{"id":47217519,"url":"https://github.com/ratschlab/aestetik","last_synced_at":"2026-03-13T16:34:19.067Z","repository":{"id":243175503,"uuid":"757518853","full_name":"ratschlab/aestetik","owner":"ratschlab","description":"AESTETIK: AutoEncoder for Spatial Transcriptomics Expression with Topology and Image Knowledge","archived":false,"fork":false,"pushed_at":"2026-03-08T10:49:40.000Z","size":28533,"stargazers_count":18,"open_issues_count":0,"forks_count":4,"subscribers_count":4,"default_branch":"main","last_synced_at":"2026-03-08T14:27:15.393Z","etag":null,"topics":["machine-learning","spatial-transcriptomics"],"latest_commit_sha":null,"homepage":"https://www.medrxiv.org/content/10.1101/2024.06.04.24308256v1","language":"Python","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/ratschlab.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","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":"2024-02-14T16:53:21.000Z","updated_at":"2026-03-08T10:49:44.000Z","dependencies_parsed_at":"2025-09-25T07:21:26.768Z","dependency_job_id":null,"html_url":"https://github.com/ratschlab/aestetik","commit_stats":null,"previous_names":["ratschlab/aestetik"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/ratschlab/aestetik","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ratschlab%2Faestetik","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ratschlab%2Faestetik/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ratschlab%2Faestetik/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ratschlab%2Faestetik/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ratschlab","download_url":"https://codeload.github.com/ratschlab/aestetik/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ratschlab%2Faestetik/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30471103,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-13T11:00:43.441Z","status":"ssl_error","status_checked_at":"2026-03-13T11:00:23.173Z","response_time":60,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["machine-learning","spatial-transcriptomics"],"created_at":"2026-03-13T16:34:17.963Z","updated_at":"2026-03-13T16:34:19.052Z","avatar_url":"https://github.com/ratschlab.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"[![Downloads](https://static.pepy.tech/badge/aestetik)](https://pepy.tech/project/aestetik)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n[![Python 3.9+](https://img.shields.io/badge/python-3.9+-blue.svg)](https://www.python.org/downloads/)\n[![medRxiv](https://img.shields.io/badge/medRxiv-2024.06.04.24308256-blue)](https://www.medrxiv.org/content/10.1101/2024.06.04.24308256v1)\n\n# AESTETIK: AutoEncoder for Spatial Transcriptomics Expression with Topology and Image Knowledge\n\nThis model is part of the paper \"Representation learning for multi-modal spatially resolved transcriptomics data\".\n\n**Authors**: Kalin Nonchev, Sonali Andani, Joanna Ficek-Pascual, Marta Nowak, Bettina Sobottka, Tumor Profiler Consortium, Viktor Hendrik Koelzer, and Gunnar Rätsch\n\nThe preprint is available [here](https://www.medrxiv.org/content/10.1101/2024.06.04.24308256v1).\n\n## News\n \n  - [03.2026] [Towards Cross-Sample Alignment for Multi-Modal Representation Learning in Spatial Transcriptomics](https://www.biorxiv.org/content/10.64898/2026.03.02.709002v1) will be at ICLR 2026 Learning Meaningful Representations of Life \n  - [09.2026] AESTETIK now supports multi-modal (e.g., H\u0026E images, spatial transcriptomics) and cross-sample integration using Harmony, scVI, etc.\n  - [08.2024] AESTETIK secured the 1st place at the Mammoth International Contest On Omics Sciences in Europe 2024 organized by China National GeneBank, BGI Genomics, MGI and CODATA [link](https://micos.cngb.org/europe/index.html).\n\n## Changelog\n**NEW version (June 2025)**\n  - **UPDATE:** Rewrote AESTETIK using the Lightning framework for improved modularity\n  - **Added:** New `fit()/predict()` API\n  - **Added:** Support for processing multiple samples at once\n  - **Removed:** Multiple old methods and parameters in AESTETIK \n\nSee [full changelog](CHANGELOG.md) for more details.\n    \n## Do you want to gain a multi-modal understanding of key biological processes through spatial transcriptomics?\n\nWe introduce AESTETIK, a convolutional autoencoder model. It jointly integrates transcriptomics and morphology information, on a spot level, and topology, on a neighborhood level, to learn accurate spot representations that capture biological complexity.\n\n![aestetik](/figures/aestetik.png)\n\n**Fig. 1 AESTETIK integrates spatial, transcriptomics, and morphology information to learn accurate spot representations.**\n**A**: Spatial transcriptomics enables in-depth molecular characterization of samples on a morphology and RNA level while preserving spatial location. **B**: Workflow of AESTETIK. Initially, the transcriptomics and morphology spot representations are preprocessed. Next, a dimensionality reduction technique (e.g., PCA) is applied. Subsequently, the processed spot representations are clustered separately to acquire labels required for the multi-triplet loss. Afterwards, the modality-specific representations are fused through concatenation and the grid per spot is built. This is used as an input for the autoencoder. Lastly, the spatial-, transcriptomics-, and morphology-informed spot representations are obtained and used for downstream tasks such as clustering, morphology analysis, etc.\n\n## Setup\n\nWe can install aestetik directly through pip.\n\n```\npip install aestetik\n```\n\nWe can also create a conda environment with the required packages.\n\n```\nconda env create --file=environment.yaml\n```\n\nWe can also install aestetik offline.\n\n```\ngit clone https://github.com/ratschlab/aestetik\ncd aestetik\npython setup.py install\n```\n\n##### NB: Please ensure you have installed [pyvips](https://github.com/libvips/pyvips) depending on your machine's requirements. We suggest installing pyvips through conda:\n```\nconda install conda-forge::pyvips\n```\n\n## Getting Started\n\nPlease take a look at our [example](example/gettingStartedWithAESTETIK.ipynb) to get started with AESTETIK.\n\n![aestetik](/figures/maynard_human_brain_analysis_151676_Transcriptomics_Morphology_AESTETIK.png)\n\n[Here](example/gettingStartedWithAESTETIKwithSimulatedData.ipynb), another example notebook with [simulated spatial transcriptomics data](https://github.com/ratschlab/simulate_spatial_transcriptomics_tool).\n\n![aestetik](/figures/AESTETIK_clustering.png)\n\n\n## Papers Citing AESTETIK\n\n\u003c!-- CITATIONS:START --\u003e\n1. Justina Dai, Kalin Nonchev, V. Koelzer, and Gunnar Rätsch \"Towards Cross-Sample Alignment for Multi-Modal Representation Learning in Spatial Transcriptomics.\" *bioRxiv* (2026). [DOI](https://doi.org/10.64898/2026.03.02.709002)\n2. Kalin Nonchev, Glib Manaiev, V. Koelzer, and Gunnar Rätsch \"DeepSpot2Cell: Predicting Virtual Single-Cell Spatial Transcriptomics from H\u0026E images using Spot-Level Supervision.\" *bioRxiv* (2025). [DOI](https://doi.org/10.1101/2025.09.23.678121)\n3. Liping Kang, Qinglong Zhang, Fan Qian, Junyao Liang, and Xiaohui Wu \"Benchmarking computational methods for detecting spatial domains and domain-specific spatially variable genes from spatial transcriptomics data.\" *Nucleic Acids Research* (2025). [DOI](https://doi.org/10.1093/nar/gkaf303)\n4. Kalin Nonchev, Sebastian Dawo, Karina Silina, H. Moch, S. Andani, Tumor Profiler Consortium, V. H. Koelzer, and Gunnar R¨atsch \"DeepSpot: Leveraging Spatial Context for Enhanced Spatial Transcriptomics Prediction from H\u0026E Images.\" *medRxiv* (2025). [DOI](https://doi.org/10.1101/2025.02.09.25321567)\n\u003c!-- CITATIONS:END --\u003e\n\n*This list is automatically updated weekly via [GitHub Actions](.github/workflows/update-citations.yml) using the [Semantic Scholar](https://www.semanticscholar.org/) and [OpenCitations](https://opencitations.net/) APIs.*\n\n## Related Projects\n\n- [DeepSpot](https://github.com/ratschlab/DeepSpot) — Predicts spatial transcriptomics from H\u0026E images at spot-level (Visium) and single-cell (Xenium) resolution. Uses AESTETIK for cross-sample integration.\n- [DeepSpot2Cell](https://github.com/ratschlab/DeepSpot2Cell) — Predicts virtual single-cell spatial transcriptomics from H\u0026E images using spot-level supervision.\n\n## Citation\n\nIn case you found our work useful, please consider citing us:\n\n```\n@article{nonchev2024representation,\n  title={Representation learning for multi-modal spatially resolved transcriptomics data},\n  author={Nonchev, Kalin and Andani, Sonali and Ficek-Pascual, Joanna and Nowak, Marta and Sobottka, Bettina and Tumor Profiler Consortium and Koelzer, Viktor Hendrik and Raetsch, Gunnar},\n  journal={medRxiv},\n  pages={2024--06},\n  year={2024},\n  publisher={Cold Spring Harbor Laboratory Press}\n}\n```\n\nThe code for reproducing the paper results can be found [here](https://github.com/ratschlab/st-rep).\n\n## Contact\n\nIn case, you have questions, please get in touch with [Kalin Nonchev](https://bmi.inf.ethz.ch/people/person/kalin-nonchev).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fratschlab%2Faestetik","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fratschlab%2Faestetik","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fratschlab%2Faestetik/lists"}