> For the complete documentation index, see [llms.txt](https://ez-lab.gitbook.io/cryodrgn/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://ez-lab.gitbook.io/cryodrgn/cryodrgn-user-guide/news-and-release-notes.md). # News and Release Notes {% hint style="info" %} ## Use commands such as \`pip install 'cryodrgn==3.5.4'\` (replacing with your preferred version number) to install a specific past version of cryoDRGN! {% endhint %} ## cryoDRGN version release timeline * 06/2026: [**v4.3.0**](https://github.com/ml-struct-bio/cryodrgn/releases/tag/4.3.0) released with the first full end-to-end version of the dashboard interactive web app and a new command builder tool through a dedicated [site](https://ml-struct-bio.github.io/cryodrgn/) * 04/2026: [**v4.2.1**](https://github.com/ml-struct-bio/cryodrgn/releases/tag/4.2.1) released, introducing the first beta version of an interactive web app for analyzing cryoDRGN results (`cryodrgn dashboard `) * 03/2026: [**v4.2.0**](https://github.com/ml-struct-bio/cryodrgn/pull/471) released, integrating the [cryoDRGN-AI pose search algorithm](https://cryodrgnai.cs.princeton.edu/) with the command `cryodrgn abinit` * 12/2025: [**v3.5.4**](https://github.com/ml-struct-bio/cryodrgn/releases/tag/3.5.4) released, fixing issues using `--vol-ind` with 1-indexing in landscape analysis and using `--first` with `backproject_voxel` * 11/2025: [**v3.5.3**](https://github.com/ml-struct-bio/cryodrgn/releases/tag/3.5.3) released, with fixes to landscape analysis to account for the previous switch to 1-indexing as well as faster generation of landscape volumes using `--multigpu` * 09/2025: [**v3.5.2**](https://github.com/ml-struct-bio/cryodrgn/releases/tag/3.5.2) released, with faster backprojection through batched data processing, faster downsampling through I/O threading, and faster reconstruction when using larger default batch sizes * 08/2025: [**v3.5.1**](https://github.com/ml-struct-bio/cryodrgn/releases/tag/3.5.1) released, with new `--force-ntilts` to only include particles with `x` available tilts in `backproject_voxel`, plotting classes in z-latent-space using scatterplots, and fixing bug with ragged tilt-series inputs to interactive filtering * 08/2025: [**v3.5.0**](https://github.com/ml-struct-bio/cryodrgn/releases/tag/3.5.0) released, with 1-indexing for output volumes and epochs, `train_dec` for reconstruction with an auto-decoder, automatic `analyze` executed on the last epoch of training, and a unified `parse_star` command * 04/2025: [**v3.4.4**](https://github.com/ml-struct-bio/cryodrgn/releases/tag/3.4.4) released, with new support for Python 3.12, as well as introducing `--shuffle-seed` to fix randomness of batch iteration during training * 12/2024: [**v3.4.3**](https://github.com/ml-struct-bio/cryodrgn/releases/tag/3.4.3) released, adding a utility `make_movies` for animations of volumes created by cryoDRGN models, as well improving the interactive filtering interface * 11/2024: [**v3.4.2**](https://github.com/ml-struct-bio/cryodrgn/releases/tag/3.4.2) released, adding auto mixed-precision training to ab-initio reconstruction for faster training, alongside speedups to `parse_pose_star` and `analyze_landscape_full` * 10/2024: [**v3.4.1**](https://github.com/ml-struct-bio/cryodrgn/releases/tag/3.4.1) released, adding support for float16-formatted input .mrcs image stacks and addressing issues with `downsample`, `filter`, and volume evaluation * 09/2024: [**v3.4.0**](https://github.com/ml-struct-bio/cryodrgn/releases/tag/3.4.0) released, introducing plotting by class labels, support for RELION 3.1, and calculation of phase-randomized Fourier Shell correlations * 06/2024: [**v3.3.3**](https://github.com/ml-struct-bio/cryodrgn/releases/tag/3.3.3) released, addressing issues in `backproject`, `write_star`, and `filter` * 05/2024: [**v3.3.2**](https://github.com/ml-struct-bio/cryodrgn/releases/tag/3.3.2) released with improvements and fixes made to several features, including filtering with notebooks, FSC plots in `backproject_voxel`, and support for RELION 3.1 inputs in `parse_pose_star` * 05/2024: [**v3.3.1**](https://github.com/ml-struct-bio/cryodrgn/releases/tag/3.3.1) released with new ability to create files per micrograph in `filter_star` using `--micrograph-files` as well as replacing `train_nn/vae` AMP error messages with warnings * 04/2024: [**v3.3.0**](https://github.com/ml-struct-bio/cryodrgn/releases/tag/3.3.0) released — first non-beta release of [cryoDRGN-ET](https://www.biorxiv.org/content/10.1101/2023.08.18.553799v1), new command `cryodrgn direct_traversal`, improved testing, and cleaned-up Jupyter notebooks * 03/2024: [**v3.2.0-beta**](https://github.com/ml-struct-bio/cryodrgn/releases/tag/3.2.0-beta) released with new commands including `cryodrgn_utils clean`, `cryodrgn_utils gen_mask`, and `cryodrgn_utils fsc` * 12/2023: [**v3.1.0-beta**](https://github.com/ml-struct-bio/cryodrgn/releases/tag/v3.1.0-beta) released with new command `cryodrgn filter` for interactive filtering of particles * 09/2023: [CryoDRGN-ET](https://www.biorxiv.org/content/10.1101/2023.08.18.553799v1) for subtomogram analysis is now available in beta, as [**cryodrgn v3.0.0-beta**](https://github.com/ml-struct-bio/cryodrgn/releases/tag/3.0.0-beta) * 06/2023: documentation clean up, available here on gitbook * 05/2023: [**cryodrgn v2.3.0**](https://github.com/ml-struct-bio/cryodrgn/releases/tag/2.3.0) released with improvements and fixes to ab initio tools. * 01/2023: [**cryodrgn v2.2.0**](https://github.com/ml-struct-bio/cryodrgn/releases/tag/2.2.0) released with new ab initio reconstruction tools and more. * 07/2022: [**cryodrgn v1.1.0**](https://github.com/ml-struct-bio/cryodrgn/releases/tag/1.1.0) released with updated default architecture * 05/2022: [**cryodrgn v1.0.0**](https://github.com/ml-struct-bio/cryodrgn/releases/tag/1.0.0) released with new landscape analysis, cryodrgn\_utils, and more ## Software Change Log Comprehensive notes on all releases including minor and patch versions can be found at the Github repository: ## Documentation Change Log * May 2024: * updating and expanding tutorial on using cryoDRGN v3 for [subtomogram analysis](/cryodrgn/cryodrgn-et-subtomogram-analysis.md) * creating [new page group](https://app.gitbook.com/o/gYlX75MBAfjzRuXIYbKH/s/z7E99j3jJUSLJDvU43U6/~/changes/37/deprecated-workflows) "Deprecated Workflows" initially populated with `cryodrgn preprocess` material * June 2023: * moving documentation to gitbook (here) — the previous documentation found at [Notion](https://www.notion.so/cryodrgn/cryoDRGN-tutorial-b932c021cb2c415282f182048bac16ff)/sphinx will no longer be updated * new page on [Making long trajectories with cryoDRGN graph\_traversal](/cryodrgn/making-long-trajectories-with-cryodrgn-graph_traversal.md) --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://ez-lab.gitbook.io/cryodrgn/cryodrgn-user-guide/news-and-release-notes.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.