
Speaker: Clara Rossi
November 24th, 2026 | 2:30 pm
DEIB, PT2 Meeting Room (Bld. 20A)
For further information please contact: Silvia Cascianelli | silvia.cascianelli@polimi.it
Abstract
Tuesday, November 24th, 2026 at 2:30 pm a new appointment of Data Science Seminars: Bioinformatics focus will take place in DEIB PT2 Meeting Room (Building 20A), on line by Webex, organized by the Data Science for Bioinformatics group.ùThe seminar will be held by Clara Rossi on the following subject: "Unveiling new mRNA stability determinants: towards a half-life prediction model".
Messenger RNA (mRNA) stability is a key regulator of gene expression, determining how long a transcript remains available for translation in the cytoplasm. Although several determinants of mRNA stability have been identified, understanding how their complex interplay shapes transcript half-lives remains a major challenge. Integrating these determinants into a predictive model could reveal new principles of post-transcriptional regulation, but also guide the design of molecules with desired stability, which is crucial in the context of mRNA-based therapeutics.
Despite the advances in predicting half-life from the mRNA sequence, state-of-the-art models are typically trained and benchmarked on datasets reflecting particular cellular contexts, without explicitly incorporating contextual and molecular information such as secondary structure, RNA binding proteins (RBPs) and poly(A) deadenylation rates. Moreover, half-life measurements are at gene-level, limiting their ability to learn stability differences between transcript isoforms.
To address these limitations, we aim at developing an RNA foundation model and fine-tune it for transcript-specific half-life prediction, integrating sequence representations with molecular and cellular information. However, the current work focuses on estimating isoform-resolved half-lives and deadenylation rates from experimental data obtained from SLAM-seq and FLAM-seq protocols, respectively.
