Deep-STP: a deep learning-based approach to predict snake toxin proteins by using word embeddings

Hasan Zulfiqar, Zhiling Guo, Ramala Masood Ahmad, Zahoor Ahmed, Peiling Cai, Xiang Chen, Yang Zhang, Hao Lin, Zheng Shi · 2024

Read Deep-STP: a deep learning-based approach to predict snake toxin proteins by using word embeddings by Hasan Zulfiqar, Zhiling Guo, Ramala Masood Ahmad, Zahoor Ahmed, Peiling Cai, Xiang Chen, Yang Zhang, Hao Lin, Zheng Shi (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-10829051.txt.

Description

Hasan Zulfiqar and eight co-authors present a deep learning tool, Deep-STP, for spotting snake toxin proteins from their amino acid sequences. The study is dated 2023 in the text itself, though the catalog lists 2024. Lab identification of these proteins is accurate but slow and costly. The proteins matter because some may become drugs for heart and nerve diseases. The team's model reads sequences through three encoding schemes, including word-style embeddings borrowed from language processing.

Statistical filters trimmed the features before training. In ten-fold cross-checks the model reached 82 percent accuracy. On a separate test set it scored about 81 percent, showing the result holds on new data. The authors present the tool as a fast first screen that can flag candidate toxins for lab follow-up.

Catalog record

CREATORHasan Zulfiqar, Zhiling Guo, Ramala Masood Ahmad, Zahoor Ahmed, Peiling Cai, Xiang Chen, Yang Zhang, Hao Lin, Zheng Shi
YEAR2024
COLLECTIONPAPERS
FORMATTXT
FILE SIZE17 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC10829051

Browse the full library · About the Tower of Babel