{"id":17255152,"url":"https://github.com/unixjunkie/rankers","last_synced_at":"2025-04-14T05:41:34.391Z","repository":{"id":144782654,"uuid":"221657102","full_name":"UnixJunkie/rankers","owner":"UnixJunkie","description":"Reference implementation of the Vanishing Ranking Kernels (VRK) method","archived":false,"fork":false,"pushed_at":"2023-01-05T03:15:44.000Z","size":370,"stargazers_count":5,"open_issues_count":2,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-03-27T19:39:35.250Z","etag":null,"topics":["applicability-domain","bandwidth-selection","cadd","chemoinformatics","classification","hts","kde","lbvs","ocaml-program","qsar","vrk"],"latest_commit_sha":null,"homepage":null,"language":"OCaml","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/UnixJunkie.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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}},"created_at":"2019-11-14T09:18:02.000Z","updated_at":"2024-11-05T00:28:26.000Z","dependencies_parsed_at":null,"dependency_job_id":"e7d412c4-11f8-4d43-be34-7fdab00c378f","html_url":"https://github.com/UnixJunkie/rankers","commit_stats":null,"previous_names":[],"tags_count":13,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/UnixJunkie%2Frankers","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/UnixJunkie%2Frankers/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/UnixJunkie%2Frankers/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/UnixJunkie%2Frankers/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/UnixJunkie","download_url":"https://codeload.github.com/UnixJunkie/rankers/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248830418,"owners_count":21168272,"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":["applicability-domain","bandwidth-selection","cadd","chemoinformatics","classification","hts","kde","lbvs","ocaml-program","qsar","vrk"],"created_at":"2024-10-15T07:10:49.580Z","updated_at":"2025-04-14T05:41:34.355Z","avatar_url":"https://github.com/UnixJunkie.png","language":"OCaml","funding_links":[],"categories":[],"sub_categories":[],"readme":"# RanKers\nReference implementation of the Vanishing Ranking Kernels (VRK) method\n\n[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.3546697.svg)](https://doi.org/10.5281/zenodo.3546697)\n\n# How to install the software\n\nFor beginners/non opam users:\ndownload and execute the latest self-installer\nshell script from (https://github.com/UnixJunkie/rankers/releases).\n\nThen execute:\n```\n./rankers-1.0.0.sh ~/usr/rankers-1.0.0\n```\n\nThis will create ~/usr/rankers-1.0.0/bin/rankers_bwmine, among other things\nin the same directory.\n\nFor opam users:\n```\nopam install rankers\n```\n\nDo not hesitate to contact the author in case you have problems installing\nor using the software or if you have any question.\n\n# Example\n\n![Logo](data/ROC.png?raw=true)\n*Example ROC curve on a hold-out test set. The test set had 38 active\nmolecules and 664 inactives. ROC AUC: 0.861; BEDROC AUC: 0.766; PR AUC: 0.678.\nThe ROC curve is in purple; the precision-recall (PR) curve in cyan. The\nprobability of activity given a raw score is the red curve.\nThe green curve is the number of actives divided by the\nnumber of decoys as a function of the scores filtering threshold.*\n\nTrain and test a model:\n```\nrankers_bwmine -i data/tox21_nrar_ligands_std_rand_01.txt\n```\n\nSame, but using 16 cores :\n```\nrankers_bwmine -np 16 -i data/tox21_nrar_ligands_std_rand_01.txt\n```\n\n# Usage\n\n```\nrankers_bwmine -i \u003ctrain.txt\u003e\n  [-p \u003cfloat\u003e]: proportion of the (randomized) dataset\n  used to train (default=0.80)\n  [-k {uni|tri|epa|biw}]: kernel function choice (default=biw)\n  [-np \u003cint\u003e]: max number of processes (default=1)\n  [-o \u003cfilename\u003e]: write raw test scores to file\n  [--train \u003ctrain.txt\u003e]: training set (overrides -p)\n  [--valid \u003cvalid.txt\u003e]: validation set (overrides -p)\n  [--test \u003ctest.txt\u003e]: test set (overrides -p)\n  [-n \u003cint\u003e]: max number of optimization steps; default=150\n  [--capf \u003cfloat\u003e]: keep only fraction of decoys\n  [--capx \u003cint\u003e]: keep only X decoys per active\n  [--capi \u003cint\u003e]: limit total number of molecules\n  (but keep all actives)\n  [--seed \u003cint\u003e: fix random seed]\n  [--pr]: use PR AUC instead of ROC AUC during optimization\n  [-kb \u003cfloat\u003e]: user-chosen kernel bandwidth\n  [--mcc-scan]: scan classif. threshold to maximize MCC\n  [--tap]: tap the train-valid-test partitions to disk\n  [-q|--quick]: exit early; just after model training\n  [--noplot]: turn off gnuplot\n  [-v]: verbose/debug mode\n  [-h|--help]: show this help message\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Funixjunkie%2Frankers","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Funixjunkie%2Frankers","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Funixjunkie%2Frankers/lists"}