University of Reading Research Data Archive

Dataset supporting the article 'Variable-temperature token sampling in decoder-GPT molecule-generation can produce more robust and potent virtual screening libraries'

How to cite this Dataset

Description

Raw data for virtual screeing libraries generated by a generative, pre-trained transformer-decoder model using variable temperature decoding. In this scheme, various temperature ramps are used during the generation process, such that each token could have a different generation temperature. The model used for this is described in our previous work:
DOI: 10.1021/acs.jcim.4c01309.

Resource Type: Dataset
Creators: Cafiero, Mauricio ORCID logoORCID: https://orcid.org/0000-0002-4895-1783
Rights-holders: University of Reading
Data Publisher: University of Reading
Publication Year: 2025
Data last accessed: 2 April 2025
DOI: https://doi.org/10.17864/1947.001408
Metadata Record URL: https://researchdata.reading.ac.uk/id/eprint/1408
Organisational units: Life Sciences > School of Chemistry, Food and Pharmacy > Department of Chemistry
Participating Organisations: University of Reading
Keywords: GPT, machine learning, drug design
Rights:
Data Availability: OPEN

Files

Download all (.zip)

Data

README file

Statistics

Altmetric

Actions (Log-in required)

View item View item