{"id":13774365,"url":"https://github.com/FangpingWan/NeoDTI","last_synced_at":"2025-05-11T06:33:12.242Z","repository":{"id":37484423,"uuid":"126759614","full_name":"FangpingWan/NeoDTI","owner":"FangpingWan","description":"NeoDTI: Neural integration of neighbor information from a heterogeneous network for discovering new drug-target interactions","archived":false,"fork":false,"pushed_at":"2021-05-13T09:39:35.000Z","size":22474,"stargazers_count":74,"open_issues_count":3,"forks_count":33,"subscribers_count":5,"default_branch":"master","last_synced_at":"2024-11-17T09:39:07.192Z","etag":null,"topics":["bioinformatics","computational-biology","deep-learning","graph-convolution","machine-learning"],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/FangpingWan.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}},"created_at":"2018-03-26T01:56:56.000Z","updated_at":"2024-11-12T08:46:55.000Z","dependencies_parsed_at":"2022-09-09T07:00:49.322Z","dependency_job_id":null,"html_url":"https://github.com/FangpingWan/NeoDTI","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FangpingWan%2FNeoDTI","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FangpingWan%2FNeoDTI/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FangpingWan%2FNeoDTI/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FangpingWan%2FNeoDTI/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/FangpingWan","download_url":"https://codeload.github.com/FangpingWan/NeoDTI/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253528407,"owners_count":21922623,"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":["bioinformatics","computational-biology","deep-learning","graph-convolution","machine-learning"],"created_at":"2024-08-03T17:01:26.044Z","updated_at":"2025-05-11T06:33:07.789Z","avatar_url":"https://github.com/FangpingWan.png","language":"Python","funding_links":[],"categories":["Drug Response Prediction","Deep Learning"],"sub_categories":["Drug Target Interaction"],"readme":"# NeoDTI\nNeoDTI: Neural integration of neighbor information from a heterogeneous network for discovering new drug-target interactions [(Bioinformatics)](https://academic.oup.com/bioinformatics/advance-article/doi/10.1093/bioinformatics/bty543/5047760).\n\n# Recent Update 09/06/2018\nL2 regularization is added.\n\n# Requirements\n* Tensorflow (tested on version 1.0.1 and version 1.2.0)\n* tflearn\n* numpy (tested on version 1.13.3 and version 1.14.0)\n* sklearn (tested on version 0.18.1 and version 0.19.0)\n\n# Quick start\nTo reproduce our results:\n1. Unzip data.zip in ./data.\n2. Run \u003ccode\u003eNeoDTI_cv.py\u003c/code\u003e to reproduce the cross validation results of NeoDTI. Options are:  \n`-d: The embedding dimension d, default: 1024.`  \n`-n: Global norm to be clipped, default: 1.`  \n`-k: The dimension of project matrices, default: 512.`  \n`-r: Positive and negative. Two choices: ten and all, the former one sets the positive:negative = 1:10, the latter one considers all unknown DTIs as negative examples. Default: ten.`  \n`-t: Test scenario. The DTI matrix to be tested. Choices are: o, mat_drug_protein.txt will be tested; homo, mat_drug_protein_homo_protein_drug.txt will be tested; drug, mat_drug_protein_drug.txt will be tested; disease, mat_drug_protein_disease.txt will be tested; sideeffect, mat_drug_protein_sideeffect.txt will be tested; unique, mat_drug_protein_drug_unique.txt will be tested. Default: o.`\n3. Run \u003ccode\u003eNeoDTI_cv_with_aff.py\u003c/code\u003e to reproduce the cross validation results of NeoDTI with additional compound-protein binding affinity data. Options are:  \n`-d: The embedding dimension d, default: 1024.`  \n`-n: Global norm to be clipped, default: 1.`  \n`-k: The dimension of project matrices, default: 512.`  \n\n# Data description\n* drug.txt: list of drug names.\n* protein.txt: list of protein names.\n* disease.txt: list of disease names.\n* se.txt: list of side effect names.\n* drug_dict_map: a complete ID mapping between drug names and DrugBank ID.\n* protein_dict_map: a complete ID mapping between protein names and UniProt ID.\n* mat_drug_se.txt : Drug-SideEffect association matrix.\n* mat_protein_protein.txt : Protein-Protein interaction matrix.\n* mat_drug_drug.txt : Drug-Drug interaction matrix.\n* mat_protein_disease.txt : Protein-Disease association matrix.\n* mat_drug_disease.txt : Drug-Disease association matrix.\n* mat_protein_drug.txt : Protein-Drug interaction matrix.\n* mat_drug_protein.txt : Drug-Protein interaction matrix.\n* Similarity_Matrix_Drugs.txt : Drug \u0026 compound similarity scores based on chemical structures of drugs (\\[0,708) are drugs, the rest are compounds).\n* Similarity_Matrix_Proteins.txt : Protein similarity scores based on primary sequences of proteins.\n* mat_drug_protein_homo_protein_drug.txt: Drug-Protein interaction matrix, in which DTIs with similar drugs (i.e., drug chemical structure similarities \u003e 0.6) or similar proteins (i.e., protein sequence similarities \u003e 40%) were removed (see the paper).\n* mat_drug_protein_drug.txt: Drug-Protein interaction matrix, in which DTIs with drugs sharing similar drug interactions (i.e., Jaccard similarities \u003e 0.6) were removed (see the paper).\n* mat_drug_protein_sideeffect.txt: Drug-Protein interaction matrix, in which DTIs with drugs sharing similar side effects (i.e., Jaccard similarities \u003e 0.6) were removed (see the paper).\n* mat_drug_protein_disease.txt: Drug-Protein interaction matrix, in which DTIs with drugs or proteins sharing similar diseases (i.e., Jaccard similarities \u003e 0.6) were removed (see the paper).\n* mat_drug_protein_unique: Drug-Protein interaction matrix, in which known unique and non-unique DTIs were labelled as 3 and 1, respectively, the corresponding unknown ones were labelled as 2 and 0 (see the paper for the definition of unique). \n* mat_compound_protein_bindingaffinity.txt: Compound-Protein binding affinity matrix (measured by negative logarithm of _Ki_).\n\nAll entities (i.e., drugs, compounds, proteins, diseases and side-effects) are organized in the same order across all files. These files: drug.txt, protein.txt, disease.txt, se.txt, drug_dict_map, protein_dict_map, mat_drug_se.txt, mat_protein_protein.txt, mat_drug_drug.txt, mat_protein_disease.txt, mat_drug_disease.txt, mat_protein_drug.txt, mat_drug_protein.txt, Similarity_Matrix_Proteins.txt, are extracted from https://github.com/luoyunan/DTINet.\n\n\n\n# Contacts\nIf you have any questions or comments, please feel free to email Fangping Wan (wfp15[at]tsinghua[dot]org[dot]cn) and/or Jianyang Zeng (zengjy321[at]tsinghua[dot]edu[dot]cn).\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FFangpingWan%2FNeoDTI","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FFangpingWan%2FNeoDTI","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FFangpingWan%2FNeoDTI/lists"}