Hackathon setup#6
Merged
tobiasploetz merged 88 commits intomainfrom Oct 17, 2025
Merged
Conversation
…ments.txt to pyproject.toml
…create predict_in_docker.sh script for running predictions
…missions for output directory
…iles using ColabFold
… and update related code
… to include modifications
…redict_hackathon.py
… enhance input handling
…g for protein complex and ligand processing
…riable assignments
…iction in preparation functions
…n-ligand predictions
…ntrypoints for the hackathon
…nd evaluation limits for hackathon participants
… multiple configurations for protein complex and ligand predictions
Clarifications
Various changes to README
Fix bash command
Clarify CUDA requirement for hackathon
|
|
wiwnopgm
pushed a commit
to wiwnopgm/boltz-hackathon-template
that referenced
this pull request
Oct 20, 2025
* feat: Add initial project structure and example files for Boltz Hackathon * feat: Add chain_id field to protein and ligand data structures and update examples * chore: Update dependencies section in README and migrate from requirements.txt to pyproject.toml * feat: Add Dockerfile and environment.yml for containerized setup and create predict_in_docker.sh script for running predictions * fix: prediction dir, and some debugging options * fix: Update submission directory path in Docker script and adjust permissions for output directory * feat: Implement MSA computation script for protein sequences using ColabFold * feat: Add msa_dir parameter to functions for computing relative paths in YAML files * fix: Remove unused MSA server flag and update relative path computation for MSA file * fix: Add ground_truth structure to protein_complex and protein_ligand JSON files * feat: Add script for computing MSAs from protein sequences in JSONL files using ColabFold * fix: Remove chain_id from protein and ligand structures in JSON files and update related code * feat: Add modifications field to Protein class and update YAML output to include modifications * refactor: Organize imports and enhance class structure in hackathon_api.py * refactor: Move everything into hackathon dir, add * refactor: Update TaskType class definition and enhance MSA processing in scripts * refactor: Enhance argument parsing and streamline input handling in predict_hackathon.py * refactor: msa naming by datapoint Id * feat: Add parallel CAPRI-Q evaluation runner with Docker support * feat: Add group ID argument for submission directory and update permissions handling * refactor: Streamline protein complex and ligand prediction functions, enhance input handling * refactor: Update comments for clarity in participant modification section * refactor: Enhance function documentation and add CLI argument handling for protein complex and ligand processing * refactor: Simplify post-processing functions by removing redundant variable assignments * refactor: Update comments to clarify example usage for structure prediction in preparation functions * refactor: Update data structure to support multiple ligands in protein-ligand predictions * refactor: update dataclasses to allow CCD-based ligands (e.g. for organometallics) * refactor: Revise README to enhance clarity on setup and participant entrypoints for the hackathon * refactor: Enhance README with additional details on post-processing and evaluation limits for hackathon participants * refactor: Update preparation and post-processing functions to support multiple configurations for protein complex and ligand predictions * feat: Add AS/OS evaluation script to calculate ligand RMSD values and generate plots * build: Add matplotlib to dependencies for enhanced plotting capabilities * feat: store top 1 model accuracy and print top 1 summary at the end * fix: ensure that the query sequence is always the first entry in MSA csv file * feat: harmonize CLI args of eval scripts * refactor: extract query sequence extraction logic into a separate method * docs: add evaluation and prediction commands for both challenges * chore: remove file * feat: add --result-folder CLI arg to predict_hackathon.py to have prediction and eval in one go * feat: add quick start section to hackathon README * docs: update setup instructions to clarify forking the repository * docs: add submission guidelines and deadline details to README * docs: add link to method description in submission guidelines * feat: remove network access and ensure submission directory exists before running docker container * feat: increase shared memory size for docker container * docs: clarify evaluation environment restrictions regarding internet access * fix: rename eval script for consistent naming * fix: path to GT structure * docs: add back evaluation instructions for existing predictions * docs: add hackathon instructions to README * feat: Smoothing over eval code and description * fix: small bug in parsing classification results * docs: extend detail on functions that participants can modify * feat: Add instructions on pre-submission checklist * feat: smoothing * fix: typos * fix: small bug * docs: update help section * docs: update dataset download instructions and paths in README * feat: remove "modifications" and "ccd" * fix: remove unused comment * Info on MSA * Clarifications * Add image folder * workflow.drawio * cleanup img creation * Additional clarifications * Add schematic of the workflow * Clarify in diagram that there are 5 predictions * fix: dataset name * fix: clarification * fix: clarify that there is only a single small molecule * Various changes to README * Smoothing, emphasize that precomputed MSAs are always provided * Fix the bash command to properly deal with line breaks * Remove empty line * Delete tmp/input/8CYH_config_0.yaml * Update gitignore with template result paths * docs: clarify CUDA requirement for hackathon * feat: add baseline results and reduce # of Ab/Ag structures to 10 * smoothing * deps: adding pymol * chore: make workflow image a bit prettier --------- Co-authored-by: Tobias Ploetz <[email protected]> Co-authored-by: Karin Hrovatin <[email protected]> Co-authored-by: Alexander V. Hopp <[email protected]>
wiwnopgm
pushed a commit
to andxeg/boltz-hackathon-template
that referenced
this pull request
Oct 21, 2025
…ffinity-predictor-using-boltz2-apvtx6 Load SAbDab without PyTDC
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
5 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.