This tool enables in silico design of synthetic promoters in yeast by predicting optimal insertion sites for transcription factor binding sites (TFBSs).

Unlike synthetic promoter libraries that ignore native genomic context, our model leverages an artificial neural network (ANN) framework trained specifically on yeast promoter sequences to suggest context-aware promoter–TFBS recombinations.

Key features:

• Identifies insertion region for a TFBS within a promoter (defined as the 400 bp upstream of the start codon).
• Refines the extent of promoter rewriting needed for successful integration.
• Provides a visualization of the recombined sequence.
• Designed for yeast promoters only (main focus on Saccharomyces cerevisiae); predictions for other organisms may not be reliable.

This predictive approach reduces experimental trial-and-error and enables scalable engineering of regulatory sequences for applications in synthetic biology, metabolic engineering, and transcriptional network rewiring.

The tool requires four inputs, provided via text fields:

1. Promoter sequence
   • Input a DNA sequence using only {A, C, T, G}.
   • Supported sequence length: exactly 400 bp.
     • If shorter → error message.
     • If longer → tool automatically trims to the last 400 bp.
2. TFBS sequence (query)
   • Input a DNA sequence using only {A, C, T, G}.
   • Supported sequence length: 8–64 bp.
     • If shorter or longer → error message.
3. Promoter name (optional)
   • Free text label for the promoter.
   • No effect on computation.
   • Appears in the generated graph title.
4. TFBS name (optional)
   • Free text label for the TFBS.
   • No effect on computation.
   • Appears in the generated graph title.

After providing the inputs, click Submit.
The tool will predict and display the synthetic promoter design with a graphical visualization of TFBS insertion site and extent of promoter rewriting.