{"id":22621061,"url":"https://github.com/jgreener64/allopred","last_synced_at":"2025-06-19T02:44:47.968Z","repository":{"id":31719275,"uuid":"35285120","full_name":"jgreener64/allopred","owner":"jgreener64","description":"Predict allosteric pockets on proteins","archived":false,"fork":false,"pushed_at":"2022-03-28T11:11:38.000Z","size":211,"stargazers_count":15,"open_issues_count":0,"forks_count":6,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-04-11T15:51:15.413Z","etag":null,"topics":["allosteric-pockets","allostery","normal-mode-analysis","protein-structure"],"latest_commit_sha":null,"homepage":"http://www.sbg.bio.ic.ac.uk/allopred/home","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/jgreener64.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2015-05-08T14:53:01.000Z","updated_at":"2023-11-09T14:10:39.000Z","dependencies_parsed_at":"2022-09-17T07:51:08.470Z","dependency_job_id":null,"html_url":"https://github.com/jgreener64/allopred","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/jgreener64/allopred","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jgreener64%2Fallopred","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jgreener64%2Fallopred/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jgreener64%2Fallopred/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jgreener64%2Fallopred/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jgreener64","download_url":"https://codeload.github.com/jgreener64/allopred/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jgreener64%2Fallopred/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":260674814,"owners_count":23045063,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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":["allosteric-pockets","allostery","normal-mode-analysis","protein-structure"],"created_at":"2024-12-08T22:17:27.052Z","updated_at":"2025-06-19T02:44:42.948Z","avatar_url":"https://github.com/jgreener64.png","language":"Python","readme":"[![DOI](https://zenodo.org/badge/doi/10.5281/zenodo.32016.svg)](http://dx.doi.org/10.5281/zenodo.32016)\n\n# AlloPred\n\nThis is the code and training/testing data used at the AlloPred web server, which predicts allosteric pockets on proteins from a PDB format file:\n\nhttp://www.sbg.bio.ic.ac.uk/allopred/home\n\n*The server is currently having problems due to configuration issues. We are looking to resolve this.*\n\nThe method is described here: Greener, JG and Sternberg, MJE, AlloPred: prediction of allosteric pockets on proteins using normal mode perturbation analysis, *BMC Bioinformatics*, 2015, 16(335). [Link to paper](http://bmcbioinformatics.biomedcentral.com/articles/10.1186/s12859-015-0771-1).\n\nDownloading this code lets you run AlloPred locally. It should work on all Unix-based systems. With modification it could be made to work on Windows.\n\nPlease contact Joe Greener (http://jgreener64.github.io) for support, queries and suggestions. Alternatively, open an issue on GitHub.\n\n\n## Requirements\n\n* Python 2.7 with the [NumPy](http://www.numpy.org/) and [ProDy](http://prody.csb.pitt.edu/) packages installed.\n* fpocket v2.0, which can be downloaded from [here](http://fpocket.sourceforge.net/). Follow the installation instructions to compile the executables.\n* SVM-light, which can be downloaded from [here](http://svmlight.joachims.org/). Follow the installation instructions to compile the executables.\n\n\n## Usage\n\nFollow these steps to set up AlloPred - the shell commands are for bash:\n\n1. Download the files and extract them as usual, or clone the repository.\n\n2. The environmental variables `$ALLOPRED_DIR` and `$SVM_LIGHT_DIR` need to be set as the filepaths to the AlloPred directory and the SVM-light directory respectively:\n  ```\n  export ALLOPRED_DIR=/path/to/allopred/\n  export SVM_LIGHT_DIR=/path/to/svm_light/\n  ```\n  Consider adding these lines to your profile so you don't have to run them every session.\n\nFollow these step to run AlloPred:\n\n1. Obtain a PDB format file (`in_file.pdb`), e.g. from the [Protein Data Bank](http://www.rcsb.org/pdb/home/home.do).\n\n2. Create a one-line file (`act_res.txt`) containing the active site residues of the protein. The format is `10:A,11:B` for residue 10 on chain A and residue 11 on chain B. These can be found using resources such as the [Catalytic Site Atlas](http://www.ebi.ac.uk/thornton-srv/databases/CSA/). An example PDB file and active residue file can be found in the example directory of AlloPred.\n\n3. Run fpocket v2.0 on the PDB file:\n  ```\n  fpocket -f in_file.pdb\n  ```\n  This assumes `fpocket` is on the path. This produces the directory `in_file_out`. AlloPred is optimised on the default fpocket parameters but you can change these in accordance with the fpocket documentation if you wish.\n\n4. The following command, from the directory containing `in_file.pdb` and `in_file_out`, runs the AlloPred pipeline:\n  ```\n  python $ALLOPRED_DIR/run_allopred.py in_file act_res.txt\n  ```\n  The arguments are the input file prefix and the path to the active site residue file. Running the `run_allopred.py` script with fewer than 2 arguments returns these instructions for the command.\n\n5. The output files are:\n  * `in_file.out`: the AlloPred output file containing the input parameters and the values for each pocket in order of AlloPred ranking.\n  * `in_file.svm`: the SVM input file in the SVM-light format.\n\n\n## Other files\n\n* `dataset` contains information on the training and testing sets.\n* `example` contains the inputs and outputs of an example run using the PDB entry with ID 1FX2.\n* `svm_model.txt` is the optimised SVM built on the whole training set.\n\n\n## Reproducibility\n\nFor reference, here are steps to reproduce the results in Figure 3 of the paper (link above):\n\n1. Obtain PDB files from the test set list in `dataset/test_set.tsv`.\n2. Keep only the chains for each file given in `dataset/test_set.tsv`.\n3. For each protein carry out steps 2-4 above using the active site residues given in `dataset/test_set.tsv`.\n4. Compare the residues for the top predicted pockets in `in_file.out` to the allosteric residues given in `dataset/test_set.tsv`.\n\n\n## Note\n\nOn some systems the normal mode calculation step fails (`More than 6 zero eigenvalues are calculated`). This appears to be due to an error in `scipy.linalg.eigh` which causes an error in the `calcModes` function of ProDy.\n\nThank you for using AlloPred!\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjgreener64%2Fallopred","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjgreener64%2Fallopred","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjgreener64%2Fallopred/lists"}