From f53061adedfee5d2c695c1ed4c89114e7d7d20b8 Mon Sep 17 00:00:00 2001 From: Emma Rand Date: Thu, 5 Oct 2023 19:12:31 +0100 Subject: [PATCH] add core 2 workshop --- _site/core/core.html | 232 +- _site/core/week-2/data/1cq2.pdb | 3177 +++++ .../data/Y101_Y102_Y201_Y202_Y101-5.csv | 1699 +++ _site/core/week-2/data/control_merged.tif | Bin 0 -> 1261484 bytes _site/core/week-2/data/tf_lthsc.csv | 444 + _site/core/week-2/data/xlaevis_counts_S30.csv | 11894 ++++++++++++++++ _site/core/week-2/images/JennyBryan.jpg | Bin 0 -> 24506 bytes _site/core/week-2/overview.html | 248 +- _site/core/week-2/study_after_workshop.html | 336 +- _site/core/week-2/study_before_workshop.html | 780 +- _site/core/week-2/workshop.html | 459 +- .../figure-html/unnamed-chunk-3-1.png | Bin 0 -> 194971 bytes .../week-3/images/fastaq_file_format.png | Bin _site/omics/week-3/study_before_workshop.html | 1479 +- _site/search.json | 565 +- _site/site_libs/bootstrap/bootstrap.min.css | 10 +- .../font-awesome/LICENSE.txt | 34 + .../font-awesome/css/all.css | 5 + .../font-awesome/css/brands.css | 5 + .../font-awesome/css/fontawesome.css | 5 + .../font-awesome/css/regular.css | 5 + .../font-awesome/css/solid.css | 5 + .../font-awesome/css/svg-with-js.css | 5 + .../font-awesome/css/v4-shims.css | 2170 +++ .../font-awesome/css/v4-shims.min.css | 5 + .../font-awesome/webfonts/fa-brands-400.eot | Bin 0 -> 115052 bytes .../font-awesome/webfonts/fa-brands-400.svg | 1127 ++ .../font-awesome/webfonts/fa-brands-400.ttf | Bin 0 -> 114816 bytes .../font-awesome/webfonts/fa-brands-400.woff | Bin 0 -> 73920 bytes .../font-awesome/webfonts/fa-regular-400.eot | Bin 0 -> 40744 bytes .../font-awesome/webfonts/fa-regular-400.svg | 467 + .../font-awesome/webfonts/fa-regular-400.ttf | Bin 0 -> 40516 bytes .../font-awesome/webfonts/fa-regular-400.woff | Bin 0 -> 18212 bytes .../webfonts/fa-regular-400.woff2 | Bin 0 -> 14952 bytes .../font-awesome/webfonts/fa-solid-900.eot | Bin 0 -> 160768 bytes .../font-awesome/webfonts/fa-solid-900.svg | 2231 +++ .../font-awesome/webfonts/fa-solid-900.ttf | Bin 0 -> 160548 bytes .../font-awesome/webfonts/fa-solid-900.woff | Bin 0 -> 76632 bytes .../font-awesome/webfonts/fa-solid-900.woff2 | Bin 0 -> 59572 bytes .../reveal-chalkboard/img/blackboard.png | Bin 0 -> 32733 bytes .../img/boardmarker-black.png | Bin 0 -> 2142 bytes .../img/boardmarker-blue.png | Bin 0 -> 2127 bytes .../img/boardmarker-green.png | Bin 0 -> 2106 bytes .../img/boardmarker-orange.png | Bin 0 -> 2240 bytes .../img/boardmarker-purple.png | Bin 0 -> 2044 bytes .../reveal-chalkboard/img/boardmarker-red.png | Bin 0 -> 2119 bytes .../reveal-chalkboard/img/chalk-blue.png | Bin 0 -> 5150 bytes .../reveal-chalkboard/img/chalk-green.png | Bin 0 -> 4801 bytes .../reveal-chalkboard/img/chalk-orange.png | Bin 0 -> 5010 bytes .../reveal-chalkboard/img/chalk-purple.png | Bin 0 -> 5250 bytes .../reveal-chalkboard/img/chalk-red.png | Bin 0 -> 4786 bytes .../reveal-chalkboard/img/chalk-white.png | Bin 0 -> 5199 bytes .../reveal-chalkboard/img/chalk-yellow.png | Bin 0 -> 5097 bytes .../plugin/reveal-chalkboard/plugin.js | 1985 +++ .../plugin/reveal-chalkboard/plugin.yml | 7 + .../plugin/reveal-chalkboard/style.css | 44 + .../reveal-highlightword/highlightword.js | 81 + .../site_libs/twitter-widget-0.0.1/widgets.js | 8 + _site/styles.css | 1 + core/week-2/chalkboard.json | 1 - core/week-2/data/1cq2.pdb | 3177 +++++ .../data/Y101_Y102_Y201_Y202_Y101-5.csv | 1699 +++ core/week-2/data/control_merged.tif | Bin 0 -> 1261484 bytes core/week-2/data/tf_lthsc.csv | 444 + core/week-2/data/trna_expr.csv | 1181 ++ core/week-2/data/xlaevis_counts_S30.csv | 11894 ++++++++++++++++ core/week-2/images/fastaq_file_format.png | Bin 0 -> 49333 bytes core/week-2/workshop.qmd | 238 +- login-key-nerc-metagenomics-instance-emma.pem | 27 + omics/week-3/images/fastaq_file_format.png | Bin 0 -> 49333 bytes omics/week-3/study_before_workshop.qmd | 2 +- renv.lock | 108 +- renv/activate.R | 69 +- test.R | 34 + 74 files changed, 47257 insertions(+), 1130 deletions(-) create mode 100644 _site/core/week-2/data/1cq2.pdb create mode 100644 _site/core/week-2/data/Y101_Y102_Y201_Y202_Y101-5.csv create mode 100644 _site/core/week-2/data/control_merged.tif create mode 100644 _site/core/week-2/data/tf_lthsc.csv create mode 100644 _site/core/week-2/data/xlaevis_counts_S30.csv create mode 100644 _site/core/week-2/images/JennyBryan.jpg create mode 100644 _site/core/week-2/workshop_files/figure-html/unnamed-chunk-3-1.png rename omics/week-3/images/fasta_file_format_l2.png => _site/omics/week-3/images/fastaq_file_format.png (100%) create mode 100644 _site/site_libs/revealjs/plugin/reveal-chalkboard/font-awesome/LICENSE.txt create mode 100644 _site/site_libs/revealjs/plugin/reveal-chalkboard/font-awesome/css/all.css create mode 100644 _site/site_libs/revealjs/plugin/reveal-chalkboard/font-awesome/css/brands.css create mode 100644 _site/site_libs/revealjs/plugin/reveal-chalkboard/font-awesome/css/fontawesome.css create mode 100644 _site/site_libs/revealjs/plugin/reveal-chalkboard/font-awesome/css/regular.css create mode 100644 _site/site_libs/revealjs/plugin/reveal-chalkboard/font-awesome/css/solid.css create mode 100644 _site/site_libs/revealjs/plugin/reveal-chalkboard/font-awesome/css/svg-with-js.css create mode 100644 _site/site_libs/revealjs/plugin/reveal-chalkboard/font-awesome/css/v4-shims.css create mode 100644 _site/site_libs/revealjs/plugin/reveal-chalkboard/font-awesome/css/v4-shims.min.css create mode 100644 _site/site_libs/revealjs/plugin/reveal-chalkboard/font-awesome/webfonts/fa-brands-400.eot create mode 100644 _site/site_libs/revealjs/plugin/reveal-chalkboard/font-awesome/webfonts/fa-brands-400.svg create mode 100644 _site/site_libs/revealjs/plugin/reveal-chalkboard/font-awesome/webfonts/fa-brands-400.ttf create mode 100644 _site/site_libs/revealjs/plugin/reveal-chalkboard/font-awesome/webfonts/fa-brands-400.woff create mode 100644 _site/site_libs/revealjs/plugin/reveal-chalkboard/font-awesome/webfonts/fa-regular-400.eot create mode 100644 _site/site_libs/revealjs/plugin/reveal-chalkboard/font-awesome/webfonts/fa-regular-400.svg create mode 100644 _site/site_libs/revealjs/plugin/reveal-chalkboard/font-awesome/webfonts/fa-regular-400.ttf create mode 100644 _site/site_libs/revealjs/plugin/reveal-chalkboard/font-awesome/webfonts/fa-regular-400.woff create mode 100644 _site/site_libs/revealjs/plugin/reveal-chalkboard/font-awesome/webfonts/fa-regular-400.woff2 create mode 100644 _site/site_libs/revealjs/plugin/reveal-chalkboard/font-awesome/webfonts/fa-solid-900.eot create mode 100644 _site/site_libs/revealjs/plugin/reveal-chalkboard/font-awesome/webfonts/fa-solid-900.svg create mode 100644 _site/site_libs/revealjs/plugin/reveal-chalkboard/font-awesome/webfonts/fa-solid-900.ttf create mode 100644 _site/site_libs/revealjs/plugin/reveal-chalkboard/font-awesome/webfonts/fa-solid-900.woff create mode 100644 _site/site_libs/revealjs/plugin/reveal-chalkboard/font-awesome/webfonts/fa-solid-900.woff2 create mode 100644 _site/site_libs/revealjs/plugin/reveal-chalkboard/img/blackboard.png create mode 100644 _site/site_libs/revealjs/plugin/reveal-chalkboard/img/boardmarker-black.png create mode 100644 _site/site_libs/revealjs/plugin/reveal-chalkboard/img/boardmarker-blue.png create mode 100644 _site/site_libs/revealjs/plugin/reveal-chalkboard/img/boardmarker-green.png create mode 100644 _site/site_libs/revealjs/plugin/reveal-chalkboard/img/boardmarker-orange.png create mode 100644 _site/site_libs/revealjs/plugin/reveal-chalkboard/img/boardmarker-purple.png create mode 100644 _site/site_libs/revealjs/plugin/reveal-chalkboard/img/boardmarker-red.png create mode 100644 _site/site_libs/revealjs/plugin/reveal-chalkboard/img/chalk-blue.png create mode 100644 _site/site_libs/revealjs/plugin/reveal-chalkboard/img/chalk-green.png create mode 100644 _site/site_libs/revealjs/plugin/reveal-chalkboard/img/chalk-orange.png create mode 100644 _site/site_libs/revealjs/plugin/reveal-chalkboard/img/chalk-purple.png create mode 100644 _site/site_libs/revealjs/plugin/reveal-chalkboard/img/chalk-red.png create mode 100644 _site/site_libs/revealjs/plugin/reveal-chalkboard/img/chalk-white.png create mode 100644 _site/site_libs/revealjs/plugin/reveal-chalkboard/img/chalk-yellow.png create mode 100644 _site/site_libs/revealjs/plugin/reveal-chalkboard/plugin.js create mode 100644 _site/site_libs/revealjs/plugin/reveal-chalkboard/plugin.yml create mode 100644 _site/site_libs/revealjs/plugin/reveal-chalkboard/style.css create mode 100644 _site/site_libs/revealjs/plugin/reveal-highlightword/highlightword.js create mode 100644 _site/site_libs/twitter-widget-0.0.1/widgets.js delete mode 100644 core/week-2/chalkboard.json create mode 100644 core/week-2/data/1cq2.pdb create mode 100644 core/week-2/data/Y101_Y102_Y201_Y202_Y101-5.csv create mode 100644 core/week-2/data/control_merged.tif create mode 100644 core/week-2/data/tf_lthsc.csv create mode 100644 core/week-2/data/trna_expr.csv create mode 100644 core/week-2/data/xlaevis_counts_S30.csv create mode 100644 core/week-2/images/fastaq_file_format.png create mode 100644 login-key-nerc-metagenomics-instance-emma.pem create mode 100644 omics/week-3/images/fastaq_file_format.png create mode 100644 test.R diff --git a/_site/core/core.html b/_site/core/core.html index 1ef3cd4..66a96e4 100644 --- a/_site/core/core.html +++ b/_site/core/core.html @@ -2,7 +2,7 @@ - + @@ -47,6 +47,12 @@ "panel-placement": "end", "type": "overlay", "limit": 20, + "keyboard-shortcut": [ + "f", + "/", + "s" + ], + "show-item-context": false, "language": { "search-no-results-text": "No results", "search-matching-documents-text": "matching documents", @@ -71,7 +77,7 @@
@@ -247,7 +253,7 @@

On this page

  • Content
    • @@ -269,7 +275,7 @@

    Core Data Analysis

    Published
    -

    28 September, 2023

    +

    3 October, 2023

    @@ -277,27 +283,21 @@

    Core Data Analysis

    + +

    Content

    There are three workshops taken by everyone on BIO00088H and BIO00070M. These are in weeks 1, 2 and 6. The first two cover some useful workflow tips and how to organise your analyses effectively so they are reproducible but you will also have the chance to revise material from stage 1 and 2.

    Good organisation is important because you will want to be able to set work aside for holidays and assessment periods and then restart easily. You will also be assessed on the organisation, reproducibility and transparency of your work.

    Week 1 Core 1 Organising reproducible data analyses

    -

    This week you will revise some essential concepts for scientific computing: file system organisation, file types, working directories and paths. The workshop will cover a rationale for working reproducibly, project oriented workflow, naming things and documenting your work. We will also examine some file types and the concept of tidy data.

    +

    This week you will revise some essential concepts for scientific computing: file system organisation, file types, working directories and paths. The workshop will cover a rationale for working reproducibly, project oriented workflow, naming things and documenting your work.

    -
    -

    Week 2 Core 2 Workflow tips

    - - - - - - - - - +
    +

    Week 2 Core 2 File types, workflow tips and other tools

    +

    This week we will consider File types, workflow tips and other tools. The independent study (~20 mins) reiterates the value of RStudio projects and shows you how you create them with usethis. You will also learn how to recognise and write cool 😎 code, not 😩 ugly code and code algorithmically. In the workshop we will examine some common biological data formats and discover some awesome short cuts to help you write cool 😎 code. You will also get a brief introduction to the command line and Google Colab.

    @@ -308,7 +308,6 @@

    Week - @@ -400,10 +399,9 @@

    Week // clear code selection e.clearSelection(); }); - function tippyHover(el, contentFn) { + function tippyHover(el, contentFn, onTriggerFn, onUntriggerFn) { const config = { allowHTML: true, - content: contentFn, maxWidth: 500, delay: 100, arrow: false, @@ -413,8 +411,17 @@

    Week interactive: true, interactiveBorder: 10, theme: 'quarto', - placement: 'bottom-start' + placement: 'bottom-start', }; + if (contentFn) { + config.content = contentFn; + } + if (onTriggerFn) { + config.onTrigger = onTriggerFn; + } + if (onUntriggerFn) { + config.onUntrigger = onUntriggerFn; + } window.tippy(el, config); } const noterefs = window.document.querySelectorAll('a[role="doc-noteref"]'); @@ -428,6 +435,128 @@

    Week const note = window.document.getElementById(id); return note.innerHTML; }); + } + const xrefs = window.document.querySelectorAll('a.quarto-xref'); + const processXRef = (id, note) => { + // Strip column container classes + const stripColumnClz = (el) => { + el.classList.remove("page-full", "page-columns"); + if (el.children) { + for (const child of el.children) { + stripColumnClz(child); + } + } + } + stripColumnClz(note) + const typesetMath = (el) => { + if (window.MathJax) { + // MathJax Typeset + window.MathJax.typeset([el]); + } else if (window.katex) { + // KaTeX Render + var mathElements = el.getElementsByClassName("math"); + var macros = []; + for (var i = 0; i < mathElements.length; i++) { + var texText = mathElements[i].firstChild; + if (mathElements[i].tagName == "SPAN") { + window.katex.render(texText.data, mathElements[i], { + displayMode: mathElements[i].classList.contains('display'), + throwOnError: false, + macros: macros, + fleqn: false + }); + } + } + } + } + if (id === null || id.startsWith('sec-')) { + // Special case sections, only their first couple elements + const container = document.createElement("div"); + if (note.children && note.children.length > 2) { + for (let i = 0; i < 2; i++) { + container.appendChild(note.children[i].cloneNode(true)); + } + typesetMath(container); + return container.innerHTML + } else { + typesetMath(note); + return note.innerHTML; + } + } else { + // Remove any anchor links if they are present + const anchorLink = note.querySelector('a.anchorjs-link'); + if (anchorLink) { + anchorLink.remove(); + } + typesetMath(note); + return note.innerHTML; + } + } + for (var i=0; i res.text()) + .then(html => { + const parser = new DOMParser(); + const htmlDoc = parser.parseFromString(html, "text/html"); + const note = htmlDoc.getElementById(id); + if (note !== null) { + const html = processXRef(id, note); + instance.setContent(html); + } + }).finally(() => { + instance.enable(); + instance.show(); + }); + } + } else { + // See if we can fetch a full url (with no hash to target) + // This is a special case and we should probably do some content thinning / targeting + fetch(url) + .then(res => res.text()) + .then(html => { + const parser = new DOMParser(); + const htmlDoc = parser.parseFromString(html, "text/html"); + const note = htmlDoc.querySelector('main.content'); + if (note !== null) { + // This should only happen for chapter cross references + // (since there is no id in the URL) + // remove the first header + if (note.children.length > 0 && note.children[0].tagName === "HEADER") { + note.children[0].remove(); + } + const html = processXRef(null, note); + instance.setContent(html); + } + }).finally(() => { + instance.enable(); + instance.show(); + }); + } + }, function(instance) { + }); } let selectedAnnoteEl; const selectorForAnnotation = ( cell, annotation) => { @@ -470,6 +599,7 @@

    Week } div.style.top = top - 2 + "px"; div.style.height = height + 4 + "px"; + div.style.left = 0; let gutterDiv = window.document.getElementById("code-annotation-line-highlight-gutter"); if (gutterDiv === null) { gutterDiv = window.document.createElement("div"); @@ -495,6 +625,32 @@

    Week }); selectedAnnoteEl = undefined; }; + // Handle positioning of the toggle + window.addEventListener( + "resize", + throttle(() => { + elRect = undefined; + if (selectedAnnoteEl) { + selectCodeLines(selectedAnnoteEl); + } + }, 10) + ); + function throttle(fn, ms) { + let throttle = false; + let timer; + return (...args) => { + if(!throttle) { // first call gets through + fn.apply(this, args); + throttle = true; + } else { // all the others get throttled + if(timer) clearTimeout(timer); // cancel #2 + timer = setTimeout(() => { + fn.apply(this, args); + timer = throttle = false; + }, ms); + } + }; + } // Attach click handler to the DT const annoteDls = window.document.querySelectorAll('dt[data-target-cell]'); for (const annoteDlNode of annoteDls) { @@ -553,12 +709,13 @@

    Week } } var localhostRegex = new RegExp(/^(?:http|https):\/\/localhost\:?[0-9]*\//); + var mailtoRegex = new RegExp(/^mailto:/); var filterRegex = new RegExp("^(?:http:|https:)\/\/3mmarand\.github\.io\/BIO00088H-data"); var isInternal = (href) => { - return filterRegex.test(href) || localhostRegex.test(href); + return filterRegex.test(href) || localhostRegex.test(href) || mailtoRegex.test(href); } // Inspect non-navigation links and adorn them if external - var links = window.document.querySelectorAll('a[href]:not(.nav-link):not(.navbar-brand):not(.toc-action):not(.sidebar-link):not(.sidebar-item-toggle):not(.pagination-link):not(.no-external):not([aria-hidden]):not(.dropdown-item)'); + var links = window.document.querySelectorAll('a[href]:not(.nav-link):not(.navbar-brand):not(.toc-action):not(.sidebar-link):not(.sidebar-item-toggle):not(.pagination-link):not(.no-external):not([aria-hidden]):not(.dropdown-item):not(.quarto-navigation-tool)'); for (var i=0; iWeek

    -
    Rand E (2023). Data Analysis for Group Project. https://3mmarand.github.io/BIO00088H-data/.
    +
    +

    Rand E (2023). Data Analysis for Group Project. https://3mmarand.github.io/BIO00088H-data/.

    +
     
    @@ -576,4 +747,5 @@

    Instructions

    + \ No newline at end of file diff --git a/_site/core/week-2/study_after_workshop.html b/_site/core/week-2/study_after_workshop.html index 5013756..0b7cab2 100644 --- a/_site/core/week-2/study_after_workshop.html +++ b/_site/core/week-2/study_after_workshop.html @@ -1,10 +1,13 @@ - + - + + + + Data Analysis for Group Project - Independent Study to consolidate this week + @@ -69,13 +39,20 @@ - +} + + + +
    -
    +
    + +
    - +
    -
    +
    + +
    +

    Independent Study to consolidate this week

    Core 2

    @@ -270,7 +263,7 @@

    Independent Study to consolidate this week

    Published
    -

    31 August, 2023

    +

    3 October, 2023

    @@ -278,18 +271,18 @@

    Independent Study to consolidate this week

    -

    Set up

    -

    If you have just opened RStudio you will want to load the packages and import the data.

    -
    - -
    -
      -
    1. 💻 xx.
      2. -
    + -
    - + + \ No newline at end of file diff --git a/_site/core/week-2/study_before_workshop.html b/_site/core/week-2/study_before_workshop.html index f7f640f..3757cf8 100644 --- a/_site/core/week-2/study_before_workshop.html +++ b/_site/core/week-2/study_before_workshop.html @@ -1,13 +1,10 @@ - + - - + - - Data Analysis for Group Project - Independent Study to prepare for workshop - +/* CSS for syntax highlighting */ +pre > code.sourceCode { white-space: pre; position: relative; } +pre > code.sourceCode > span { line-height: 1.25; } +pre > code.sourceCode > span:empty { height: 1.2em; } +.sourceCode { overflow: visible; } +code.sourceCode > span { color: inherit; text-decoration: inherit; } +div.sourceCode { margin: 1em 0; } +pre.sourceCode { margin: 0; } +@media screen { +div.sourceCode { overflow: auto; } +} +@media print { +pre > code.sourceCode { white-space: pre-wrap; } +pre > code.sourceCode > span { text-indent: -5em; padding-left: 5em; } +} +pre.numberSource code + { counter-reset: source-line 0; } +pre.numberSource code > span + { position: relative; left: -4em; counter-increment: source-line; } +pre.numberSource code > span > a:first-child::before + { content: counter(source-line); + position: relative; left: -1em; text-align: right; vertical-align: baseline; + border: none; display: inline-block; + -webkit-touch-callout: none; -webkit-user-select: none; + -khtml-user-select: none; -moz-user-select: none; + -ms-user-select: none; user-select: none; + padding: 0 4px; width: 4em; + } +pre.numberSource { margin-left: 3em; padding-left: 4px; } +div.sourceCode + { } +@media screen { +pre > code.sourceCode > span > a:first-child::before { text-decoration: underline; } +} +/* CSS for citations */ +div.csl-bib-body { } +div.csl-entry { + clear: both; + margin-bottom: 0em; +} +.hanging-indent div.csl-entry { + margin-left:2em; + text-indent:-2em; +} +div.csl-left-margin { + min-width:2em; + float:left; +} +div.csl-right-inline { + margin-left:2em; + padding-left:1em; +} +div.csl-indent { + margin-left: 2em; +} @@ -39,14 +89,19 @@ - - - - - +} - - +
    -
    -
    -
    - + -
    - -
    -
    +

    Independent Study to prepare for workshop

    -

    Core 2

    +

    Core 2: File types, workflow tips and other tools

    +
    +
    Author
    +
    +

    Emma Rand

    +
    +
    Published
    -

    31 August, 2023

    +

    3 October, 2023

    @@ -265,16 +312,437 @@

    Independent Study to prepare for workshop

    -
    +

    Overview

    +
      +
    • RStudio Projects revisited +
        +
      • using usethis package
        • +
      • Adding a README
        • +
      +
      • +
    • Formatting code
      • +
    • Code algorithmically / algebraically.
      • +

    Reproducibility is a continuum

    +

    Some is better than none!

    +
      +
    • Organise your project
      +
      • +
    • Script everything.
      +
      • +
    • Format code and follow a consistent style.
      +
      • +
    • Code algorithmically
      • +
    • Modularise your code: organise into sections and scripts
      • +
    • Document your project - commenting, READMEs
      • +
    • Use literate programming e.g., R Markdown or Quarto
      • +
    +

    . . .

    +
      +
    • More advanced: Version control, continuous integration, environments, containers
      • +

    RStudio Projects revisited

    +

    RStudio Projects

    +
    +
      +

    • We used RStudio Projects in stage one but they are so useful, it is worth covering them again in case you are not yet using them.

      • +

    • We will also cover the usethisworkflow to create an RStudio Project.

      • +

    • RStudio Projects make it easy to manage working directories and paths because they set the working directory to the RStudio Projects directory automatically.

      • +
    +
    +

    RStudio Projects

    +
    +
    +
    +
    -- stem_cell_rna
+   |__stem_cell_rna.Rproj   
+   |__raw_ data/            
+      |__2019-03-21_donor_1.csv
+   |__README. md
+   |__R/
+      |__01_data_processing.R
+      |__02_exploratory.R
+      |__functions/
+         |__theme_volcano.R
+         |__normalise.R
    +
    +
    +

    The project directory is the folder at the top 1

    +
    +
    +

    RStudio Projects

    +
    +
    +
    +
    -- stem_cell_rna
+   |__stem_cell_rna.Rproj   
+   |__raw_ data/            
+      |__2019-03-21_donor_1.csv
+   |__README. md
+   |__R/
+      |__01_data_processing.R
+      |__02_exploratory.R
+      |__functions/
+         |__theme_volcano.R
+         |__normalise.R
    +
    +
    +

    the .RProj file is directly under the project folder. Its presence is what makes the folder an RStudio Project

    +
    +
    +

    RStudio Projects

    +
    +
      +

    • When you open an RStudio Project, the working directory is set to the Project directory (i.e., the location of the .Rproj file).

      • +

    • When you use an RStudio Project you do not need to use setwd()

      • +

    • When someone, including future you, opens the project on another machine, all the paths just work.

      • +
    +
    +

    RStudio Projects

    +
    +

    +
    Jenny Bryan
    +
    +

    In the words of Jenny Bryan:

    +
    +

    “If the first line of your R script is setwd(”C:/Users/jenny/path/that/only/I/have”) I will come into your office and SET YOUR COMPUTER ON FIRE”

    +
    +

    Creating an RStudio Project

    +

    There are two ways to create an RStudio Project.

    +
      +

    1. Using one of the two menus

      2. +

    2. Using the usethis package

      3. +

    Using a menu

    +

    There are two menus:

    +
      +

    1. Top left, File menu

      2. +

    2. Top Right, drop-down indicated by the .RProj icon

      3. +
    +

    They both do the same thing.

    +

    In both cases you choose: New Project | New Directory | New Project

    +

    . . .

    +

    Make sure you “Browse” to the folder you want to create the project.

    +

    Using the usethis package

    +

    Using the usethis package

    +

    I occasionally use the menu but I mostly use the usethis package.

    +

    . . .

    +

    🎬 Go to RStudio and check your working directory:

    +
    + +
    +

    "C:/Users/er13/Desktop"

    +

    . . .

    +

    ❔ Is your working directory a good place to create a Project folder?

    +

    Using the usethis package

    +

    If this is a good place to create a Project directory then…

    +

    🎬 Create a project with:

    +
    +
    usethis::create_project("bananas")
    +
    +

    Using the usethis package

    +

    Otherwise

    +

    If you want the project directory elsewhere, you will need to give the relative path, e.g.

    +
    +
    usethis::create_project("../Documents/bananas")
    +
    +

    Using the usethis package

    +

    The output will look like this and a new RStudio session will start.

    +
    > usethis::create_project("bananas")
+√ Creating 'bananas/'
+√ Setting active project to 'C:/Users/er13/Desktop/bananas'
+√ Creating 'R/'
+√ Writing 'bananas.Rproj'
+√ Adding '.Rproj.user' to '.gitignore'
+√ Opening 'C:/Users/er13/Desktop/bananas/' in new RStudio session
+√ Setting active project to '<no active project>'
    +

    Using the usethis package

    +

    When you create a new RStudio Project with usethis:

    +
    +
      +
    • A folder called bananas/ is created
      • +
    • RStudio starts a new session in bananas/ i.e., your working directory is now bananas/ +
      • +
    • A folder called R/ is created
      • +
    • A file called bananas.Rproj is created
      • +
    • A file called .gitignore is created
      • +
    • A hidden directory called .Rproj.user is created
      • +
    +
    +

    Using the usethis package

    +
    +
      +

    • the .Rproj file is what makes the directory an RStudio Project

      • +

    • the Rproj.user directory is where project-specific temporary files are stored. You don’t need to mess with it.

      • +

    • the .gitignore is used for version controlled projects. If not using git, you can ignore it.

      • +
    +
    +

    Opening and closing

    +

    You can close an RStudio Project with ONE of:

      -
    1. 📖 Read xxxx
      2. +
    2. File | Close Project
      3. +
    3. Using the drop-down option on the far right of the tool bar where you see the Project name
    +

    . . .

    +

    You can open an RStudio Project with ONE of:

    +
      +
    1. File | Open Project or File | Recent Projects
      +
      2. +
    2. Using the drop-down option on the far right of the tool bar where you see the Project name
      +
      3. +
    3. Double-clicking an .Rproj file from your file explorer/finder
      4. +
    +

    When you open project, a new R session starts.

    +

    Adding a README

    +

    Using the usethis package

    +

    Once the RStudio project has been created, usethis helps you follow good practice.

    +

    . . .

    +

    🎬 We can add a README with:

    +
    +
    usethis::use_readme_md()
    +
    +

    . . .

    +

    This creates a file called README.md, with a little default text, in the Project directory and opens it for editing.

    +

    . . .

    +

    md stands for markdown, it is a extremely widely used text formatting language which is readable as plain text. If you have ever used asterisks to make text bold or italic, you have used markdown.

    +

    Code formatting and style

    +

    Code formatting and style

    +
    +

    “Good coding style is like correct punctuation: you can manage without it, butitsuremakesthingseasiertoread.”

    +
    +

    The tidyverse style guide

    +

    Code formatting and style

    +

    We have all written code which is hard to read!

    +

    We all improve over time.

    +
    +
    + + +
    +
    +

    Code formatting and style

    +

    Some keys points:

    +
      +
    • be consistent, emulate experienced coders
      +
      • +
    • use snake_case for variable names (not CamelCase, dot.case)
      +
      • +
    • use <- not = for assignment
      +
      • +
    • use spacing around most operators and after commas
      +
      • +
    • use indentation
      +
      • +
    • avoid long lines, break up code blocks with new lines
      +
      • +
    • use " for quoting text (not ') unless the text contains double quotes
      • +

    😩 Ugly code 😩

    +
    +
    data<-read_csv('../data-raw/Y101_Y102_Y201_Y202_Y101-5.csv',skip=2)
+library(janitor);sol<-clean_names(data)
+data=data|>filter(str_detect(description,"OS=Homo sapiens"))|>filter(x1pep=='x')
+data=data|>
+mutate(g=str_extract(description,
+"GN=[^\\s]+")|>str_replace("GN=",''))
+data<-data|>mutate(id=str_extract(accession,"1::[^;]+")|>str_replace("1::",""))
    +
    +

    😩 Ugly code 😩

    +
      +
    • no spacing or indentation
      • +
    • inconsistent splitting of code blocks over lines
      • +
    • inconsistent use of quote characters
      • +
    • no comments
      • +
    • variable names convey no meaning
      • +
    • use of = for assignment and inconsistently
      • +
    • multiple commands on a line
      • +
    • library statement in the middle of the analysis
      • +

    😎 Cool code 😎

    +
    +
    # Packages ----------------------------------------------------------------
+library(tidyverse)
+library(janitor)
+
+# Import ------------------------------------------------------------------
+
+# define file name
+file <- "../data-raw/Y101_Y102_Y201_Y202_Y101-5.csv"
+
+# import: column headers and data are from row 3
+solu_protein <- read_csv(file, skip = 2) |>
+  janitor::clean_names()
+
+# Tidy data ----------------------------------------------------------------
+
+# filter out the bovine proteins and those proteins 
+# identified from fewer than 2 peptides
+solu_protein <- solu_protein |>
+  filter(str_detect(description, "OS=Homo sapiens")) |>
+  filter(x1pep == "x")
+
+# Extract the genename from description column to a column
+# of its own
+solu_protein <- solu_protein |>
+  mutate(genename =  str_extract(description,"GN=[^\\s]+") |>
+           str_replace("GN=", ""))
+
+# Extract the top protein identifier from accession column (first
+# Uniprot ID after "1::") to a column of its own
+solu_protein <- solu_protein |>
+  mutate(protid =  str_extract(accession, "1::[^;]+") |>
+           str_replace("1::", ""))
    +
    +

    😎 Cool code 😎

    +
      +

    • library() calls collected

      • +

    • Uses code sections to make it easier to navigate

      • +

    • Uses white space and proper indentation

      • +

    • Commented

      • +

    • Uses more informative name for the dataframe

      • +

    Code ‘algorithmically’

    +

    Code ‘algorithmically’

    +
    +
      +

    • Write code which expresses the structure of the problem/solution.

      • +

    • Avoid hard coding numbers if at all possible - declare variables instead

      • +

    • Declare frequently used values as variables at the start e.g., colour schemes, figure saving settings

      • +
    +
    +

    😩 Hard coding numbers.

    +
    +
      +

    • Suppose we want to calculate the sums of squares, \(SS(x)\), for the number of eggs in five nests.

      • +

    • The formula is given by: \(\sum (x_i- \bar{x})^2\)

      • +

    • We could calculate the mean and copy it, and the individual numbers into the formula

      • +
    +
    +

    😩 Hard coding numbers.

    +
    +
    # mean number of eggs per nest
+sum(3, 5, 6, 7, 8) / 5
    +
    +
    [1] 5.8
    +
    +
    # ss(x) of number of eggs
+(3 - 5.8)^2 + (5 - 5.8)^2 + (6 - 5.8)^2 + (7 - 5.8)^2 + (8 - 5.8)^2
    +
    +
    [1] 14.8
    +
    +
    +

    I am coding the calculation of the mean rather using the mean() function only to explain what ‘coding algorithmically’ means using a simple example.

    +

    😩 Hard coding numbers

    +
    +
      +

    • if any of the sample numbers must be altered, all the code needs changing

      • +

    • it is hard to tell that the output of the first line is a mean

      • +

    • its hard to recognise that the numbers in the mean calculation correspond to those in the next calculation

      • +

    • it is hard to tell that 5 is just the number of nests

      • +

    • no way of know if numbers are the same by coincidence or they refer to the same thing

      • +
    +
    +

    😎 Better

    +
    +
    # eggs each nest
+eggs <- c(3, 5, 6, 7, 8)
+
+# mean eggs per nest
+mean_eggs <- sum(eggs) / length(eggs)
+
+# ss(x) of number of eggs
+sum((eggs - mean_eggs)^2)
    +
    +
    [1] 14.8
    +
    +
    +

    😎 Better

    +
    +
      +

    • the commenting is similar but it is easier to follow

      • +

    • if any of the sample numbers must be altered, only that number needs changing

      • +

    • assigning a value you will later use to a variable with a meaningful name allows us to understand the first and second calculations

      • +

    • makes use of R’s elementwise calculation which resembles the formula (i.e., is expressed as the general rule)

      • +
    +
    +

    Summary

    +
    +
      +

    • Use an RStudio project for any R work (you can also incorporate other languages)

      • +

    • Write Cool code not Ugly code: space, consistency, indentation, comments, meaningful variable names

      • +

    • Write code which expresses the structure of the problem/solution.

      • +

    • Avoid hard coding numbers if at all possible - declare variables instead

      • +
    +
    +

    Reading

    +

    Recommended if you still need convincing to use RStudio Projects

    + +

    Completely optional suggestions for further reading

    +
      +
    • Ten simple rules for reproducible computational research (Sandve et al. 2013) +
      • +
    • Good enough practices in scientific computing (Wilson et al. 2017) +
      • +
    • Excuse Me, Do You Have a Moment to Talk About Version Control? (Bryan 2018) +
      • +
    +
    + + + +

    References

    +
    +Bryan, Jennifer. 2018. “Excuse Me, Do You Have a Moment to Talk about Version Control?” Am. Stat. 72 (1): 20–27. https://doi.org/10.1080/00031305.2017.1399928. +
    +
    +Bryan, Jennifer, Jim Hester, Shannon Pileggi, and E. David Aja. n.d. What They Forgot to Teach You about r. https://rstats.wtf/. +
    +
    +Sandve, Geir Kjetil, Anton Nekrutenko, James Taylor, and Eivind Hovig. 2013. “Ten Simple Rules for Reproducible Computational Research.” PLoS Comput. Biol. 9 (10): e1003285. https://doi.org/10.1371/journal.pcbi.1003285. +
    +
    +Wilson, Greg, Jennifer Bryan, Karen Cranston, Justin Kitzes, Lex Nederbragt, and Tracy K Teal. 2017. “Good Enough Practices in Scientific Computing.” PLoS Comput. Biol. 13 (6): e1005510. https://doi.org/10.1371/journal.pcbi.1005510. +
    +
    - - \ No newline at end of file diff --git a/_site/core/week-2/workshop.html b/_site/core/week-2/workshop.html index f694c4c..8e33f7f 100644 --- a/_site/core/week-2/workshop.html +++ b/_site/core/week-2/workshop.html @@ -2,7 +2,7 @@ - + Data Analysis for Group Project - Workshop @@ -18,10 +18,45 @@ margin: 0 0.8em 0.2em -1em; /* quarto-specific, see https://github.com/quarto-dev/quarto-cli/issues/4556 */ vertical-align: middle; } +/* CSS for syntax highlighting */ +pre > code.sourceCode { white-space: pre; position: relative; } +pre > code.sourceCode > span { line-height: 1.25; } +pre > code.sourceCode > span:empty { height: 1.2em; } +.sourceCode { overflow: visible; } +code.sourceCode > span { color: inherit; text-decoration: inherit; } +div.sourceCode { margin: 1em 0; } +pre.sourceCode { margin: 0; } +@media screen { +div.sourceCode { overflow: auto; } +} +@media print { +pre > code.sourceCode { white-space: pre-wrap; } +pre > code.sourceCode > span { text-indent: -5em; padding-left: 5em; } +} +pre.numberSource code + { counter-reset: source-line 0; } +pre.numberSource code > span + { position: relative; left: -4em; counter-increment: source-line; } +pre.numberSource code > span > a:first-child::before + { content: counter(source-line); + position: relative; left: -1em; text-align: right; vertical-align: baseline; + border: none; display: inline-block; + -webkit-touch-callout: none; -webkit-user-select: none; + -khtml-user-select: none; -moz-user-select: none; + -ms-user-select: none; user-select: none; + padding: 0 4px; width: 4em; + } +pre.numberSource { margin-left: 3em; padding-left: 4px; } +div.sourceCode + { } +@media screen { +pre > code.sourceCode > span > a:first-child::before { text-decoration: underline; } +} /* CSS for citations */ div.csl-bib-body { } div.csl-entry { clear: both; + margin-bottom: 0em; } .hanging-indent div.csl-entry { margin-left:2em; @@ -61,6 +96,12 @@ "panel-placement": "end", "type": "overlay", "limit": 20, + "keyboard-shortcut": [ + "f", + "/", + "s" + ], + "show-item-context": false, "language": { "search-no-results-text": "No results", "search-matching-documents-text": "matching documents", @@ -79,7 +120,7 @@
    @@ -248,7 +289,34 @@ Introduction + +
  • +File types + +
    • +
  • Workflow tips
    • +
  • +Other tools + +
    • +
  • Google Colab
    • +
  • +Python +
  • 🥳 Well Done! 🎉
    • @@ -258,9 +326,9 @@
    -
    +

    Workshop

    -

    xxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

    +

    File types, workflow tips and other tools

    @@ -277,7 +345,7 @@

    Workshop

    Published
    -

    28 September, 2023

    +

    5 October, 2023

    @@ -285,20 +353,177 @@

    Workshop

    +

    Introduction

    Session overview

    In this workshop you will

    -

    File formats

    -

    Data files. - Sequences data - Image data - Structure data PDB/mmCIF www.pdb.org

    -

    Similarities and differences

    -

    🎬

    -

    what is markdown

    -

    Google Colab

    -

    snippets

    -

    python

    -

    differences between r and python

    -

    rstudio terminal

    -

    basic bash

    +

    File types

    +

    Omics

    +

    Images

    +

    control_merged.tif

    +
    +
    library(ijtiff)
+img <- read_tif("data/control_merged.tif")
    +
    +
    +
    img
    +
    +
         [,1] [,2] [,3] [,4] [,5] [,6]
+[1,]    0    0    0    0    0    0
+[2,]    0    0    0    0    0    0
+[3,]    0    0    0    0    0    0
+[4,]    0    0    0    0    0    0
+[5,]    0    0    0    0    0    0
+[6,]    0    0    0    0    0    0
+── TIFF tags ───────────────────────────────────────────────────────────────────
    +
    +
    +
      +

    • an image at least one and usually more matrices of numbers representing the intensity of light at each pixel in the image

      • +

    • the number of matrices depends on the number of ‘channels’ in the image

      • +

    • a channel is a colour in the image

      • +

    • a frame is a single image in a series of images

      • +

    • we might normally call this a multi-dimensional array: x and y coordinates of the pixels are 2 dimensions, the channel is the third dimension and time is the forth dimension

      • +
    +
    +
    display(img)
    +
    +

    +
    +
    +

    Structure

    +

    1cq2.pdb

    +

    Workflow tips

    +

    🎬 Start by making a new RStudio project (use the workflow from in the independent study). Add some files

    +
      +

    • multiple cursors

      • +

    • open a file/function or find a variable CONTROL+.

      • +

    • the command palette CONTROL+SHIFT+P

      • +

    • segmenting code CONTROL+SHIFT+R

      • +

    • to correct indentation CONTROL+i

      • +

    • to reformat code CONTROL+SHIFT+A Not perfect but corrects spacing, indentation, multiple commands on lines and assignment with =

      • +

    • to comment and uncomment lines CONTROL+SHIFT+C

      • +

    • Tools | Global options | Code | Display | Show margin

      • +

    • Tools | Global options | Code | Diagnostic | Provide R style diagnostics

      • +

    • GitHub Copilot in RStudio, it’s finally here!

      • +

    Other tools

    +

    The command line

    +

    The command line - or shell - is a text interface for your computer. It’s a program that takes in commands, which it passes on to the computer’s operating system to run.

    +
      +

    • Windows PowerShell is a command-line in windows. It uses bash-like commands unlike the Command Prompt which uses dos commands (a sort of windows only language). You can open is by going to Start | Windows PowerShell or by searching for it in the search bar.

      • +

    • Terminal is the command line in Mac OS X. You can open it by going to Applications | Utilities | Terminal or by searching for it in the Spotlight search bar.

      • +

    • git bash. I used the bash shell that comes with Git

      • +

    RStudio terminal

    +

    The RStudio terminal is a convenient interface to the shell without leaving RStudio. It is useful for running commands that are not available in R. For example, you can use it to run other programs like fasqc, git, ftp, ssh

    +

    Google Colab

    +

    Python

    +

    Differences between R and python

    You’re finished!

    🥳 Well Done! 🎉

    Independent study following the workshop

    @@ -311,7 +536,7 @@

    Workshop

    -

    References

    +

    References

    Allaire, J. J., Charles Teague, Carlos Scheidegger, Yihui Xie, and Christophe Dervieux. 2022. Quarto. https://doi.org/10.5281/zenodo.5960048.
    @@ -403,10 +628,9 @@

    Workshop

    // clear code selection e.clearSelection(); }); - function tippyHover(el, contentFn) { + function tippyHover(el, contentFn, onTriggerFn, onUntriggerFn) { const config = { allowHTML: true, - content: contentFn, maxWidth: 500, delay: 100, arrow: false, @@ -416,8 +640,17 @@

    Workshop

    interactive: true, interactiveBorder: 10, theme: 'quarto', - placement: 'bottom-start' + placement: 'bottom-start', }; + if (contentFn) { + config.content = contentFn; + } + if (onTriggerFn) { + config.onTrigger = onTriggerFn; + } + if (onUntriggerFn) { + config.onUntrigger = onUntriggerFn; + } window.tippy(el, config); } const noterefs = window.document.querySelectorAll('a[role="doc-noteref"]'); @@ -431,6 +664,128 @@

    Workshop

    const note = window.document.getElementById(id); return note.innerHTML; }); + } + const xrefs = window.document.querySelectorAll('a.quarto-xref'); + const processXRef = (id, note) => { + // Strip column container classes + const stripColumnClz = (el) => { + el.classList.remove("page-full", "page-columns"); + if (el.children) { + for (const child of el.children) { + stripColumnClz(child); + } + } + } + stripColumnClz(note) + const typesetMath = (el) => { + if (window.MathJax) { + // MathJax Typeset + window.MathJax.typeset([el]); + } else if (window.katex) { + // KaTeX Render + var mathElements = el.getElementsByClassName("math"); + var macros = []; + for (var i = 0; i < mathElements.length; i++) { + var texText = mathElements[i].firstChild; + if (mathElements[i].tagName == "SPAN") { + window.katex.render(texText.data, mathElements[i], { + displayMode: mathElements[i].classList.contains('display'), + throwOnError: false, + macros: macros, + fleqn: false + }); + } + } + } + } + if (id === null || id.startsWith('sec-')) { + // Special case sections, only their first couple elements + const container = document.createElement("div"); + if (note.children && note.children.length > 2) { + for (let i = 0; i < 2; i++) { + container.appendChild(note.children[i].cloneNode(true)); + } + typesetMath(container); + return container.innerHTML + } else { + typesetMath(note); + return note.innerHTML; + } + } else { + // Remove any anchor links if they are present + const anchorLink = note.querySelector('a.anchorjs-link'); + if (anchorLink) { + anchorLink.remove(); + } + typesetMath(note); + return note.innerHTML; + } + } + for (var i=0; i res.text()) + .then(html => { + const parser = new DOMParser(); + const htmlDoc = parser.parseFromString(html, "text/html"); + const note = htmlDoc.getElementById(id); + if (note !== null) { + const html = processXRef(id, note); + instance.setContent(html); + } + }).finally(() => { + instance.enable(); + instance.show(); + }); + } + } else { + // See if we can fetch a full url (with no hash to target) + // This is a special case and we should probably do some content thinning / targeting + fetch(url) + .then(res => res.text()) + .then(html => { + const parser = new DOMParser(); + const htmlDoc = parser.parseFromString(html, "text/html"); + const note = htmlDoc.querySelector('main.content'); + if (note !== null) { + // This should only happen for chapter cross references + // (since there is no id in the URL) + // remove the first header + if (note.children.length > 0 && note.children[0].tagName === "HEADER") { + note.children[0].remove(); + } + const html = processXRef(null, note); + instance.setContent(html); + } + }).finally(() => { + instance.enable(); + instance.show(); + }); + } + }, function(instance) { + }); } let selectedAnnoteEl; const selectorForAnnotation = ( cell, annotation) => { @@ -473,6 +828,7 @@

    Workshop

    } div.style.top = top - 2 + "px"; div.style.height = height + 4 + "px"; + div.style.left = 0; let gutterDiv = window.document.getElementById("code-annotation-line-highlight-gutter"); if (gutterDiv === null) { gutterDiv = window.document.createElement("div"); @@ -498,6 +854,32 @@

    Workshop

    }); selectedAnnoteEl = undefined; }; + // Handle positioning of the toggle + window.addEventListener( + "resize", + throttle(() => { + elRect = undefined; + if (selectedAnnoteEl) { + selectCodeLines(selectedAnnoteEl); + } + }, 10) + ); + function throttle(fn, ms) { + let throttle = false; + let timer; + return (...args) => { + if(!throttle) { // first call gets through + fn.apply(this, args); + throttle = true; + } else { // all the others get throttled + if(timer) clearTimeout(timer); // cancel #2 + timer = setTimeout(() => { + fn.apply(this, args); + timer = throttle = false; + }, ms); + } + }; + } // Attach click handler to the DT const annoteDls = window.document.querySelectorAll('dt[data-target-cell]'); for (const annoteDlNode of annoteDls) { @@ -556,12 +938,13 @@

    Workshop

    } } var localhostRegex = new RegExp(/^(?:http|https):\/\/localhost\:?[0-9]*\//); + var mailtoRegex = new RegExp(/^mailto:/); var filterRegex = new RegExp("^(?:http:|https:)\/\/3mmarand\.github\.io\/BIO00088H-data"); var isInternal = (href) => { - return filterRegex.test(href) || localhostRegex.test(href); + return filterRegex.test(href) || localhostRegex.test(href) || mailtoRegex.test(href); } // Inspect non-navigation links and adorn them if external - var links = window.document.querySelectorAll('a[href]:not(.nav-link):not(.navbar-brand):not(.toc-action):not(.sidebar-link):not(.sidebar-item-toggle):not(.pagination-link):not(.no-external):not([aria-hidden]):not(.dropdown-item)'); + var links = window.document.querySelectorAll('a[href]:not(.nav-link):not(.navbar-brand):not(.toc-action):not(.sidebar-link):not(.sidebar-item-toggle):not(.pagination-link):not(.no-external):not([aria-hidden]):not(.dropdown-item):not(.quarto-navigation-tool)'); for (var i=0; iWorkshop