MATHEMATICAL SEQUENCE DESCRIPTORS ILLUMINATE POORLY CHARACTERIZED PROTEINS FUNCTION IN TISSUE REGENERATION OF DEROCERAS LAEVE SLUG THROUGH MACHINE LEARNING

Luis Felipe Hernández Ramírez; Wilbert Gutiérrez-Sarmiento; Katia Aviña-Padilla; Jerónimo R. Miranda-Rodríguez; Carlos A. González-Castro; Alfredo Varela-Echavarría; Maribel Hernandez Rosales

Paper Title

Authors

Luis Felipe Hernández Ramírez
Wilbert Gutiérrez-Sarmiento
Katia Aviña-Padilla
Jerónimo R. Miranda-Rodríguez
Carlos A. González-Castro
Alfredo Varela-Echavarría
Maribel Hernandez Rosales

Modality

RIABIO

Subject area

RNA and transcriptomics

Publishing Date

21/11/2024

Country of Publishing

Brazil | Brasil

Language of Publishing

Inglês

Paper Page

https://www.even3.com.br/anais/xmeeting-2024/831531-mathematical-sequence-descriptors-illuminate-poorly-characterized-proteins-function-in-tissue-regeneration-of-der

ISBN

978-65-272-0843-3

Keywords

regeneration, rna-seq, feature extraction, machine learning, prediction, mathematical descriptors, biological sequences, python

Summary

The application of machine learning (ML) methodologies to address challenges across genomics, transcriptomics, and proteomics has been validated. In this study, we expand the application of ML to investigate tissue regeneration in a non-model organism, Deroceras laeve slug. Our aim is to elucidate the functional roles of proteins that remain poorly characterized in regenerative mechanisms by analyzing RNA-seq data obtained under both control and post-amputation scenarios. We constructed a de novo transcriptome and conducted differential expression analysis, identifying transcripts that underwent significant changes post-amputation. Transcripts were then used to predict proteins. Following this, intrinsic sequence characteristics or descriptors were extracted, including canonical descriptors such as amino acid composition and physicochemical properties, as well as representing sequences as mathematical objects such as graphs. Furthermore, through the application of feature selection and ML training, we identified clusters where proteins exhibited closely correlated functions, thereby facilitating the characterization of proteins with ambiguous roles. This approach provides a valuable resource for understanding the molecular mechanisms underlying tissue regeneration in mollusks, elucidating the intricate interplay of genes and proteins governing this complex biological phenomenon. By adopting this methodology, we contribute to the expanding knowledge base regarding regenerative processes in non-traditional model organisms. In summary, our research underscores the efficacy of ML techniques in unraveling the mysteries of tissue regeneration, particularly in understudied organisms like the Deroceras laeve slug. Through data analysis, transcriptome construction, and predictive modeling of protein sequences, we provide a nuanced understanding of the molecular dynamics driving regenerative processes. This integrative approach not only advances scientific understanding but also holds promise for the development of novel therapeutic strategies and sheds light on evolutionary adaptations in regenerative biology.

Title of the Event: 20º Congresso Brasileiro de Bioinformática: X-Meeting 2024
City of the Event: Salvador
Title of the Proceedings of the event: X-Meeting presentations
Name of the Publisher: Even3
Means of Dissemination: Meio Digital

How to cite

RAMÍREZ, Luis Felipe Hernández et al.. MATHEMATICAL SEQUENCE DESCRIPTORS ILLUMINATE POORLY CHARACTERIZED PROTEINS FUNCTION IN TISSUE REGENERATION OF DEROCERAS LAEVE SLUG THROUGH MACHINE LEARNING.. In: X-Meeting presentations. Anais...Salvador(BA) Hotel Deville Prime, 2024. Available in: https//www.even3.com.br/anais/xmeeting-2024/831531-MATHEMATICAL-SEQUENCE-DESCRIPTORS-ILLUMINATE-POORLY-CHARACTERIZED-PROTEINS-FUNCTION-IN-TISSUE-REGENERATION-OF-DER. Access in: 16/06/2025