeline 1
Pipeline 1: molecules for your targets
Start with a target (for example, a disease-relevant protein). denovoX applies high-level ML-driven generation and prioritization workflows to produce candidate molecules ranked for exploration.
Input → process → output
High-level pipeline framing
Process
Computational exploration with an ensemble of ML models and generative approaches, described at high level.
Output
Prioritized candidate molecules aligned to criteria for follow-up experimental planning.
Process
Three-step workflow
-
1
Define target
Provide the disease-relevant target and project constraints for computational prioritization.
-
2
denovoX runs ML pipeline
Explore chemical space and generate candidate sets through high-level machine-learning workflows.
-
3
Prioritize candidates
Rank generated options against project-relevant criteria to focus downstream experiments.
Benefits
Why teams use Pipeline 1
- Faster early exploration cycles around biologically relevant targets.
- Reduced cost pressure by narrowing candidate space before wet-lab expansion.
- Improved focus of experimental work through ranked molecule outputs.
Applications
Example domains
Oncology
Rare diseases
Inflammation
Neurodegeneration
Cardiometabolic
Contact sales