MRSLpred: A computational tool for multilabel mRNA subcellular localization prediction

MRSLpred: A computational tool for multilabel mRNA subcellular localization prediction | Zenodo Skip to main Communities My dashboard Log in Sign up Zenodo is currently experiencing slowness and intermittent outages due to heavy automated traffic from bots and AI crawlers. We are aware of the problem, and our team is focused on stabilizing the service. Thank you for your patience. raghavagps Published May 1, 2026 | Version v1.0 Software Open MRSLpred: A computational tool for multilabel mRNA subcellular localization prediction Authors/Creators Choudhury, Shubham (Researcher) 1 Raghava, Gajendra (Supervisor) 2 Show affiliations 1.

Indraprastha Institute of Information Technology 2. Indraprastha Institute of Information Technology Delhi Description Title: MRSLpred Dataset – Multi‑label subcellular localization of human mRNA sequences (6 compartments) Description: Project: MRSLpred – A hybrid approach for predicting multi‑label subcellular localization of mRNA at the genome scale Publication: Choudhury, S., Bajiya, N., Patiyal, S., & Raghava, G.P.S. (2024). MRSLpred – a hybrid approach for predicting multi‑label subcellular localization of mRNA at the genome scale. Frontiers in Bioinformatics , 4, 1341479. https://doi.org/10.3389/fbinf.2024.1341479 Overview: This dataset accompanies MRSLpred, a multi‑label classifier for predicting subcellular localization of human mRNA. Unlike traditional single‑label methods, MRSLpred assigns multiple locations to each mRNA (e.g., nucleus AND exosome), reflecting real‑world biology. mRNA localization controls protein synthesis spatially and is critical for neuronal maturation, embryonic patterning, cell migration, and stress adaptation. The dataset is derived from RNALocate v2 and pre‑processed by DM3Loc, with redundancy reduced at 80% similarity. Content: 17,277 non‑exclusive human mRNA sequences distributed across 6 subcellular compartments: Compartment Number of mRNAs Exosome 17,156 Nucleus 11,923 Ribosome 5,210 Membrane 3,232 Cytosol 2,338 Endoplasmic reticulum (ER) 1,976 Train/validation split: 80/20 (stratified by location labels) Best Model Performance (XGBoost + motif module – validation set): Location Sensitivity Specificity AUC MCC Exosome 0.696 0.692 0.816 0.073 Membrane 0.675 0.676 0.736 0.280 Nucleus 0.671 0.671 0.736 0.319 Ribosome 0.664 0.664 0.728 0.304 Cytosol 0.650 0.650 0.708 0.211 ER 0.657 0.656 0.727 0.205 Average 0.669 0.668 0.742 0.232 Features (CDK3 + RDK4 combined) – XGBoost alone (validation): Average AUC = 0.710, Average MCC = 0.216 Benchmarking comparison (validation set): Method Average AUC Multi‑label? Notes MRSLpred 0.742 ✅ Fast, genome‑scale DM3Loc 0.704 ✅ Deep learning, slow, high resource iLoc‑mRNA ~0.50 ❌ Single‑label only mRNALoc ~0.46 ❌ Single‑label only Computational efficiency (500 mRNA sequences): Method Real time User time MRSLpred ~23 sec ~5 sec DM3Loc ~32 min ~28 min MRSLpred is >80× faster than DM3Loc with comparable performance. Motif coverage (training set): Exosome (1,655 sequences), Nucleus (95), ER (65), Ribosome (32), Membrane (29), Cytosol (25) Data Curation & Quality Control: Source: RNALocate v2 (via DM3Loc pre‑processed dataset) Organism: Homo sapiens Redundancy reduction: CD‑HIT at 80% sequence identity Labels: Multi‑hot encoding (6 locations) Features: Nfeature (CDK3 + RDK4) → 200 features Motifs: MERCI (discriminative location‑specific motifs) Train/validation split: 80/20 stratified Usage: Multi‑label mRNA subcellular localization prediction (genome scale), identifying location‑specific sequence motifs, understanding mRNA spatial regulation, developmental biology research. Related Resources: Web server: https://webs.iiitd.edu.in/raghava/mrslpred/ | GitHub: https://github.com/raghavagps/mrslpred Contact: raghava@iiitd.ac.in (Gajendra P. S. Raghava) Files raghavagps/mrslpred-v1.0.zip Files (19.9 MB) Name Size Download all raghavagps/mrslpred-v1.0.zip md5:88aa82fae92a453bb4e068d71af5ec57 19.9 MB Preview Download Additional details Related works Is supplement to Software: https://github.com/raghavagps/mrslpred/tree/v1.0 (URL) Software Repository URL https://github.com/raghavagps/mrslpred 13 Views 2 Downloads Show more details All versions This version Views Total views 13 13 Downloads Total downloads 2 2 Data volume Total data volume 39.7 MB 39.7 MB More info on how stats are collected.... Versions External resources Archived in Software Heritage swh:1:dir:69b064b99cf90780d75d2c9b17f59941eb020110 Available in raghavagps/mrslpred Release: v1.0 Indexed in OpenAIRE Communities Details DOI DOI Badge DOI 10.5281/zenodo.19941115 Markdown [](https://doi.org/10.5281/zenodo.19941115) reStructuredText .. image:: https://zenodo.org/badge/DOI/10.5281/zenodo.19941115.svg :target: https://doi.org/10.5281/zenodo.19941115 HTML <a href="https://doi.org/10.5281/zenodo.19941115"><img src="https://zenodo.org/badge/DOI/10.5281/zenodo.19941115.svg" alt="DOI"></a> Image URL https://zenodo.org/badge/DOI/10.5281/zenodo.19941115.svg Target URL https://doi.org/10.5281/zenodo.19941115 Resource type Software Publisher Zenodo Rights License GNU General Public License v3.0 only No further description. Read more Citation Export Technical metadata Created May 1, 2026 Modified May 1, 2026 Jump up About About Policies Infrastructure Principles Projects Roadmap Contact Blog Blog Support Help FAQ Developers REST API OAI-PMH Contribute GitHub Donate Funded by Powered by CERN Data Centre & InvenioRDM Status Privacy policy Cookie policy Terms of Use This site uses cookies. Find out more on how we use cookies Accept all cookies Accept only essential cookies

Related documents

• SpaNiche: spatial niche analysis to explore colocalization patterns and cellular interactions in spatial transcriptomics data.#258155
• Brownotate, a Comprehensive Solution to Generate Protein Sequence Databases for Any Species#1146448
• Evaluation of Deep Neural Network ProSPr for Accurate Protein Distance Predictions on CASP14 Targets#394565
• Bridging local-global transmembrane protein contexts with contrastive pretraining for alignment-free pathogenicity prediction.#342607
• Hierarchical classification of immune cell transcriptomes at population-scale#383442