6 |
7 | * Using MeSH:
8 |
--------------------------------------------------------------------------------
/prototypes/shiny_app/abstract_display/app.R:
--------------------------------------------------------------------------------
1 | # Simple application that displays abstracts from EuropePMC
2 |
3 | library(shiny)
4 | library(europepmc)
5 |
6 | get_abstract <- function(pmid) {
7 |
8 | api_result <- epmc_details(pmid)
9 | api_result[["basic"]][["abstractText"]]
10 |
11 | }
12 |
13 | ui <- fluidPage(
14 | textInput(inputId = "pmid", value = "32180547", "PMID"),
15 | h2("Abstract:"),
16 | textOutput("abstract"),
17 | )
18 |
19 | server <- function(input, output) {
20 | abstract_text <- eventReactive(input$pmid, {
21 | get_abstract(input$pmid)
22 | })
23 |
24 | output$abstract <- renderText(abstract_text())
25 | }
26 |
27 | shinyApp(ui = ui, server = server)
28 |
--------------------------------------------------------------------------------
/hypothesis_parsing/plot_counts.R:
--------------------------------------------------------------------------------
1 | library(readr)
2 | library(dplyr)
3 | library(urltools)
4 |
5 | annotations <- read.csv("hypothesis_annotations.csv")
6 |
7 |
8 | abstract_annotations <-
9 | annotations %>% dplyr::filter(url != "https://europepmc.org/article/MED/29206104")
10 |
11 |
12 | library(ggplot2)
13 |
14 |
15 |
16 |
17 | abstract_annotations %>%
18 | group_by(url) %>%
19 | count() %>%
20 | ggplot(aes(y = n, x = "abstracts")) +
21 | geom_boxplot()
22 |
23 |
24 | p <- abstract_annotations %>%
25 | group_by(typeLabel) %>%
26 | count() %>%
27 | filter(typeLabel != "") %>%
28 | filter(n > 10) %>%
29 | ggplot(aes(y = n, x = reorder(typeLabel, -n))) +
30 | geom_point() + theme(axis.text.x = element_text(angle = 60, hjust=1))
31 |
32 |
33 | ggsave("test.pdf")
34 | plot(p)
35 | dev.off()
36 |
37 |
38 |
39 |
40 | dev.off()
41 |
42 |
43 |
44 |
--------------------------------------------------------------------------------
/CONTRIBUTING.md:
--------------------------------------------------------------------------------
1 | # So you want to contribute? That is great!
2 |
3 | This is an open project, and we love contributions!
4 |
5 | A good start is contributing with ideas or questions via the [issues page](https://github.com/lubianat/annotate_them_all/issues).
6 |
7 | * Are you in the eLife Sprint 2020? Let me know at [issue #1](https://github.com/lubianat/annotate_them_all/issues/1) and I add you as a colaborator right away.
8 | * **Be bold** and contribute however you can.
9 | * Adding an issue? Please mark it with labels.
10 | * Making a commit? Take a quick look at [this post](https://chris.beams.io/posts/git-commit/) on how to write a good commit message :)
11 |
12 | For code in Python, let's try and follow [PEP8](https://pybit.es/pep8.html) standards.
13 | For code in R, let's try and follow the [tidyverse style guide](https://style.tidyverse.org/).
14 |
15 | At this stage, everything is a prototype, so feel free to make pull requests and commit directly to the master branch.
16 |
--------------------------------------------------------------------------------
/hypothesis_parsing/render_SPARQL_visualization.R:
--------------------------------------------------------------------------------
1 | library(readr)
2 | library(dplyr)
3 | library(urltools)
4 | annotations <- read.csv("hypothesis_annotations.csv")
5 |
6 | thymus_annotations <- annotations %>% filter(url == "https://europepmc.org/article/MED/32079746")
7 |
8 | qids = unique(c(thymus_annotations[,"type"], thymus_annotations[,"item"]))
9 |
10 | items <- "{ "
11 | for (i in qids)
12 | {
13 | items <- paste0(items, " wd:", i)
14 | }
15 | items <- paste0(items, " }")
16 | descriptions_query <- paste0(' #defaultView:Graph
17 | SELECT DISTINCT ?item_1 ?item_1Label ?item_2 ?item_2Label
18 | WHERE
19 | {
20 | VALUES ?item_1', items,' .
21 | VALUES ?item_2', items,' .
22 |
23 | {?item_1 ?p ?item_2 .}
24 |
25 |
26 | SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". }
27 | }')
28 |
29 | url = paste0("https://query.wikidata.org/#",url_encode(descriptions_query))
30 | print(url)
31 |
32 |
33 |
34 |
35 |
36 |
37 |
38 |
39 |
40 |
41 |
42 |
--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
1 | # Annotate Them All eLife Sprint 2020
2 | A repository for brainstorming and prototyping ideas related to the eLifeSprint project [Annotate Them All](https://sprint.elifesciences.org/annotate-them-all/)
3 |
4 | Want to know more about it? Check our [preprint/report](https://zenodo.org/record/4279611#.X7VqBXVKgQY) !
5 |
6 | # So you want to contribute? That is great!
7 |
8 | This is an open project, and we love contributions!
9 |
10 | A good start is contributing with ideas or questions via the [issues page](https://github.com/lubianat/annotate_them_all/issues).
11 |
12 | * **Be bold** and contribute however you can.
13 | * Adding an issue? Please mark it with labels.
14 | * Making a commit? Take a quick look at [this post](https://chris.beams.io/posts/git-commit/) on how to write a good commit message :)
15 |
16 | For code in Python, let's try and follow [PEP8](https://pybit.es/pep8.html) standards.
17 | For code in R, let's try and follow the [tidyverse style guide](https://style.tidyverse.org/).
18 |
19 | At this stage, everything is a prototype, so feel free to make pull requests and commit directly to the master branch.
20 |
--------------------------------------------------------------------------------
/CODE_OF_CONDUCT.md:
--------------------------------------------------------------------------------
1 | # Contributor Covenant Code of Conduct
2 |
3 | ## Our Pledge
4 |
5 | In the interest of fostering an open and welcoming environment, we as
6 | contributors and maintainers pledge to making participation in our project and
7 | our community a harassment-free experience for everyone, regardless of age, body
8 | size, disability, ethnicity, sex characteristics, gender identity and expression,
9 | level of experience, education, socio-economic status, nationality, personal
10 | appearance, race, religion, or sexual identity and orientation.
11 |
12 | ## Our Standards
13 |
14 | Examples of behavior that contributes to creating a positive environment
15 | include:
16 |
17 | * Using welcoming and inclusive language
18 | * Being respectful of differing viewpoints and experiences
19 | * Gracefully accepting constructive criticism
20 | * Focusing on what is best for the community
21 | * Showing empathy towards other community members
22 |
23 | Examples of unacceptable behavior by participants include:
24 |
25 | * The use of sexualized language or imagery and unwelcome sexual attention or
26 | advances
27 | * Trolling, insulting/derogatory comments, and personal or political attacks
28 | * Public or private harassment
29 | * Publishing others' private information, such as a physical or electronic
30 | address, without explicit permission
31 | * Other conduct which could reasonably be considered inappropriate in a
32 | professional setting
33 |
34 | ## Our Responsibilities
35 |
36 | Project maintainers are responsible for clarifying the standards of acceptable
37 | behavior and are expected to take appropriate and fair corrective action in
38 | response to any instances of unacceptable behavior.
39 |
40 | Project maintainers have the right and responsibility to remove, edit, or
41 | reject comments, commits, code, wiki edits, issues, and other contributions
42 | that are not aligned to this Code of Conduct, or to ban temporarily or
43 | permanently any contributor for other behaviors that they deem inappropriate,
44 | threatening, offensive, or harmful.
45 |
46 | ## Scope
47 |
48 | This Code of Conduct applies both within project spaces and in public spaces
49 | when an individual is representing the project or its community. Examples of
50 | representing a project or community include using an official project e-mail
51 | address, posting via an official social media account, or acting as an appointed
52 | representative at an online or offline event. Representation of a project may be
53 | further defined and clarified by project maintainers.
54 |
55 | ## Enforcement
56 |
57 | Instances of abusive, harassing, or otherwise unacceptable behavior may be
58 | reported by contacting the project team at tiago.lubiana.alves@usp.br. All
59 | complaints will be reviewed and investigated and will result in a response that
60 | is deemed necessary and appropriate to the circumstances. The project team is
61 | obligated to maintain confidentiality with regard to the reporter of an incident.
62 | Further details of specific enforcement policies may be posted separately.
63 |
64 | Project maintainers who do not follow or enforce the Code of Conduct in good
65 | faith may face temporary or permanent repercussions as determined by other
66 | members of the project's leadership.
67 |
68 | ## Attribution
69 |
70 | This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
71 | available at https://www.contributor-covenant.org/version/1/4/code-of-conduct.html
72 |
73 | [homepage]: https://www.contributor-covenant.org
74 |
75 | For answers to common questions about this code of conduct, see
76 | https://www.contributor-covenant.org/faq
77 |
--------------------------------------------------------------------------------
/.gitignore:
--------------------------------------------------------------------------------
1 | ### Linux ###
2 | *~
3 |
4 | # temporary files which can be created if a process still has a handle open of a deleted file
5 | .fuse_hidden*
6 |
7 | # KDE directory preferences
8 | .directory
9 |
10 | # Linux trash folder which might appear on any partition or disk
11 | .Trash-*
12 |
13 | # .nfs files are created when an open file is removed but is still being accessed
14 | .nfs*
15 |
16 | ### Python ###
17 | # Byte-compiled / optimized / DLL files
18 | __pycache__/
19 | *.py[cod]
20 | *$py.class
21 |
22 | # C extensions
23 | *.so
24 |
25 | # Distribution / packaging
26 | .Python
27 | build/
28 | develop-eggs/
29 | dist/
30 | downloads/
31 | eggs/
32 | .eggs/
33 | lib/
34 | lib64/
35 | parts/
36 | sdist/
37 | var/
38 | wheels/
39 | pip-wheel-metadata/
40 | share/python-wheels/
41 | *.egg-info/
42 | .installed.cfg
43 | *.egg
44 | MANIFEST
45 |
46 | # PyInstaller
47 | # Usually these files are written by a python script from a template
48 | # before PyInstaller builds the exe, so as to inject date/other infos into it.
49 | *.manifest
50 | *.spec
51 |
52 | # Installer logs
53 | pip-log.txt
54 | pip-delete-this-directory.txt
55 |
56 | # Unit test / coverage reports
57 | htmlcov/
58 | .tox/
59 | .nox/
60 | .coverage
61 | .coverage.*
62 | .cache
63 | nosetests.xml
64 | coverage.xml
65 | *.cover
66 | *.py,cover
67 | .hypothesis/
68 | .pytest_cache/
69 | pytestdebug.log
70 |
71 | # Translations
72 | *.mo
73 | *.pot
74 |
75 | # Django stuff:
76 | *.log
77 | local_settings.py
78 | db.sqlite3
79 | db.sqlite3-journal
80 |
81 | # Flask stuff:
82 | instance/
83 | .webassets-cache
84 |
85 | # Scrapy stuff:
86 | .scrapy
87 |
88 | # Sphinx documentation
89 | docs/_build/
90 | doc/_build/
91 |
92 | # PyBuilder
93 | target/
94 |
95 | # Jupyter Notebook
96 | .ipynb_checkpoints
97 |
98 | # IPython
99 | profile_default/
100 | ipython_config.py
101 |
102 | # pyenv
103 | .python-version
104 |
105 | # pipenv
106 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
107 | # However, in case of collaboration, if having platform-specific dependencies or dependencies
108 | # having no cross-platform support, pipenv may install dependencies that don't work, or not
109 | # install all needed dependencies.
110 | #Pipfile.lock
111 |
112 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow
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 | pythonenv*
131 |
132 | # Spyder project settings
133 | .spyderproject
134 | .spyproject
135 |
136 | # Rope project settings
137 | .ropeproject
138 |
139 | # mkdocs documentation
140 | /site
141 |
142 | # mypy
143 | .mypy_cache/
144 | .dmypy.json
145 | dmypy.json
146 |
147 | # Pyre type checker
148 | .pyre/
149 |
150 | # pytype static type analyzer
151 | .pytype/
152 |
153 | # profiling data
154 | .prof
155 |
156 | ### R ###
157 | # History files
158 | .Rhistory
159 | .Rapp.history
160 |
161 | # Session Data files
162 | .RData
163 |
164 | # User-specific files
165 | .Ruserdata
166 |
167 | # Example code in package build process
168 | *-Ex.R
169 |
170 | # Output files from R CMD build
171 | /*.tar.gz
172 |
173 | # Output files from R CMD check
174 | /*.Rcheck/
175 |
176 | # RStudio files
177 | .Rproj.user/
178 |
179 | # produced vignettes
180 | vignettes/*.html
181 | vignettes/*.pdf
182 |
183 | # OAuth2 token, see https://github.com/hadley/httr/releases/tag/v0.3
184 | .httr-oauth
185 |
186 | # knitr and R markdown default cache directories
187 | *_cache/
188 | /cache/
189 |
190 | # Temporary files created by R markdown
191 | *.utf8.md
192 | *.knit.md
193 |
194 | # R Environment Variables
195 | .Renviron
196 |
197 | ### R.Bookdown Stack ###
198 | # R package: bookdown caching files
199 | /*_files/
200 |
201 | ### VisualStudioCode ###
202 | .vscode/*
203 | !.vscode/settings.json
204 | !.vscode/tasks.json
205 | !.vscode/launch.json
206 | !.vscode/extensions.json
207 | *.code-workspace
208 |
209 | ### VisualStudioCode Patch ###
210 | # Ignore all local history of files
211 | .history
212 | .ionide
213 |
214 |
--------------------------------------------------------------------------------
/prototypes/shiny_app/abstract_display/renv.lock:
--------------------------------------------------------------------------------
1 | {
2 | "R": {
3 | "Version": "4.0.0",
4 | "Repositories": [
5 | {
6 | "Name": "CRAN",
7 | "URL": "https://cloud.r-project.org"
8 | }
9 | ]
10 | },
11 | "Packages": {
12 | "BH": {
13 | "Package": "BH",
14 | "Version": "1.72.0-3",
15 | "Source": "Repository",
16 | "Repository": "CRAN",
17 | "Hash": "8f9ce74c6417d61f0782cbae5fd2b7b0"
18 | },
19 | "R6": {
20 | "Package": "R6",
21 | "Version": "2.4.1",
22 | "Source": "Repository",
23 | "Repository": "CRAN",
24 | "Hash": "292b54f8f4b94669b08f94e5acce6be2"
25 | },
26 | "Rcpp": {
27 | "Package": "Rcpp",
28 | "Version": "1.0.4.6",
29 | "Source": "Repository",
30 | "Repository": "CRAN",
31 | "Hash": "e652f23d8b1807cc975c51410d05b72f"
32 | },
33 | "askpass": {
34 | "Package": "askpass",
35 | "Version": "1.1",
36 | "Source": "Repository",
37 | "Repository": "CRAN",
38 | "Hash": "e8a22846fff485f0be3770c2da758713"
39 | },
40 | "assertthat": {
41 | "Package": "assertthat",
42 | "Version": "0.2.1",
43 | "Source": "Repository",
44 | "Repository": "CRAN",
45 | "Hash": "50c838a310445e954bc13f26f26a6ecf"
46 | },
47 | "base64enc": {
48 | "Package": "base64enc",
49 | "Version": "0.1-3",
50 | "Source": "Repository",
51 | "Repository": "CRAN",
52 | "Hash": "543776ae6848fde2f48ff3816d0628bc"
53 | },
54 | "cli": {
55 | "Package": "cli",
56 | "Version": "2.0.2",
57 | "Source": "Repository",
58 | "Repository": "CRAN",
59 | "Hash": "ff0becff7bfdfe3f75d29aff8f3172dd"
60 | },
61 | "crayon": {
62 | "Package": "crayon",
63 | "Version": "1.3.4",
64 | "Source": "Repository",
65 | "Repository": "CRAN",
66 | "Hash": "0d57bc8e27b7ba9e45dba825ebc0de6b"
67 | },
68 | "curl": {
69 | "Package": "curl",
70 | "Version": "4.3",
71 | "Source": "Repository",
72 | "Repository": "CRAN",
73 | "Hash": "2b7d10581cc730804e9ed178c8374bd6"
74 | },
75 | "digest": {
76 | "Package": "digest",
77 | "Version": "0.6.25",
78 | "Source": "Repository",
79 | "Repository": "CRAN",
80 | "Hash": "f697db7d92b7028c4b3436e9603fb636"
81 | },
82 | "dplyr": {
83 | "Package": "dplyr",
84 | "Version": "1.0.0",
85 | "Source": "Repository",
86 | "Repository": "CRAN",
87 | "Hash": "4011f62581a34080e44105d4aa05a97f"
88 | },
89 | "ellipsis": {
90 | "Package": "ellipsis",
91 | "Version": "0.3.1",
92 | "Source": "Repository",
93 | "Repository": "CRAN",
94 | "Hash": "fd2844b3a43ae2d27e70ece2df1b4e2a"
95 | },
96 | "europepmc": {
97 | "Package": "europepmc",
98 | "Version": "0.4",
99 | "Source": "Repository",
100 | "Repository": "CRAN",
101 | "Hash": "69b8843c951bab927f80e101fa268002"
102 | },
103 | "fansi": {
104 | "Package": "fansi",
105 | "Version": "0.4.1",
106 | "Source": "Repository",
107 | "Repository": "CRAN",
108 | "Hash": "7fce217eaaf8016e72065e85c73027b5"
109 | },
110 | "fastmap": {
111 | "Package": "fastmap",
112 | "Version": "1.0.1",
113 | "Source": "Repository",
114 | "Repository": "CRAN",
115 | "Hash": "83ab58a0518afe3d17e41da01af13b60"
116 | },
117 | "generics": {
118 | "Package": "generics",
119 | "Version": "0.0.2",
120 | "Source": "Repository",
121 | "Repository": "CRAN",
122 | "Hash": "b8cff1d1391fd1ad8b65877f4c7f2e53"
123 | },
124 | "glue": {
125 | "Package": "glue",
126 | "Version": "1.4.1",
127 | "Source": "Repository",
128 | "Repository": "CRAN",
129 | "Hash": "f43e0d5e85ccb0a4045670c0607ee504"
130 | },
131 | "hms": {
132 | "Package": "hms",
133 | "Version": "0.5.3",
134 | "Source": "Repository",
135 | "Repository": "CRAN",
136 | "Hash": "726671f634529d470545f9fd1a9d1869"
137 | },
138 | "htmltools": {
139 | "Package": "htmltools",
140 | "Version": "0.5.0",
141 | "Source": "Repository",
142 | "Repository": "CRAN",
143 | "Hash": "7d651b7131794fe007b1ad6f21aaa401"
144 | },
145 | "httpuv": {
146 | "Package": "httpuv",
147 | "Version": "1.5.4",
148 | "Source": "Repository",
149 | "Repository": "CRAN",
150 | "Hash": "4e6dabb220b006ccdc3b3b5ff993b205"
151 | },
152 | "httr": {
153 | "Package": "httr",
154 | "Version": "1.4.1",
155 | "Source": "Repository",
156 | "Repository": "CRAN",
157 | "Hash": "7146fea4685b4252ebf478978c75f597"
158 | },
159 | "jsonlite": {
160 | "Package": "jsonlite",
161 | "Version": "1.6.1",
162 | "Source": "Repository",
163 | "Repository": "CRAN",
164 | "Hash": "84b0ee361e2f78d6b7d670db9471c0c5"
165 | },
166 | "later": {
167 | "Package": "later",
168 | "Version": "1.1.0.1",
169 | "Source": "Repository",
170 | "Repository": "CRAN",
171 | "Hash": "d0a62b247165aabf397fded504660d8a"
172 | },
173 | "lifecycle": {
174 | "Package": "lifecycle",
175 | "Version": "0.2.0",
176 | "Source": "Repository",
177 | "Repository": "CRAN",
178 | "Hash": "361811f31f71f8a617a9a68bf63f1f42"
179 | },
180 | "magrittr": {
181 | "Package": "magrittr",
182 | "Version": "1.5",
183 | "Source": "Repository",
184 | "Repository": "CRAN",
185 | "Hash": "1bb58822a20301cee84a41678e25d9b7"
186 | },
187 | "mime": {
188 | "Package": "mime",
189 | "Version": "0.9",
190 | "Source": "Repository",
191 | "Repository": "CRAN",
192 | "Hash": "e87a35ec73b157552814869f45a63aa3"
193 | },
194 | "openssl": {
195 | "Package": "openssl",
196 | "Version": "1.4.1",
197 | "Source": "Repository",
198 | "Repository": "CRAN",
199 | "Hash": "49f7258fd86ebeaea1df24d9ded00478"
200 | },
201 | "pillar": {
202 | "Package": "pillar",
203 | "Version": "1.4.6",
204 | "Source": "Repository",
205 | "Repository": "CRAN",
206 | "Hash": "bdf26e55ccb7df3e49a490150277f002"
207 | },
208 | "pkgconfig": {
209 | "Package": "pkgconfig",
210 | "Version": "2.0.3",
211 | "Source": "Repository",
212 | "Repository": "CRAN",
213 | "Hash": "01f28d4278f15c76cddbea05899c5d6f"
214 | },
215 | "plyr": {
216 | "Package": "plyr",
217 | "Version": "1.8.6",
218 | "Source": "Repository",
219 | "Repository": "CRAN",
220 | "Hash": "ec0e5ab4e5f851f6ef32cd1d1984957f"
221 | },
222 | "prettyunits": {
223 | "Package": "prettyunits",
224 | "Version": "1.1.1",
225 | "Source": "Repository",
226 | "Repository": "CRAN",
227 | "Hash": "95ef9167b75dde9d2ccc3c7528393e7e"
228 | },
229 | "progress": {
230 | "Package": "progress",
231 | "Version": "1.2.2",
232 | "Source": "Repository",
233 | "Repository": "CRAN",
234 | "Hash": "14dc9f7a3c91ebb14ec5bb9208a07061"
235 | },
236 | "promises": {
237 | "Package": "promises",
238 | "Version": "1.1.1",
239 | "Source": "Repository",
240 | "Repository": "CRAN",
241 | "Hash": "a8730dcbdd19f9047774909f0ec214a4"
242 | },
243 | "purrr": {
244 | "Package": "purrr",
245 | "Version": "0.3.4",
246 | "Source": "Repository",
247 | "Repository": "CRAN",
248 | "Hash": "97def703420c8ab10d8f0e6c72101e02"
249 | },
250 | "renv": {
251 | "Package": "renv",
252 | "Version": "0.10.0-28",
253 | "Source": "GitHub",
254 | "RemoteType": "github",
255 | "RemoteHost": "api.github.com",
256 | "RemoteRepo": "renv",
257 | "RemoteUsername": "rstudio",
258 | "RemoteRef": "master",
259 | "RemoteSha": "2359f9356dfe3295c3a347504523de74207f1696",
260 | "Hash": "4128b3662ea1ea51644e3b2cd7d29f0c"
261 | },
262 | "rlang": {
263 | "Package": "rlang",
264 | "Version": "0.4.7",
265 | "Source": "Repository",
266 | "Repository": "CRAN",
267 | "Hash": "c06d2a6887f4b414f8e927afd9ee976a"
268 | },
269 | "shiny": {
270 | "Package": "shiny",
271 | "Version": "1.4.0.2",
272 | "Source": "Repository",
273 | "Repository": "CRAN",
274 | "Hash": "a56d058adfc9df30bdd45dbb01cec39f"
275 | },
276 | "sourcetools": {
277 | "Package": "sourcetools",
278 | "Version": "0.1.7",
279 | "Source": "Repository",
280 | "Repository": "CRAN",
281 | "Hash": "947e4e02a79effa5d512473e10f41797"
282 | },
283 | "stringi": {
284 | "Package": "stringi",
285 | "Version": "1.4.6",
286 | "Source": "Repository",
287 | "Repository": "CRAN",
288 | "Hash": "e99d8d656980d2dd416a962ae55aec90"
289 | },
290 | "sys": {
291 | "Package": "sys",
292 | "Version": "3.3",
293 | "Source": "Repository",
294 | "Repository": "CRAN",
295 | "Hash": "507f3116a38d37ad330a038b3be07b66"
296 | },
297 | "tibble": {
298 | "Package": "tibble",
299 | "Version": "3.0.3",
300 | "Source": "Repository",
301 | "Repository": "CRAN",
302 | "Hash": "08bd36bd34b20d4f7971d49e81deaab0"
303 | },
304 | "tidyr": {
305 | "Package": "tidyr",
306 | "Version": "1.1.0",
307 | "Source": "Repository",
308 | "Repository": "CRAN",
309 | "Hash": "7395a05640bf91502dd475a84008d87e"
310 | },
311 | "tidyselect": {
312 | "Package": "tidyselect",
313 | "Version": "1.1.0",
314 | "Source": "Repository",
315 | "Repository": "CRAN",
316 | "Hash": "6ea435c354e8448819627cf686f66e0a"
317 | },
318 | "triebeard": {
319 | "Package": "triebeard",
320 | "Version": "0.3.0",
321 | "Source": "Repository",
322 | "Repository": "CRAN",
323 | "Hash": "847a9d113b78baca4a9a8639609ea228"
324 | },
325 | "urltools": {
326 | "Package": "urltools",
327 | "Version": "1.7.3",
328 | "Source": "Repository",
329 | "Repository": "CRAN",
330 | "Hash": "e86a704261a105f4703f653e05defa3e"
331 | },
332 | "utf8": {
333 | "Package": "utf8",
334 | "Version": "1.1.4",
335 | "Source": "Repository",
336 | "Repository": "CRAN",
337 | "Hash": "4a5081acfb7b81a572e4384a7aaf2af1"
338 | },
339 | "vctrs": {
340 | "Package": "vctrs",
341 | "Version": "0.3.1",
342 | "Source": "Repository",
343 | "Repository": "CRAN",
344 | "Hash": "1739235995f08583db4095a28c357207"
345 | },
346 | "xml2": {
347 | "Package": "xml2",
348 | "Version": "1.3.2",
349 | "Source": "Repository",
350 | "Repository": "CRAN",
351 | "Hash": "d4d71a75dd3ea9eb5fa28cc21f9585e2"
352 | },
353 | "xtable": {
354 | "Package": "xtable",
355 | "Version": "1.8-4",
356 | "Source": "Repository",
357 | "Repository": "CRAN",
358 | "Hash": "b8acdf8af494d9ec19ccb2481a9b11c2"
359 | }
360 | }
361 | }
362 |
--------------------------------------------------------------------------------
/prototypes/shiny_app/abstract_display/renv/activate.R:
--------------------------------------------------------------------------------
1 |
2 | local({
3 |
4 | # the requested version of renv
5 | version <- "0.10.0-28"
6 |
7 | # the project directory
8 | project <- getwd()
9 |
10 | # avoid recursion
11 | if (!is.na(Sys.getenv("RENV_R_INITIALIZING", unset = NA)))
12 | return(invisible(TRUE))
13 |
14 | # signal that we're loading renv during R startup
15 | Sys.setenv("RENV_R_INITIALIZING" = "true")
16 | on.exit(Sys.unsetenv("RENV_R_INITIALIZING"), add = TRUE)
17 |
18 | # signal that we've consented to use renv
19 | options(renv.consent = TRUE)
20 |
21 | # load the 'utils' package eagerly -- this ensures that renv shims, which
22 | # mask 'utils' packages, will come first on the search path
23 | library(utils, lib.loc = .Library)
24 |
25 | # check to see if renv has already been loaded
26 | if ("renv" %in% loadedNamespaces()) {
27 |
28 | # if renv has already been loaded, and it's the requested version of renv,
29 | # nothing to do
30 | spec <- .getNamespaceInfo(.getNamespace("renv"), "spec")
31 | if (identical(spec[["version"]], version))
32 | return(invisible(TRUE))
33 |
34 | # otherwise, unload and attempt to load the correct version of renv
35 | unloadNamespace("renv")
36 |
37 | }
38 |
39 | # load bootstrap tools
40 | bootstrap <- function(version, library) {
41 |
42 | # read repos (respecting override if set)
43 | repos <- Sys.getenv("RENV_CONFIG_REPOS_OVERRIDE", unset = NA)
44 | if (is.na(repos))
45 | repos <- getOption("repos")
46 |
47 | # fix up repos
48 | on.exit(options(repos = repos), add = TRUE)
49 | repos[repos == "@CRAN@"] <- "https://cloud.r-project.org"
50 | options(repos = repos)
51 |
52 | # attempt to download renv
53 | tarball <- tryCatch(renv_bootstrap_download(version), error = identity)
54 | if (inherits(tarball, "error"))
55 | stop("failed to download renv ", version)
56 |
57 | # now attempt to install
58 | status <- tryCatch(renv_bootstrap_install(version, tarball, library), error = identity)
59 | if (inherits(status, "error"))
60 | stop("failed to install renv ", version)
61 |
62 | }
63 |
64 | renv_bootstrap_download_impl <- function(url, destfile) {
65 |
66 | mode <- "wb"
67 |
68 | # https://bugs.r-project.org/bugzilla/show_bug.cgi?id=17715
69 | fixup <-
70 | Sys.info()[["sysname"]] == "Windows" &&
71 | substring(url, 1L, 5L) == "file:"
72 |
73 | if (fixup)
74 | mode <- "w+b"
75 |
76 | download.file(
77 | url = url,
78 | destfile = destfile,
79 | mode = mode,
80 | quiet = TRUE
81 | )
82 |
83 | }
84 |
85 | renv_bootstrap_download <- function(version) {
86 |
87 | methods <- list(
88 | renv_bootstrap_download_cran_latest,
89 | renv_bootstrap_download_cran_archive,
90 | renv_bootstrap_download_github
91 | )
92 |
93 | for (method in methods) {
94 | path <- tryCatch(method(version), error = identity)
95 | if (is.character(path) && file.exists(path))
96 | return(path)
97 | }
98 |
99 | stop("failed to download renv ", version)
100 |
101 | }
102 |
103 | renv_bootstrap_download_cran_latest <- function(version) {
104 |
105 | # check for renv on CRAN matching this version
106 | db <- as.data.frame(available.packages(), stringsAsFactors = FALSE)
107 |
108 | entry <- db[db$Package %in% "renv" & db$Version %in% version, ]
109 | if (nrow(entry) == 0) {
110 | fmt <- "renv %s is not available from your declared package repositories"
111 | stop(sprintf(fmt, version))
112 | }
113 |
114 | message("* Downloading renv ", version, " from CRAN ... ", appendLF = FALSE)
115 |
116 | info <- tryCatch(
117 | download.packages("renv", destdir = tempdir()),
118 | condition = identity
119 | )
120 |
121 | if (inherits(info, "condition")) {
122 | message("FAILED")
123 | return(FALSE)
124 | }
125 |
126 | message("OK")
127 | info[1, 2]
128 |
129 | }
130 |
131 | renv_bootstrap_download_cran_archive <- function(version) {
132 |
133 | name <- sprintf("renv_%s.tar.gz", version)
134 | repos <- getOption("repos")
135 | urls <- file.path(repos, "src/contrib/Archive/renv", name)
136 | destfile <- file.path(tempdir(), name)
137 |
138 | message("* Downloading renv ", version, " from CRAN archive ... ", appendLF = FALSE)
139 |
140 | for (url in urls) {
141 |
142 | status <- tryCatch(
143 | renv_bootstrap_download_impl(url, destfile),
144 | condition = identity
145 | )
146 |
147 | if (identical(status, 0L)) {
148 | message("OK")
149 | return(destfile)
150 | }
151 |
152 | }
153 |
154 | message("FAILED")
155 | return(FALSE)
156 |
157 | }
158 |
159 | renv_bootstrap_download_github <- function(version) {
160 |
161 | enabled <- Sys.getenv("RENV_BOOTSTRAP_FROM_GITHUB", unset = "TRUE")
162 | if (!identical(enabled, "TRUE"))
163 | return(FALSE)
164 |
165 | # prepare download options
166 | pat <- Sys.getenv("GITHUB_PAT")
167 | if (nzchar(Sys.which("curl")) && nzchar(pat)) {
168 | fmt <- "--location --fail --header \"Authorization: token %s\""
169 | extra <- sprintf(fmt, pat)
170 | saved <- options("download.file.method", "download.file.extra")
171 | options(download.file.method = "curl", download.file.extra = extra)
172 | on.exit(do.call(base::options, saved), add = TRUE)
173 | } else if (nzchar(Sys.which("wget")) && nzchar(pat)) {
174 | fmt <- "--header=\"Authorization: token %s\""
175 | extra <- sprintf(fmt, pat)
176 | saved <- options("download.file.method", "download.file.extra")
177 | options(download.file.method = "wget", download.file.extra = extra)
178 | on.exit(do.call(base::options, saved), add = TRUE)
179 | }
180 |
181 | message("* Downloading renv ", version, " from GitHub ... ", appendLF = FALSE)
182 |
183 | url <- file.path("https://api.github.com/repos/rstudio/renv/tarball", version)
184 | name <- sprintf("renv_%s.tar.gz", version)
185 | destfile <- file.path(tempdir(), name)
186 |
187 | status <- tryCatch(
188 | renv_bootstrap_download_impl(url, destfile),
189 | condition = identity
190 | )
191 |
192 | if (!identical(status, 0L)) {
193 | message("FAILED")
194 | return(FALSE)
195 | }
196 |
197 | message("Done!")
198 | return(destfile)
199 |
200 | }
201 |
202 | renv_bootstrap_install <- function(version, tarball, library) {
203 |
204 | # attempt to install it into project library
205 | message("* Installing renv ", version, " ... ", appendLF = FALSE)
206 | dir.create(library, showWarnings = FALSE, recursive = TRUE)
207 |
208 | # invoke using system2 so we can capture and report output
209 | bin <- R.home("bin")
210 | exe <- if (Sys.info()[["sysname"]] == "Windows") "R.exe" else "R"
211 | r <- file.path(bin, exe)
212 | args <- c("--vanilla", "CMD", "INSTALL", "-l", shQuote(library), shQuote(tarball))
213 | output <- system2(r, args, stdout = TRUE, stderr = TRUE)
214 | message("Done!")
215 |
216 | # check for successful install
217 | status <- attr(output, "status")
218 | if (is.numeric(status) && !identical(status, 0L)) {
219 | header <- "Error installing renv:"
220 | lines <- paste(rep.int("=", nchar(header)), collapse = "")
221 | text <- c(header, lines, output)
222 | writeLines(text, con = stderr())
223 | }
224 |
225 | status
226 |
227 | }
228 |
229 | renv_bootstrap_prefix <- function() {
230 |
231 | # construct version prefix
232 | version <- paste(R.version$major, R.version$minor, sep = ".")
233 | prefix <- paste("R", numeric_version(version)[1, 1:2], sep = "-")
234 |
235 | # include SVN revision for development versions of R
236 | # (to avoid sharing platform-specific artefacts with released versions of R)
237 | devel <-
238 | identical(R.version[["status"]], "Under development (unstable)") ||
239 | identical(R.version[["nickname"]], "Unsuffered Consequences")
240 |
241 | if (devel)
242 | prefix <- paste(prefix, R.version[["svn rev"]], sep = "-r")
243 |
244 | # build list of path components
245 | components <- c(prefix, R.version$platform)
246 |
247 | # include prefix if provided by user
248 | prefix <- Sys.getenv("RENV_PATHS_PREFIX")
249 | if (nzchar(prefix))
250 | components <- c(prefix, components)
251 |
252 | # build prefix
253 | paste(components, collapse = "/")
254 |
255 | }
256 |
257 | renv_bootstrap_library_root <- function(project) {
258 |
259 | path <- Sys.getenv("RENV_PATHS_LIBRARY", unset = NA)
260 | if (!is.na(path))
261 | return(path)
262 |
263 | path <- Sys.getenv("RENV_PATHS_LIBRARY_ROOT", unset = NA)
264 | if (!is.na(path))
265 | return(file.path(path, basename(project)))
266 |
267 | file.path(project, "renv/library")
268 |
269 | }
270 |
271 | renv_bootstrap_validate_version <- function(version) {
272 |
273 | loadedversion <- utils::packageDescription("renv", fields = "Version")
274 | if (version == loadedversion)
275 | return(TRUE)
276 |
277 | # assume four-component versions are from GitHub; three-component
278 | # versions are from CRAN
279 | components <- strsplit(loadedversion, "[.-]")[[1]]
280 | remote <- if (length(components) == 4L)
281 | paste("rstudio/renv", loadedversion, sep = "@")
282 | else
283 | paste("renv", loadedversion, sep = "@")
284 |
285 | fmt <- paste(
286 | "renv %1$s was loaded from project library, but renv %2$s is recorded in lockfile.",
287 | "Use `renv::record(\"%3$s\")` to record this version in the lockfile.",
288 | "Use `renv::restore(packages = \"renv\")` to install renv %2$s into the project library.",
289 | sep = "\n"
290 | )
291 |
292 | msg <- sprintf(fmt, loadedversion, version, remote)
293 | warning(msg, call. = FALSE)
294 |
295 | FALSE
296 |
297 | }
298 |
299 | renv_bootstrap_load <- function(project, libpath, version) {
300 |
301 | # try to load renv from the project library
302 | if (!requireNamespace("renv", lib.loc = libpath, quietly = TRUE))
303 | return(FALSE)
304 |
305 | # warn if the version of renv loaded does not match
306 | renv_bootstrap_validate_version(version)
307 |
308 | # load the project
309 | renv::load(project)
310 |
311 | TRUE
312 |
313 | }
314 |
315 | # construct path to library root
316 | root <- renv_bootstrap_library_root(project)
317 |
318 | # construct library prefix for platform
319 | prefix <- renv_bootstrap_prefix()
320 |
321 | # construct full libpath
322 | libpath <- file.path(root, prefix)
323 |
324 | # attempt to load
325 | if (renv_bootstrap_load(project, libpath, version))
326 | return(TRUE)
327 |
328 | # load failed; attempt to bootstrap
329 | bootstrap(version, libpath)
330 |
331 | # exit early if we're just testing bootstrap
332 | if (!is.na(Sys.getenv("RENV_BOOTSTRAP_INSTALL_ONLY", unset = NA)))
333 | return(TRUE)
334 |
335 | # try again to load
336 | if (requireNamespace("renv", lib.loc = libpath, quietly = TRUE)) {
337 | message("Successfully installed and loaded renv ", version, ".")
338 | return(renv::load())
339 | }
340 |
341 | # failed to download or load renv; warn the user
342 | msg <- c(
343 | "Failed to find an renv installation: the project will not be loaded.",
344 | "Use `renv::activate()` to re-initialize the project."
345 | )
346 |
347 | warning(paste(msg, collapse = "\n"), call. = FALSE)
348 |
349 | })
350 |
--------------------------------------------------------------------------------
/LICENSE:
--------------------------------------------------------------------------------
1 | Apache License
2 | Version 2.0, January 2004
3 | http://www.apache.org/licenses/
4 |
5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
6 |
7 | 1. Definitions.
8 |
9 | "License" shall mean the terms and conditions for use, reproduction,
10 | and distribution as defined by Sections 1 through 9 of this document.
11 |
12 | "Licensor" shall mean the copyright owner or entity authorized by
13 | the copyright owner that is granting the License.
14 |
15 | "Legal Entity" shall mean the union of the acting entity and all
16 | other entities that control, are controlled by, or are under common
17 | control with that entity. For the purposes of this definition,
18 | "control" means (i) the power, direct or indirect, to cause the
19 | direction or management of such entity, whether by contract or
20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the
21 | outstanding shares, or (iii) beneficial ownership of such entity.
22 |
23 | "You" (or "Your") shall mean an individual or Legal Entity
24 | exercising permissions granted by this License.
25 |
26 | "Source" form shall mean the preferred form for making modifications,
27 | including but not limited to software source code, documentation
28 | source, and configuration files.
29 |
30 | "Object" form shall mean any form resulting from mechanical
31 | transformation or translation of a Source form, including but
32 | not limited to compiled object code, generated documentation,
33 | and conversions to other media types.
34 |
35 | "Work" shall mean the work of authorship, whether in Source or
36 | Object form, made available under the License, as indicated by a
37 | copyright notice that is included in or attached to the work
38 | (an example is provided in the Appendix below).
39 |
40 | "Derivative Works" shall mean any work, whether in Source or Object
41 | form, that is based on (or derived from) the Work and for which the
42 | editorial revisions, annotations, elaborations, or other modifications
43 | represent, as a whole, an original work of authorship. For the purposes
44 | of this License, Derivative Works shall not include works that remain
45 | separable from, or merely link (or bind by name) to the interfaces of,
46 | the Work and Derivative Works thereof.
47 |
48 | "Contribution" shall mean any work of authorship, including
49 | the original version of the Work and any modifications or additions
50 | to that Work or Derivative Works thereof, that is intentionally
51 | submitted to Licensor for inclusion in the Work by the copyright owner
52 | or by an individual or Legal Entity authorized to submit on behalf of
53 | the copyright owner. For the purposes of this definition, "submitted"
54 | means any form of electronic, verbal, or written communication sent
55 | to the Licensor or its representatives, including but not limited to
56 | communication on electronic mailing lists, source code control systems,
57 | and issue tracking systems that are managed by, or on behalf of, the
58 | Licensor for the purpose of discussing and improving the Work, but
59 | excluding communication that is conspicuously marked or otherwise
60 | designated in writing by the copyright owner as "Not a Contribution."
61 |
62 | "Contributor" shall mean Licensor and any individual or Legal Entity
63 | on behalf of whom a Contribution has been received by Licensor and
64 | subsequently incorporated within the Work.
65 |
66 | 2. Grant of Copyright License. Subject to the terms and conditions of
67 | this License, each Contributor hereby grants to You a perpetual,
68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable
69 | copyright license to reproduce, prepare Derivative Works of,
70 | publicly display, publicly perform, sublicense, and distribute the
71 | Work and such Derivative Works in Source or Object form.
72 |
73 | 3. Grant of Patent License. Subject to the terms and conditions of
74 | this License, each Contributor hereby grants to You a perpetual,
75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable
76 | (except as stated in this section) patent license to make, have made,
77 | use, offer to sell, sell, import, and otherwise transfer the Work,
78 | where such license applies only to those patent claims licensable
79 | by such Contributor that are necessarily infringed by their
80 | Contribution(s) alone or by combination of their Contribution(s)
81 | with the Work to which such Contribution(s) was submitted. If You
82 | institute patent litigation against any entity (including a
83 | cross-claim or counterclaim in a lawsuit) alleging that the Work
84 | or a Contribution incorporated within the Work constitutes direct
85 | or contributory patent infringement, then any patent licenses
86 | granted to You under this License for that Work shall terminate
87 | as of the date such litigation is filed.
88 |
89 | 4. Redistribution. You may reproduce and distribute copies of the
90 | Work or Derivative Works thereof in any medium, with or without
91 | modifications, and in Source or Object form, provided that You
92 | meet the following conditions:
93 |
94 | (a) You must give any other recipients of the Work or
95 | Derivative Works a copy of this License; and
96 |
97 | (b) You must cause any modified files to carry prominent notices
98 | stating that You changed the files; and
99 |
100 | (c) You must retain, in the Source form of any Derivative Works
101 | that You distribute, all copyright, patent, trademark, and
102 | attribution notices from the Source form of the Work,
103 | excluding those notices that do not pertain to any part of
104 | the Derivative Works; and
105 |
106 | (d) If the Work includes a "NOTICE" text file as part of its
107 | distribution, then any Derivative Works that You distribute must
108 | include a readable copy of the attribution notices contained
109 | within such NOTICE file, excluding those notices that do not
110 | pertain to any part of the Derivative Works, in at least one
111 | of the following places: within a NOTICE text file distributed
112 | as part of the Derivative Works; within the Source form or
113 | documentation, if provided along with the Derivative Works; or,
114 | within a display generated by the Derivative Works, if and
115 | wherever such third-party notices normally appear. The contents
116 | of the NOTICE file are for informational purposes only and
117 | do not modify the License. You may add Your own attribution
118 | notices within Derivative Works that You distribute, alongside
119 | or as an addendum to the NOTICE text from the Work, provided
120 | that such additional attribution notices cannot be construed
121 | as modifying the License.
122 |
123 | You may add Your own copyright statement to Your modifications and
124 | may provide additional or different license terms and conditions
125 | for use, reproduction, or distribution of Your modifications, or
126 | for any such Derivative Works as a whole, provided Your use,
127 | reproduction, and distribution of the Work otherwise complies with
128 | the conditions stated in this License.
129 |
130 | 5. Submission of Contributions. Unless You explicitly state otherwise,
131 | any Contribution intentionally submitted for inclusion in the Work
132 | by You to the Licensor shall be under the terms and conditions of
133 | this License, without any additional terms or conditions.
134 | Notwithstanding the above, nothing herein shall supersede or modify
135 | the terms of any separate license agreement you may have executed
136 | with Licensor regarding such Contributions.
137 |
138 | 6. Trademarks. This License does not grant permission to use the trade
139 | names, trademarks, service marks, or product names of the Licensor,
140 | except as required for reasonable and customary use in describing the
141 | origin of the Work and reproducing the content of the NOTICE file.
142 |
143 | 7. Disclaimer of Warranty. Unless required by applicable law or
144 | agreed to in writing, Licensor provides the Work (and each
145 | Contributor provides its Contributions) on an "AS IS" BASIS,
146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
147 | implied, including, without limitation, any warranties or conditions
148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
149 | PARTICULAR PURPOSE. You are solely responsible for determining the
150 | appropriateness of using or redistributing the Work and assume any
151 | risks associated with Your exercise of permissions under this License.
152 |
153 | 8. Limitation of Liability. In no event and under no legal theory,
154 | whether in tort (including negligence), contract, or otherwise,
155 | unless required by applicable law (such as deliberate and grossly
156 | negligent acts) or agreed to in writing, shall any Contributor be
157 | liable to You for damages, including any direct, indirect, special,
158 | incidental, or consequential damages of any character arising as a
159 | result of this License or out of the use or inability to use the
160 | Work (including but not limited to damages for loss of goodwill,
161 | work stoppage, computer failure or malfunction, or any and all
162 | other commercial damages or losses), even if such Contributor
163 | has been advised of the possibility of such damages.
164 |
165 | 9. Accepting Warranty or Additional Liability. While redistributing
166 | the Work or Derivative Works thereof, You may choose to offer,
167 | and charge a fee for, acceptance of support, warranty, indemnity,
168 | or other liability obligations and/or rights consistent with this
169 | License. However, in accepting such obligations, You may act only
170 | on Your own behalf and on Your sole responsibility, not on behalf
171 | of any other Contributor, and only if You agree to indemnify,
172 | defend, and hold each Contributor harmless for any liability
173 | incurred by, or claims asserted against, such Contributor by reason
174 | of your accepting any such warranty or additional liability.
175 |
176 | END OF TERMS AND CONDITIONS
177 |
178 | APPENDIX: How to apply the Apache License to your work.
179 |
180 | To apply the Apache License to your work, attach the following
181 | boilerplate notice, with the fields enclosed by brackets "[]"
182 | replaced with your own identifying information. (Don't include
183 | the brackets!) The text should be enclosed in the appropriate
184 | comment syntax for the file format. We also recommend that a
185 | file or class name and description of purpose be included on the
186 | same "printed page" as the copyright notice for easier
187 | identification within third-party archives.
188 |
189 | Copyright [yyyy] [name of copyright owner]
190 |
191 | Licensed under the Apache License, Version 2.0 (the "License");
192 | you may not use this file except in compliance with the License.
193 | You may obtain a copy of the License at
194 |
195 | http://www.apache.org/licenses/LICENSE-2.0
196 |
197 | Unless required by applicable law or agreed to in writing, software
198 | distributed under the License is distributed on an "AS IS" BASIS,
199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
200 | See the License for the specific language governing permissions and
201 | limitations under the License.
202 |
--------------------------------------------------------------------------------
/prototypes/notebooks/scispacy_linking_via_umls.ipynb:
--------------------------------------------------------------------------------
1 | {
2 | "nbformat": 4,
3 | "nbformat_minor": 0,
4 | "metadata": {
5 | "colab": {
6 | "name": "scispacy_linking_via_umls.ipynb",
7 | "provenance": [],
8 | "collapsed_sections": []
9 | },
10 | "kernelspec": {
11 | "name": "python3",
12 | "display_name": "Python 3"
13 | }
14 | },
15 | "cells": [
16 | {
17 | "cell_type": "markdown",
18 | "metadata": {
19 | "id": "v0hVqAJ-nKzF"
20 | },
21 | "source": [
22 | "#### Enviroment setup\n",
23 | "\n",
24 | "Downloading models and defining functions, this takes a while."
25 | ]
26 | },
27 | {
28 | "cell_type": "code",
29 | "metadata": {
30 | "id": "G_no39qRZzRi"
31 | },
32 | "source": [
33 | "!pip install scispacy\n",
34 | "!pip install https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.2.5/en_core_sci_md-0.2.5.tar.gz # Medium sized language model\n",
35 | "!pip install wikidataintegrator"
36 | ],
37 | "execution_count": null,
38 | "outputs": []
39 | },
40 | {
41 | "cell_type": "code",
42 | "metadata": {
43 | "id": "3xR9dKnWZBAO"
44 | },
45 | "source": [
46 | "import scispacy\n",
47 | "import spacy\n",
48 | "import pandas as pd\n",
49 | "from wikidataintegrator import wdi_core\n",
50 | "from scispacy.abbreviation import AbbreviationDetector\n",
51 | "from scispacy.linking import EntityLinker\n",
52 | "from functools import lru_cache"
53 | ],
54 | "execution_count": null,
55 | "outputs": []
56 | },
57 | {
58 | "cell_type": "code",
59 | "metadata": {
60 | "id": "5yG2Qz05ZuTj"
61 | },
62 | "source": [
63 | "import en_core_sci_md\n",
64 | "nlp = en_core_sci_md.load()"
65 | ],
66 | "execution_count": null,
67 | "outputs": []
68 | },
69 | {
70 | "cell_type": "code",
71 | "metadata": {
72 | "id": "RS_YKN4vetXI",
73 | "outputId": "61e705d3-934d-474d-acb1-2880cc96aab6",
74 | "colab": {
75 | "base_uri": "https://localhost:8080/",
76 | "height": 106
77 | }
78 | },
79 | "source": [
80 | "abbreviation_pipe = AbbreviationDetector(nlp)\n",
81 | "nlp.add_pipe(abbreviation_pipe)\n",
82 | "linker = EntityLinker(resolve_abbreviations=True, name=\"umls\")\n",
83 | "nlp.add_pipe(linker)"
84 | ],
85 | "execution_count": null,
86 | "outputs": [
87 | {
88 | "output_type": "stream",
89 | "text": [
90 | "/usr/local/lib/python3.6/dist-packages/sklearn/base.py:318: UserWarning: Trying to unpickle estimator TfidfTransformer from version 0.20.3 when using version 0.22.2.post1. This might lead to breaking code or invalid results. Use at your own risk.\n",
91 | " UserWarning)\n",
92 | "/usr/local/lib/python3.6/dist-packages/sklearn/base.py:318: UserWarning: Trying to unpickle estimator TfidfVectorizer from version 0.20.3 when using version 0.22.2.post1. This might lead to breaking code or invalid results. Use at your own risk.\n",
93 | " UserWarning)\n"
94 | ],
95 | "name": "stderr"
96 | }
97 | ]
98 | },
99 | {
100 | "cell_type": "code",
101 | "metadata": {
102 | "id": "7oFnYiRygZNo"
103 | },
104 | "source": [
105 | "# Function by github.com/lubianat with some slight alterations by github.com/jvfe\n",
106 | "@lru_cache(maxsize=None)\n",
107 | "def get_wikidata_item(wikidata_property, value):\n",
108 | " \"\"\"Gets a Wikidata item for a determined property-value pair\n",
109 | "\n",
110 | "\n",
111 | " Args:\n",
112 | " property (str): The property to search\n",
113 | " value (str): The value of said property\n",
114 | " \n",
115 | " Returns:\n",
116 | " str: A Wikidata item or a \"None\" value if no item found.\n",
117 | " \"\"\"\n",
118 | " query_result = wdi_core.WDItemEngine.execute_sparql_query(\n",
119 | " f'SELECT distinct ?item WHERE {{ ?item wdt:{wikidata_property} \"{value}\" }}'\n",
120 | " )\n",
121 | " try:\n",
122 | " match = query_result[\"results\"][\"bindings\"][0]\n",
123 | " except:\n",
124 | " return None\n",
125 | " qid = match[\"item\"][\"value\"]\n",
126 | "\n",
127 | " qid = qid.split(\"/\")[4]\n",
128 | " return qid"
129 | ],
130 | "execution_count": null,
131 | "outputs": []
132 | },
133 | {
134 | "cell_type": "code",
135 | "metadata": {
136 | "id": "SXzHNaoOnajc"
137 | },
138 | "source": [
139 | "def get_wdt_items_from_umls_entities(doc):\n",
140 | " \"\"\"Create a table from the UMLS entities and link them to WDT\n",
141 | " \"\"\"\n",
142 | " identified = []\n",
143 | " for ent in doc.ents:\n",
144 | " try:\n",
145 | " best_id = ent._.kb_ents[0][0]\n",
146 | " except IndexError:\n",
147 | " best_id = None\n",
148 | " identified.append([ent.text, ent.start_char, ent.end_char, best_id])\n",
149 | "\n",
150 | " entity_df = pd.DataFrame.from_records(identified, \n",
151 | " columns=['label', 'start_pos', 'end_pos', 'umls_id'])\n",
152 | " \n",
153 | " entity_df['qid'] = entity_df['umls_id'].apply(lambda x: get_wikidata_item(\"P2892\", x))\n",
154 | "\n",
155 | " return entity_df"
156 | ],
157 | "execution_count": null,
158 | "outputs": []
159 | },
160 | {
161 | "cell_type": "markdown",
162 | "metadata": {
163 | "id": "yrZ4EdWuoCq3"
164 | },
165 | "source": [
166 | "### Testing out"
167 | ]
168 | },
169 | {
170 | "cell_type": "code",
171 | "metadata": {
172 | "id": "MHXGNR-UeRHf"
173 | },
174 | "source": [
175 | "text = \"\"\"\n",
176 | "Spinal and bulbar muscular atrophy (SBMA) is an\n",
177 | "inherited motor neuron disease caused by the expansion\n",
178 | "of a polyglutamine tract within the androgen receptor (AR).\n",
179 | "SBMA can be caused by this easily.\n",
180 | "\"\"\"\n",
181 | "\n",
182 | "doc = nlp(text)"
183 | ],
184 | "execution_count": null,
185 | "outputs": []
186 | },
187 | {
188 | "cell_type": "code",
189 | "metadata": {
190 | "id": "CQx9w-Q-mZNc",
191 | "outputId": "28e61d93-8d31-47ee-f3d3-b9adf8ef78ea",
192 | "colab": {
193 | "base_uri": "https://localhost:8080/",
194 | "height": 363
195 | }
196 | },
197 | "source": [
198 | "get_wdt_items_from_umls_entities(doc)"
199 | ],
200 | "execution_count": null,
201 | "outputs": [
202 | {
203 | "output_type": "execute_result",
204 | "data": {
205 | "text/html": [
206 | "| \n", 224 | " | label | \n", 225 | "start_pos | \n", 226 | "end_pos | \n", 227 | "umls_id | \n", 228 | "qid | \n", 229 | "
|---|---|---|---|---|---|
| 0 | \n", 234 | "Spinal | \n", 235 | "1 | \n", 236 | "7 | \n", 237 | "C0521329 | \n", 238 | "None | \n", 239 | "
| 1 | \n", 242 | "bulbar muscular atrophy | \n", 243 | "12 | \n", 244 | "35 | \n", 245 | "C1839259 | \n", 246 | "Q1995327 | \n", 247 | "
| 2 | \n", 250 | "SBMA | \n", 251 | "37 | \n", 252 | "41 | \n", 253 | "C1839259 | \n", 254 | "Q1995327 | \n", 255 | "
| 3 | \n", 258 | "inherited | \n", 259 | "49 | \n", 260 | "58 | \n", 261 | "C0439660 | \n", 262 | "None | \n", 263 | "
| 4 | \n", 266 | "motor neuron disease | \n", 267 | "59 | \n", 268 | "79 | \n", 269 | "C0085084 | \n", 270 | "Q3221083 | \n", 271 | "
| 5 | \n", 274 | "expansion | \n", 275 | "94 | \n", 276 | "103 | \n", 277 | "C0007595 | \n", 278 | "None | \n", 279 | "
| 6 | \n", 282 | "polyglutamine tract | \n", 283 | "109 | \n", 284 | "128 | \n", 285 | "C0032500 | \n", 286 | "None | \n", 287 | "
| 7 | \n", 290 | "androgen receptor | \n", 291 | "140 | \n", 292 | "157 | \n", 293 | "C0034786 | \n", 294 | "None | \n", 295 | "
| 8 | \n", 298 | "AR | \n", 299 | "159 | \n", 300 | "161 | \n", 301 | "C0034786 | \n", 302 | "None | \n", 303 | "
| 9 | \n", 306 | "SBMA | \n", 307 | "164 | \n", 308 | "168 | \n", 309 | "C1839259 | \n", 310 | "Q1995327 | \n", 311 | "
| \n", 312 | " | label | \n", 313 | "start_pos | \n", 314 | "end_pos | \n", 315 | "mesh_id | \n", 316 | "meshid_match_score | \n", 317 | "arbitary_wdata_id | \n", 318 | "wdata_id | \n", 319 | "
|---|---|---|---|---|---|---|---|
| 0 | \n", 324 | "Exosomes | \n", 325 | "12 | \n", 326 | "20 | \n", 327 | "D055354 | \n", 328 | "0.721988 | \n", 329 | "Q903634 | \n", 330 | "Q903634 | \n", 331 | "
| 1 | \n", 334 | "membranous vesicles | \n", 335 | "42 | \n", 336 | "61 | \n", 337 | "None | \n", 338 | "NA | \n", 339 | "None | \n", 340 | "None | \n", 341 | "
| 2 | \n", 344 | "RNA | \n", 345 | "69 | \n", 346 | "72 | \n", 347 | "D012313 | \n", 348 | "0.760737 | \n", 349 | "Q11053 | \n", 350 | "Q11053 | \n", 351 | "
| 3 | \n", 354 | "content | \n", 355 | "73 | \n", 356 | "80 | \n", 357 | "None | \n", 358 | "NA | \n", 359 | "Q1260632 | \n", 360 | "None | \n", 361 | "
| 4 | \n", 364 | "exosomes | \n", 365 | "99 | \n", 366 | "107 | \n", 367 | "D055354 | \n", 368 | "0.721988 | \n", 369 | "Q903634 | \n", 370 | "Q903634 | \n", 371 | "
| ... | \n", 374 | "... | \n", 375 | "... | \n", 376 | "... | \n", 377 | "... | \n", 378 | "... | \n", 379 | "... | \n", 380 | "... | \n", 381 | "
| 84 | \n", 384 | "bioindicator | \n", 385 | "1910 | \n", 386 | "1922 | \n", 387 | "D000074062 | \n", 388 | "0.790585 | \n", 389 | "Q864438 | \n", 390 | "None | \n", 391 | "
| 85 | \n", 394 | "diagnosis | \n", 395 | "1931 | \n", 396 | "1940 | \n", 397 | "D003933 | \n", 398 | "0.87343 | \n", 399 | "Q177719 | \n", 400 | "Q16644043 | \n", 401 | "
| 86 | \n", 404 | "prognosis | \n", 405 | "1945 | \n", 406 | "1954 | \n", 407 | "None | \n", 408 | "NA | \n", 409 | "Q592442 | \n", 410 | "None | \n", 411 | "
| 87 | \n", 414 | "solid tumors | \n", 415 | "1958 | \n", 416 | "1970 | \n", 417 | "None | \n", 418 | "NA | \n", 419 | "None | \n", 420 | "None | \n", 421 | "
| 88 | \n", 424 | "INPLASY Registration Number | \n", 425 | "1972 | \n", 426 | "1999 | \n", 427 | "None | \n", 428 | "NA | \n", 429 | "None | \n", 430 | "None | \n", 431 | "
89 rows × 7 columns
\n", 435 | "| \n", 195 | " | item | \n", 196 | "typeLabel | \n", 197 | "type | \n", 198 | "itemLabel | \n", 199 | "article_url | \n", 200 | "
|---|---|---|---|---|---|
| 0 | \n", 205 | "Q3 | \n", 206 | "property | \n", 207 | "Q937228 | \n", 208 | "life | \n", 209 | "https://europepmc.org/article/MED/29206104 | \n", 210 | "
| 1 | \n", 213 | "Q4 | \n", 214 | "biological process | \n", 215 | "Q2996394 | \n", 216 | "death | \n", 217 | "https://europepmc.org/article/MED/29206104 | \n", 218 | "
| 2 | \n", 221 | "Q60 | \n", 222 | "city | \n", 223 | "Q515 | \n", 224 | "New York City | \n", 225 | "https://europepmc.org/article/MED/29206104 | \n", 226 | "
| 3 | \n", 229 | "Q60 | \n", 230 | "global city | \n", 231 | "Q208511 | \n", 232 | "New York City | \n", 233 | "https://europepmc.org/article/MED/29206104 | \n", 234 | "
| 4 | \n", 237 | "Q60 | \n", 238 | "city of the United States | \n", 239 | "Q1093829 | \n", 240 | "New York City | \n", 241 | "https://europepmc.org/article/MED/29206104 | \n", 242 | "
| ... | \n", 245 | "... | \n", 246 | "... | \n", 247 | "... | \n", 248 | "... | \n", 249 | "... | \n", 250 | "
| 378 | \n", 253 | "Q106439843 | \n", 254 | "None | \n", 255 | "None | \n", 256 | "adult tissue | \n", 257 | "https://europepmc.org/article/MED/29206104 | \n", 258 | "
| 379 | \n", 261 | "Q106466573 | \n", 262 | "None | \n", 263 | "None | \n", 264 | "automated DNA sequencing machine | \n", 265 | "https://europepmc.org/article/MED/29206104 | \n", 266 | "
| 380 | \n", 269 | "Q106466587 | \n", 270 | "None | \n", 271 | "None | \n", 272 | "large-insert DNA cloning | \n", 273 | "https://europepmc.org/article/MED/29206104 | \n", 274 | "
| 381 | \n", 277 | "Q106501661 | \n", 278 | "None | \n", 279 | "None | \n", 280 | "intermediate milestone | \n", 281 | "https://europepmc.org/article/MED/29206104 | \n", 282 | "
| 382 | \n", 285 | "Q106501997 | \n", 286 | "None | \n", 287 | "None | \n", 288 | "biological organization | \n", 289 | "https://europepmc.org/article/MED/29206104 | \n", 290 | "
1288 rows × 5 columns
\n", 294 | "