PyScale: A software package for analysis of nucleotide sequences


Creators: Chattopadhyay, Amit ORCID logoORCID: and Flower, Darren
Keywords: Protein sequencing, Python, Deep Learning
Divisions: College of Engineering and Physical Sciences > Systems Analytics Research Institute (SARI)
Funders: Nuffield Foundation through Aston University
Projects: Antimicrobial Drug Repurposing Using Clinical Data – Acquisition, Analysis & Modelling
Data Publisher: Aston University
Date Made Available: 5 November 2019
Collection period:
Data Collection and Processing Methods: Nucleotide scales were collected by scrutinising the primary scientific literature. Data acquisition progressed in two stages. Initially, two re-views (Sandberg et al., 1996; Polyansky et al., 2013) were parsed, identifying a core set of scales. We also undertook quasi-exhaustive literature searches, using assorted search terms within PUBMED, Sco-pus, and ISI Web of Knowledge, together with retrospective and pro-spective searching using citation look-up. In all cases, we read original articles to identify data items. PyScale 1.0 contains 243 mononucleotide, 46 dinucleotide, and 17 trinucleotide scales. Data were processed using two codes, one terminal based ( and the other GUI based (, both based on python3.
Identification Number:




Additional statistics for this record