{"id":50341222,"url":"https://github.com/manchesterbioinference/mrna_llm","last_synced_at":"2026-05-29T17:01:31.007Z","repository":{"id":361188120,"uuid":"986205606","full_name":"ManchesterBioinference/mRNA_LLM","owner":"ManchesterBioinference","description":"Using LLMs to understand mRNA features","archived":false,"fork":false,"pushed_at":"2026-05-29T13:59:52.000Z","size":107572,"stargazers_count":0,"open_issues_count":1,"forks_count":1,"subscribers_count":15,"default_branch":"translationEfficiency","last_synced_at":"2026-05-29T15:15:57.078Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"HTML","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ManchesterBioinference.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-05-19T09:08:11.000Z","updated_at":"2026-05-29T13:45:42.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/ManchesterBioinference/mRNA_LLM","commit_stats":null,"previous_names":["manchesterbioinference/mrna_llm"],"tags_count":3,"template":false,"template_full_name":null,"purl":"pkg:github/ManchesterBioinference/mRNA_LLM","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ManchesterBioinference%2FmRNA_LLM","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ManchesterBioinference%2FmRNA_LLM/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ManchesterBioinference%2FmRNA_LLM/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ManchesterBioinference%2FmRNA_LLM/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ManchesterBioinference","download_url":"https://codeload.github.com/ManchesterBioinference/mRNA_LLM/tar.gz/refs/heads/translationEfficiency","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ManchesterBioinference%2FmRNA_LLM/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33662205,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-05-29T02:00:06.066Z","response_time":107,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2026-05-29T17:01:29.940Z","updated_at":"2026-05-29T17:01:30.992Z","avatar_url":"https://github.com/ManchesterBioinference.png","language":"HTML","funding_links":[],"categories":[],"sub_categories":[],"readme":"# mRNA Ribosome Density Prediction\n\nThis project predicts mRNA ribosome density (a.k.a. translation efficiency or TE) and decay rates in *Drosophila melanogaster* using a fine-tuned RNA Language Model (LLM). It integrates sequence information from 3' UTRs with additional features like codon usage and RNA secondary structure stability.\n\n## Publication\n\n- **Preprint**: A preprint describing this work is available on bioRxiv: [10.64898/2025.12.04.692303v1](https://www.biorxiv.org/content/10.64898/2025.12.04.692303v1)\n\n## Project Overview\n\n- **Goal**: Predict ribosome density and mRNA decay from sequence data.\n- **Model**: Extended the pretraining of GenaLM Fly (BERT-based) on 5' \u0026 3' UTR pairs and fine-tuned the model with a regression head.\n- **Features**:\n  - 5' \u0026 3' UTR sequences\n  - Codon usage metrics\n  - Minimum Free Energy (MFE) from RNA folding (LinearFold)\n  - GC content and sequence length\n- **Pipeline**: Managed by DVC for reproducibility, covering data download, preprocessing, feature extraction, and model training.\n\n- **Decay analysis**: Detailed decay-rate analyses are kept on the `decay` branch of this repository (see the `decay` branch for notebooks and results).\n\n## Installation Requirements\n\nApptainer, conda, and DVC must be installed on your system and in your path.\n\n- [Apptainer installation guide](https://apptainer.org/docs/user/latest/quick_start.html#installation)\n- [Conda installation guide](https://www.anaconda.com/docs/getting-started/miniconda/install)\n- [DVC installation guide](https://dvc.org/doc/install)\n\n## Usage\n\nThis DVC pipeline will build the necessary conda environment using the provided `environment.yaml`.\n\nTo reproduce the pipeline run the following command:\n\n``` {bash}\ndvc repro\n```\n\n## Repository Structure\n\n- `dvc.yaml`: Pipeline definition.\n- `params.yaml`: Configuration parameters.\n- `scripts/`: Source code for data processing and training.\n- `notebooks/`: Exploratory analysis and visualization.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmanchesterbioinference%2Fmrna_llm","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmanchesterbioinference%2Fmrna_llm","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmanchesterbioinference%2Fmrna_llm/lists"}