├── .gitignore ├── .readthedocs.yaml ├── App_network_view.JPG ├── CITATION.cff ├── COPD_PI_test.py ├── LICENSE ├── ModellingFrameworks_v7.png ├── ModellingFrameworks_white.png ├── PathIntegrateGraphic.png ├── README.md ├── docs ├── docs │ ├── gendocs_docs │ │ └── reference │ │ │ └── pathintegrate.md │ ├── images │ │ └── ModellingFrameworks_white.png │ ├── index.md │ └── input.md └── mkdocs.yml ├── mkgendocs.yml ├── pages ├── About.py ├── DetailsView.py └── __init__.py ├── plot_functs.py ├── quickstart.ipynb ├── requirements.txt ├── root_cmap.csv ├── setup.py └── src └── pathintegrate ├── __init__.py ├── app.py ├── data ├── ReactomePathwaysRelation.txt ├── Reactome_Homo_sapiens_pathways_multiomics_R85.gmt ├── copd_pvals.csv ├── metabolomics_example.csv └── proteomics_example.csv ├── pathintegrate.py ├── plot.py └── utils.py /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | 6 | # C extensions 7 | *.so 8 | 9 | # Distribution / packaging 10 | .Python 11 | build/ 12 | develop-eggs/ 13 | dist/ 14 | downloads/ 15 | eggs/ 16 | .eggs/ 17 | lib/ 18 | lib64/ 19 | parts/ 20 | sdist/ 21 | var/ 22 | wheels/ 23 | share/python-wheels/ 24 | *.egg-info/ 25 | .installed.cfg 26 | *.egg 27 | MANIFEST 28 | 29 | # PyInstaller 30 | # Usually these files are written by a python script from a template 31 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 32 | *.manifest 33 | *.spec 34 | 35 | # Installer logs 36 | pip-log.txt 37 | pip-delete-this-directory.txt 38 | 39 | # Unit test / coverage reports 40 | htmlcov/ 41 | .tox/ 42 | .nox/ 43 | .coverage 44 | .coverage.* 45 | .cache 46 | nosetests.xml 47 | coverage.xml 48 | *.cover 49 | *.py,cover 50 | .hypothesis/ 51 | .pytest_cache/ 52 | cover/ 53 | 54 | # Translations 55 | *.mo 56 | *.pot 57 | 58 | # Django stuff: 59 | *.log 60 | local_settings.py 61 | db.sqlite3 62 | db.sqlite3-journal 63 | 64 | # Flask stuff: 65 | instance/ 66 | .webassets-cache 67 | 68 | # Scrapy stuff: 69 | .scrapy 70 | 71 | # Sphinx documentation 72 | docs/_build/ 73 | 74 | # PyBuilder 75 | .pybuilder/ 76 | target/ 77 | 78 | # Jupyter Notebook 79 | .ipynb_checkpoints 80 | 81 | # IPython 82 | profile_default/ 83 | ipython_config.py 84 | 85 | # pyenv 86 | # For a library or package, you might want to ignore these files since the code is 87 | # intended to run in multiple environments; otherwise, check them in: 88 | # .python-version 89 | 90 | # pipenv 91 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. 92 | # However, in case of collaboration, if having platform-specific dependencies or dependencies 93 | # having no cross-platform support, pipenv may install dependencies that don't work, or not 94 | # install all needed dependencies. 95 | #Pipfile.lock 96 | 97 | # poetry 98 | # Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control. 99 | # This is especially recommended for binary packages to ensure reproducibility, and is more 100 | # commonly ignored for libraries. 101 | # https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control 102 | #poetry.lock 103 | 104 | # pdm 105 | # Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control. 106 | #pdm.lock 107 | # pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it 108 | # in version control. 109 | # https://pdm.fming.dev/#use-with-ide 110 | .pdm.toml 111 | 112 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm 113 | __pypackages__/ 114 | 115 | # Celery stuff 116 | celerybeat-schedule 117 | celerybeat.pid 118 | 119 | # SageMath parsed files 120 | *.sage.py 121 | 122 | # Environments 123 | .env 124 | .venv 125 | env/ 126 | venv/ 127 | ENV/ 128 | env.bak/ 129 | venv.bak/ 130 | 131 | # Spyder project settings 132 | .spyderproject 133 | .spyproject 134 | 135 | # Rope project settings 136 | .ropeproject 137 | 138 | # mkdocs documentation 139 | /site 140 | 141 | # mypy 142 | .mypy_cache/ 143 | .dmypy.json 144 | dmypy.json 145 | 146 | # Pyre type checker 147 | .pyre/ 148 | 149 | # pytype static type analyzer 150 | .pytype/ 151 | 152 | # Cython debug symbols 153 | cython_debug/ 154 | 155 | # PyCharm 156 | # JetBrains specific template is maintained in a separate JetBrains.gitignore that can 157 | # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore 158 | # and can be added to the global gitignore or merged into this file. For a more nuclear 159 | # option (not recommended) you can uncomment the following to ignore the entire idea folder. 160 | #.idea/ 161 | -------------------------------------------------------------------------------- /.readthedocs.yaml: -------------------------------------------------------------------------------- 1 | # Required 2 | version: 2 3 | 4 | build: 5 | os: ubuntu-20.04 6 | tools: 7 | python: "3.10" 8 | 9 | mkdocs: 10 | configuration: docs/mkdocs.yml 11 | 12 | # Optionally declare the Python requirements required to build your docs 13 | python: 14 | install: 15 | - requirements: requirements.txt -------------------------------------------------------------------------------- /App_network_view.JPG: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cwieder/PathIntegrate/f3071a7fb93cc866cec98bee9874782918d9cc53/App_network_view.JPG -------------------------------------------------------------------------------- /CITATION.cff: -------------------------------------------------------------------------------- 1 | cff-version: 1.2.0 2 | message: "If you use this software, please cite it as below." 3 | authors: 4 | - family-names: "Wieder" 5 | given-names: "Cecilia" 6 | orcid: "https://orcid.org/0000-0003-1548-4346" 7 | - family-names: "Popham" 8 | given-names: "Jude" 9 | orcid: "https://orcid.org/0009-0004-1116-1034" 10 | title: "PathIntegrate Unsupervised" 11 | version: 1.0.0 12 | doi: 10.5281/zenodo.14060723 13 | date-released: 2024-11-09 14 | url: "https://github.com/cwieder/PathIntegrate" 15 | -------------------------------------------------------------------------------- /COPD_PI_test.py: -------------------------------------------------------------------------------- 1 | import pandas as pd 2 | import numpy as np 3 | import pathintegrate 4 | import sspa 5 | 6 | 7 | md = pd.read_csv('H:/Documents/pathway-integration/COPDgene/COPDgene_phonotype.txt', sep='\t') 8 | prot = pd.read_csv('H:/Documents/pathway-integration/COPDgene/COPDgene_proteomics_UniProt.csv', index_col=0) 9 | metab = pd.read_csv('H:/Documents/pathway-integration/COPDgene/COPDgene_metabolomics_CHEBI_mapped.csv', index_col=0) 10 | trans = pd.read_csv('D:/COPDgene/Processed/COPDgene_transcriptomics_filt_Q1_scaled.csv', index_col=0) 11 | metab['Group'] = metab.index.map(dict(zip(md['sid'], md["COPD"]))) 12 | 13 | metab = metab[metab['Group'].isin([0, 1])] 14 | intersect_samples = set(metab.index.tolist()) & set(prot.index.tolist()) & set(trans.index.tolist()) 15 | prot = prot.loc[intersect_samples, :] 16 | metab = metab.loc[intersect_samples, :] 17 | trans = trans.loc[intersect_samples, :] 18 | 19 | mo_paths_all = pd.read_csv('D:/Pathway_databases\Reactome_multi_omics_ChEBI_Uniprot_Ensembl.csv', index_col=0, dtype=object) 20 | 21 | pi_model = pathintegrate.PathIntegrate(omics_data={'Metabolomics': metab, 'Proteomics':prot.iloc[:, :-1], 'Transcriptomics': trans.iloc[:, :-1]}, 22 | metadata=metab['Group'], 23 | pathway_source=mo_paths_all, 24 | sspa_scoring='svd', 25 | min_coverage=2) 26 | 27 | copdgene_multi_view = pi_model.MultiView(ncomp=4) 28 | 29 | # launch the pathwy network explorer on a local server 30 | pathintegrate.launch_network_app(copdgene_multi_view, mo_paths_all) -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | GNU GENERAL PUBLIC LICENSE 2 | Version 3, 29 June 2007 3 | 4 | Copyright (C) 2007 Free Software Foundation, Inc. 5 | Everyone is permitted to copy and distribute verbatim copies 6 | of this license document, but changing it is not allowed. 7 | 8 | Preamble 9 | 10 | The GNU General Public License is a free, copyleft license for 11 | software and other kinds of works. 12 | 13 | The licenses for most software and other practical works are designed 14 | to take away your freedom to share and change the works. By contrast, 15 | the GNU General Public License is intended to guarantee your freedom to 16 | share and change all versions of a program--to make sure it remains free 17 | software for all its users. We, the Free Software Foundation, use the 18 | GNU General Public License for most of our software; it applies also to 19 | any other work released this way by its authors. You can apply it to 20 | your programs, too. 21 | 22 | When we speak of free software, we are referring to freedom, not 23 | price. Our General Public Licenses are designed to make sure that you 24 | have the freedom to distribute copies of free software (and charge for 25 | them if you wish), that you receive source code or can get it if you 26 | want it, that you can change the software or use pieces of it in new 27 | free programs, and that you know you can do these things. 28 | 29 | To protect your rights, we need to prevent others from denying you 30 | these rights or asking you to surrender the rights. Therefore, you have 31 | certain responsibilities if you distribute copies of the software, or if 32 | you modify it: responsibilities to respect the freedom of others. 33 | 34 | For example, if you distribute copies of such a program, whether 35 | gratis or for a fee, you must pass on to the recipients the same 36 | freedoms that you received. You must make sure that they, too, receive 37 | or can get the source code. And you must show them these terms so they 38 | know their rights. 39 | 40 | Developers that use the GNU GPL protect your rights with two steps: 41 | (1) assert copyright on the software, and (2) offer you this License 42 | giving you legal permission to copy, distribute and/or modify it. 43 | 44 | For the developers' and authors' protection, the GPL clearly explains 45 | that there is no warranty for this free software. For both users' and 46 | authors' sake, the GPL requires that modified versions be marked as 47 | changed, so that their problems will not be attributed erroneously to 48 | authors of previous versions. 49 | 50 | Some devices are designed to deny users access to install or run 51 | modified versions of the software inside them, although the manufacturer 52 | can do so. This is fundamentally incompatible with the aim of 53 | protecting users' freedom to change the software. The systematic 54 | pattern of such abuse occurs in the area of products for individuals to 55 | use, which is precisely where it is most unacceptable. Therefore, we 56 | have designed this version of the GPL to prohibit the practice for those 57 | products. If such problems arise substantially in other domains, we 58 | stand ready to extend this provision to those domains in future versions 59 | of the GPL, as needed to protect the freedom of users. 60 | 61 | Finally, every program is threatened constantly by software patents. 62 | States should not allow patents to restrict development and use of 63 | software on general-purpose computers, but in those that do, we wish to 64 | avoid the special danger that patents applied to a free program could 65 | make it effectively proprietary. To prevent this, the GPL assures that 66 | patents cannot be used to render the program non-free. 67 | 68 | The precise terms and conditions for copying, distribution and 69 | modification follow. 70 | 71 | TERMS AND CONDITIONS 72 | 73 | 0. Definitions. 74 | 75 | "This License" refers to version 3 of the GNU General Public License. 76 | 77 | "Copyright" also means copyright-like laws that apply to other kinds of 78 | works, such as semiconductor masks. 79 | 80 | "The Program" refers to any copyrightable work licensed under this 81 | License. Each licensee is addressed as "you". "Licensees" and 82 | "recipients" may be individuals or organizations. 83 | 84 | To "modify" a work means to copy from or adapt all or part of the work 85 | in a fashion requiring copyright permission, other than the making of an 86 | exact copy. The resulting work is called a "modified version" of the 87 | earlier work or a work "based on" the earlier work. 88 | 89 | A "covered work" means either the unmodified Program or a work based 90 | on the Program. 91 | 92 | To "propagate" a work means to do anything with it that, without 93 | permission, would make you directly or secondarily liable for 94 | infringement under applicable copyright law, except executing it on a 95 | computer or modifying a private copy. Propagation includes copying, 96 | distribution (with or without modification), making available to the 97 | public, and in some countries other activities as well. 98 | 99 | To "convey" a work means any kind of propagation that enables other 100 | parties to make or receive copies. Mere interaction with a user through 101 | a computer network, with no transfer of a copy, is not conveying. 102 | 103 | An interactive user interface displays "Appropriate Legal Notices" 104 | to the extent that it includes a convenient and prominently visible 105 | feature that (1) displays an appropriate copyright notice, and (2) 106 | tells the user that there is no warranty for the work (except to the 107 | extent that warranties are provided), that licensees may convey the 108 | work under this License, and how to view a copy of this License. If 109 | the interface presents a list of user commands or options, such as a 110 | menu, a prominent item in the list meets this criterion. 111 | 112 | 1. Source Code. 113 | 114 | The "source code" for a work means the preferred form of the work 115 | for making modifications to it. "Object code" means any non-source 116 | form of a work. 117 | 118 | A "Standard Interface" means an interface that either is an official 119 | standard defined by a recognized standards body, or, in the case of 120 | interfaces specified for a particular programming language, one that 121 | is widely used among developers working in that language. 122 | 123 | The "System Libraries" of an executable work include anything, other 124 | than the work as a whole, that (a) is included in the normal form of 125 | packaging a Major Component, but which is not part of that Major 126 | Component, and (b) serves only to enable use of the work with that 127 | Major Component, or to implement a Standard Interface for which an 128 | implementation is available to the public in source code form. A 129 | "Major Component", in this context, means a major essential component 130 | (kernel, window system, and so on) of the specific operating system 131 | (if any) on which the executable work runs, or a compiler used to 132 | produce the work, or an object code interpreter used to run it. 133 | 134 | The "Corresponding Source" for a work in object code form means all 135 | the source code needed to generate, install, and (for an executable 136 | work) run the object code and to modify the work, including scripts to 137 | control those activities. However, it does not include the work's 138 | System Libraries, or general-purpose tools or generally available free 139 | programs which are used unmodified in performing those activities but 140 | which are not part of the work. For example, Corresponding Source 141 | includes interface definition files associated with source files for 142 | the work, and the source code for shared libraries and dynamically 143 | linked subprograms that the work is specifically designed to require, 144 | such as by intimate data communication or control flow between those 145 | subprograms and other parts of the work. 146 | 147 | The Corresponding Source need not include anything that users 148 | can regenerate automatically from other parts of the Corresponding 149 | Source. 150 | 151 | The Corresponding Source for a work in source code form is that 152 | same work. 153 | 154 | 2. Basic Permissions. 155 | 156 | All rights granted under this License are granted for the term of 157 | copyright on the Program, and are irrevocable provided the stated 158 | conditions are met. This License explicitly affirms your unlimited 159 | permission to run the unmodified Program. The output from running a 160 | covered work is covered by this License only if the output, given its 161 | content, constitutes a covered work. This License acknowledges your 162 | rights of fair use or other equivalent, as provided by copyright law. 163 | 164 | You may make, run and propagate covered works that you do not 165 | convey, without conditions so long as your license otherwise remains 166 | in force. You may convey covered works to others for the sole purpose 167 | of having them make modifications exclusively for you, or provide you 168 | with facilities for running those works, provided that you comply with 169 | the terms of this License in conveying all material for which you do 170 | not control copyright. Those thus making or running the covered works 171 | for you must do so exclusively on your behalf, under your direction 172 | and control, on terms that prohibit them from making any copies of 173 | your copyrighted material outside their relationship with you. 174 | 175 | Conveying under any other circumstances is permitted solely under 176 | the conditions stated below. Sublicensing is not allowed; section 10 177 | makes it unnecessary. 178 | 179 | 3. Protecting Users' Legal Rights From Anti-Circumvention Law. 180 | 181 | No covered work shall be deemed part of an effective technological 182 | measure under any applicable law fulfilling obligations under article 183 | 11 of the WIPO copyright treaty adopted on 20 December 1996, or 184 | similar laws prohibiting or restricting circumvention of such 185 | measures. 186 | 187 | When you convey a covered work, you waive any legal power to forbid 188 | circumvention of technological measures to the extent such circumvention 189 | is effected by exercising rights under this License with respect to 190 | the covered work, and you disclaim any intention to limit operation or 191 | modification of the work as a means of enforcing, against the work's 192 | users, your or third parties' legal rights to forbid circumvention of 193 | technological measures. 194 | 195 | 4. Conveying Verbatim Copies. 196 | 197 | You may convey verbatim copies of the Program's source code as you 198 | receive it, in any medium, provided that you conspicuously and 199 | appropriately publish on each copy an appropriate copyright notice; 200 | keep intact all notices stating that this License and any 201 | non-permissive terms added in accord with section 7 apply to the code; 202 | keep intact all notices of the absence of any warranty; and give all 203 | recipients a copy of this License along with the Program. 204 | 205 | You may charge any price or no price for each copy that you convey, 206 | and you may offer support or warranty protection for a fee. 207 | 208 | 5. Conveying Modified Source Versions. 209 | 210 | You may convey a work based on the Program, or the modifications to 211 | produce it from the Program, in the form of source code under the 212 | terms of section 4, provided that you also meet all of these conditions: 213 | 214 | a) The work must carry prominent notices stating that you modified 215 | it, and giving a relevant date. 216 | 217 | b) The work must carry prominent notices stating that it is 218 | released under this License and any conditions added under section 219 | 7. This requirement modifies the requirement in section 4 to 220 | "keep intact all notices". 221 | 222 | c) You must license the entire work, as a whole, under this 223 | License to anyone who comes into possession of a copy. This 224 | License will therefore apply, along with any applicable section 7 225 | additional terms, to the whole of the work, and all its parts, 226 | regardless of how they are packaged. This License gives no 227 | permission to license the work in any other way, but it does not 228 | invalidate such permission if you have separately received it. 229 | 230 | d) If the work has interactive user interfaces, each must display 231 | Appropriate Legal Notices; however, if the Program has interactive 232 | interfaces that do not display Appropriate Legal Notices, your 233 | work need not make them do so. 234 | 235 | A compilation of a covered work with other separate and independent 236 | works, which are not by their nature extensions of the covered work, 237 | and which are not combined with it such as to form a larger program, 238 | in or on a volume of a storage or distribution medium, is called an 239 | "aggregate" if the compilation and its resulting copyright are not 240 | used to limit the access or legal rights of the compilation's users 241 | beyond what the individual works permit. Inclusion of a covered work 242 | in an aggregate does not cause this License to apply to the other 243 | parts of the aggregate. 244 | 245 | 6. Conveying Non-Source Forms. 246 | 247 | You may convey a covered work in object code form under the terms 248 | of sections 4 and 5, provided that you also convey the 249 | machine-readable Corresponding Source under the terms of this License, 250 | in one of these ways: 251 | 252 | a) Convey the object code in, or embodied in, a physical product 253 | (including a physical distribution medium), accompanied by the 254 | Corresponding Source fixed on a durable physical medium 255 | customarily used for software interchange. 256 | 257 | b) Convey the object code in, or embodied in, a physical product 258 | (including a physical distribution medium), accompanied by a 259 | written offer, valid for at least three years and valid for as 260 | long as you offer spare parts or customer support for that product 261 | model, to give anyone who possesses the object code either (1) a 262 | copy of the Corresponding Source for all the software in the 263 | product that is covered by this License, on a durable physical 264 | medium customarily used for software interchange, for a price no 265 | more than your reasonable cost of physically performing this 266 | conveying of source, or (2) access to copy the 267 | Corresponding Source from a network server at no charge. 268 | 269 | c) Convey individual copies of the object code with a copy of the 270 | written offer to provide the Corresponding Source. This 271 | alternative is allowed only occasionally and noncommercially, and 272 | only if you received the object code with such an offer, in accord 273 | with subsection 6b. 274 | 275 | d) Convey the object code by offering access from a designated 276 | place (gratis or for a charge), and offer equivalent access to the 277 | Corresponding Source in the same way through the same place at no 278 | further charge. You need not require recipients to copy the 279 | Corresponding Source along with the object code. If the place to 280 | copy the object code is a network server, the Corresponding Source 281 | may be on a different server (operated by you or a third party) 282 | that supports equivalent copying facilities, provided you maintain 283 | clear directions next to the object code saying where to find the 284 | Corresponding Source. Regardless of what server hosts the 285 | Corresponding Source, you remain obligated to ensure that it is 286 | available for as long as needed to satisfy these requirements. 287 | 288 | e) Convey the object code using peer-to-peer transmission, provided 289 | you inform other peers where the object code and Corresponding 290 | Source of the work are being offered to the general public at no 291 | charge under subsection 6d. 292 | 293 | A separable portion of the object code, whose source code is excluded 294 | from the Corresponding Source as a System Library, need not be 295 | included in conveying the object code work. 296 | 297 | A "User Product" is either (1) a "consumer product", which means any 298 | tangible personal property which is normally used for personal, family, 299 | or household purposes, or (2) anything designed or sold for incorporation 300 | into a dwelling. In determining whether a product is a consumer product, 301 | doubtful cases shall be resolved in favor of coverage. For a particular 302 | product received by a particular user, "normally used" refers to a 303 | typical or common use of that class of product, regardless of the status 304 | of the particular user or of the way in which the particular user 305 | actually uses, or expects or is expected to use, the product. A product 306 | is a consumer product regardless of whether the product has substantial 307 | commercial, industrial or non-consumer uses, unless such uses represent 308 | the only significant mode of use of the product. 309 | 310 | "Installation Information" for a User Product means any methods, 311 | procedures, authorization keys, or other information required to install 312 | and execute modified versions of a covered work in that User Product from 313 | a modified version of its Corresponding Source. The information must 314 | suffice to ensure that the continued functioning of the modified object 315 | code is in no case prevented or interfered with solely because 316 | modification has been made. 317 | 318 | If you convey an object code work under this section in, or with, or 319 | specifically for use in, a User Product, and the conveying occurs as 320 | part of a transaction in which the right of possession and use of the 321 | User Product is transferred to the recipient in perpetuity or for a 322 | fixed term (regardless of how the transaction is characterized), the 323 | Corresponding Source conveyed under this section must be accompanied 324 | by the Installation Information. But this requirement does not apply 325 | if neither you nor any third party retains the ability to install 326 | modified object code on the User Product (for example, the work has 327 | been installed in ROM). 328 | 329 | The requirement to provide Installation Information does not include a 330 | requirement to continue to provide support service, warranty, or updates 331 | for a work that has been modified or installed by the recipient, or for 332 | the User Product in which it has been modified or installed. Access to a 333 | network may be denied when the modification itself materially and 334 | adversely affects the operation of the network or violates the rules and 335 | protocols for communication across the network. 336 | 337 | Corresponding Source conveyed, and Installation Information provided, 338 | in accord with this section must be in a format that is publicly 339 | documented (and with an implementation available to the public in 340 | source code form), and must require no special password or key for 341 | unpacking, reading or copying. 342 | 343 | 7. Additional Terms. 344 | 345 | "Additional permissions" are terms that supplement the terms of this 346 | License by making exceptions from one or more of its conditions. 347 | Additional permissions that are applicable to the entire Program shall 348 | be treated as though they were included in this License, to the extent 349 | that they are valid under applicable law. If additional permissions 350 | apply only to part of the Program, that part may be used separately 351 | under those permissions, but the entire Program remains governed by 352 | this License without regard to the additional permissions. 353 | 354 | When you convey a copy of a covered work, you may at your option 355 | remove any additional permissions from that copy, or from any part of 356 | it. (Additional permissions may be written to require their own 357 | removal in certain cases when you modify the work.) You may place 358 | additional permissions on material, added by you to a covered work, 359 | for which you have or can give appropriate copyright permission. 360 | 361 | Notwithstanding any other provision of this License, for material you 362 | add to a covered work, you may (if authorized by the copyright holders of 363 | that material) supplement the terms of this License with terms: 364 | 365 | a) Disclaiming warranty or limiting liability differently from the 366 | terms of sections 15 and 16 of this License; or 367 | 368 | b) Requiring preservation of specified reasonable legal notices or 369 | author attributions in that material or in the Appropriate Legal 370 | Notices displayed by works containing it; or 371 | 372 | c) Prohibiting misrepresentation of the origin of that material, or 373 | requiring that modified versions of such material be marked in 374 | reasonable ways as different from the original version; or 375 | 376 | d) Limiting the use for publicity purposes of names of licensors or 377 | authors of the material; or 378 | 379 | e) Declining to grant rights under trademark law for use of some 380 | trade names, trademarks, or service marks; or 381 | 382 | f) Requiring indemnification of licensors and authors of that 383 | material by anyone who conveys the material (or modified versions of 384 | it) with contractual assumptions of liability to the recipient, for 385 | any liability that these contractual assumptions directly impose on 386 | those licensors and authors. 387 | 388 | All other non-permissive additional terms are considered "further 389 | restrictions" within the meaning of section 10. If the Program as you 390 | received it, or any part of it, contains a notice stating that it is 391 | governed by this License along with a term that is a further 392 | restriction, you may remove that term. If a license document contains 393 | a further restriction but permits relicensing or conveying under this 394 | License, you may add to a covered work material governed by the terms 395 | of that license document, provided that the further restriction does 396 | not survive such relicensing or conveying. 397 | 398 | If you add terms to a covered work in accord with this section, you 399 | must place, in the relevant source files, a statement of the 400 | additional terms that apply to those files, or a notice indicating 401 | where to find the applicable terms. 402 | 403 | Additional terms, permissive or non-permissive, may be stated in the 404 | form of a separately written license, or stated as exceptions; 405 | the above requirements apply either way. 406 | 407 | 8. Termination. 408 | 409 | You may not propagate or modify a covered work except as expressly 410 | provided under this License. Any attempt otherwise to propagate or 411 | modify it is void, and will automatically terminate your rights under 412 | this License (including any patent licenses granted under the third 413 | paragraph of section 11). 414 | 415 | However, if you cease all violation of this License, then your 416 | license from a particular copyright holder is reinstated (a) 417 | provisionally, unless and until the copyright holder explicitly and 418 | finally terminates your license, and (b) permanently, if the copyright 419 | holder fails to notify you of the violation by some reasonable means 420 | prior to 60 days after the cessation. 421 | 422 | Moreover, your license from a particular copyright holder is 423 | reinstated permanently if the copyright holder notifies you of the 424 | violation by some reasonable means, this is the first time you have 425 | received notice of violation of this License (for any work) from that 426 | copyright holder, and you cure the violation prior to 30 days after 427 | your receipt of the notice. 428 | 429 | Termination of your rights under this section does not terminate the 430 | licenses of parties who have received copies or rights from you under 431 | this License. If your rights have been terminated and not permanently 432 | reinstated, you do not qualify to receive new licenses for the same 433 | material under section 10. 434 | 435 | 9. Acceptance Not Required for Having Copies. 436 | 437 | You are not required to accept this License in order to receive or 438 | run a copy of the Program. Ancillary propagation of a covered work 439 | occurring solely as a consequence of using peer-to-peer transmission 440 | to receive a copy likewise does not require acceptance. However, 441 | nothing other than this License grants you permission to propagate or 442 | modify any covered work. These actions infringe copyright if you do 443 | not accept this License. Therefore, by modifying or propagating a 444 | covered work, you indicate your acceptance of this License to do so. 445 | 446 | 10. Automatic Licensing of Downstream Recipients. 447 | 448 | Each time you convey a covered work, the recipient automatically 449 | receives a license from the original licensors, to run, modify and 450 | propagate that work, subject to this License. You are not responsible 451 | for enforcing compliance by third parties with this License. 452 | 453 | An "entity transaction" is a transaction transferring control of an 454 | organization, or substantially all assets of one, or subdividing an 455 | organization, or merging organizations. If propagation of a covered 456 | work results from an entity transaction, each party to that 457 | transaction who receives a copy of the work also receives whatever 458 | licenses to the work the party's predecessor in interest had or could 459 | give under the previous paragraph, plus a right to possession of the 460 | Corresponding Source of the work from the predecessor in interest, if 461 | the predecessor has it or can get it with reasonable efforts. 462 | 463 | You may not impose any further restrictions on the exercise of the 464 | rights granted or affirmed under this License. For example, you may 465 | not impose a license fee, royalty, or other charge for exercise of 466 | rights granted under this License, and you may not initiate litigation 467 | (including a cross-claim or counterclaim in a lawsuit) alleging that 468 | any patent claim is infringed by making, using, selling, offering for 469 | sale, or importing the Program or any portion of it. 470 | 471 | 11. Patents. 472 | 473 | A "contributor" is a copyright holder who authorizes use under this 474 | License of the Program or a work on which the Program is based. The 475 | work thus licensed is called the contributor's "contributor version". 476 | 477 | A contributor's "essential patent claims" are all patent claims 478 | owned or controlled by the contributor, whether already acquired or 479 | hereafter acquired, that would be infringed by some manner, permitted 480 | by this License, of making, using, or selling its contributor version, 481 | but do not include claims that would be infringed only as a 482 | consequence of further modification of the contributor version. For 483 | purposes of this definition, "control" includes the right to grant 484 | patent sublicenses in a manner consistent with the requirements of 485 | this License. 486 | 487 | Each contributor grants you a non-exclusive, worldwide, royalty-free 488 | patent license under the contributor's essential patent claims, to 489 | make, use, sell, offer for sale, import and otherwise run, modify and 490 | propagate the contents of its contributor version. 491 | 492 | In the following three paragraphs, a "patent license" is any express 493 | agreement or commitment, however denominated, not to enforce a patent 494 | (such as an express permission to practice a patent or covenant not to 495 | sue for patent infringement). To "grant" such a patent license to a 496 | party means to make such an agreement or commitment not to enforce a 497 | patent against the party. 498 | 499 | If you convey a covered work, knowingly relying on a patent license, 500 | and the Corresponding Source of the work is not available for anyone 501 | to copy, free of charge and under the terms of this License, through a 502 | publicly available network server or other readily accessible means, 503 | then you must either (1) cause the Corresponding Source to be so 504 | available, or (2) arrange to deprive yourself of the benefit of the 505 | patent license for this particular work, or (3) arrange, in a manner 506 | consistent with the requirements of this License, to extend the patent 507 | license to downstream recipients. "Knowingly relying" means you have 508 | actual knowledge that, but for the patent license, your conveying the 509 | covered work in a country, or your recipient's use of the covered work 510 | in a country, would infringe one or more identifiable patents in that 511 | country that you have reason to believe are valid. 512 | 513 | If, pursuant to or in connection with a single transaction or 514 | arrangement, you convey, or propagate by procuring conveyance of, a 515 | covered work, and grant a patent license to some of the parties 516 | receiving the covered work authorizing them to use, propagate, modify 517 | or convey a specific copy of the covered work, then the patent license 518 | you grant is automatically extended to all recipients of the covered 519 | work and works based on it. 520 | 521 | A patent license is "discriminatory" if it does not include within 522 | the scope of its coverage, prohibits the exercise of, or is 523 | conditioned on the non-exercise of one or more of the rights that are 524 | specifically granted under this License. You may not convey a covered 525 | work if you are a party to an arrangement with a third party that is 526 | in the business of distributing software, under which you make payment 527 | to the third party based on the extent of your activity of conveying 528 | the work, and under which the third party grants, to any of the 529 | parties who would receive the covered work from you, a discriminatory 530 | patent license (a) in connection with copies of the covered work 531 | conveyed by you (or copies made from those copies), or (b) primarily 532 | for and in connection with specific products or compilations that 533 | contain the covered work, unless you entered into that arrangement, 534 | or that patent license was granted, prior to 28 March 2007. 535 | 536 | Nothing in this License shall be construed as excluding or limiting 537 | any implied license or other defenses to infringement that may 538 | otherwise be available to you under applicable patent law. 539 | 540 | 12. No Surrender of Others' Freedom. 541 | 542 | If conditions are imposed on you (whether by court order, agreement or 543 | otherwise) that contradict the conditions of this License, they do not 544 | excuse you from the conditions of this License. If you cannot convey a 545 | covered work so as to satisfy simultaneously your obligations under this 546 | License and any other pertinent obligations, then as a consequence you may 547 | not convey it at all. For example, if you agree to terms that obligate you 548 | to collect a royalty for further conveying from those to whom you convey 549 | the Program, the only way you could satisfy both those terms and this 550 | License would be to refrain entirely from conveying the Program. 551 | 552 | 13. Use with the GNU Affero General Public License. 553 | 554 | Notwithstanding any other provision of this License, you have 555 | permission to link or combine any covered work with a work licensed 556 | under version 3 of the GNU Affero General Public License into a single 557 | combined work, and to convey the resulting work. The terms of this 558 | License will continue to apply to the part which is the covered work, 559 | but the special requirements of the GNU Affero General Public License, 560 | section 13, concerning interaction through a network will apply to the 561 | combination as such. 562 | 563 | 14. Revised Versions of this License. 564 | 565 | The Free Software Foundation may publish revised and/or new versions of 566 | the GNU General Public License from time to time. Such new versions will 567 | be similar in spirit to the present version, but may differ in detail to 568 | address new problems or concerns. 569 | 570 | Each version is given a distinguishing version number. If the 571 | Program specifies that a certain numbered version of the GNU General 572 | Public License "or any later version" applies to it, you have the 573 | option of following the terms and conditions either of that numbered 574 | version or of any later version published by the Free Software 575 | Foundation. If the Program does not specify a version number of the 576 | GNU General Public License, you may choose any version ever published 577 | by the Free Software Foundation. 578 | 579 | If the Program specifies that a proxy can decide which future 580 | versions of the GNU General Public License can be used, that proxy's 581 | public statement of acceptance of a version permanently authorizes you 582 | to choose that version for the Program. 583 | 584 | Later license versions may give you additional or different 585 | permissions. However, no additional obligations are imposed on any 586 | author or copyright holder as a result of your choosing to follow a 587 | later version. 588 | 589 | 15. Disclaimer of Warranty. 590 | 591 | THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY 592 | APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT 593 | HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY 594 | OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, 595 | THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR 596 | PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM 597 | IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF 598 | ALL NECESSARY SERVICING, REPAIR OR CORRECTION. 599 | 600 | 16. Limitation of Liability. 601 | 602 | IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING 603 | WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS 604 | THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY 605 | GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE 606 | USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF 607 | DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD 608 | PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), 609 | EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF 610 | SUCH DAMAGES. 611 | 612 | 17. Interpretation of Sections 15 and 16. 613 | 614 | If the disclaimer of warranty and limitation of liability provided 615 | above cannot be given local legal effect according to their terms, 616 | reviewing courts shall apply local law that most closely approximates 617 | an absolute waiver of all civil liability in connection with the 618 | Program, unless a warranty or assumption of liability accompanies a 619 | copy of the Program in return for a fee. 620 | 621 | END OF TERMS AND CONDITIONS 622 | 623 | How to Apply These Terms to Your New Programs 624 | 625 | If you develop a new program, and you want it to be of the greatest 626 | possible use to the public, the best way to achieve this is to make it 627 | free software which everyone can redistribute and change under these terms. 628 | 629 | To do so, attach the following notices to the program. It is safest 630 | to attach them to the start of each source file to most effectively 631 | state the exclusion of warranty; and each file should have at least 632 | the "copyright" line and a pointer to where the full notice is found. 633 | 634 | 635 | Copyright (C) 636 | 637 | This program is free software: you can redistribute it and/or modify 638 | it under the terms of the GNU General Public License as published by 639 | the Free Software Foundation, either version 3 of the License, or 640 | (at your option) any later version. 641 | 642 | This program is distributed in the hope that it will be useful, 643 | but WITHOUT ANY WARRANTY; without even the implied warranty of 644 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 645 | GNU General Public License for more details. 646 | 647 | You should have received a copy of the GNU General Public License 648 | along with this program. If not, see . 649 | 650 | Also add information on how to contact you by electronic and paper mail. 651 | 652 | If the program does terminal interaction, make it output a short 653 | notice like this when it starts in an interactive mode: 654 | 655 | Copyright (C) 656 | This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'. 657 | This is free software, and you are welcome to redistribute it 658 | under certain conditions; type `show c' for details. 659 | 660 | The hypothetical commands `show w' and `show c' should show the appropriate 661 | parts of the General Public License. Of course, your program's commands 662 | might be different; for a GUI interface, you would use an "about box". 663 | 664 | You should also get your employer (if you work as a programmer) or school, 665 | if any, to sign a "copyright disclaimer" for the program, if necessary. 666 | For more information on this, and how to apply and follow the GNU GPL, see 667 | . 668 | 669 | The GNU General Public License does not permit incorporating your program 670 | into proprietary programs. If your program is a subroutine library, you 671 | may consider it more useful to permit linking proprietary applications with 672 | the library. If this is what you want to do, use the GNU Lesser General 673 | Public License instead of this License. But first, please read 674 | . 675 | -------------------------------------------------------------------------------- /ModellingFrameworks_v7.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cwieder/PathIntegrate/f3071a7fb93cc866cec98bee9874782918d9cc53/ModellingFrameworks_v7.png -------------------------------------------------------------------------------- /ModellingFrameworks_white.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cwieder/PathIntegrate/f3071a7fb93cc866cec98bee9874782918d9cc53/ModellingFrameworks_white.png -------------------------------------------------------------------------------- /PathIntegrateGraphic.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cwieder/PathIntegrate/f3071a7fb93cc866cec98bee9874782918d9cc53/PathIntegrateGraphic.png -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # PathIntegrate 2 | PathIntegrate Python package for pathway-based multi-omics data integration 3 | 4 | ![PyPI - Version](https://img.shields.io/pypi/v/PathIntegrate) 5 | [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.14060723.svg)](https://doi.org/10.5281/zenodo.14060723) 6 | [![License: GPL v3](https://img.shields.io/badge/License-GPLv3-blue.svg)](https://www.gnu.org/licenses/gpl-3.0) 7 | ![PyPI - Downloads](https://img.shields.io/pypi/dm/pathintegrate) 8 | 9 | 10 | ![PathIntegrate graphical abstract](ModellingFrameworks_white.png "PathIntegrate graphical abstract") 11 | 12 | #### Abstract 13 | >As terabytes of multi-omics data are being generated, there is an ever-increasing need for methods facilitating the integration and interpretation of such data. Current multi-omics integration methods typically output lists, clusters, or subnetworks of molecules related to an outcome. Even with expert domain knowledge, discerning the biological processes involved is a time-consuming activity. Here we propose PathIntegrate, a method for integrating multi-omics datasets based on pathways, designed to exploit knowledge of biological systems and thus provide interpretable models for such studies. PathIntegrate employs single-sample pathway analysis to transform multi-omics datasets from the molecular to the pathway-level, and applies a predictive single-view or multi-view model to integrate the data. Model outputs include multi-omics pathways ranked by their contribution to the outcome prediction, the contribution of each omics layer, and the importance of each molecule in a pathway. 14 | 15 | ## Features 16 | - Pathway-based multi-omics data integration using PathIntegrate Multi-View and Single-View models 17 | - Multi-View model: Integrates multiple omics datasets using a shared pathway-based latent space 18 | - Single-View model: Integrates multi-omics data into one set of multi-omics pathway scores and applies an SKlearn-compatible predictive model 19 | - Pathway importance 20 | - Sample prediction 21 | - NEW unsupervised SingleView models (dimensionality reduction and clustering in the pathway space) 22 | - SKlearn-like API for easy integration into existing pipelines 23 | - Support for multiple pathway databases, including KEGG, Reactome, PathBank, and custom GMT files 24 | - Support for multiple pathway scoring methods available via the [sspa](https://github.com/cwieder/py-ssPA) package 25 | - Cytoscape Network Viewer app for visualizing pathway-based multi-omics data integration results 26 | 27 | ![PathIntegrate Cytoscape app](App_network_view.JPG "Network viewer") 28 | 29 | ## System requirements 30 | ### Hardware 31 | At least 8BG RAM recommended. PathIntegrate models can run on a Google Colab notebook server (see walkthrough tutorial below with example data). 32 | 33 | ### Software 34 | PathIntegrate has been tested on MacOs, Windows 10 and Linux. Python 3.10 or higher is required. Python dependencies are listed in the requirements.txt file. 35 | 36 | ## Installation 37 | ```bash 38 | pip install PathIntegrate 39 | ``` 40 | 41 | ## Tutorials and documentation 42 | Please see our Quickstart guide on [Google Colab](https://colab.research.google.com/drive/1MmGJp8I4JaIgFGNihYjaa4KJqYTGzdtv?usp=sharing) 43 | 44 | Full documentation and function reference for PathIntegrate can be found via our [ReadTheDocs page](https://cwieder.github.io/PathIntegrate/) 45 | 46 | ## Citing PathIntegrate 47 | If you use PathIntegrate in your research, please consider citing our paper: 48 | ```bibtex 49 | @article{Wieder2024, 50 | author = {Cecilia Wieder and Juliette Cooke and Clement Frainay and Nathalie Poupin and Russell Bowler and Fabien Jourdan and Katerina J. Kechris and Rachel P.J. Lai and Timothy Ebbels}, 51 | doi = {10.1371/JOURNAL.PCBI.1011814}, 52 | issue = {3}, 53 | journal = {PLOS Computational Biology}, 54 | month = {3}, 55 | pages = {e1011814}, 56 | pmid = {38527092}, 57 | publisher = {Public Library of Science}, 58 | title = {PathIntegrate: Multivariate modelling approaches for pathway-based multi-omics data integration}, 59 | volume = {20}, 60 | url = {https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1011814}, 61 | year = {2024}, 62 | } 63 | ``` 64 | 65 | ## PathIntegrate applications 66 | Check out the following papers to see how PathIntegrate has been used in research: 67 | - [Time-resolved, integrated multi-omic analysis reveals central role of amino acid pathways for defense responses in Arabidopsis thaliana](https://www.biorxiv.org/content/10.1101/2024.08.27.609849v1.full) 68 | 69 | ## License 70 | GNU GPL v3 71 | 72 | ## Contributors 73 | - Jude Popham @[judepops](https://github.com/judepops) -------------------------------------------------------------------------------- /docs/docs/gendocs_docs/reference/pathintegrate.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cwieder/PathIntegrate/f3071a7fb93cc866cec98bee9874782918d9cc53/docs/docs/gendocs_docs/reference/pathintegrate.md -------------------------------------------------------------------------------- /docs/docs/images/ModellingFrameworks_white.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cwieder/PathIntegrate/f3071a7fb93cc866cec98bee9874782918d9cc53/docs/docs/images/ModellingFrameworks_white.png -------------------------------------------------------------------------------- /docs/docs/index.md: -------------------------------------------------------------------------------- 1 | # PathIntegrate 2 | PathIntegrate Python package for pathway-based multi-omics data integration 3 | 4 | ![PathIntegrate graphical abstract](images/ModellingFrameworks_white.png "PathIntegrate graphical abstract") 5 | 6 | ## Features 7 | - Pathway-based multi-omics data integration using PathIntegrate Multi-View and Single-View models 8 | - Multi-View model: Integrates multiple omics datasets using a shared pathway-based latent space 9 | - Single-View model: Integrates multi-omics data into one set of multi-omics pathway scores and applies an SKlearn-compatible predictive model 10 | - Pathway importance 11 | - Sample prediction 12 | - SKlearn-like API for easy integration into existing pipelines 13 | - Support for multiple pathway databases, including KEGG and Reactome 14 | - Support for multiple pathway scoring methods available via the [sspa](https://github.com/cwieder/py-ssPA) package 15 | - Cytoscape Network Viewer app for visualizing pathway-based multi-omics data integration results 16 | 17 | ![PathIntegrate Cytoscape app](App_network_view.jpg "Network viewer") 18 | 19 | ## Installation 20 | ```bash 21 | pip install PathIntegrate 22 | ``` 23 | 24 | ## Tutorials and documentation 25 | Please see our Quickstart guide on [Google Colab](https://colab.research.google.com/drive/1MmGJp8I4JaIgFGNihYjaa4KJqYTGzdtv?usp=sharing) 26 | 27 | 28 | ## Citing PathIntegrate 29 | If you use PathIntegrate in your research, please cite our paper: 30 | ```bibtex 31 | PathIntegrate: Multivariate modelling approaches for pathway-based multi-omics data integration 32 | 33 | Cecilia Wieder, Juliette Cooke, Clement Frainay, Nathalie Poupin, Jacob G. Bundy, Russell Bowler, Fabien Jourdan, Katerina J. Kechris, Rachel PJ Lai, Timothy Ebbels 34 | 35 | Manuscript in preparation 36 | ``` -------------------------------------------------------------------------------- /docs/docs/input.md: -------------------------------------------------------------------------------- 1 | # Input data for PathIntegrate 2 | 3 | ## Omics data 4 | Each multi-omics dataset should be in the form of a pandas DataFrame with samples as rows and molecules as columns. The index of the DataFrame should be the sample IDs, and the columns should be the molecule IDs. 5 | 6 | The molecule IDs should match those of the desired pathway database (i.e. ChEBI IDs, UniProt IDs, and ENSEMBL genes for Reactome; and KEGG IDs for KEGG). The values in the DataFrame should be the molecule abundances for each sample. 7 | 8 | !!! note 9 | 10 | The omics data should be pre-processed before inputting into PathIntegrate. PathIntgrate will automatically standardise the data, but it is recommended to log-transform the data before inputting into PathIntegrate. 11 | 12 | 13 | | sample_id | 1372 | 16610 | 72665 | 30915 | 37373 | Group | 14 | | ----------- | -------- | -------- | -------- | -------- | -------- | --------- | 15 | | INCOV092-BL | 1.541009 | 1.228611 | 1.224076 | 1.962028 | 0.652984 | COVID | 16 | | INCOV107-BL | 0.910486 | 2.169111 | 2.819585 | 1.234384 | 1.453066 | COVID | 17 | | INCOV020-BL | 0.831297 | 0.23298 | 2.126393 | 0.861793 | 2.877589 | COVID | 18 | | INCOV035-BL | 1.862011 | 0.792962 | 1.434183 | 1.223473 | 0.706152 | COVID | 19 | | INCOV122-BL | 1.416927 | 2.493762 | 1.77004 | 0.888144 | 0.693444 | Non-covid | 20 | | INCOV084-BL | 1.622171 | 1.021112 | 2.323956 | 0.573877 | 0.764003 | Non-covid | 21 | | INCOV086-BL | 1.610941 | 1.205343 | 0.83498 | 2.600065 | 1.700068 | Non-covid | 22 | | INCOV133-BL | 0.83727 | 2.144127 | 1.24222 | 1.035411 | 2.037335 | Non-covid | 23 | 24 | ## Pathways 25 | Pathways should be in the form of a pandas DataFrame with pathways as rows and molecules as columns. The index of the DataFrame should be the pathway IDs, and the columns should be the molecule IDs. The first column should be the pathway names or descriptions. 26 | 27 | Pathways can be from any pathway database, but the molecule IDs should match those of the omics data. 28 | 29 | Each pathway can either contain molecules from a single omics, or a combination of omics. 30 | 31 | !!! note 32 | 33 | Pathways can be downloaded using the [sspa package](github.com/cwieder/py-ssPA) 34 | 35 | | | Pathway_name | 0 | 1 | 2 | 3 | 4 | 36 | | - | ------------ | ------ | ------ | ------ | ------ | ------ | 37 | | 1 | Pathway_52 | Q13554 | P61289 | P05114 | P62081 | P54760 | 38 | | 2 | Pathway_53 | Q9Y243 | P17252 | | | | 39 | | 3 | Pathway_54 | 16708 | P06732 | P61289 | O00220 | O75914 | 40 | | 4 | Pathway_55 | O15264 | P25786 | | | | 41 | | 5 | Pathway_56 | P07858 | P62979 | Q9Y625 | P14778 | P12314 | 42 | | 6 | Pathway_57 | P18510 | P15260 | Q13557 | P32942 | P04818 | 43 | | 7 | Pathway_58 | P00738 | P37023 | P01588 | P63098 | P05362 | 44 | | 8 | Pathway_59 | P52798 | P15498 | | | | -------------------------------------------------------------------------------- /docs/mkdocs.yml: -------------------------------------------------------------------------------- 1 | site_name: PathIntegrate Docs 2 | 3 | theme: 4 | name: "material" 5 | palette: 6 | primary: teal 7 | accent: teal 8 | 9 | docs_dir: 'docs' 10 | site_dir: 'site' 11 | 12 | markdown_extensions: 13 | - pymdownx.arithmatex: 14 | generic: true 15 | - admonition 16 | - pymdownx.details 17 | - pymdownx.superfences: 18 | custom_fences: 19 | - name: mermaid 20 | class: mermaid 21 | format: !!python/name:pymdownx.superfences.fence_code_format 22 | 23 | 24 | extra_javascript: 25 | - javascripts/mathjax.js 26 | - https://polyfill.io/v3/polyfill.min.js?features=es6 27 | - https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js 28 | 29 | 30 | plugins: 31 | - search 32 | - mkdocstrings: 33 | default_handler: python 34 | handlers: 35 | python: 36 | rendering: 37 | show_source: false 38 | options: 39 | docstring_style: google 40 | docstring_options: 41 | ignore_init_summary: no 42 | merge_init_into_class: no 43 | show_submodules: yes 44 | 45 | nav: 46 | - Home: index.md 47 | - Input data: input.md 48 | # - Tutorials: 49 | # - tutorials.md 50 | # - ssPA and SKLearn: 51 | # - gendocs_docs/reference/sklearn_sspa.md 52 | - Reference: 53 | - gendocs_docs/reference/pathintegrate.md 54 | # - gendocs_docs/reference/download_pathways.md 55 | # - gendocs_docs/reference/load_pathways.md 56 | # - gendocs_docs/reference/utils.md 57 | # - Pathway analysis: 58 | # - gendocs_docs/reference/ORA.md 59 | # - gendocs_docs/reference/GSEA.md 60 | # - Single sample methods: 61 | # - gendocs_docs/reference/SVD.md 62 | # - gendocs_docs/reference/kPCA.md 63 | # - gendocs_docs/reference/ssClustPA.md 64 | # - gendocs_docs/reference/ssGSEA.md 65 | # - gendocs_docs/reference/zscore.md 66 | 67 | -------------------------------------------------------------------------------- /mkgendocs.yml: -------------------------------------------------------------------------------- 1 | sources_dir: docs/docs/gendocs_docs 2 | templates_dir: docs/docs/gendocs_templates 3 | repo: https://github.com/cwieder/pathintegrate 4 | version: master 5 | 6 | pages: 7 | 8 | - page: "reference/pathintegrate.md" 9 | source: "src/pathintegrate/pathintegrate.py" 10 | # functions: 11 | # - MultiView 12 | # - SingleView 13 | classes: 14 | - PathIntegrate 15 | 16 | # - page: "reference/identifier_conversion.md" 17 | # source: "src/sspa/identifier_conversion.py" 18 | # functions: 19 | # - identifier_conversion 20 | # - map_identifiers 21 | 22 | # - page: "reference/load_pathways.md" 23 | # source: "src/sspa/process_pathways.py" 24 | # functions: 25 | # - process_reactome 26 | # - process_kegg 27 | # - process_gmt 28 | 29 | # - page: "reference/utils.md" 30 | # source: "src/sspa/utils.py" 31 | # functions: 32 | # - load_example_data 33 | # - t_tests 34 | # - pathwaydf_to_dict 35 | 36 | # - page: "reference/ORA.md" 37 | # source: "src/sspa/sspa_ora.py" 38 | # classes: 39 | # - sspa_ora 40 | 41 | # - page: "reference/GSEA.md" 42 | # source: "src/sspa/sspa_gsea.py" 43 | # functions: 44 | # - sspa_gsea 45 | 46 | # - page: "reference/SVD.md" 47 | # source: "src/sspa/sspa_svd.py" 48 | # classes: 49 | # - sspa_SVD 50 | 51 | # - page: "reference/kPCA.md" 52 | # source: "src/sspa/sspa_kpca.py" 53 | # classes: 54 | # - sspa_KPCA 55 | 56 | # - page: "reference/ssClustPA.md" 57 | # source: "src/sspa/sspa_cluster.py" 58 | # classes: 59 | # - sspa_ssClustPA 60 | 61 | # # - page: "reference/GSVA.md" 62 | # # source: "src/sspa/sspa_gsva.py" 63 | # # functions: 64 | # # - sspa_gsva 65 | 66 | # - page: "reference/ssGSEA.md" 67 | # source: "src/sspa/sspa_ssGSEA.py" 68 | # classes: 69 | # - sspa_ssGSEA 70 | 71 | # - page: "reference/zscore.md" 72 | # source: "src/sspa/sspa_zscore.py" 73 | # classes: 74 | # - sspa_zscore -------------------------------------------------------------------------------- /pages/About.py: -------------------------------------------------------------------------------- 1 | # import packages 2 | import pandas as pd 3 | import numpy as np 4 | import dash 5 | from dash import Dash, html, dcc, Input, Output, State, ctx 6 | import plotly.express as px 7 | import dash_cytoscape as cyto 8 | import matplotlib.pyplot as plt 9 | import matplotlib.colors as mcolors 10 | import seaborn as sns 11 | import networkx as nx 12 | import dash_bootstrap_components as dbc 13 | import matplotlib.cm as cm 14 | import matplotlib as matplotlib 15 | import svgwrite 16 | from datauri import DataURI 17 | from dash_bootstrap_components._components.Container import Container 18 | from pathlib import Path 19 | dash.register_page(__name__, path='/about') 20 | 21 | 22 | layout = html.Div(children=[ 23 | html.H1(children='About'), 24 | 25 | html.Div(children=''' 26 | This is our Home page content. 27 | '''), 28 | 29 | ]) -------------------------------------------------------------------------------- /pages/DetailsView.py: -------------------------------------------------------------------------------- 1 | # import packages 2 | import pandas as pd 3 | import numpy as np 4 | import dash 5 | from dash import Dash, html, dcc, Input, Output, State, ctx 6 | import plotly.express as px 7 | import dash_cytoscape as cyto 8 | import matplotlib.pyplot as plt 9 | import matplotlib.colors as mcolors 10 | import seaborn as sns 11 | import networkx as nx 12 | import dash_bootstrap_components as dbc 13 | import matplotlib.cm as cm 14 | import matplotlib as matplotlib 15 | import svgwrite 16 | from datauri import DataURI 17 | from dash_bootstrap_components._components.Container import Container 18 | from pathlib import Path 19 | dash.register_page(__name__, path='/details') 20 | 21 | 22 | layout = html.Div(children=[ 23 | html.H1(children='Pathway details view'), 24 | 25 | html.Div(children=''' 26 | This is our Home page content. 27 | '''), 28 | 29 | ]) -------------------------------------------------------------------------------- /pages/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cwieder/PathIntegrate/f3071a7fb93cc866cec98bee9874782918d9cc53/pages/__init__.py -------------------------------------------------------------------------------- /plot_functs.py: -------------------------------------------------------------------------------- 1 | import matplotlib.pyplot as plt 2 | import seaborn as sns 3 | import pandas as pd 4 | import numpy as np 5 | from cmcrameri import cm 6 | 7 | sns.set_style('ticks') 8 | 9 | def plot_block_importance(model): 10 | plt.figure(figsize=(7, 5)) 11 | sns.heatmap(model.A_corrected_*100, cmap='cmc.devon_r', linewidth=5, square=True, 12 | cbar_kws={'label': '% variance explained in Y'}, 13 | annot=True, 14 | vmin=0, 15 | vmax=100) 16 | plt.yticks([i + 0.5 for i in range(0, len(model.A_corrected_))], model.omics_names) 17 | plt.xticks([i+0.5 for i in range(0, 5)], [str(n+1) + ': ' + str(np.around(i*100, 1))+'%' for n, i in enumerate(model.explained_var_y_)]) 18 | # plt.xticks([i+0.5 for i in range(0, 5)], range(1, 6)) 19 | plt.xlabel('Component % explained variance in Y') 20 | plt.ylabel('Omics view') 21 | plt.tight_layout() 22 | # plt.savefig('../Figures/MBPLS_COPD_Model1_3o_block_importance.png', dpi=300) 23 | plt.show() -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | cmcrameri==1.3 2 | dash==2.14.1 3 | dash_bootstrap_components==1.5.0 4 | dash_cytoscape==0.3.0 5 | datauri==1.0.0 6 | matplotlib==3.8.1 7 | mbpls==1.0.4 8 | networkx==3.2.1 9 | numpy==1.26.1 10 | pandas==2.1.2 11 | plotly==5.18.0 12 | scikit_learn==1.3.2 13 | scipy==1.11.3 14 | seaborn==0.13.0 15 | setuptools==68.0.0 16 | sspa>=1.0.1 17 | statsmodels==0.14.0 18 | svgwrite==1.4.3 19 | -------------------------------------------------------------------------------- /root_cmap.csv: -------------------------------------------------------------------------------- 1 | ,0 2 | R-HSA-1640170,#f77189 3 | R-HSA-5653656,#f77467 4 | R-HSA-9609507,#f17b32 5 | R-HSA-73894,#da8a32 6 | R-HSA-9709957,#c89332 7 | R-HSA-397014,#b99932 8 | R-HSA-162582,#ab9e31 9 | R-HSA-8953897,#9ba331 10 | R-HSA-9748784,#89a731 11 | R-HSA-1266738,#6ead31 12 | R-HSA-112316,#34b331 13 | R-HSA-8953854,#33b16a 14 | R-HSA-392499,#34b082 15 | R-HSA-1643685,#35ae92 16 | R-HSA-400253,#35ad9f 17 | R-HSA-69306,#36aca9 18 | R-HSA-382551,#37abb4 19 | R-HSA-5357801,#38aac0 20 | R-HSA-9612973,#39a8ce 21 | R-HSA-109582,#3ba5e3 22 | R-HSA-168256,#5e9ef4 23 | R-HSA-1430728,#8c94f4 24 | R-HSA-8963743,#ab89f4 25 | R-HSA-1500931,#c77df4 26 | R-HSA-1474244,#e36bf4 27 | R-HSA-4839726,#f55fe7 28 | R-HSA-74160,#f565ce 29 | R-HSA-1852241,#f669b9 30 | R-HSA-1474165,#f66da3 31 | -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- 1 | from setuptools import setup 2 | from pathlib import Path 3 | this_directory = Path(__file__).parent 4 | long_description = (this_directory / "README.md").read_text() 5 | 6 | 7 | setup( 8 | name='PathIntegrate', 9 | version='1.0.2', 10 | packages=['pathintegrate'], 11 | package_dir={'':'src'}, 12 | url='https://github.com/cwieder/PathIntegrate', 13 | license='GNU 3.0', 14 | author='Cecilia Wieder', 15 | author_email='cw2019@ic.ac.uk', 16 | description='PathIntegrate: multivariate modelling approaches for pathway-based muti-omics integration', 17 | long_description=long_description, 18 | long_description_content_type='text/markdown', 19 | package_data={'pathintegrate': ['data/*']}, 20 | classifiers=[ 21 | 'Programming Language :: Python', 22 | 'Programming Language :: Python :: 3', 23 | 'Programming Language :: Python :: 3.10', 24 | ], 25 | install_requires=[ 26 | 'cmcrameri', 27 | 'dash', 28 | 'dash-bootstrap-components', 29 | 'dash-cytoscape', 30 | 'datauri', 31 | 'mbpls', 32 | 'scikit-learn', 33 | 'networkx', 34 | 'setuptools', 35 | 'sspa>=1.0.1', 36 | 'statsmodels', 37 | 'svgwrite' 38 | ], 39 | ) 40 | -------------------------------------------------------------------------------- /src/pathintegrate/__init__.py: -------------------------------------------------------------------------------- 1 | from pkg_resources import get_distribution 2 | __version__ = get_distribution('pathintegrate').version 3 | 4 | from .pathintegrate import PathIntegrate 5 | from .app import launch_network_app 6 | from .plot import * 7 | from .utils import * -------------------------------------------------------------------------------- /src/pathintegrate/app.py: -------------------------------------------------------------------------------- 1 | # PathIntegrate network explorer app 2 | # Takes a PathIntegrate model as input 3 | 4 | # import packages 5 | import pandas as pd 6 | import numpy as np 7 | import dash 8 | from dash import Dash, html, dcc, Input, Output, State, ctx 9 | import plotly.express as px 10 | import dash_cytoscape as cyto 11 | import matplotlib.pyplot as plt 12 | import matplotlib.colors as mcolors 13 | import seaborn as sns 14 | import networkx as nx 15 | import dash_bootstrap_components as dbc 16 | import matplotlib.cm as cm 17 | import matplotlib as matplotlib 18 | from dash_bootstrap_components._components.Container import Container 19 | from pathlib import Path 20 | from dash.exceptions import PreventUpdate 21 | from plotly.subplots import make_subplots 22 | import plotly.graph_objects as go 23 | import cmcrameri as cmc 24 | import pkg_resources 25 | import matplotlib.colorbar as cbar 26 | import base64 27 | from io import BytesIO 28 | 29 | 30 | # Save downloads to default Downloads folder 31 | downloads_path = str(Path.home() / "Downloads") 32 | 33 | # Load extra layouts 34 | cyto.load_extra_layouts() 35 | 36 | # Set stylesheet 37 | app = Dash(__name__, external_stylesheets=[dbc.themes.YETI], use_pages=False) 38 | 39 | # generate node colours based on model attributes 40 | def get_hex_colors(values, cmap): 41 | norm = plt.Normalize(min(values), max(values)) 42 | cmap = plt.cm.get_cmap(cmap) # Change the colormap here as desired 43 | 44 | hex_colors = [mcolors.rgb2hex(cmap(norm(value))) for value in values] 45 | return hex_colors 46 | 47 | # find parent pathway for each pathway 48 | def find_root(G,child): 49 | parent = list(G.predecessors(child)) 50 | if len(parent) == 0: 51 | return child 52 | else: 53 | return find_root(G, parent[0]) 54 | 55 | # load the pathway database file from the data folder 56 | stream = pkg_resources.resource_stream(__name__, 'data/ReactomePathwaysRelation.txt') 57 | hierarchy = pd.read_csv(stream, sep='\t', header=None) 58 | hierarchy_hsa = hierarchy[hierarchy[0].str.contains('HSA')] 59 | hierarchy_hsa_parents = np.setdiff1d(hierarchy_hsa[0], hierarchy_hsa[1]) 60 | hierarchy_hsa_all = pd.concat([hierarchy_hsa, pd.DataFrame([hierarchy_hsa_parents, hierarchy_hsa_parents], index=[0, 1]).T]) 61 | 62 | # the default graph is the pathway hierarchy coloured by root pathway membership as defined by Reactome 63 | G = nx.from_pandas_edgelist(hierarchy_hsa, source=0, target=1, create_using=nx.DiGraph()) 64 | hierarchy_hsa_all['Root'] = [find_root(G, i) for i in hierarchy_hsa_all[1]] 65 | root_cmap = dict(zip(set(hierarchy_hsa_all['Root']), sns.color_palette("husl", len(set(hierarchy_hsa_all['Root']))).as_hex())) 66 | 67 | cy_mo = nx.readwrite.json_graph.cytoscape_data(G) 68 | 69 | # another figure for the network legend 70 | def get_colorbar_image(values, cmap_name, title): 71 | fig, ax = plt.subplots(figsize=(6, 1)) 72 | fig.subplots_adjust(bottom=0.5) 73 | 74 | norm = plt.Normalize(min(values), max(values)) 75 | cmap = plt.cm.get_cmap(cmap_name) # Change the colormap here as desired 76 | # norm = mcolors.Normalize(vmin=min(values), vmax=max(values)) 77 | 78 | cbar.ColorbarBase(ax, cmap=cmap, norm=norm, orientation='horizontal') 79 | ax.set_title(title) 80 | 81 | # Save the figure to a BytesIO object 82 | buf = BytesIO() 83 | plt.savefig(buf, format='png', bbox_inches='tight') 84 | plt.close(fig) 85 | buf.seek(0) 86 | 87 | return buf 88 | 89 | 90 | def encode_image(image): 91 | return base64.b64encode(image.read()).decode('ascii') 92 | 93 | 94 | # Network layout configuration 95 | SIDEBAR_STYLE = { 96 | "position": "fixed", 97 | "top": 0, 98 | "left": 0, 99 | "bottom": 0, 100 | "width": "16rem", 101 | "padding": "1rem", 102 | "padding-top": "5rem", 103 | "background-color": "#BBDEFB", 104 | # "padding": "6rem 1rem 2rem", 105 | } 106 | CONTENT_STYLE = { 107 | "margin-left": "16rem", 108 | "margin-right": "16rem", 109 | # "padding": "1rem 1rem", 110 | "padding-top": "4rem", 111 | "padding-bottom": "1rem", 112 | "padding-left": "1rem", 113 | "padding-right": "1rem", 114 | # "border":"2px black solid" 115 | "background-color": "#FFFFFF", 116 | } 117 | 118 | sidebar = html.Div( 119 | [ 120 | 121 | html.P("Network options"), 122 | html.Hr(), 123 | 124 | html.P( 125 | "Layout option" 126 | ), 127 | dcc.Dropdown( 128 | id='dropdown-update-layout', 129 | value='random', 130 | clearable=False, 131 | options=[ 132 | {'label': name.capitalize(), 'value': name} 133 | for name in ['random', 'cose', 'circle', 'grid', 'concentric', 'cola'] 134 | ]), 135 | html.P( 136 | "Colour nodes by" 137 | ), 138 | dcc.Dropdown( 139 | id='dropdown-update-node-color', 140 | value='Hierarchy', 141 | clearable=False, 142 | options=[ 143 | {'label': name.capitalize(), 'value': name} 144 | for name in ['Hierarchy', 'Feature importance', 'VIP (MultiView only)'] 145 | ]), 146 | # html.P( 147 | # "Show omics" 148 | # ), 149 | # dcc.Dropdown( 150 | # id='dropdown-update-omics', 151 | # value='multi-omics', 152 | # clearable=False, 153 | # options=[ 154 | # {'label': name.capitalize(), 'value': name} 155 | # for name in ['metabolomics', 'proteomics', 'multi-omics'] 156 | # ]), 157 | html.P( 158 | "Export network" 159 | ), 160 | 161 | dbc.Button("SVG", color="primary", id='btn-get-svg'), 162 | dbc.Button("PNG", color="primary", id='btn-get-png'), 163 | dbc.Button("Network", color="primary", id='btn-get-gml'), 164 | dcc.Download(id="download-network") 165 | ], 166 | style=SIDEBAR_STYLE, 167 | ) 168 | 169 | 170 | 171 | 172 | navbar = dbc.NavbarSimple( 173 | # children=[ 174 | # dbc.NavItem(dbc.NavLink("Home", href="/")), 175 | # dbc.DropdownMenu( 176 | # children=[ 177 | # dbc.DropdownMenuItem("Detail view", href="/details"), 178 | # dbc.DropdownMenuItem("About", href="/about"), 179 | 180 | # ], 181 | # nav=True, 182 | # in_navbar=True, 183 | # label="More", 184 | # ), 185 | # ], 186 | brand="PathIntegrate multi-omics pathway network explorer", 187 | brand_href="#", 188 | color="primary", 189 | dark=True, 190 | fixed='top', 191 | style={ 192 | # "position": "fixed", 193 | # "top": 0, 194 | # "right": 0, 195 | # "bottom": 0, 196 | # "padding-bottom": "2rem", 197 | # "width": "20rem", 198 | # "padding": "2rem 1rem", 199 | # "background-color": "#BBDEFB", 200 | # "padding": "6rem 1rem 2rem", 201 | }, 202 | ) 203 | 204 | # default stylesheet 205 | default_stylesheet = [ 206 | { 207 | 'selector': 'node', 208 | 'style': { 209 | 'background-color': 'data(color)', 210 | 'shape': 'ellipse', 211 | # 'label': 'data(label)', 212 | 'text-wrap': 'wrap', 213 | 'text-background-color': 'yellow', 214 | 'text-max-width': '120px', 215 | 'width': 'data(MO_coverage)', 216 | 'height':'data(MO_coverage)', 217 | 'text-justification': 'auto', 218 | 'font-family': ['Verdana', 'Roboto', 'Arial'], 219 | 'font-size': '0px' 220 | } 221 | }, 222 | { 223 | 'selector': 'edge', 224 | 'style': { 225 | 'line-color': '#A3C4BC' 226 | } 227 | } 228 | ] 229 | 230 | 231 | 232 | # Callback for updating the graph layout 233 | @app.callback(Output('mo_graph', 'layout'), Input('dropdown-update-layout', 'value')) 234 | def update_layout(layout): 235 | return { 236 | 'name': layout, 237 | 'animate': True 238 | } 239 | 240 | # callback for updating node colour 241 | @app.callback(Output('mo_graph', 'stylesheet'), 242 | Input('dropdown-update-node-color', 'value')) 243 | def update_stylesheet(node_value): 244 | node_value_color = {'Hierarchy': 'data(color)', 'Feature importance': 'data(BetaColour)', 'VIP (MultiView only)': 'data(VIPColour)'} 245 | 246 | new_styles = [ 247 | { 248 | 'selector': 'node', 249 | 'style': { 250 | 'background-color': node_value_color[node_value], 251 | 'border-width': '1px', 252 | 'border-color': 'black', 253 | 'background-fit': 'cover', 254 | 'height': 'data(MO_coverage)', 255 | 'width':'data(MO_coverage)' 256 | # 'background-image': bg_img[node_value] 257 | } 258 | }, 259 | { 260 | 'selector': 'edge', 261 | 'style': { 262 | 'line-color': '#A3C4BC' 263 | } 264 | }] 265 | 266 | 267 | return default_stylesheet + new_styles 268 | 269 | 270 | @app.callback(Output('cytoscape-mouseoverNodeData-output-name', 'children'), 271 | Input('mo_graph', 'mouseoverNodeData')) 272 | def displayTapNodeData(data): 273 | if data: 274 | return data['label'] 275 | 276 | @app.callback(Output('cytoscape-mouseoverNodeData-output-root', 'children'), 277 | Input('mo_graph', 'mouseoverNodeData')) 278 | def displayTapNodeData(data): 279 | if data: 280 | return data['Root'] 281 | 282 | @app.callback(Output('cytoscape-mouseoverNodeData-output-coverage', 'children'), 283 | Input('mo_graph', 'mouseoverNodeData')) 284 | def displayTapNodeData(data): 285 | if data: 286 | return data['Coverage'] 287 | 288 | 289 | # Download image 290 | @app.callback( 291 | Output("mo_graph", "generateImage"), 292 | [ 293 | Input("btn-get-svg", "n_clicks"), 294 | Input("btn-get-png", "n_clicks") 295 | ]) 296 | def get_image(get_clicks_svg, get_clicks_png): 297 | 298 | # File type to output of 'svg, 'png', 'jpg', or 'jpeg' (alias of 'jpg') 299 | 300 | # 'store': Stores the image data in 'imageData' !only jpg/png are supported 301 | # 'download'`: Downloads the image as a file with all data handling 302 | # 'both'`: Stores image data and downloads image as file. 303 | ftype='png' 304 | action = 'store' 305 | 306 | if ctx.triggered: 307 | if ctx.triggered_id != "tabs": 308 | action = "download" 309 | ftype = ctx.triggered_id.split("-")[-1] 310 | print(ftype) 311 | 312 | return { 313 | 'type': ftype, 314 | 'action': action 315 | } 316 | 317 | @app.callback( 318 | Output("download-network", "data"), 319 | Input("btn-get-gml", "n_clicks"), 320 | prevent_initial_call=True, 321 | ) 322 | def download_network(n_clicks): 323 | download_path = downloads_path+"/PathIntegrate_network.gml" 324 | nx.write_gml(MO_graph, download_path) 325 | print("Network .gml file saved to: "+download_path) 326 | 327 | return nx.write_gml(MO_graph, download_path) 328 | 329 | 330 | @app.callback([Output("fig_molecular", "figure"), 331 | Output("pathway_selected", "children")], 332 | Input("dropdown", "value")) 333 | def update_bar_chart(pathway): 334 | if modelname == 'MultiView': 335 | pathways_dfs = [] 336 | for k, v in molecule_importances.items(): 337 | try: 338 | pdf = v[pathway] 339 | pdf = pdf.add_suffix(k) 340 | pathways_dfs.append(pdf) 341 | except KeyError: 342 | pass 343 | 344 | pathway_df_molec = pd.concat(pathways_dfs, axis=1) 345 | fig = make_subplots(rows=1, cols=len(pathways_dfs), shared_xaxes='rows') 346 | 347 | for i in range(0, len(pathways_dfs)): 348 | fig.add_trace(go.Bar(x=pathway_df_molec.index, y=pathway_df_molec.iloc[:,i], name=pathway_df_molec.columns[i]), row=1, col=i+1) 349 | 350 | return fig, name_dict[pathway] 351 | else: 352 | pathway_df_molec = molecule_importances[pathway] 353 | fig = go.Figure() 354 | fig.add_trace(go.Bar(x=pathway_df_molec.index.tolist(), y=pathway_df_molec['PC1_Loadings'])) 355 | return fig, name_dict[pathway] 356 | # molecule level vis 357 | # @app.callback( 358 | # Output("bar-plot", "figure"), 359 | # Input("input-pathway", "value")) 360 | # def update_bar_chart(data): 361 | # if data: 362 | # mean_vals = metab.loc[:, metab.columns.isin(mo_paths_dict[data] + ['Group'])].groupby('Group').mean() 363 | # mean_vals_long = mean_vals.melt(ignore_index=False).reset_index() 364 | # fig = px.bar(mean_vals_long, x="variable", y="value", 365 | # color="Group", barmode="group") 366 | # return fig 367 | 368 | # update legend coloubar based on selected node colour 369 | @app.callback(Output('colorbar-image', 'src'), 370 | Input('dropdown-update-node-color', 'value')) 371 | def update_legend(node_value): 372 | # Generate the colorbar image in memory based on selected 373 | if node_value == 'Hierarchy': 374 | # hide the legend for hierarchy - do not display 375 | return None 376 | 377 | elif node_value == 'Feature importance': 378 | if modelname == 'MultiView': 379 | colorbar_image = get_colorbar_image(cmaps['Beta_cmap'][0], cmaps['Beta_cmap'][1], 'Beta') 380 | elif modelname == 'SingleView': 381 | if ['Beta_cmap' in cmaps]: 382 | colorbar_image = get_colorbar_image(cmaps['Beta_cmap'][0], cmaps['Beta_cmap'][1], 'Beta') 383 | elif ['Importance_cmap' in cmaps]: 384 | colorbar_image = get_colorbar_image(cmaps['Importance_cmap'][0], cmaps['Importance_cmap'][1],'Feature importance') 385 | 386 | # Encode the image to base64 387 | encoded_image = encode_image(colorbar_image) 388 | # Return the image source for the html.Img component 389 | return 'data:image/png;base64,{}'.format(encoded_image) 390 | 391 | elif node_value == 'VIP (MultiView only)': 392 | if modelname == 'MultiView': 393 | colorbar_image = get_colorbar_image(cmaps['VIP_cmap'][0], cmaps['VIP_cmap'][1],'VIP (scaled)') 394 | # Encode the image to base64 395 | encoded_image = encode_image(colorbar_image) 396 | # Return the image source for the html.Img component 397 | return 'data:image/png;base64,{}'.format(encoded_image) 398 | else: 399 | return None 400 | 401 | 402 | cmaps = {} 403 | 404 | # start local server 405 | def launch_network_app(pi_model, pathway_source, hierarchy_source='preloaded', p_values=None, **kwargs): 406 | global pathways_accessible 407 | 408 | # Add model attributes to network 409 | global name_dict 410 | name_dict = dict(zip(pathway_source.index, pathway_source['Pathway_name'])) 411 | G.add_nodes_from([(node, {'Name': attr, 'label': attr}) for (node, attr) in name_dict.items()]) 412 | 413 | global modelname 414 | modelname = pi_model.name 415 | 416 | 417 | if pi_model.name == 'MultiView': 418 | pathways_accessible = list(set(sum([i.columns.tolist() for i in pi_model.sspa_scores.values()], []))) 419 | # add beta as node colour 420 | betas_cmap = dict(zip(pathways_accessible, get_hex_colors(pi_model.beta, 'RdBu'))) 421 | G.add_nodes_from([(node, {'BetaColour': attr}) for (node, attr) in betas_cmap.items()]) 422 | 423 | # add vip as node colour 424 | vip_cmap = dict(zip(pathways_accessible, get_hex_colors(pi_model.vip['VIP_scaled'].tolist(), 'Blues'))) 425 | G.add_nodes_from([(node, {'VIPColour': attr}) for (node, attr) in vip_cmap.items()]) 426 | 427 | cmaps['VIP_cmap'] = [pi_model.vip['VIP_scaled'].tolist(), 'Blues'] 428 | cmaps['Beta_cmap'] = [pi_model.beta, 'RdBu'] 429 | 430 | 431 | if pi_model.name == 'SingleView': 432 | pathways_accessible = pi_model.sspa_scores.columns.tolist() 433 | # add beta as node colour 434 | 435 | # if logistic or svm use coef_ attribute 436 | # if random forest use feature_importances_ 437 | if hasattr(pi_model, 'coef_'): 438 | betas_cmap = dict(zip(pathways_accessible, get_hex_colors(pi_model.coef_[0], 'RdBu'))) 439 | G.add_nodes_from([(node, {'BetaColour': attr}) for (node, attr) in betas_cmap.items()]) 440 | cmaps['Beta_cmap'] = [pi_model.coef_[0], 'RdBu'] 441 | elif hasattr(pi_model, 'feature_importances_'): 442 | betas_cmap = dict(zip(pathways_accessible, get_hex_colors(pi_model.feature_importances_, 'Blues'))) 443 | G.add_nodes_from([(node, {'BetaColour': attr}) for (node, attr) in betas_cmap.items()]) 444 | cmaps['Importane_cmap'] = [pi_model.feature_importances_, 'Blues'] 445 | 446 | # filter root pathways for pathways accessible by the model 447 | hierarchy_hsa_all_filt = hierarchy_hsa_all[hierarchy_hsa_all[1].isin(pathways_accessible)] 448 | root_cmap = dict(zip(set(hierarchy_hsa_all_filt['Root']), sns.color_palette("husl", len(set(hierarchy_hsa_all_filt['Root']))).as_hex())) 449 | 450 | G.add_nodes_from([(node, {'Root': attr, 451 | 'RootCol': root_cmap[attr], 452 | 'color': root_cmap[attr], 453 | 'RootName': name_dict[attr]}) for (node, attr) in dict(zip(hierarchy_hsa_all_filt[1], hierarchy_hsa_all_filt['Root'])).items()]) 454 | G.add_nodes_from([(node, {'MO_coverage': np.sqrt(attr)*2.5}) for (node, attr) in pi_model.coverage.items()]) 455 | G.add_nodes_from([(node, {'Coverage': attr}) for (node, attr) in pi_model.coverage.items()]) 456 | if p_values: 457 | pval_cmap = dict(zip(p_values.keys(), get_hex_colors(p_values.values(), 'cmc.lajolla_r'))) 458 | G.add_nodes_from([(node, {'PvalColour': attr}) for (node, attr) in pval_cmap.items()]) 459 | 460 | # add molecular importances for plotting 461 | global molecule_importances 462 | if hasattr(pi_model, 'molecular_importance'): 463 | molecule_importances = pi_model.molecular_importance 464 | 465 | # only show nodes with sufficient coverage 466 | global MO_graph 467 | MO_graph = G.subgraph(pathways_accessible) 468 | cy_mo = nx.readwrite.json_graph.cytoscape_data(MO_graph) 469 | # network generation 470 | content = html.Div( 471 | cyto.Cytoscape( 472 | id='mo_graph', 473 | layout={'name': 'random'}, 474 | style={'width': '100%', 'height': '800px'}, 475 | elements=cy_mo['elements']['nodes'] + cy_mo['elements']['edges'], 476 | stylesheet=default_stylesheet 477 | ), 478 | # style=CONTENT_STYLE 479 | ) 480 | 481 | 482 | 483 | legend_panel = html.Div(children=[ 484 | html.Center([ 485 | html.Img(id='colorbar-image') 486 | ]) 487 | ]) 488 | 489 | sidebar2 = html.Div( 490 | [html.P("Node information"), 491 | html.Hr(), 492 | dbc.ListGroup( 493 | [ 494 | dbc.ListGroupItem( 495 | html.Div( 496 | [html.P("Pathway name"), html.P(id='cytoscape-mouseoverNodeData-output-name') 497 | ])), 498 | dbc.ListGroupItem(html.Div( 499 | [html.P("Parent pathway"), html.P(id='cytoscape-mouseoverNodeData-output-root') 500 | ])), 501 | dbc.ListGroupItem(html.Div( 502 | [html.P("Coverage"), html.P(id='cytoscape-mouseoverNodeData-output-coverage') 503 | ])), 504 | ]), 505 | 506 | html.Br(), 507 | # Legend for node colours 508 | html.P("Node colour legend"), 509 | html.Hr(), 510 | # make a legend for the root pathway colours 511 | html.Div([ 512 | html.P("Root pathway"), 513 | dbc.ListGroup( 514 | [ 515 | dbc.ListGroupItem( 516 | html.Div( 517 | [html.P(i), html.P(name_dict[i]) 518 | ], style={'background-color': root_cmap[i]}) 519 | ) for i in root_cmap.keys() 520 | ]), 521 | ]), 522 | html.Br(), 523 | 524 | ], 525 | style={ 526 | "position": "fixed", 527 | "top": 0, 528 | "right": 0, 529 | "bottom": 0, 530 | "width": "16rem", 531 | "padding": "1rem", 532 | "padding-top": "5rem", 533 | "background-color": "#BBDEFB", 534 | }, 535 | ) 536 | 537 | 538 | 539 | app.layout = html.Div([ 540 | navbar, 541 | sidebar, 542 | sidebar2, 543 | dcc.Tabs([ 544 | dcc.Tab(label='Network', children=[ 545 | legend_panel, 546 | content, 547 | ]), 548 | dcc.Tab(label='Molecular importance', children=[ 549 | html.Div([ 550 | html.Br(), 551 | html.H4( 552 | "Select a pathway from the dropdown menu to view molecular importance:"), 553 | dcc.Dropdown(pathways_accessible, 554 | pathways_accessible[0], 555 | placeholder="Select a pathway", 556 | id="dropdown"), 557 | html.Br(), 558 | html.P(id="pathway_selected") 559 | ]), 560 | dcc.Graph(id="fig_molecular"), 561 | 562 | ]), 563 | ]) 564 | ], 565 | style=CONTENT_STYLE 566 | 567 | ) 568 | 569 | # app.layout = dbc.Container([ 570 | # html.Div([ dcc.Location(id="url",refresh=False), 571 | # navbar, 572 | # sidebar, 573 | # content, 574 | # sidebar2, 575 | # ]),],fluid=True) 576 | # app.layout = html.Div([dcc.Location(id="url"), navbar, sidebar, content, sidebar2]) 577 | app.run() 578 | 579 | 580 | 581 | -------------------------------------------------------------------------------- /src/pathintegrate/pathintegrate.py: -------------------------------------------------------------------------------- 1 | import pandas as pd 2 | import numpy as np 3 | import sklearn.decomposition 4 | import sspa 5 | import sklearn 6 | from mbpls.mbpls import MBPLS 7 | from pathintegrate.app import launch_network_app 8 | from sklearn.preprocessing import StandardScaler 9 | from sklearn.pipeline import Pipeline 10 | from sklearn.model_selection import cross_val_score, GridSearchCV 11 | import scipy 12 | import seaborn as sns 13 | import matplotlib.pyplot as plt 14 | import requests 15 | import json 16 | from sklearn.metrics import confusion_matrix 17 | import plotly.graph_objects as go 18 | from io import BytesIO 19 | import base64 20 | 21 | class PathIntegrate: 22 | '''PathIntegrate class for multi-omics pathway integration. 23 | 24 | Args: 25 | omics_data (dict): Dictionary of omics data. Keys are omics names, values are pandas DataFrames containing omics data where rows contain samples and columns reprsent features. 26 | metadata (pandas.Series): Metadata for samples. Index is sample names, values are class labels. 27 | pathway_source (pandas.DataFrame): GMT style pathway source data. Must contain column 'Pathway_name'. 28 | sspa_scoring (object, optional): Scoring method for ssPA. Defaults to sspa.sspa_SVD. Options are sspa.sspa_SVD, sspa.sspa_ssGSEA, sspa.sspa_KPCA, sspa.sspa_ssClustPA, sspa.sspa_zscore. 29 | min_coverage (int, optional): Minimum number of molecules required in a pathway. Defaults to 3. 30 | 31 | Attributes: 32 | omics_data (dict): Dictionary of omics data. Keys are omics names, values are pandas DataFrames. 33 | omics_data_scaled (dict): Dictionary of omics data scaled to mean 0 and unit variance. Keys are omics names, values are pandas DataFrames. 34 | metadata (pandas.Series): Metadata for samples. Index is sample names, values are class labels. 35 | pathway_source (pandas.DataFrame): Pathway source data. 36 | pathway_dict (dict): Dictionary of pathways. Keys are pathway names, values are lists of molecules. 37 | sspa_scoring (object): Scoring method for SSPA. 38 | min_coverage (int): Minimum number of molecules required to cover a pathway. 39 | sspa_method (object): SSPA scoring method. 40 | sspa_scores_mv (dict): Dictionary of SSPA scores for each omics data. Keys are omics names, values are pandas DataFrames. 41 | sspa_scores_sv (pandas.DataFrame): SSPA scores for all omics data concatenated. 42 | coverage (dict): Dictionary of pathway coverage. Keys are pathway names, values are number of omics covering the pathway. 43 | mv (object): Fitted MultiView model. 44 | sv (object): Fitted SingleView model. 45 | labels (pandas.Series): Class labels for samples. Index is sample names, values are class labels. 46 | ''' 47 | 48 | def __init__(self, omics_data:dict, metadata, pathway_source, sspa_scoring=sspa.sspa_SVD, min_coverage=3): 49 | self.omics_data = omics_data 50 | self.omics_data_scaled = {k: pd.DataFrame(StandardScaler().fit_transform(v), columns=v.columns, index=v.index) for k, v in self.omics_data.items()} 51 | self.metadata = metadata 52 | self.pathway_source = pathway_source 53 | self.pathway_dict = sspa.utils.pathwaydf_to_dict(pathway_source) 54 | self.sspa_scoring = sspa_scoring 55 | self.min_coverage = min_coverage 56 | 57 | # sspa_methods = {'svd': sspa.sspa_SVD, 'ssGSEA': sspa.sspa_ssGSEA, 'kpca': sspa.sspa_KPCA, 'ssClustPA': sspa.sspa_ssClustPA, 'zscore': sspa.sspa_zscore} 58 | self.sspa_method = self.sspa_scoring 59 | self.sspa_scores_mv = None 60 | self.sspa_scores_sv = None 61 | self.coverage = self.get_multi_omics_coverage() 62 | 63 | self.mv = None 64 | self.sv = None 65 | self.sv_us = None 66 | 67 | self.labels = self.metadata 68 | 69 | def get_multi_omics_coverage(self): 70 | all_molecules = sum([i.columns.tolist() for i in self.omics_data.values()], []) 71 | coverage = {k: len(set(all_molecules).intersection(set(v))) for k, v in self.pathway_dict.items()} 72 | return coverage 73 | 74 | def MultiView(self, ncomp=2): 75 | """Fits a PathIntegrate MultiView model using MBPLS. 76 | 77 | Args: 78 | ncomp (int, optional): Number of components. Defaults to 2. 79 | 80 | Returns: 81 | object: Fitted PathIntegrate MultiView model. 82 | """ 83 | 84 | print('Generating pathway scores...') 85 | sspa_scores_ = [self.sspa_method(self.pathway_source, self.min_coverage) for i in self.omics_data_scaled.values()] 86 | sspa_scores = [sspa_scores_[n].fit_transform(i) for n, i in enumerate(self.omics_data_scaled.values())] 87 | # sspa_scores = [self.sspa_method(self.pathway_source, self.min_coverage).fit_transform(i) for i in self.omics_data_scaled.values()] 88 | # sspa_scores = [self.sspa_method(i, self.pathway_source, self.min_coverage, return_molecular_importance=True) for i in self.omics_data.values()] 89 | 90 | self.sspa_scores_mv = dict(zip(self.omics_data.keys(), sspa_scores)) 91 | print('Fitting MultiView model') 92 | try: 93 | mv = MBPLS(n_components=ncomp) 94 | mv.fit([i.copy(deep=True) for i in self.sspa_scores_mv.values()], self.labels) 95 | except ValueError: 96 | print('Error: binary class labels are required for Multi-View (mbpls) model') 97 | 98 | # compute VIP and scale VIP across omics 99 | vip_scores = VIP_multiBlock(mv.W_, mv.Ts_, mv.P_, mv.V_) 100 | vip_df = pd.DataFrame(vip_scores, index=sum([i.columns.tolist() for i in self.sspa_scores_mv.values()], [])) 101 | vip_df['Name'] = vip_df.index.map(dict(zip(self.pathway_source.index, self.pathway_source['Pathway_name']))) 102 | vip_df['Source'] = sum([[k] * v.shape[1] for k, v in self.sspa_scores_mv.items()], []) 103 | vip_df['VIP_scaled'] = vip_df.groupby('Source')[0].transform(lambda x: StandardScaler().fit_transform(x.values[:,np.newaxis]).ravel()) 104 | vip_df['VIP'] = vip_scores 105 | mv.name = 'MultiView' 106 | 107 | # only some sspa methods can return the molecular importance 108 | if hasattr(sspa_scores_[0], 'molecular_importance'): 109 | mv.molecular_importance = dict(zip(self.omics_data.keys(), [i.molecular_importance for i in sspa_scores_])) 110 | mv.beta = mv.beta_.flatten() 111 | mv.vip = vip_df 112 | mv.omics_names = list(self.omics_data.keys()) 113 | mv.sspa_scores = self.sspa_scores_mv 114 | mv.coverage = self.coverage 115 | self.mv = mv 116 | 117 | return self.mv 118 | 119 | def SingleView(self, model=sklearn.linear_model.LogisticRegression, model_params=None): 120 | """Fits a PathIntegrate SingleView model using an SKLearn-compatible predictive model. 121 | 122 | Args: 123 | model (object, optional): SKlearn prediction model class. Defaults to sklearn.linear_model.LogisticRegression. 124 | model_params (_type_, optional): Model-specific hyperparameters. Defaults to None. 125 | 126 | Returns: 127 | object: Fitted PathIntegrate SingleView model. 128 | """ 129 | 130 | concat_data = pd.concat(self.omics_data_scaled.values(), axis=1) 131 | print('Generating pathway scores...') 132 | 133 | sspa_scores = self.sspa_method(self.pathway_source, self.min_coverage) 134 | self.sspa_scores_sv = sspa_scores.fit_transform(concat_data) 135 | 136 | if model_params: 137 | sv = model(**model_params) # ** this is inputed into the scikit learn model 138 | else: 139 | sv = model() 140 | print('Fitting SingleView model') 141 | 142 | # fitting the model 143 | 144 | sv.fit(X=self.sspa_scores_sv, y=self.labels) 145 | sv.sspa_scores = self.sspa_scores_sv 146 | sv.name = 'SingleView' 147 | sv.coverage = self.coverage 148 | 149 | # only some sspa methods can return the molecular importance 150 | if hasattr(sspa_scores, 'molecular_importance'): 151 | sv.molecular_importance = sspa_scores.molecular_importance 152 | self.sv = sv 153 | 154 | return self.sv 155 | 156 | 157 | def SingleViewClust(self, model=sklearn.cluster.KMeans,n_clusters_range=(2, 10), model_params=None, use_pca=True, pca_params=None, consensus_clustering=False, n_runs=10, auto_n_clusters=False, subsample_fraction=0.8, return_plot=False, return_ground_truth_plot=False, return_confusion_matrix=False, return_metrics_table=False): 158 | """ 159 | Fits a PathIntegrate SingleView Unsupervised model using an SKLearn-compatible KMeans model. 160 | Credit: Jude Popham 161 | 162 | Args: 163 | model (object, optional): SKLearn clustering model class. Defaults to sklearn.cluster.KMeans. 164 | model_params (dict, optional): Model-specific hyperparameters. Defaults to None. 165 | use_pca (bool, optional): Whether to perform PCA before clustering. Defaults to False. 166 | pca_params (dict, optional): PCA-specific hyperparameters. Defaults to None. 167 | consensus_clustering (bool, optional): Whether to perform consensus clustering. Defaults to False. 168 | n_runs (int, optional): Number of runs for consensus clustering. Defaults to 10. 169 | auto_n_clusters (bool, optional): Automatically determine the optimal number of clusters. Defaults to False. 170 | n_clusters_range (tuple, optional): Range of cluster numbers to evaluate for optimal clusters. Defaults to (2, 10). 171 | subsample_fraction (float, optional): Fraction of samples to use for each consensus clustering run. Defaults to 0.8. 172 | return_plot (bool, optional): Whether to return a plot of the clustering result. Defaults to False. 173 | return_ground_truth_plot (bool, optional): Whether to return a plot comparing the clustering result with ground truth. Defaults to False. 174 | return_confusion_matrix (bool, optional): Whether to return a plot comparing different clustering algorithms. Defaults to False. 175 | return_metrics_table (bool, optional): Whether to return a table of clustering evaluation metrics. Defaults to False. 176 | 177 | Returns: 178 | object: Fitted PathIntegrate SingleView Clustering model with various plots saved inside. 179 | 180 | """ 181 | 182 | # function to normalise the metrics later on 183 | def normalize_score(score, score_min, score_max): 184 | return (score - score_min) / (score_max - score_min) 185 | 186 | # forming the concatenated data 187 | concat_data = pd.concat(self.omics_data_scaled.values(), axis=1) 188 | print('Generating pathway scores...') 189 | sspa_scores = self.sspa_method(self.pathway_source, self.min_coverage) 190 | self.sspa_scores_sv = sspa_scores.fit_transform(concat_data) 191 | combined_data_scaled = StandardScaler().fit_transform(self.sspa_scores_sv) 192 | combined_data_final = pd.DataFrame(combined_data_scaled, index=self.sspa_scores_sv.index, columns=self.sspa_scores_sv.columns) 193 | self.sspa_scores_sv = combined_data_final 194 | 195 | # if using PCA 196 | if use_pca: 197 | print('Performing PCA...') 198 | if pca_params is None: 199 | pca_params = {'n_components': min(concat_data.shape[1], 50)} 200 | pca = sklearn.decomposition.PCA(**pca_params) 201 | pca_components = pca.fit_transform(self.sspa_scores_sv) 202 | component_names = [f'PC{i+1}' for i in range(pca_components.shape[1])] 203 | self.sspa_scores_sv = pd.DataFrame(data=pca_components, columns=component_names, index=self.sspa_scores_sv.index) 204 | else: 205 | print('Not Using PCA...') 206 | 207 | # if no model parameters 208 | if model_params is None: 209 | model_params = {} 210 | 211 | # if automatically determining clusters 212 | if auto_n_clusters: 213 | print('Determining optimal number of clusters...') 214 | best_score = -1 215 | best_n_clusters = None 216 | silhouette_scores = [] 217 | for n_clusters in range(*n_clusters_range): 218 | sv_clust = model(n_clusters=n_clusters, **model_params) 219 | labels = sv_clust.fit_predict(self.sspa_scores_sv) 220 | silhouette_avg = sklearn.metrics.silhouette_score(self.sspa_scores_sv, labels) 221 | silhouette_scores.append(silhouette_avg) 222 | if silhouette_avg > best_score: 223 | best_score = silhouette_avg 224 | best_n_clusters = n_clusters 225 | model_params['n_clusters'] = best_n_clusters 226 | print(f'Optimal number of clusters determined: {best_n_clusters}') 227 | 228 | # if using consensus clustering 229 | # please provide subsample size 230 | if consensus_clustering and n_runs > 0: 231 | n_samples = self.sspa_scores_sv.shape[0] 232 | consensus_matrix = np.zeros((n_samples, n_samples)) 233 | for run in range(n_runs): 234 | print(f'Run {run + 1}/{n_runs}') 235 | subsample_idx = np.random.choice(n_samples, int(subsample_fraction * n_samples), replace=False) 236 | subsample_data = self.sspa_scores_sv.iloc[subsample_idx] 237 | sv_clust = model(**(model_params or {})) 238 | labels = sv_clust.fit_predict(subsample_data) 239 | for i in range(len(subsample_idx)): 240 | for j in range(i + 1, len(subsample_idx)): 241 | if labels[i] == labels[j]: 242 | consensus_matrix[subsample_idx[i], subsample_idx[j]] += 1 243 | consensus_matrix[subsample_idx[j], subsample_idx[i]] += 1 244 | consensus_matrix /= n_runs 245 | consensus_labels = model(n_clusters=model_params['n_clusters']).fit_predict(consensus_matrix) 246 | else: 247 | sv_clust = model(**(model_params or {})) 248 | consensus_labels = sv_clust.fit_predict(self.sspa_scores_sv) 249 | 250 | # saving the variables in the object 251 | self.sv_clust = sv_clust 252 | self.sv_clust.sspa_scores = self.sspa_scores_sv 253 | self.sv_clust.labels_ = consensus_labels 254 | self.sv_clust.name = 'SingleViewClust' 255 | 256 | print('Calculating clustering metrics...') 257 | 258 | # various metrics caluclated 259 | silhouette_avg = sklearn.metrics.silhouette_score(self.sspa_scores_sv, consensus_labels) 260 | calinski_harabasz = sklearn.metrics.calinski_harabasz_score(self.sspa_scores_sv, consensus_labels) 261 | davies_bouldin = sklearn.metrics.davies_bouldin_score(self.sspa_scores_sv, consensus_labels) 262 | 263 | # normalising their scores using the previous function 264 | silhouette_norm = normalize_score(silhouette_avg, -1, 1) 265 | calinski_harabasz_norm = normalize_score(calinski_harabasz, 0, np.max([calinski_harabasz])) 266 | davies_bouldin_norm = normalize_score(davies_bouldin, 0, np.max([davies_bouldin])) 267 | davies_bouldin_norm = 1 - davies_bouldin_norm 268 | combined_score = (silhouette_norm + calinski_harabasz_norm + davies_bouldin_norm) / 3 269 | 270 | # saving the metrics 271 | self.sv_clust.metrics = { 272 | 'Silhouette_Score': silhouette_avg, 273 | } 274 | 275 | # creating a clustering plot 276 | if return_plot: 277 | consensus_labels_series = pd.Series(consensus_labels, index=self.sspa_scores_sv.index, name='Consensus_Cluster') 278 | sspa_scores_labels = self.sspa_scores_sv 279 | sspa_scores_labels['Consensus_Cluster'] = consensus_labels_series 280 | fig_clust = plt.figure(figsize=(10, 8)) 281 | sns.scatterplot(x=sspa_scores_labels.iloc[:, 0], y=sspa_scores_labels.iloc[:, 1], hue=sspa_scores_labels['Consensus_Cluster'], palette='coolwarm', s=100, edgecolor='black') 282 | plt.title('Clustering Results', fontsize=20) 283 | plt.xlabel('Component 1', fontsize=16) 284 | plt.ylabel('Component 2', fontsize=16) 285 | plt.xticks(fontsize=14) 286 | plt.yticks(fontsize=14) 287 | plt.legend(title='Cluster', title_fontsize=16, fontsize=14) 288 | plt.grid(True) 289 | plt.show() 290 | sv_clust.clusters_plot = fig_clust 291 | 292 | # creating a ground truth plot for comparison 293 | if return_ground_truth_plot: 294 | metadata_pca = self.metadata.to_frame(name='Who_Group') 295 | sspa_scores_meta = pd.concat([self.sspa_scores_sv, metadata_pca], axis=1) 296 | fig_ground = plt.figure(figsize=(10, 8)) 297 | sns.scatterplot(x=sspa_scores_meta.iloc[:, 0], y=sspa_scores_meta.iloc[:, 1], hue=sspa_scores_meta['Who_Group'], palette='coolwarm', s=100, edgecolor='black') 298 | plt.title('Ground Truth Labels', fontsize=20) 299 | plt.xlabel('Component 1', fontsize=16) 300 | plt.ylabel('Component 2', fontsize=16) 301 | plt.xticks(fontsize=14) 302 | plt.yticks(fontsize=14) 303 | plt.legend(title='Ground Truth', title_fontsize=16, fontsize=14) 304 | plt.grid(True) 305 | plt.show() 306 | sv_clust.ground_truth_plot = fig_ground 307 | 308 | # creating a confusion matrix to compare labels 309 | if return_confusion_matrix: 310 | metadata_pca = self.metadata.to_frame(name='Who_Group') 311 | sspa_scores_meta = pd.concat([self.sspa_scores_sv, metadata_pca], axis=1) 312 | consensus_labels_series = pd.Series(consensus_labels, index=sspa_scores_meta.index, name='Consensus_Cluster') 313 | sspa_scores_meta['Consensus_Cluster'] = consensus_labels_series 314 | confusion_df = pd.crosstab(sspa_scores_meta['Who_Group'], sspa_scores_meta['Consensus_Cluster']) 315 | normalized_confusion_df = confusion_df.div(confusion_df.sum(axis=1), axis=0) 316 | fig = go.Figure(data=go.Heatmap( 317 | z=normalized_confusion_df.values, 318 | x=normalized_confusion_df.columns, 319 | y=normalized_confusion_df.index, 320 | colorscale='Blues', 321 | text=confusion_df.values, 322 | texttemplate="%{text}", 323 | hovertemplate="True Label: %{y}
Predicted: %{x}
Count: %{text}", 324 | colorbar=dict(title="Normalized Value") 325 | )) 326 | fig.update_layout( 327 | title=dict( 328 | text="Confusion Matrix: Cluster vs Ground Truth Label", 329 | font=dict(size=24) 330 | ), 331 | xaxis_title=dict( 332 | text="Predicted Cluster", 333 | font=dict(size=18) 334 | ), 335 | yaxis_title=dict( 336 | text="Ground Truth Label", 337 | font=dict(size=18) 338 | ), 339 | xaxis=dict( 340 | tickmode='array', 341 | tickvals=list(range(len(confusion_df.columns))), 342 | ticktext=confusion_df.columns, 343 | tickfont=dict(size=14) 344 | ), 345 | yaxis=dict( 346 | tickmode='array', 347 | tickvals=list(range(len(confusion_df.index))), 348 | ticktext=confusion_df.index, 349 | tickfont=dict(size=14) 350 | ), 351 | height=600, 352 | width=800 353 | ) 354 | fig.show() 355 | 356 | # calculating the ari score and adding this to the metrics (if confusion matrix is created) 357 | ari_score = sklearn.metrics.adjusted_rand_score(sspa_scores_meta['Who_Group'], sspa_scores_meta['Consensus_Cluster']) 358 | self.sv_clust.metrics['Adjusted_Rand_Index'] = ari_score 359 | sv_clust.confusion_matrix = fig 360 | 361 | # if the metrics table is requested 362 | if return_metrics_table: 363 | metrics_df = pd.DataFrame(self.sv_clust.metrics, index=[0]) 364 | metrics_df = metrics_df.T.reset_index() 365 | metrics_df.columns = ['Metric', 'Value'] 366 | custom_palette = ['red' if i % 2 == 0 else 'blue' for i in range(len(metrics_df))] 367 | fig_metrics = plt.figure(figsize=(10, 8)) 368 | ax = sns.barplot(y='Metric', x='Value', data=metrics_df, palette=custom_palette) 369 | for index, value in enumerate(metrics_df['Value']): 370 | plt.text(value / 2, index, f'{value:.2f}', color='white', ha='center', va='center', fontsize=18, weight='bold') 371 | plt.ylabel('Metric', fontsize=18) 372 | plt.xlabel('Value', fontsize=18) 373 | plt.xticks(fontsize=18) 374 | plt.yticks(fontsize=18) 375 | plt.tight_layout() 376 | plt.show() 377 | sv_clust.metrics_plot = fig_metrics 378 | 379 | print('Finished') 380 | 381 | # creating a new sspa_scores object with clusters 382 | self.sv_clust.sspa_scores_clusters = self.sspa_scores_sv 383 | 384 | return self.sv_clust 385 | 386 | 387 | def SingleViewDimRed(self, model=sklearn.decomposition.PCA, model_params=None, return_pca_plot=False,return_tsne_plot = False, return_biplot=False, return_loadings_plot=False, return_tsne_density_plot=False ,metadata_continuous=False): 388 | """ 389 | Applies a dimensionality reduction technique to the input data. 390 | Credit: Jude Popham 391 | 392 | Args: 393 | model (object, optional): The dimensionality reduction model to use. Defaults to sklearn.decomposition.PCA. 394 | model_params (dict, optional): Model-specific hyperparameters. Defaults to None. 395 | return_pca_plot (bool, optional): Whether to return a PCA scatter plot of the first two principal components. 396 | return_tsne_plot (bool, optional): Whether to return a t-SNE scatter plot of the first two components. 397 | return_biplot (bool, optional): Whether to return a biplot (PCA plot with loadings). 398 | return_loadings_plot (bool, optional): Whether to return a plot of the top loadings for each component. 399 | return_tsne_density_plot (bool, optional): Whether to return a t-SNE scatter plot with a density overlay. 400 | metadata_continuous (bool, optional): Whether metadata is continuous or categorical. 401 | 402 | Returns: 403 | object: Fitted dimensionality reduction model with reduced data and optional plots. 404 | """ 405 | 406 | # creating concatenated and data 407 | concat_data = pd.concat(self.omics_data_scaled.values(), axis=1) 408 | print('Generating pathway scores...') 409 | sspa_scores = self.sspa_method(self.pathway_source, self.min_coverage) 410 | self.sspa_scores_sv = sspa_scores.fit_transform(concat_data) 411 | if model_params is None: 412 | model_params = {} 413 | sv_dim = model(**model_params) if model_params else model() 414 | print('Fitting SingleView Dimensionality Reduction model') 415 | 416 | # setging the model parameters depending on the model used (PCA or t-SNE) 417 | if sklearn.decomposition.PCA: 418 | if return_biplot or return_loadings_plot: 419 | if model_params.get('n_components', 2) != 2: 420 | print("Warning: n_components has been set to 2 for the biplot.") 421 | model_params['n_components'] = 2 422 | else: 423 | model_params['n_components'] = 2 424 | sv_dim = model(**model_params) 425 | 426 | # scaling data and fitting the models 427 | if model == sklearn.decomposition.PCA: 428 | reduced_data_scaled = StandardScaler().fit_transform(self.sspa_scores_sv) 429 | reduced_data_sspa = pd.DataFrame(reduced_data_scaled, columns=self.sspa_scores_sv.columns) 430 | reduced_data = sv_dim.fit_transform(reduced_data_sspa) 431 | explained_variance = sv_dim.explained_variance_ratio_ if hasattr(sv_dim, 'explained_variance_ratio_') else None 432 | else: 433 | reduced_data = sv_dim.fit_transform(self.sspa_scores_sv) 434 | explained_variance = None 435 | 436 | # saving to the dim object 437 | sv_dim.reduced_data = reduced_data 438 | sv_dim.explained_variance = explained_variance 439 | sv_dim.sspa_scores_pca = self.sspa_scores_sv 440 | sv_dim.name = 'SingleViewDimRed' 441 | 442 | # incorporating metadata and setting it on a continuous scale if necessary 443 | pca_df = pd.DataFrame(data=reduced_data[:, :2], columns=['PC1', 'PC2']) 444 | metadata_pca = self.metadata.to_frame(name='Metadata').reset_index(drop=True) 445 | if metadata_continuous: 446 | metadata_pca['Meta_Group_Midpoint'] = metadata_pca['Metadata'].apply(self.convert_range_to_midpoint) 447 | pca_df_named = pd.concat([pca_df, metadata_pca], axis=1) 448 | pca_df_named = pca_df_named.sort_values('Meta_Group_Midpoint').reset_index(drop=True) 449 | pca_df_named = pca_df_named.drop(columns=['Meta_Group_Midpoint']) 450 | else: 451 | pca_df_named = pd.concat([pca_df, metadata_pca], axis=1) 452 | if return_tsne_plot or return_tsne_density_plot: 453 | tsne_df = pd.DataFrame(data=reduced_data[:, :2], columns=['Component 1', 'Component 2']) 454 | metadata_pca['Meta_Group_Midpoint'] = metadata_pca['Metadata'].apply(self.convert_range_to_midpoint) 455 | tsne_df_named = pd.concat([tsne_df, metadata_pca], axis=1) 456 | tsne_df_named = tsne_df_named.sort_values('Meta_Group_Midpoint').reset_index(drop=True) 457 | tsne_df_named = tsne_df_named.drop(columns=['Meta_Group_Midpoint']) 458 | 459 | # if returning tsne plot 460 | if return_tsne_plot: 461 | if model != sklearn.manifold.TSNE: 462 | raise ValueError("Error: Please use sklearn.manifold.TSNE for t-SNE plots.") 463 | sns.set_style("white") 464 | fig_tsne = plt.figure() 465 | sns.set_style("white") 466 | sns.scatterplot(data=tsne_df_named, x='Component 1', y='Component 2', hue='Metadata', palette='coolwarm', s=100, edgecolor='black') 467 | plt.title('t-SNE of Integrated Data (First 2 Components)') 468 | plt.xlabel('Component 1') 469 | plt.ylabel('Component 2') 470 | plt.legend(title='Metadata Group') 471 | plt.grid(True) 472 | plt.show() 473 | sv_dim.tsne_plot = fig_tsne 474 | 475 | # if returning tsne density plot 476 | if return_tsne_density_plot: 477 | if model != sklearn.manifold.TSNE: 478 | raise ValueError("Error: Please use sklearn.manifold.TSNE for t-SNE plots.") 479 | sns.set_style("white") 480 | fig_tsne_density = plt.figure(figsize=(10, 8)) 481 | sns.scatterplot(data=tsne_df_named, x='Component 1', y='Component 2', hue='Metadata', s=50, edgecolor='black', alpha=0.6, palette="coolwarm") 482 | sns.kdeplot(data=tsne_df_named, x='Component 1', y='Component 2', hue='Metadata', fill=True, alpha=0.3, palette="coolwarm") 483 | plt.title('t-SNE of Integrated Data with Density Overlay') 484 | plt.xlabel('Component 1') 485 | plt.ylabel('Component 2') 486 | plt.legend(title='Metadata Group') 487 | plt.grid(True) 488 | plt.show() 489 | sv_dim.tsne_density_plot = fig_tsne_density 490 | 491 | # if a biplot or loadings plot is requested - need to convert pathways to names 492 | if return_loadings_plot or return_biplot: 493 | if model != sklearn.decomposition.PCA: 494 | raise ValueError("Error: Please use sklearn.decomposition.PCA to examine loadings.") 495 | loadings_df = pd.DataFrame(sv_dim.components_.T, columns=['Component 1', 'Component 2'], index=reduced_data_sspa.columns) 496 | 497 | # function to download a kegg conversion file - reactome conversion file is already within code 498 | url = "https://rest.kegg.jp/get/br:br08901/json" 499 | response = requests.get(url) 500 | if response.status_code == 200: 501 | hierarchy_json = response.json() 502 | with open('br08901.json', 'w') as f: 503 | json.dump(hierarchy_json, f, indent=4) 504 | else: 505 | print("Failed to retrieve data. Status code:", response.status_code) 506 | def create_id_name_mapping(node): 507 | id_name_mapping = {} 508 | if 'children' in node: 509 | for child in node['children']: 510 | id_name_mapping.update(create_id_name_mapping(child)) 511 | else: 512 | pathway_id, pathway_name = node['name'].split(' ', 1) 513 | id_name_mapping[pathway_id] = pathway_name.strip() 514 | return id_name_mapping 515 | pathway_mapping = create_id_name_mapping(hierarchy_json) 516 | 517 | # extracting the top pathway loadings 518 | top_loadings_pc1 = loadings_df['Component 1'].sort_values(key=abs, ascending=False).head(10) 519 | top_loadings_pc2 = loadings_df['Component 2'].sort_values(key=abs, ascending=False).head(10) 520 | top_loadings = pd.concat([top_loadings_pc1, top_loadings_pc2]) 521 | sv_dim.loadings_df = loadings_df 522 | 523 | # creating a PCA plot 524 | if return_pca_plot: 525 | sns.set_style("white") 526 | fig_pca = plt.figure() 527 | sns.scatterplot(data=pca_df_named, x='PC1', y='PC2', hue='Metadata', palette="coolwarm", s=100, edgecolor='black') 528 | plt.title('PCA of Integrated Data (First 2 Principal Components)') 529 | plt.xlabel('Principal Component 1') 530 | plt.ylabel('Principal Component 2') 531 | plt.legend(title='Metadata Group') 532 | plt.grid(True) 533 | plt.show() 534 | sv_dim.pca_plot = fig_pca 535 | 536 | # creatign a biplot 537 | if return_biplot: 538 | scaling_factor = 200 539 | sns.set_style("white") 540 | fig_biplot = plt.figure(figsize=(10, 8)) 541 | sns.scatterplot(data=pca_df_named, x='PC1', y='PC2', hue='Metadata', s=100, edgecolor='black', alpha=0.2, legend=False) 542 | for variable in top_loadings.index: 543 | color = 'red' if variable in top_loadings_pc1.index else 'blue' 544 | plt.arrow(0, 0, loadings_df.loc[variable, 'Component 1'] * scaling_factor, 545 | loadings_df.loc[variable, 'Component 2'] * scaling_factor, 546 | color=color, alpha=0.8, head_width=0.5, linewidth=2) 547 | plt.text(loadings_df.loc[variable, 'Component 1'] * scaling_factor * 1.15, 548 | loadings_df.loc[variable, 'Component 2'] * scaling_factor * 1.15, 549 | variable, color='black', ha='center', va='center', fontsize=10) 550 | plt.xticks(fontsize=14) 551 | plt.yticks(fontsize=14) 552 | plt.title('Biplot of PCA with Top 10 Loadings Highlighted') 553 | plt.xlabel('Principal Component 1') 554 | plt.ylabel('Principal Component 2') 555 | plt.grid(True) 556 | plt.show() 557 | sv_dim.biplot = fig_biplot 558 | 559 | # creating a loadings plot 560 | if return_loadings_plot: 561 | fig_loadings_plot = plt.figure(figsize=(12, 10)) 562 | index_mapping = self.pathway_source['Pathway_name'].to_dict() 563 | def rename_index(index): 564 | if index.startswith('R-HSA'): 565 | return index_mapping.get(index, index) 566 | else: 567 | return pathway_mapping.get(index, index) 568 | loadings_df.index = [rename_index(idx) for idx in loadings_df.index] 569 | top_loadings_pc1 = loadings_df['Component 1'].sort_values(key=abs, ascending=False).head(10) 570 | top_loadings_pc2 = loadings_df['Component 2'].sort_values(key=abs, ascending=False).head(10) 571 | top_loadings = pd.concat([top_loadings_pc1, top_loadings_pc2]) 572 | colors = ['red' if variable in top_loadings_pc1.index else 'blue' for variable in top_loadings.index] 573 | top_loadings.plot(kind='barh', color=colors, width=0.3) 574 | plt.title('Top 5 Loadings for PC1 and PC2', fontsize=24) 575 | plt.xlabel('Loading Value', fontsize=20) 576 | plt.ylabel('', fontsize=30) 577 | plt.axvline(0, color='black', linewidth=0.1) 578 | plt.xticks(rotation=45, fontsize=18) 579 | plt.yticks(fontsize=30) 580 | plt.show() 581 | sv_dim.loadings_plot = fig_loadings_plot 582 | 583 | sv_dim.metadata_pca = metadata_pca 584 | self.sv_dim = sv_dim 585 | 586 | return self.sv_dim 587 | 588 | # function to convert ranges to midpoints 589 | def convert_range_to_midpoint(self, value): 590 | """ 591 | Converts a range like '10-20' into its midpoint value '15'. 592 | """ 593 | if isinstance(value, str) and '-' in value: 594 | try: 595 | start, end = map(float, value.split('-')) 596 | return (start + end) / 2 597 | except ValueError: 598 | return value 599 | return value 600 | 601 | def SingleViewCV(self, model=sklearn.linear_model.LogisticRegression, model_params=None, cv_params=None): 602 | '''Cross-validation for SingleView model. 603 | 604 | Args: 605 | model (object, optional): SKlearn prediction model class. Defaults to sklearn.linear_model.LogisticRegression. 606 | model_params (_type_, optional): Model-specific hyperparameters. Defaults to None. 607 | cv_params (dict, optional): Cross-validation parameters. Defaults to None. 608 | Returns: 609 | object: Cross-validation results. 610 | 611 | ''' 612 | # concatenate omics - unscaled to avoid data leakage 613 | concat_data = pd.concat(self.omics_data.values(), axis=1) 614 | 615 | # Set up sklearn pipeline 616 | pipe_sv = sklearn.pipeline.Pipeline([ 617 | ('Scaler', StandardScaler().set_output(transform="pandas")), 618 | ('sspa', self.sspa_method(self.pathway_source, self.min_coverage)), 619 | ('sv', model(**model_params)) 620 | ]) 621 | 622 | cv_res = cross_val_score(pipe_sv, X=concat_data, y=self.labels, **cv_params) 623 | return cv_res 624 | 625 | def SingleViewGridSearchCV(self, param_grid, model=sklearn.linear_model.LogisticRegression, grid_search_params=None): 626 | '''Grid search cross-validation for SingleView model. 627 | 628 | Args: 629 | param_grid (dict): Grid search parameters. 630 | model (object, optional): SKlearn prediction model class. Defaults to sklearn.linear_model.LogisticRegression. 631 | grid_search_params (dict, optional): Grid search parameters. Defaults to None. 632 | 633 | Returns: 634 | object: GridSearchCV object. 635 | 636 | ''' 637 | # concatenate omics - unscaled to avoid data leakage 638 | concat_data = pd.concat(self.omics_data.values(), axis=1) 639 | 640 | # Set up sklearn pipeline 641 | pipe_sv = sklearn.pipeline.Pipeline([ 642 | ('Scaler', StandardScaler().set_output(transform="pandas")), 643 | ('sspa', self.sspa_method(self.pathway_source, self.min_coverage)), 644 | ('model', model()) 645 | ]) 646 | 647 | # Set up cross-validation 648 | grid_search = GridSearchCV(pipe_sv, param_grid=param_grid, **grid_search_params) 649 | grid_search.fit(X=concat_data, y=self.labels) 650 | return grid_search 651 | 652 | # only 1 model so one parameter way to grid search pca components 653 | # advantage of multi view is interpretation of contribution 654 | 655 | def MultiViewCV(self): 656 | '''Cross-validation for MultiView model. 657 | 658 | Returns: 659 | object: Cross-validation results. 660 | ''' 661 | 662 | # Set up sklearn pipeline 663 | pipe_mv = sklearn.pipeline.Pipeline([ 664 | ('sspa', self.sspa_method(self.pathway_source, self.min_coverage)), 665 | ('mbpls', MBPLS(n_components=2)) 666 | ]) 667 | 668 | # Set up cross-validation 669 | cv_res = cross_val_score(pipe_mv, X=[i.copy(deep=True) for i in self.omics_data.values()], y=self.labels) 670 | return cv_res 671 | 672 | def MultiViewGridSearchCV(self): 673 | raise NotImplementedError('See tutorial for Multi-View latent variable optimisation approach') 674 | 675 | 676 | def VIP_multiBlock(x_weights, x_superscores, x_loadings, y_loadings): 677 | """Calculate VIP scores for multi-block PLS. 678 | 679 | Args: 680 | x_weights (list): List of x weights. 681 | x_superscores (list): List of x superscores. 682 | x_loadings (list): List of x loadings. 683 | y_loadings (list): List of y loadings. 684 | 685 | Returns: 686 | numpy.ndarray: VIP scores for each feature across all blocks. Features are in original order. 687 | """ 688 | # stack the weights from all blocks 689 | weights = np.vstack(x_weights) 690 | # calculate product of sum of squares of superscores and y loadings 691 | sumsquares = np.sum(x_superscores**2, axis=0) * np.sum(y_loadings**2, axis=0) 692 | # p = number of variables - stack the loadings from all blocks 693 | p = np.vstack(x_loadings).shape[0] 694 | 695 | # VIP is a weighted sum of squares of PLS weights 696 | vip_scores = np.sqrt(p * np.sum(sumsquares*(weights**2), axis=1) / np.sum(sumsquares)) 697 | return vip_scores 698 | 699 | 700 | -------------------------------------------------------------------------------- /src/pathintegrate/plot.py: -------------------------------------------------------------------------------- 1 | # plotting functions 2 | 3 | import numpy as np 4 | import pandas as pd 5 | import matplotlib.pyplot as plt 6 | import seaborn as sns 7 | 8 | def omics_view_importance(pi_model, outfile=None): 9 | """Plot the importance of each omics view in the MultiView model 10 | 11 | Args: 12 | pi_model (object): Fitted PathIntegrate multi-view model. 13 | """ 14 | plt.figure(figsize=(7, 5)) 15 | block_importance = pd.DataFrame(pi_model.A_corrected_*100, index=pi_model.omics_names, columns=range(0, pi_model.A_corrected_.shape[1])) 16 | pev_per_lv = np.round(pi_model.explained_var_y_, 2)*100 17 | sns.heatmap( 18 | data=block_importance, 19 | cmap='Blues', 20 | annot=True, 21 | fmt='.2f', 22 | linewidths=.5, 23 | square=True, 24 | vmin=0, 25 | vmax=100) 26 | 27 | plt.ylabel('Omics view') 28 | plt.xticks([i+0.5 for i in range(0, pi_model.A_corrected_.shape[1])], [str(n+1) + ': ' + str(i)+'%' for n, i in enumerate(pev_per_lv)]) 29 | plt.xlabel('Percentage explained in Y per LV') 30 | plt.title('Omics view importance') 31 | 32 | plt.tight_layout() 33 | if outfile: 34 | plt.savefig(outfile) 35 | plt.show() 36 | 37 | 38 | # def top_n_pathways(pi_model, n_top_paths=10, outfile=None): 39 | 40 | # if pi_model.mv: 41 | # pass 42 | 43 | # elif pi_model.sv: 44 | # paths_df = pi_model.feature_importances_.sort_values(ascending=False).head(n_top_paths) 45 | # sns.barplot() 46 | 47 | # plt.tight_layout() 48 | # if outfile: 49 | # plt.savefig(outfile) 50 | # plt.show() 51 | -------------------------------------------------------------------------------- /src/pathintegrate/utils.py: -------------------------------------------------------------------------------- 1 | import pandas as pd 2 | import numpy as np 3 | import pkg_resources 4 | import scipy.stats as stats 5 | import statsmodels.api as sm 6 | 7 | def load_example_data(omicstype): 8 | """ 9 | Loads example datasets 10 | 11 | Args: 12 | omicstype (str): type of omics for example data. 13 | Available options are "metabolomics" or "proteomics". 14 | Data are from Su et al 2020 https://doi.org/10.1016/j.cell.2020.10.037. 15 | 16 | Returns: 17 | pre-processed omics data matrix consisting of m samples and n entities (metabolites/genes) in the form of a pandas DataFrame. 18 | Contains one of more metadata columns at the end. 19 | """ 20 | 21 | if omicstype == "metabolomics": 22 | stream = pkg_resources.resource_stream(__name__, 'data/metabolomics_example.csv') 23 | f = pd.read_csv(stream, index_col=0, encoding='latin-1') 24 | return f 25 | if omicstype == "proteomics": 26 | stream = pkg_resources.resource_stream(__name__, 'data/proteomics_example.csv') 27 | f = pd.read_csv(stream, index_col=0, encoding='latin-1') 28 | return f 29 | --------------------------------------------------------------------------------