Generation Tasks›Retrosynthesis

Retrosynthesis

Predict synthetic routes for target molecules

Task Overview

Retrosynthesis is the process of deconstructing target molecules into simpler, commercially available starting materials through a series of chemical transformations. This task involves planning the sequence of reactions needed to synthesize a target molecule.

Impact

Computer-aided retrosynthesis can dramatically accelerate synthetic planning by rapidly proposing multiple synthetic routes. This is crucial for complex molecule synthesis in drug development, reducing the time from target identification to synthesis.

Generalization

Models must generalize to propose synthetic routes for novel molecular structures, including those with unusual scaffolds or functional groups not well-represented in training data.

Product

Small-molecule.

Pipeline Stage

Synthesis planning and manufacturing.

Usage Example

You can access generation tasks using the PyTDC library:

from tdc_ml.generation import Retrosynthesis

# Load the task
task = Retrosynthesis()

# Generate or predict
result = task.generate()
print(result)

Key Features

  • ✓State-of-the-art generative models and baselines
  • ✓Standardized evaluation metrics and benchmarks
  • ✓Oracle functions for property evaluation
  • ✓Integration with popular deep learning frameworks

Resources