Functional yeast promoter sequence design using autoregressive generative models

Read full text
Authors: Ibrahim Alsaggaf, Alex Alves Freitas, João Pedro de Magalhães, Cen Wan
Cited by: 0

Abstract

This repository includes the models' checkpoints and the generated synthetic yeast promoter DNA sequences used in the paper titled "Functional yeast promoter sequence design using autoregressive generative models". The ZIP file includes two directories: The first one is named "Model checkpoints" and includes the three variants of the Gen-DNA-TCN model (i.e. Model 1, Model 2, and Model 3), in addition to the Pre-DNA-TCN model. The second directory is named "Yeast promoter sequences" and includes the real training and validation yeast promoter DNA sequences, in addition to the generated synthetic yeast promoter DNA sequences using two different approaches (i.e. different real starting nucleotides [Table 3] and random permutation [Table 4]). For more details on how to load the checkpoints and reproduce the results, please check our GitHub repo at https://github.com/ibrahimsaggaf/Gen-DNA-TCN.

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
8 January 2026
Language
EN
Document type
Dataset