From 1bc7b0d7898bc8558962decf7d38f83cd8b915d7 Mon Sep 17 00:00:00 2001 From: ahernank Date: Wed, 12 Jun 2024 05:22:31 -0500 Subject: [PATCH] add af1.x pages --- docs/_toc.yml | 4 +- docs/af1/af1.1.ipynb | 292 +++++++++++++++++- docs/af1/af1.2.ipynb | 709 +++++++++++++++++++++++++++++++++++++++++++ docs/af1/af1.3.ipynb | 672 ++++++++++++++++++++++++++++++++++++++++ 4 files changed, 1671 insertions(+), 6 deletions(-) create mode 100644 docs/af1/af1.2.ipynb create mode 100644 docs/af1/af1.3.ipynb diff --git a/docs/_toc.yml b/docs/_toc.yml index 6fd621b..09db0e9 100644 --- a/docs/_toc.yml +++ b/docs/_toc.yml @@ -20,6 +20,9 @@ parts: - caption: Anopheles funestus chapters: - file: af1/af1.0 + - file: af1/af1.1 + - file: af1/af1.2 + - file: af1/af1.3 - file: af1/cloud - file: af1/download - file: af1/api @@ -33,7 +36,6 @@ parts: - caption: Partners and community chapters: - file: studies-ag1000g - - file: studies-af1.0-consortium - caption: Release notes chapters: - file: release-notes diff --git a/docs/af1/af1.1.ipynb b/docs/af1/af1.1.ipynb index 068e91a..eed7d59 100644 --- a/docs/af1/af1.1.ipynb +++ b/docs/af1/af1.1.ipynb @@ -10,7 +10,7 @@ "\n", "The **[Af1.1](af1.1): _Anopheles gambiae_ data resource** contains single nucleotide polymorphism (SNP) calls, copy number variant (CNV) calls and SNP haplotypes from whole-genome sequencing of 1138 mosquitoes.\n", "\n", - "More information about this release can be found in the [data resource website](https://www.malariagen.net/data/af31-anopheles-funestus-data-resource). \n", + "More information about this release can be found in the [data resource website](https://www.malariagen.net/data_package/af11-anopheles-funestus-data-resource/). \n", "\n", "This page provides an introduction to open data resources released as part of `Af1.1`. \n", "\n", @@ -29,9 +29,9 @@ "\n", "Although malaria is generally an endemic rather than an epidemic disease, and the focus of this project is on surveillance of disease vectors rather than pathogens, our data terms of use build on MalariaGEN's approach to data sharing, and adopt norms which have been established for rapid sharing of pathogen genomic data during disease outbreaks. The primary rationale for this approach is that malaria remains a public health emergency, where ethically appropriate and rapid sharing of genomic surveillance data can help to detect and respond to biological threats such as new forms of insecticide resistance, and to adapt malaria vector control strategies to different settings and changing circumstances.\n", "\n", - "The publication embargo for all data on this release will expire on the **8th of December 2025**. \n", + "The publication embargo for all data on this release will expire on the **29th of April 2026**. \n", "\n", - "If you have any questions about the terms of use, please email [data@malariagen.net](mailto:data@malariagen.net)" + "If you have any questions about the terms of use, please email [support@malariagen.net](mailto:support@malariagen.net)" ] }, { @@ -130,7 +130,289 @@ "outputs": [ { "data": { - "application/javascript": "(function(root) {\n function now() {\n return new Date();\n }\n\n const force = true;\n\n if (typeof root._bokeh_onload_callbacks === \"undefined\" || force === true) {\n root._bokeh_onload_callbacks = [];\n root._bokeh_is_loading = undefined;\n }\n\nconst JS_MIME_TYPE = 'application/javascript';\n const HTML_MIME_TYPE = 'text/html';\n const EXEC_MIME_TYPE = 'application/vnd.bokehjs_exec.v0+json';\n const CLASS_NAME = 'output_bokeh rendered_html';\n\n /**\n * Render data to the DOM node\n */\n function render(props, node) {\n const script = document.createElement(\"script\");\n node.appendChild(script);\n }\n\n /**\n * Handle when an output is cleared or removed\n */\n function handleClearOutput(event, handle) {\n function drop(id) {\n const view = Bokeh.index.get_by_id(id)\n if (view != null) {\n view.model.document.clear()\n Bokeh.index.delete(view)\n }\n }\n\n const cell = handle.cell;\n\n const id = cell.output_area._bokeh_element_id;\n const server_id = cell.output_area._bokeh_server_id;\n\n // Clean up Bokeh references\n if (id != null) {\n drop(id)\n }\n\n if (server_id !== undefined) {\n // Clean up Bokeh references\n const cmd_clean = \"from bokeh.io.state import curstate; print(curstate().uuid_to_server['\" + server_id + \"'].get_sessions()[0].document.roots[0]._id)\";\n cell.notebook.kernel.execute(cmd_clean, {\n iopub: {\n output: function(msg) {\n const id = msg.content.text.trim()\n drop(id)\n }\n }\n });\n // Destroy server and session\n const cmd_destroy = \"import bokeh.io.notebook as ion; ion.destroy_server('\" + server_id + \"')\";\n cell.notebook.kernel.execute(cmd_destroy);\n }\n }\n\n /**\n * Handle when a new output is added\n */\n function handleAddOutput(event, handle) {\n const output_area = handle.output_area;\n const output = handle.output;\n\n // limit handleAddOutput to display_data with EXEC_MIME_TYPE content only\n if ((output.output_type != \"display_data\") || (!Object.prototype.hasOwnProperty.call(output.data, EXEC_MIME_TYPE))) {\n return\n }\n\n const toinsert = output_area.element.find(\".\" + CLASS_NAME.split(' ')[0]);\n\n if (output.metadata[EXEC_MIME_TYPE][\"id\"] !== undefined) {\n toinsert[toinsert.length - 1].firstChild.textContent = output.data[JS_MIME_TYPE];\n // store reference to embed id on output_area\n output_area._bokeh_element_id = output.metadata[EXEC_MIME_TYPE][\"id\"];\n }\n if (output.metadata[EXEC_MIME_TYPE][\"server_id\"] !== undefined) {\n const bk_div = document.createElement(\"div\");\n bk_div.innerHTML = output.data[HTML_MIME_TYPE];\n const script_attrs = bk_div.children[0].attributes;\n for (let i = 0; i < script_attrs.length; i++) {\n toinsert[toinsert.length - 1].firstChild.setAttribute(script_attrs[i].name, script_attrs[i].value);\n toinsert[toinsert.length - 1].firstChild.textContent = bk_div.children[0].textContent\n }\n // store reference to server id on output_area\n output_area._bokeh_server_id = output.metadata[EXEC_MIME_TYPE][\"server_id\"];\n }\n }\n\n function register_renderer(events, OutputArea) {\n\n function append_mime(data, metadata, element) {\n // create a DOM node to render to\n const toinsert = this.create_output_subarea(\n metadata,\n CLASS_NAME,\n EXEC_MIME_TYPE\n );\n this.keyboard_manager.register_events(toinsert);\n // Render to node\n const props = {data: data, metadata: metadata[EXEC_MIME_TYPE]};\n render(props, toinsert[toinsert.length - 1]);\n element.append(toinsert);\n return toinsert\n }\n\n /* Handle when an output is cleared or removed */\n events.on('clear_output.CodeCell', handleClearOutput);\n events.on('delete.Cell', handleClearOutput);\n\n /* Handle when a new output is added */\n events.on('output_added.OutputArea', handleAddOutput);\n\n /**\n * Register the mime type and append_mime function with output_area\n */\n OutputArea.prototype.register_mime_type(EXEC_MIME_TYPE, append_mime, {\n /* Is output safe? */\n safe: true,\n /* Index of renderer in `output_area.display_order` */\n index: 0\n });\n }\n\n // register the mime type if in Jupyter Notebook environment and previously unregistered\n if (root.Jupyter !== undefined) {\n const events = require('base/js/events');\n const OutputArea = require('notebook/js/outputarea').OutputArea;\n\n if (OutputArea.prototype.mime_types().indexOf(EXEC_MIME_TYPE) == -1) {\n register_renderer(events, OutputArea);\n }\n }\n if (typeof (root._bokeh_timeout) === \"undefined\" || force === true) {\n root._bokeh_timeout = Date.now() + 5000;\n root._bokeh_failed_load = false;\n }\n\n const NB_LOAD_WARNING = {'data': {'text/html':\n \"
\\n\"+\n \"

\\n\"+\n \"BokehJS does not appear to have successfully loaded. If loading BokehJS from CDN, this \\n\"+\n \"may be due to a slow or bad network connection. Possible fixes:\\n\"+\n \"

\\n\"+\n \"\\n\"+\n \"\\n\"+\n \"from bokeh.resources import INLINE\\n\"+\n \"output_notebook(resources=INLINE)\\n\"+\n \"\\n\"+\n \"
\"}};\n\n function display_loaded() {\n const el = document.getElementById(null);\n if (el != null) {\n el.textContent = \"BokehJS is loading...\";\n }\n if (root.Bokeh !== undefined) {\n if (el != null) {\n el.textContent = \"BokehJS \" + root.Bokeh.version + \" successfully loaded.\";\n }\n } else if (Date.now() < root._bokeh_timeout) {\n setTimeout(display_loaded, 100)\n }\n }\n\n function run_callbacks() {\n try {\n root._bokeh_onload_callbacks.forEach(function(callback) {\n if (callback != null)\n callback();\n });\n } finally {\n delete root._bokeh_onload_callbacks\n }\n console.debug(\"Bokeh: all callbacks have finished\");\n }\n\n function load_libs(css_urls, js_urls, callback) {\n if (css_urls == null) css_urls = [];\n if (js_urls == null) js_urls = [];\n\n root._bokeh_onload_callbacks.push(callback);\n if (root._bokeh_is_loading > 0) {\n console.debug(\"Bokeh: BokehJS is being loaded, scheduling callback at\", now());\n return null;\n }\n if (js_urls == null || js_urls.length === 0) {\n run_callbacks();\n return null;\n }\n console.debug(\"Bokeh: BokehJS not loaded, scheduling load and callback at\", now());\n root._bokeh_is_loading = css_urls.length + js_urls.length;\n\n function on_load() {\n root._bokeh_is_loading--;\n if (root._bokeh_is_loading === 0) {\n console.debug(\"Bokeh: all BokehJS libraries/stylesheets loaded\");\n run_callbacks()\n }\n }\n\n function on_error(url) {\n console.error(\"failed to load \" + url);\n }\n\n for (let i = 0; i < css_urls.length; i++) {\n const url = css_urls[i];\n const element = document.createElement(\"link\");\n element.onload = on_load;\n element.onerror = on_error.bind(null, url);\n element.rel = \"stylesheet\";\n element.type = \"text/css\";\n element.href = url;\n console.debug(\"Bokeh: injecting link tag for BokehJS stylesheet: \", url);\n document.body.appendChild(element);\n }\n\n for (let i = 0; i < js_urls.length; i++) {\n const url = js_urls[i];\n const element = document.createElement('script');\n element.onload = on_load;\n element.onerror = on_error.bind(null, url);\n element.async = false;\n element.src = url;\n console.debug(\"Bokeh: injecting script tag for BokehJS library: \", url);\n document.head.appendChild(element);\n }\n };\n\n function inject_raw_css(css) {\n const element = document.createElement(\"style\");\n element.appendChild(document.createTextNode(css));\n document.body.appendChild(element);\n }\n\n const js_urls = [\"https://cdn.bokeh.org/bokeh/release/bokeh-3.3.0.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-gl-3.3.0.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-widgets-3.3.0.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-tables-3.3.0.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-mathjax-3.3.0.min.js\"];\n const css_urls = [];\n\n const inline_js = [ function(Bokeh) {\n Bokeh.set_log_level(\"info\");\n },\nfunction(Bokeh) {\n }\n ];\n\n function run_inline_js() {\n if (root.Bokeh !== undefined || force === true) {\n for (let i = 0; i < inline_js.length; i++) {\n inline_js[i].call(root, root.Bokeh);\n }\n} else if (Date.now() < root._bokeh_timeout) {\n setTimeout(run_inline_js, 100);\n } else if (!root._bokeh_failed_load) {\n console.log(\"Bokeh: BokehJS failed to load within specified timeout.\");\n root._bokeh_failed_load = true;\n } else if (force !== true) {\n const cell = $(document.getElementById(null)).parents('.cell').data().cell;\n cell.output_area.append_execute_result(NB_LOAD_WARNING)\n }\n }\n\n if (root._bokeh_is_loading === 0) {\n console.debug(\"Bokeh: BokehJS loaded, going straight to plotting\");\n run_inline_js();\n } else {\n load_libs(css_urls, js_urls, function() {\n console.debug(\"Bokeh: BokehJS plotting callback run at\", now());\n run_inline_js();\n });\n }\n}(window));", + "application/javascript": [ + "(function(root) {\n", + " function now() {\n", + " return new Date();\n", + " }\n", + "\n", + " const force = true;\n", + "\n", + " if (typeof root._bokeh_onload_callbacks === \"undefined\" || force === true) {\n", + " root._bokeh_onload_callbacks = [];\n", + " root._bokeh_is_loading = undefined;\n", + " }\n", + "\n", + "const JS_MIME_TYPE = 'application/javascript';\n", + " const HTML_MIME_TYPE = 'text/html';\n", + " const EXEC_MIME_TYPE = 'application/vnd.bokehjs_exec.v0+json';\n", + " const CLASS_NAME = 'output_bokeh rendered_html';\n", + "\n", + " /**\n", + " * Render data to the DOM node\n", + " */\n", + " function render(props, node) {\n", + " const script = document.createElement(\"script\");\n", + " node.appendChild(script);\n", + " }\n", + "\n", + " /**\n", + " * Handle when an output is cleared or removed\n", + " */\n", + " function handleClearOutput(event, handle) {\n", + " function drop(id) {\n", + " const view = Bokeh.index.get_by_id(id)\n", + " if (view != null) {\n", + " view.model.document.clear()\n", + " Bokeh.index.delete(view)\n", + " }\n", + " }\n", + "\n", + " const cell = handle.cell;\n", + "\n", + " const id = cell.output_area._bokeh_element_id;\n", + " const server_id = cell.output_area._bokeh_server_id;\n", + "\n", + " // Clean up Bokeh references\n", + " if (id != null) {\n", + " drop(id)\n", + " }\n", + "\n", + " if (server_id !== undefined) {\n", + " // Clean up Bokeh references\n", + " const cmd_clean = \"from bokeh.io.state import curstate; print(curstate().uuid_to_server['\" + server_id + \"'].get_sessions()[0].document.roots[0]._id)\";\n", + " cell.notebook.kernel.execute(cmd_clean, {\n", + " iopub: {\n", + " output: function(msg) {\n", + " const id = msg.content.text.trim()\n", + " drop(id)\n", + " }\n", + " }\n", + " });\n", + " // Destroy server and session\n", + " const cmd_destroy = \"import bokeh.io.notebook as ion; ion.destroy_server('\" + server_id + \"')\";\n", + " cell.notebook.kernel.execute(cmd_destroy);\n", + " }\n", + " }\n", + "\n", + " /**\n", + " * Handle when a new output is added\n", + " */\n", + " function handleAddOutput(event, handle) {\n", + " const output_area = handle.output_area;\n", + " const output = handle.output;\n", + "\n", + " // limit handleAddOutput to display_data with EXEC_MIME_TYPE content only\n", + " if ((output.output_type != \"display_data\") || (!Object.prototype.hasOwnProperty.call(output.data, EXEC_MIME_TYPE))) {\n", + " return\n", + " }\n", + "\n", + " const toinsert = output_area.element.find(\".\" + CLASS_NAME.split(' ')[0]);\n", + "\n", + " if (output.metadata[EXEC_MIME_TYPE][\"id\"] !== undefined) {\n", + " toinsert[toinsert.length - 1].firstChild.textContent = output.data[JS_MIME_TYPE];\n", + " // store reference to embed id on output_area\n", + " output_area._bokeh_element_id = output.metadata[EXEC_MIME_TYPE][\"id\"];\n", + " }\n", + " if (output.metadata[EXEC_MIME_TYPE][\"server_id\"] !== undefined) {\n", + " const bk_div = document.createElement(\"div\");\n", + " bk_div.innerHTML = output.data[HTML_MIME_TYPE];\n", + " const script_attrs = bk_div.children[0].attributes;\n", + " for (let i = 0; i < script_attrs.length; i++) {\n", + " toinsert[toinsert.length - 1].firstChild.setAttribute(script_attrs[i].name, script_attrs[i].value);\n", + " toinsert[toinsert.length - 1].firstChild.textContent = bk_div.children[0].textContent\n", + " }\n", + " // store reference to server id on output_area\n", + " output_area._bokeh_server_id = output.metadata[EXEC_MIME_TYPE][\"server_id\"];\n", + " }\n", + " }\n", + "\n", + " function register_renderer(events, OutputArea) {\n", + "\n", + " function append_mime(data, metadata, element) {\n", + " // create a DOM node to render to\n", + " const toinsert = this.create_output_subarea(\n", + " metadata,\n", + " CLASS_NAME,\n", + " EXEC_MIME_TYPE\n", + " );\n", + " this.keyboard_manager.register_events(toinsert);\n", + " // Render to node\n", + " const props = {data: data, metadata: metadata[EXEC_MIME_TYPE]};\n", + " render(props, toinsert[toinsert.length - 1]);\n", + " element.append(toinsert);\n", + " return toinsert\n", + " }\n", + "\n", + " /* Handle when an output is cleared or removed */\n", + " events.on('clear_output.CodeCell', handleClearOutput);\n", + " events.on('delete.Cell', handleClearOutput);\n", + "\n", + " /* Handle when a new output is added */\n", + " events.on('output_added.OutputArea', handleAddOutput);\n", + "\n", + " /**\n", + " * Register the mime type and append_mime function with output_area\n", + " */\n", + " OutputArea.prototype.register_mime_type(EXEC_MIME_TYPE, append_mime, {\n", + " /* Is output safe? */\n", + " safe: true,\n", + " /* Index of renderer in `output_area.display_order` */\n", + " index: 0\n", + " });\n", + " }\n", + "\n", + " // register the mime type if in Jupyter Notebook environment and previously unregistered\n", + " if (root.Jupyter !== undefined) {\n", + " const events = require('base/js/events');\n", + " const OutputArea = require('notebook/js/outputarea').OutputArea;\n", + "\n", + " if (OutputArea.prototype.mime_types().indexOf(EXEC_MIME_TYPE) == -1) {\n", + " register_renderer(events, OutputArea);\n", + " }\n", + " }\n", + " if (typeof (root._bokeh_timeout) === \"undefined\" || force === true) {\n", + " root._bokeh_timeout = Date.now() + 5000;\n", + " root._bokeh_failed_load = false;\n", + " }\n", + "\n", + " const NB_LOAD_WARNING = {'data': {'text/html':\n", + " \"
\\n\"+\n", + " \"

\\n\"+\n", + " \"BokehJS does not appear to have successfully loaded. If loading BokehJS from CDN, this \\n\"+\n", + " \"may be due to a slow or bad network connection. Possible fixes:\\n\"+\n", + " \"

\\n\"+\n", + " \"\\n\"+\n", + " \"\\n\"+\n", + " \"from bokeh.resources import INLINE\\n\"+\n", + " \"output_notebook(resources=INLINE)\\n\"+\n", + " \"\\n\"+\n", + " \"
\"}};\n", + "\n", + " function display_loaded() {\n", + " const el = document.getElementById(null);\n", + " if (el != null) {\n", + " el.textContent = \"BokehJS is loading...\";\n", + " }\n", + " if (root.Bokeh !== undefined) {\n", + " if (el != null) {\n", + " el.textContent = \"BokehJS \" + root.Bokeh.version + \" successfully loaded.\";\n", + " }\n", + " } else if (Date.now() < root._bokeh_timeout) {\n", + " setTimeout(display_loaded, 100)\n", + " }\n", + " }\n", + "\n", + " function run_callbacks() {\n", + " try {\n", + " root._bokeh_onload_callbacks.forEach(function(callback) {\n", + " if (callback != null)\n", + " callback();\n", + " });\n", + " } finally {\n", + " delete root._bokeh_onload_callbacks\n", + " }\n", + " console.debug(\"Bokeh: all callbacks have finished\");\n", + " }\n", + "\n", + " function load_libs(css_urls, js_urls, callback) {\n", + " if (css_urls == null) css_urls = [];\n", + " if (js_urls == null) js_urls = [];\n", + "\n", + " root._bokeh_onload_callbacks.push(callback);\n", + " if (root._bokeh_is_loading > 0) {\n", + " console.debug(\"Bokeh: BokehJS is being loaded, scheduling callback at\", now());\n", + " return null;\n", + " }\n", + " if (js_urls == null || js_urls.length === 0) {\n", + " run_callbacks();\n", + " return null;\n", + " }\n", + " console.debug(\"Bokeh: BokehJS not loaded, scheduling load and callback at\", now());\n", + " root._bokeh_is_loading = css_urls.length + js_urls.length;\n", + "\n", + " function on_load() {\n", + " root._bokeh_is_loading--;\n", + " if (root._bokeh_is_loading === 0) {\n", + " console.debug(\"Bokeh: all BokehJS libraries/stylesheets loaded\");\n", + " run_callbacks()\n", + " }\n", + " }\n", + "\n", + " function on_error(url) {\n", + " console.error(\"failed to load \" + url);\n", + " }\n", + "\n", + " for (let i = 0; i < css_urls.length; i++) {\n", + " const url = css_urls[i];\n", + " const element = document.createElement(\"link\");\n", + " element.onload = on_load;\n", + " element.onerror = on_error.bind(null, url);\n", + " element.rel = \"stylesheet\";\n", + " element.type = \"text/css\";\n", + " element.href = url;\n", + " console.debug(\"Bokeh: injecting link tag for BokehJS stylesheet: \", url);\n", + " document.body.appendChild(element);\n", + " }\n", + "\n", + " for (let i = 0; i < js_urls.length; i++) {\n", + " const url = js_urls[i];\n", + " const element = document.createElement('script');\n", + " element.onload = on_load;\n", + " element.onerror = on_error.bind(null, url);\n", + " element.async = false;\n", + " element.src = url;\n", + " console.debug(\"Bokeh: injecting script tag for BokehJS library: \", url);\n", + " document.head.appendChild(element);\n", + " }\n", + " };\n", + "\n", + " function inject_raw_css(css) {\n", + " const element = document.createElement(\"style\");\n", + " element.appendChild(document.createTextNode(css));\n", + " document.body.appendChild(element);\n", + " }\n", + "\n", + " const js_urls = [\"https://cdn.bokeh.org/bokeh/release/bokeh-3.3.0.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-gl-3.3.0.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-widgets-3.3.0.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-tables-3.3.0.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-mathjax-3.3.0.min.js\"];\n", + " const css_urls = [];\n", + "\n", + " const inline_js = [ function(Bokeh) {\n", + " Bokeh.set_log_level(\"info\");\n", + " },\n", + "function(Bokeh) {\n", + " }\n", + " ];\n", + "\n", + " function run_inline_js() {\n", + " if (root.Bokeh !== undefined || force === true) {\n", + " for (let i = 0; i < inline_js.length; i++) {\n", + " inline_js[i].call(root, root.Bokeh);\n", + " }\n", + "} else if (Date.now() < root._bokeh_timeout) {\n", + " setTimeout(run_inline_js, 100);\n", + " } else if (!root._bokeh_failed_load) {\n", + " console.log(\"Bokeh: BokehJS failed to load within specified timeout.\");\n", + " root._bokeh_failed_load = true;\n", + " } else if (force !== true) {\n", + " const cell = $(document.getElementById(null)).parents('.cell').data().cell;\n", + " cell.output_area.append_execute_result(NB_LOAD_WARNING)\n", + " }\n", + " }\n", + "\n", + " if (root._bokeh_is_loading === 0) {\n", + " console.debug(\"Bokeh: BokehJS loaded, going straight to plotting\");\n", + " run_inline_js();\n", + " } else {\n", + " load_libs(css_urls, js_urls, function() {\n", + " console.debug(\"Bokeh: BokehJS plotting callback run at\", now());\n", + " run_inline_js();\n", + " });\n", + " }\n", + "}(window));" + ], "application/vnd.bokehjs_load.v0+json": "" }, "metadata": {}, @@ -954,7 +1236,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.9.10" + "version": "3.10.11" } }, "nbformat": 4, diff --git a/docs/af1/af1.2.ipynb b/docs/af1/af1.2.ipynb new file mode 100644 index 0000000..72bf313 --- /dev/null +++ b/docs/af1/af1.2.ipynb @@ -0,0 +1,709 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": { + "id": "LBNBl2exUYWu" + }, + "source": [ + "# Af1.2\n", + "\n", + "The **[Af1.2](af1.2): _Anopheles gambiae_ data resource** contains single nucleotide polymorphism (SNP) calls and SNP haplotypes from whole-genome sequencing of 317 mosquitoes.\n", + "\n", + "More information about this release can be found in the [data resource website](https://www.malariagen.net/data_package/af12-anopheles-funestus-data-resource/). \n", + "\n", + "This page provides an introduction to open data resources released as part of `Af1.2`. \n", + "\n", + "If you have any questions about this guide or how to use the data, please [start a new discussion](https://github.com/malariagen/vector-public-data/discussions/new) on the malariagen/vector-open-data repo on GitHub. If you find any bugs, please [raise an issue](https://github.com/malariagen/vector-public-data/issues/new/choose)." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "kJqs4cXppk8j" + }, + "source": [ + "## Terms of use\n", + "\n", + "Data from this project will be made publicly available before journal publication. Unless otherwise stated, analyses of project data are ongoing and publications are in preparation by project partners, and it is not permitted to use project data for publication (including any type of communication with the general public) without prior permission from the originating partner studies. \n", + "\n", + "Although malaria is generally an endemic rather than an epidemic disease, and the focus of this project is on surveillance of disease vectors rather than pathogens, our data terms of use build on MalariaGEN's approach to data sharing, and adopt norms which have been established for rapid sharing of pathogen genomic data during disease outbreaks. The primary rationale for this approach is that malaria remains a public health emergency, where ethically appropriate and rapid sharing of genomic surveillance data can help to detect and respond to biological threats such as new forms of insecticide resistance, and to adapt malaria vector control strategies to different settings and changing circumstances.\n", + "\n", + "The publication embargo for all data on this release will expire on the **29th of April 2026**. \n", + "\n", + "If you have any questions about the terms of use, please email [support@malariagen.net](mailto:support@malariagen.net)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "iNSicUCtpk8j" + }, + "source": [ + "## Partner studies\n", + "\n", + "- [1236-VO-TZ-OKUMU](https://www.malariagen.net/network/where-we-work/1236-VO-TZ-OKUMU) - _Anopheles funestus_ vector surveillance in Tanzania\n", + "\n", + "- [1281-VO-CM-CHRISTOPHE](https://www.malariagen.net/network/where-we-work/1281-VO-CM-CHRISTOPHE) - PAMCA _Anopheles_ genomics programme - Malaria vector surveillance, population genetics and insecticide resistance characterization in four eco-epidemiological settings in Cameroon\n", + "\n", + "This release also includes data from one study openly available in the literature: [small-2023](https://doi.org/10.1073/pnas.2219835120)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "5RHbe7N6pk8k" + }, + "source": [ + "## Whole-genome sequencing and variant calling\n", + "\n", + "All samples in `Af1.2` have been sequenced individually to high coverage using Illumina technology at the Wellcome Sanger Institute. These sequence data have then been analysed to identify genetic variants such as single nucleotide polymorphisms (SNPs). After variant calling, both the samples and the variants have been through a range of quality control analyses, to ensure the data are of high quality. Both the raw sequence data and the curated variant calls are openly available for download and analysis. \n", + "\n", + "\n", + "For further information about the sequencing and variant calling methods used, please see the [methods page](methods)." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "9Hfchko2pk8l" + }, + "source": [ + "## Data hosting\n", + "\n", + "Data from `Af1.2` are hosted by several different services. \n", + "\n", + "The SNP data have also been uploaded to Google Cloud, and can be analysed directly within the cloud without having to download or copy any data, including via free interactive computing services such as [MyBinder](https://gke.mybinder.org/) and [Google Colab](https://colab.research.google.com/). Further information about analysing these data in the cloud is provided in the [cloud data access guide](cloud)." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "lTJ_EnvOpk8l" + }, + "source": [ + "## Sample sets\n", + "\n", + "The samples included in `Af1.2` have been organised into 3 sample sets. \n", + "\n", + "Each sample set corresponds to a set of mosquito specimens from a contributing study. Study details can be found in the partner studies webpages listed above." + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "hGA4d7Yrpk8m", + "outputId": "c29827c1-0361-4926-c227-8f6e76c2a497", + "tags": [ + "remove-input" + ] + }, + "outputs": [], + "source": [ + "%pip install -qq malariagen_data" + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": { + "id": "AnmzLmEgpk8n", + "tags": [ + "remove-input" + ] + }, + "outputs": [ + { + "data": { + "application/javascript": [ + "'use strict';\n", + "(function(root) {\n", + " function now() {\n", + " return new Date();\n", + " }\n", + "\n", + " const force = true;\n", + "\n", + " if (typeof root._bokeh_onload_callbacks === \"undefined\" || force === true) {\n", + " root._bokeh_onload_callbacks = [];\n", + " root._bokeh_is_loading = undefined;\n", + " }\n", + "\n", + "const JS_MIME_TYPE = 'application/javascript';\n", + " const HTML_MIME_TYPE = 'text/html';\n", + " const EXEC_MIME_TYPE = 'application/vnd.bokehjs_exec.v0+json';\n", + " const CLASS_NAME = 'output_bokeh rendered_html';\n", + "\n", + " /**\n", + " * Render data to the DOM node\n", + " */\n", + " function render(props, node) {\n", + " const script = document.createElement(\"script\");\n", + " node.appendChild(script);\n", + " }\n", + "\n", + " /**\n", + " * Handle when an output is cleared or removed\n", + " */\n", + " function handleClearOutput(event, handle) {\n", + " function drop(id) {\n", + " const view = Bokeh.index.get_by_id(id)\n", + " if (view != null) {\n", + " view.model.document.clear()\n", + " Bokeh.index.delete(view)\n", + " }\n", + " }\n", + "\n", + " const cell = handle.cell;\n", + "\n", + " const id = cell.output_area._bokeh_element_id;\n", + " const server_id = cell.output_area._bokeh_server_id;\n", + "\n", + " // Clean up Bokeh references\n", + " if (id != null) {\n", + " drop(id)\n", + " }\n", + "\n", + " if (server_id !== undefined) {\n", + " // Clean up Bokeh references\n", + " const cmd_clean = \"from bokeh.io.state import curstate; print(curstate().uuid_to_server['\" + server_id + \"'].get_sessions()[0].document.roots[0]._id)\";\n", + " cell.notebook.kernel.execute(cmd_clean, {\n", + " iopub: {\n", + " output: function(msg) {\n", + " const id = msg.content.text.trim()\n", + " drop(id)\n", + " }\n", + " }\n", + " });\n", + " // Destroy server and session\n", + " const cmd_destroy = \"import bokeh.io.notebook as ion; ion.destroy_server('\" + server_id + \"')\";\n", + " cell.notebook.kernel.execute(cmd_destroy);\n", + " }\n", + " }\n", + "\n", + " /**\n", + " * Handle when a new output is added\n", + " */\n", + " function handleAddOutput(event, handle) {\n", + " const output_area = handle.output_area;\n", + " const output = handle.output;\n", + "\n", + " // limit handleAddOutput to display_data with EXEC_MIME_TYPE content only\n", + " if ((output.output_type != \"display_data\") || (!Object.prototype.hasOwnProperty.call(output.data, EXEC_MIME_TYPE))) {\n", + " return\n", + " }\n", + "\n", + " const toinsert = output_area.element.find(\".\" + CLASS_NAME.split(' ')[0]);\n", + "\n", + " if (output.metadata[EXEC_MIME_TYPE][\"id\"] !== undefined) {\n", + " toinsert[toinsert.length - 1].firstChild.textContent = output.data[JS_MIME_TYPE];\n", + " // store reference to embed id on output_area\n", + " output_area._bokeh_element_id = output.metadata[EXEC_MIME_TYPE][\"id\"];\n", + " }\n", + " if (output.metadata[EXEC_MIME_TYPE][\"server_id\"] !== undefined) {\n", + " const bk_div = document.createElement(\"div\");\n", + " bk_div.innerHTML = output.data[HTML_MIME_TYPE];\n", + " const script_attrs = bk_div.children[0].attributes;\n", + " for (let i = 0; i < script_attrs.length; i++) {\n", + " toinsert[toinsert.length - 1].firstChild.setAttribute(script_attrs[i].name, script_attrs[i].value);\n", + " toinsert[toinsert.length - 1].firstChild.textContent = bk_div.children[0].textContent\n", + " }\n", + " // store reference to server id on output_area\n", + " output_area._bokeh_server_id = output.metadata[EXEC_MIME_TYPE][\"server_id\"];\n", + " }\n", + " }\n", + "\n", + " function register_renderer(events, OutputArea) {\n", + "\n", + " function append_mime(data, metadata, element) {\n", + " // create a DOM node to render to\n", + " const toinsert = this.create_output_subarea(\n", + " metadata,\n", + " CLASS_NAME,\n", + " EXEC_MIME_TYPE\n", + " );\n", + " this.keyboard_manager.register_events(toinsert);\n", + " // Render to node\n", + " const props = {data: data, metadata: metadata[EXEC_MIME_TYPE]};\n", + " render(props, toinsert[toinsert.length - 1]);\n", + " element.append(toinsert);\n", + " return toinsert\n", + " }\n", + "\n", + " /* Handle when an output is cleared or removed */\n", + " events.on('clear_output.CodeCell', handleClearOutput);\n", + " events.on('delete.Cell', handleClearOutput);\n", + "\n", + " /* Handle when a new output is added */\n", + " events.on('output_added.OutputArea', handleAddOutput);\n", + "\n", + " /**\n", + " * Register the mime type and append_mime function with output_area\n", + " */\n", + " OutputArea.prototype.register_mime_type(EXEC_MIME_TYPE, append_mime, {\n", + " /* Is output safe? */\n", + " safe: true,\n", + " /* Index of renderer in `output_area.display_order` */\n", + " index: 0\n", + " });\n", + " }\n", + "\n", + " // register the mime type if in Jupyter Notebook environment and previously unregistered\n", + " if (root.Jupyter !== undefined) {\n", + " const events = require('base/js/events');\n", + " const OutputArea = require('notebook/js/outputarea').OutputArea;\n", + "\n", + " if (OutputArea.prototype.mime_types().indexOf(EXEC_MIME_TYPE) == -1) {\n", + " register_renderer(events, OutputArea);\n", + " }\n", + " }\n", + " if (typeof (root._bokeh_timeout) === \"undefined\" || force === true) {\n", + " root._bokeh_timeout = Date.now() + 5000;\n", + " root._bokeh_failed_load = false;\n", + " }\n", + "\n", + " const NB_LOAD_WARNING = {'data': {'text/html':\n", + " \"
\\n\"+\n", + " \"

\\n\"+\n", + " \"BokehJS does not appear to have successfully loaded. If loading BokehJS from CDN, this \\n\"+\n", + " \"may be due to a slow or bad network connection. Possible fixes:\\n\"+\n", + " \"

\\n\"+\n", + " \"\\n\"+\n", + " \"\\n\"+\n", + " \"from bokeh.resources import INLINE\\n\"+\n", + " \"output_notebook(resources=INLINE)\\n\"+\n", + " \"\\n\"+\n", + " \"
\"}};\n", + "\n", + " function display_loaded(error = null) {\n", + " const el = document.getElementById(null);\n", + " if (el != null) {\n", + " const html = (() => {\n", + " if (typeof root.Bokeh === \"undefined\") {\n", + " if (error == null) {\n", + " return \"BokehJS is loading ...\";\n", + " } else {\n", + " return \"BokehJS failed to load.\";\n", + " }\n", + " } else {\n", + " const prefix = `BokehJS ${root.Bokeh.version}`;\n", + " if (error == null) {\n", + " return `${prefix} successfully loaded.`;\n", + " } else {\n", + " return `${prefix} encountered errors while loading and may not function as expected.`;\n", + " }\n", + " }\n", + " })();\n", + " el.innerHTML = html;\n", + "\n", + " if (error != null) {\n", + " const wrapper = document.createElement(\"div\");\n", + " wrapper.style.overflow = \"auto\";\n", + " wrapper.style.height = \"5em\";\n", + " wrapper.style.resize = \"vertical\";\n", + " const content = document.createElement(\"div\");\n", + " content.style.fontFamily = \"monospace\";\n", + " content.style.whiteSpace = \"pre-wrap\";\n", + " content.style.backgroundColor = \"rgb(255, 221, 221)\";\n", + " content.textContent = error.stack ?? error.toString();\n", + " wrapper.append(content);\n", + " el.append(wrapper);\n", + " }\n", + " } else if (Date.now() < root._bokeh_timeout) {\n", + " setTimeout(() => display_loaded(error), 100);\n", + " }\n", + " }\n", + "\n", + " function run_callbacks() {\n", + " try {\n", + " root._bokeh_onload_callbacks.forEach(function(callback) {\n", + " if (callback != null)\n", + " callback();\n", + " });\n", + " } finally {\n", + " delete root._bokeh_onload_callbacks\n", + " }\n", + " console.debug(\"Bokeh: all callbacks have finished\");\n", + " }\n", + "\n", + " function load_libs(css_urls, js_urls, callback) {\n", + " if (css_urls == null) css_urls = [];\n", + " if (js_urls == null) js_urls = [];\n", + "\n", + " root._bokeh_onload_callbacks.push(callback);\n", + " if (root._bokeh_is_loading > 0) {\n", + " console.debug(\"Bokeh: BokehJS is being loaded, scheduling callback at\", now());\n", + " return null;\n", + " }\n", + " if (js_urls == null || js_urls.length === 0) {\n", + " run_callbacks();\n", + " return null;\n", + " }\n", + " console.debug(\"Bokeh: BokehJS not loaded, scheduling load and callback at\", now());\n", + " root._bokeh_is_loading = css_urls.length + js_urls.length;\n", + "\n", + " function on_load() {\n", + " root._bokeh_is_loading--;\n", + " if (root._bokeh_is_loading === 0) {\n", + " console.debug(\"Bokeh: all BokehJS libraries/stylesheets loaded\");\n", + " run_callbacks()\n", + " }\n", + " }\n", + "\n", + " function on_error(url) {\n", + " console.error(\"failed to load \" + url);\n", + " }\n", + "\n", + " for (let i = 0; i < css_urls.length; i++) {\n", + " const url = css_urls[i];\n", + " const element = document.createElement(\"link\");\n", + " element.onload = on_load;\n", + " element.onerror = on_error.bind(null, url);\n", + " element.rel = \"stylesheet\";\n", + " element.type = \"text/css\";\n", + " element.href = url;\n", + " console.debug(\"Bokeh: injecting link tag for BokehJS stylesheet: \", url);\n", + " document.body.appendChild(element);\n", + " }\n", + "\n", + " for (let i = 0; i < js_urls.length; i++) {\n", + " const url = js_urls[i];\n", + " const element = document.createElement('script');\n", + " element.onload = on_load;\n", + " element.onerror = on_error.bind(null, url);\n", + " element.async = false;\n", + " element.src = url;\n", + " console.debug(\"Bokeh: injecting script tag for BokehJS library: \", url);\n", + " document.head.appendChild(element);\n", + " }\n", + " };\n", + "\n", + " function inject_raw_css(css) {\n", + " const element = document.createElement(\"style\");\n", + " element.appendChild(document.createTextNode(css));\n", + " document.body.appendChild(element);\n", + " }\n", + "\n", + " const js_urls = [\"https://cdn.bokeh.org/bokeh/release/bokeh-3.4.1.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-gl-3.4.1.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-widgets-3.4.1.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-tables-3.4.1.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-mathjax-3.4.1.min.js\"];\n", + " const css_urls = [];\n", + "\n", + " const inline_js = [ function(Bokeh) {\n", + " Bokeh.set_log_level(\"info\");\n", + " },\n", + "function(Bokeh) {\n", + " }\n", + " ];\n", + "\n", + " function run_inline_js() {\n", + " if (root.Bokeh !== undefined || force === true) {\n", + " try {\n", + " for (let i = 0; i < inline_js.length; i++) {\n", + " inline_js[i].call(root, root.Bokeh);\n", + " }\n", + "\n", + " } catch (error) {throw error;\n", + " }} else if (Date.now() < root._bokeh_timeout) {\n", + " setTimeout(run_inline_js, 100);\n", + " } else if (!root._bokeh_failed_load) {\n", + " console.log(\"Bokeh: BokehJS failed to load within specified timeout.\");\n", + " root._bokeh_failed_load = true;\n", + " } else if (force !== true) {\n", + " const cell = $(document.getElementById(null)).parents('.cell').data().cell;\n", + " cell.output_area.append_execute_result(NB_LOAD_WARNING)\n", + " }\n", + " }\n", + "\n", + " if (root._bokeh_is_loading === 0) {\n", + " console.debug(\"Bokeh: BokehJS loaded, going straight to plotting\");\n", + " run_inline_js();\n", + " } else {\n", + " load_libs(css_urls, js_urls, function() {\n", + " console.debug(\"Bokeh: BokehJS plotting callback run at\", now());\n", + " run_inline_js();\n", + " });\n", + " }\n", + "}(window));" + ], + "application/vnd.bokehjs_load.v0+json": "'use strict';\n(function(root) {\n function now() {\n return new Date();\n }\n\n const force = true;\n\n if (typeof root._bokeh_onload_callbacks === \"undefined\" || force === true) {\n root._bokeh_onload_callbacks = [];\n root._bokeh_is_loading = undefined;\n }\n\n\n if (typeof (root._bokeh_timeout) === \"undefined\" || force === true) {\n root._bokeh_timeout = Date.now() + 5000;\n root._bokeh_failed_load = false;\n }\n\n const NB_LOAD_WARNING = {'data': {'text/html':\n \"
\\n\"+\n \"

\\n\"+\n \"BokehJS does not appear to have successfully loaded. If loading BokehJS from CDN, this \\n\"+\n \"may be due to a slow or bad network connection. Possible fixes:\\n\"+\n \"

\\n\"+\n \"\\n\"+\n \"\\n\"+\n \"from bokeh.resources import INLINE\\n\"+\n \"output_notebook(resources=INLINE)\\n\"+\n \"\\n\"+\n \"
\"}};\n\n function display_loaded(error = null) {\n const el = document.getElementById(null);\n if (el != null) {\n const html = (() => {\n if (typeof root.Bokeh === \"undefined\") {\n if (error == null) {\n return \"BokehJS is loading ...\";\n } else {\n return \"BokehJS failed to load.\";\n }\n } else {\n const prefix = `BokehJS ${root.Bokeh.version}`;\n if (error == null) {\n return `${prefix} successfully loaded.`;\n } else {\n return `${prefix} encountered errors while loading and may not function as expected.`;\n }\n }\n })();\n el.innerHTML = html;\n\n if (error != null) {\n const wrapper = document.createElement(\"div\");\n wrapper.style.overflow = \"auto\";\n wrapper.style.height = \"5em\";\n wrapper.style.resize = \"vertical\";\n const content = document.createElement(\"div\");\n content.style.fontFamily = \"monospace\";\n content.style.whiteSpace = \"pre-wrap\";\n content.style.backgroundColor = \"rgb(255, 221, 221)\";\n content.textContent = error.stack ?? error.toString();\n wrapper.append(content);\n el.append(wrapper);\n }\n } else if (Date.now() < root._bokeh_timeout) {\n setTimeout(() => display_loaded(error), 100);\n }\n }\n\n function run_callbacks() {\n try {\n root._bokeh_onload_callbacks.forEach(function(callback) {\n if (callback != null)\n callback();\n });\n } finally {\n delete root._bokeh_onload_callbacks\n }\n console.debug(\"Bokeh: all callbacks have finished\");\n }\n\n function load_libs(css_urls, js_urls, callback) {\n if (css_urls == null) css_urls = [];\n if (js_urls == null) js_urls = [];\n\n root._bokeh_onload_callbacks.push(callback);\n if (root._bokeh_is_loading > 0) {\n console.debug(\"Bokeh: BokehJS is being loaded, scheduling callback at\", now());\n return null;\n }\n if (js_urls == null || js_urls.length === 0) {\n run_callbacks();\n return null;\n }\n console.debug(\"Bokeh: BokehJS not loaded, scheduling load and callback at\", now());\n root._bokeh_is_loading = css_urls.length + js_urls.length;\n\n function on_load() {\n root._bokeh_is_loading--;\n if (root._bokeh_is_loading === 0) {\n console.debug(\"Bokeh: all BokehJS libraries/stylesheets loaded\");\n run_callbacks()\n }\n }\n\n function on_error(url) {\n console.error(\"failed to load \" + url);\n }\n\n for (let i = 0; i < css_urls.length; i++) {\n const url = css_urls[i];\n const element = document.createElement(\"link\");\n element.onload = on_load;\n element.onerror = on_error.bind(null, url);\n element.rel = \"stylesheet\";\n element.type = \"text/css\";\n element.href = url;\n console.debug(\"Bokeh: injecting link tag for BokehJS stylesheet: \", url);\n document.body.appendChild(element);\n }\n\n for (let i = 0; i < js_urls.length; i++) {\n const url = js_urls[i];\n const element = document.createElement('script');\n element.onload = on_load;\n element.onerror = on_error.bind(null, url);\n element.async = false;\n element.src = url;\n console.debug(\"Bokeh: injecting script tag for BokehJS library: \", url);\n document.head.appendChild(element);\n }\n };\n\n function inject_raw_css(css) {\n const element = document.createElement(\"style\");\n element.appendChild(document.createTextNode(css));\n document.body.appendChild(element);\n }\n\n const js_urls = [\"https://cdn.bokeh.org/bokeh/release/bokeh-3.4.1.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-gl-3.4.1.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-widgets-3.4.1.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-tables-3.4.1.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-mathjax-3.4.1.min.js\"];\n const css_urls = [];\n\n const inline_js = [ function(Bokeh) {\n Bokeh.set_log_level(\"info\");\n },\nfunction(Bokeh) {\n }\n ];\n\n function run_inline_js() {\n if (root.Bokeh !== undefined || force === true) {\n try {\n for (let i = 0; i < inline_js.length; i++) {\n inline_js[i].call(root, root.Bokeh);\n }\n\n } catch (error) {throw error;\n }} else if (Date.now() < root._bokeh_timeout) {\n setTimeout(run_inline_js, 100);\n } else if (!root._bokeh_failed_load) {\n console.log(\"Bokeh: BokehJS failed to load within specified timeout.\");\n root._bokeh_failed_load = true;\n } else if (force !== true) {\n const cell = $(document.getElementById(null)).parents('.cell').data().cell;\n cell.output_area.append_execute_result(NB_LOAD_WARNING)\n }\n }\n\n if (root._bokeh_is_loading === 0) {\n console.debug(\"Bokeh: BokehJS loaded, going straight to plotting\");\n run_inline_js();\n } else {\n load_libs(css_urls, js_urls, function() {\n console.debug(\"Bokeh: BokehJS plotting callback run at\", now());\n run_inline_js();\n });\n }\n}(window));" + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "import malariagen_data\n", + "af1 = malariagen_data.Af1()" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 927 + }, + "id": "qsElasBepk8n", + "outputId": "4bf80a06-c2e8-4d2d-b4a6-99c8c66da7db", + "tags": [ + "remove-input" + ] + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
sample_setsample_count
study_id
1236-VO-TZ-OKUMU1236-VO-TZ-OKUMU-VMF0025259
1281-VO-CM-CHRISTOPHE1281-VO-CM-CHRISTOPHE-VMF0022781
small-2023small-2023177
\n", + "
" + ], + "text/plain": [ + " sample_set sample_count\n", + "study_id \n", + "1236-VO-TZ-OKUMU 1236-VO-TZ-OKUMU-VMF00252 59\n", + "1281-VO-CM-CHRISTOPHE 1281-VO-CM-CHRISTOPHE-VMF00227 81\n", + "small-2023 small-2023 177" + ] + }, + "execution_count": 3, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df_sample_sets = af1.sample_sets(release=\"1.2\")\n", + "df_sample_sets[['study_id','sample_set', 'sample_count']].set_index('study_id')" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "yJ16OQ0Hpk8o" + }, + "source": [ + "Here is a more detailed breakdown of the samples contained within this sample set, summarised by country, year of collection, and species:" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 1000 + }, + "id": "a1OMvuTxUWpJ", + "outputId": "9f872334-fd50-4649-990a-df60ea71c12c", + "tags": [ + "remove-input" + ] + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " \r" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
taxonfunestus
study_idsample_setcountryyear
1236-VO-TZ-OKUMU1236-VO-TZ-OKUMU-VMF00252Tanzania202259
1281-VO-CM-CHRISTOPHE1281-VO-CM-CHRISTOPHE-VMF00227Cameroon202081
small-2023small-2023Burkina Faso200055
200112
2002110
\n", + "
" + ], + "text/plain": [ + "taxon funestus\n", + "study_id sample_set country year \n", + "1236-VO-TZ-OKUMU 1236-VO-TZ-OKUMU-VMF00252 Tanzania 2022 59\n", + "1281-VO-CM-CHRISTOPHE 1281-VO-CM-CHRISTOPHE-VMF00227 Cameroon 2020 81\n", + "small-2023 small-2023 Burkina Faso 2000 55\n", + " 2001 12\n", + " 2002 110" + ] + }, + "execution_count": 4, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df_samples = af1.sample_metadata(sample_sets=\"1.2\")\n", + "df_summary = df_samples.pivot_table(\n", + " index=[\"study_id\",\"sample_set\", \"country\", \"year\"], \n", + " columns=[\"taxon\"],\n", + " values=\"sample_id\", \n", + " aggfunc=len,\n", + " fill_value=0)\n", + "df_summary" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "dLiU0ulIpk8p" + }, + "source": [ + "Note that there can be multiple sampling sites represented within the same sample set." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "OToX5vhfpk8p" + }, + "source": [ + "## Further reading\n", + "\n", + "We hope this page has provided a useful introduction to the `Af1.2` data resource. If you would like to start working with these data, please visit the [cloud data access guide](cloud) or the [data download guide](download) or continue browsing the other documentation on this site.\n", + "\n", + "If you have any questions about the data and how to use them, please do get in touch by [starting a new discussion](https://github.com/malariagen/vector-data/discussions/new) on the malariagen/vector-data repository on GitHub." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "celltoolbar": "Tags", + "colab": { + "name": "Ag3.0-intro.ipynb", + "provenance": [] + }, + "kernelspec": { + "display_name": "global-global-binder-5.0.0", + "language": "python", + "name": "conda-env-global-global-binder-5.0.0-py" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.10.14" + } + }, + "nbformat": 4, + "nbformat_minor": 4 +} diff --git a/docs/af1/af1.3.ipynb b/docs/af1/af1.3.ipynb new file mode 100644 index 0000000..826e048 --- /dev/null +++ b/docs/af1/af1.3.ipynb @@ -0,0 +1,672 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": { + "id": "LBNBl2exUYWu" + }, + "source": [ + "# Af1.3\n", + "\n", + "The **[Af1.3](af1.3): _Anopheles gambiae_ data resource** contains single nucleotide polymorphism (SNP) calls and SNP haplotypes from whole-genome sequencing of 193 mosquitoes.\n", + "\n", + "More information about this release can be found in the [data resource website](https://www.malariagen.net/data_package/af13-anopheles-funestus-data-resource/). \n", + "\n", + "This page provides an introduction to open data resources released as part of `Af1.3`. \n", + "\n", + "If you have any questions about this guide or how to use the data, please [start a new discussion](https://github.com/malariagen/vector-public-data/discussions/new) on the malariagen/vector-open-data repo on GitHub. If you find any bugs, please [raise an issue](https://github.com/malariagen/vector-public-data/issues/new/choose)." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "kJqs4cXppk8j" + }, + "source": [ + "## Terms of use\n", + "\n", + "Data from this project will be made publicly available before journal publication. Unless otherwise stated, analyses of project data are ongoing and publications are in preparation by project partners, and it is not permitted to use project data for publication (including any type of communication with the general public) without prior permission from the originating partner studies. \n", + "\n", + "Although malaria is generally an endemic rather than an epidemic disease, and the focus of this project is on surveillance of disease vectors rather than pathogens, our data terms of use build on MalariaGEN's approach to data sharing, and adopt norms which have been established for rapid sharing of pathogen genomic data during disease outbreaks. The primary rationale for this approach is that malaria remains a public health emergency, where ethically appropriate and rapid sharing of genomic surveillance data can help to detect and respond to biological threats such as new forms of insecticide resistance, and to adapt malaria vector control strategies to different settings and changing circumstances.\n", + "\n", + "The publication embargo for all data on this release will expire on the **29th of April 2026**. \n", + "\n", + "If you have any questions about the terms of use, please email [support@malariagen.net](mailto:support@malariagen.net)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "iNSicUCtpk8j" + }, + "source": [ + "## Partner studies\n", + "\n", + "- [1236-VO-TZ-OKUMU](https://www.malariagen.net/network/where-we-work/1236-VO-TZ-OKUMU) - _Anopheles funestus_ vector surveillance in Tanzania" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "5RHbe7N6pk8k" + }, + "source": [ + "## Whole-genome sequencing and variant calling\n", + "\n", + "All samples in `Af1.3` have been sequenced individually to high coverage using Illumina technology at the Wellcome Sanger Institute. These sequence data have then been analysed to identify genetic variants such as single nucleotide polymorphisms (SNPs). After variant calling, both the samples and the variants have been through a range of quality control analyses, to ensure the data are of high quality. Both the raw sequence data and the curated variant calls are openly available for download and analysis. \n", + "\n", + "\n", + "For further information about the sequencing and variant calling methods used, please see the [methods page](methods)." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "9Hfchko2pk8l" + }, + "source": [ + "## Data hosting\n", + "\n", + "Data from `Af1.3` are hosted by several different services. \n", + "\n", + "The SNP data have also been uploaded to Google Cloud, and can be analysed directly within the cloud without having to download or copy any data, including via free interactive computing services such as [MyBinder](https://gke.mybinder.org/) and [Google Colab](https://colab.research.google.com/). Further information about analysing these data in the cloud is provided in the [cloud data access guide](cloud)." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "lTJ_EnvOpk8l" + }, + "source": [ + "## Sample sets\n", + "\n", + "The samples included in `Af1.3` have been organised into 1 sample set. \n", + "\n", + "Each sample set corresponds to a set of mosquito specimens from a contributing study. Study details can be found in the partner studies webpages listed above." + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "hGA4d7Yrpk8m", + "outputId": "c29827c1-0361-4926-c227-8f6e76c2a497", + "tags": [ + "remove-input" + ] + }, + "outputs": [], + "source": [ + "%pip install -qq malariagen_data" + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": { + "id": "AnmzLmEgpk8n", + "tags": [ + "remove-input" + ] + }, + "outputs": [ + { + "data": { + "application/javascript": [ + "'use strict';\n", + "(function(root) {\n", + " function now() {\n", + " return new Date();\n", + " }\n", + "\n", + " const force = true;\n", + "\n", + " if (typeof root._bokeh_onload_callbacks === \"undefined\" || force === true) {\n", + " root._bokeh_onload_callbacks = [];\n", + " root._bokeh_is_loading = undefined;\n", + " }\n", + "\n", + "const JS_MIME_TYPE = 'application/javascript';\n", + " const HTML_MIME_TYPE = 'text/html';\n", + " const EXEC_MIME_TYPE = 'application/vnd.bokehjs_exec.v0+json';\n", + " const CLASS_NAME = 'output_bokeh rendered_html';\n", + "\n", + " /**\n", + " * Render data to the DOM node\n", + " */\n", + " function render(props, node) {\n", + " const script = document.createElement(\"script\");\n", + " node.appendChild(script);\n", + " }\n", + "\n", + " /**\n", + " * Handle when an output is cleared or removed\n", + " */\n", + " function handleClearOutput(event, handle) {\n", + " function drop(id) {\n", + " const view = Bokeh.index.get_by_id(id)\n", + " if (view != null) {\n", + " view.model.document.clear()\n", + " Bokeh.index.delete(view)\n", + " }\n", + " }\n", + "\n", + " const cell = handle.cell;\n", + "\n", + " const id = cell.output_area._bokeh_element_id;\n", + " const server_id = cell.output_area._bokeh_server_id;\n", + "\n", + " // Clean up Bokeh references\n", + " if (id != null) {\n", + " drop(id)\n", + " }\n", + "\n", + " if (server_id !== undefined) {\n", + " // Clean up Bokeh references\n", + " const cmd_clean = \"from bokeh.io.state import curstate; print(curstate().uuid_to_server['\" + server_id + \"'].get_sessions()[0].document.roots[0]._id)\";\n", + " cell.notebook.kernel.execute(cmd_clean, {\n", + " iopub: {\n", + " output: function(msg) {\n", + " const id = msg.content.text.trim()\n", + " drop(id)\n", + " }\n", + " }\n", + " });\n", + " // Destroy server and session\n", + " const cmd_destroy = \"import bokeh.io.notebook as ion; ion.destroy_server('\" + server_id + \"')\";\n", + " cell.notebook.kernel.execute(cmd_destroy);\n", + " }\n", + " }\n", + "\n", + " /**\n", + " * Handle when a new output is added\n", + " */\n", + " function handleAddOutput(event, handle) {\n", + " const output_area = handle.output_area;\n", + " const output = handle.output;\n", + "\n", + " // limit handleAddOutput to display_data with EXEC_MIME_TYPE content only\n", + " if ((output.output_type != \"display_data\") || (!Object.prototype.hasOwnProperty.call(output.data, EXEC_MIME_TYPE))) {\n", + " return\n", + " }\n", + "\n", + " const toinsert = output_area.element.find(\".\" + CLASS_NAME.split(' ')[0]);\n", + "\n", + " if (output.metadata[EXEC_MIME_TYPE][\"id\"] !== undefined) {\n", + " toinsert[toinsert.length - 1].firstChild.textContent = output.data[JS_MIME_TYPE];\n", + " // store reference to embed id on output_area\n", + " output_area._bokeh_element_id = output.metadata[EXEC_MIME_TYPE][\"id\"];\n", + " }\n", + " if (output.metadata[EXEC_MIME_TYPE][\"server_id\"] !== undefined) {\n", + " const bk_div = document.createElement(\"div\");\n", + " bk_div.innerHTML = output.data[HTML_MIME_TYPE];\n", + " const script_attrs = bk_div.children[0].attributes;\n", + " for (let i = 0; i < script_attrs.length; i++) {\n", + " toinsert[toinsert.length - 1].firstChild.setAttribute(script_attrs[i].name, script_attrs[i].value);\n", + " toinsert[toinsert.length - 1].firstChild.textContent = bk_div.children[0].textContent\n", + " }\n", + " // store reference to server id on output_area\n", + " output_area._bokeh_server_id = output.metadata[EXEC_MIME_TYPE][\"server_id\"];\n", + " }\n", + " }\n", + "\n", + " function register_renderer(events, OutputArea) {\n", + "\n", + " function append_mime(data, metadata, element) {\n", + " // create a DOM node to render to\n", + " const toinsert = this.create_output_subarea(\n", + " metadata,\n", + " CLASS_NAME,\n", + " EXEC_MIME_TYPE\n", + " );\n", + " this.keyboard_manager.register_events(toinsert);\n", + " // Render to node\n", + " const props = {data: data, metadata: metadata[EXEC_MIME_TYPE]};\n", + " render(props, toinsert[toinsert.length - 1]);\n", + " element.append(toinsert);\n", + " return toinsert\n", + " }\n", + "\n", + " /* Handle when an output is cleared or removed */\n", + " events.on('clear_output.CodeCell', handleClearOutput);\n", + " events.on('delete.Cell', handleClearOutput);\n", + "\n", + " /* Handle when a new output is added */\n", + " events.on('output_added.OutputArea', handleAddOutput);\n", + "\n", + " /**\n", + " * Register the mime type and append_mime function with output_area\n", + " */\n", + " OutputArea.prototype.register_mime_type(EXEC_MIME_TYPE, append_mime, {\n", + " /* Is output safe? */\n", + " safe: true,\n", + " /* Index of renderer in `output_area.display_order` */\n", + " index: 0\n", + " });\n", + " }\n", + "\n", + " // register the mime type if in Jupyter Notebook environment and previously unregistered\n", + " if (root.Jupyter !== undefined) {\n", + " const events = require('base/js/events');\n", + " const OutputArea = require('notebook/js/outputarea').OutputArea;\n", + "\n", + " if (OutputArea.prototype.mime_types().indexOf(EXEC_MIME_TYPE) == -1) {\n", + " register_renderer(events, OutputArea);\n", + " }\n", + " }\n", + " if (typeof (root._bokeh_timeout) === \"undefined\" || force === true) {\n", + " root._bokeh_timeout = Date.now() + 5000;\n", + " root._bokeh_failed_load = false;\n", + " }\n", + "\n", + " const NB_LOAD_WARNING = {'data': {'text/html':\n", + " \"
\\n\"+\n", + " \"

\\n\"+\n", + " \"BokehJS does not appear to have successfully loaded. If loading BokehJS from CDN, this \\n\"+\n", + " \"may be due to a slow or bad network connection. Possible fixes:\\n\"+\n", + " \"

\\n\"+\n", + " \"\\n\"+\n", + " \"\\n\"+\n", + " \"from bokeh.resources import INLINE\\n\"+\n", + " \"output_notebook(resources=INLINE)\\n\"+\n", + " \"\\n\"+\n", + " \"
\"}};\n", + "\n", + " function display_loaded(error = null) {\n", + " const el = document.getElementById(null);\n", + " if (el != null) {\n", + " const html = (() => {\n", + " if (typeof root.Bokeh === \"undefined\") {\n", + " if (error == null) {\n", + " return \"BokehJS is loading ...\";\n", + " } else {\n", + " return \"BokehJS failed to load.\";\n", + " }\n", + " } else {\n", + " const prefix = `BokehJS ${root.Bokeh.version}`;\n", + " if (error == null) {\n", + " return `${prefix} successfully loaded.`;\n", + " } else {\n", + " return `${prefix} encountered errors while loading and may not function as expected.`;\n", + " }\n", + " }\n", + " })();\n", + " el.innerHTML = html;\n", + "\n", + " if (error != null) {\n", + " const wrapper = document.createElement(\"div\");\n", + " wrapper.style.overflow = \"auto\";\n", + " wrapper.style.height = \"5em\";\n", + " wrapper.style.resize = \"vertical\";\n", + " const content = document.createElement(\"div\");\n", + " content.style.fontFamily = \"monospace\";\n", + " content.style.whiteSpace = \"pre-wrap\";\n", + " content.style.backgroundColor = \"rgb(255, 221, 221)\";\n", + " content.textContent = error.stack ?? error.toString();\n", + " wrapper.append(content);\n", + " el.append(wrapper);\n", + " }\n", + " } else if (Date.now() < root._bokeh_timeout) {\n", + " setTimeout(() => display_loaded(error), 100);\n", + " }\n", + " }\n", + "\n", + " function run_callbacks() {\n", + " try {\n", + " root._bokeh_onload_callbacks.forEach(function(callback) {\n", + " if (callback != null)\n", + " callback();\n", + " });\n", + " } finally {\n", + " delete root._bokeh_onload_callbacks\n", + " }\n", + " console.debug(\"Bokeh: all callbacks have finished\");\n", + " }\n", + "\n", + " function load_libs(css_urls, js_urls, callback) {\n", + " if (css_urls == null) css_urls = [];\n", + " if (js_urls == null) js_urls = [];\n", + "\n", + " root._bokeh_onload_callbacks.push(callback);\n", + " if (root._bokeh_is_loading > 0) {\n", + " console.debug(\"Bokeh: BokehJS is being loaded, scheduling callback at\", now());\n", + " return null;\n", + " }\n", + " if (js_urls == null || js_urls.length === 0) {\n", + " run_callbacks();\n", + " return null;\n", + " }\n", + " console.debug(\"Bokeh: BokehJS not loaded, scheduling load and callback at\", now());\n", + " root._bokeh_is_loading = css_urls.length + js_urls.length;\n", + "\n", + " function on_load() {\n", + " root._bokeh_is_loading--;\n", + " if (root._bokeh_is_loading === 0) {\n", + " console.debug(\"Bokeh: all BokehJS libraries/stylesheets loaded\");\n", + " run_callbacks()\n", + " }\n", + " }\n", + "\n", + " function on_error(url) {\n", + " console.error(\"failed to load \" + url);\n", + " }\n", + "\n", + " for (let i = 0; i < css_urls.length; i++) {\n", + " const url = css_urls[i];\n", + " const element = document.createElement(\"link\");\n", + " element.onload = on_load;\n", + " element.onerror = on_error.bind(null, url);\n", + " element.rel = \"stylesheet\";\n", + " element.type = \"text/css\";\n", + " element.href = url;\n", + " console.debug(\"Bokeh: injecting link tag for BokehJS stylesheet: \", url);\n", + " document.body.appendChild(element);\n", + " }\n", + "\n", + " for (let i = 0; i < js_urls.length; i++) {\n", + " const url = js_urls[i];\n", + " const element = document.createElement('script');\n", + " element.onload = on_load;\n", + " element.onerror = on_error.bind(null, url);\n", + " element.async = false;\n", + " element.src = url;\n", + " console.debug(\"Bokeh: injecting script tag for BokehJS library: \", url);\n", + " document.head.appendChild(element);\n", + " }\n", + " };\n", + "\n", + " function inject_raw_css(css) {\n", + " const element = document.createElement(\"style\");\n", + " element.appendChild(document.createTextNode(css));\n", + " document.body.appendChild(element);\n", + " }\n", + "\n", + " const js_urls = [\"https://cdn.bokeh.org/bokeh/release/bokeh-3.4.1.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-gl-3.4.1.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-widgets-3.4.1.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-tables-3.4.1.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-mathjax-3.4.1.min.js\"];\n", + " const css_urls = [];\n", + "\n", + " const inline_js = [ function(Bokeh) {\n", + " Bokeh.set_log_level(\"info\");\n", + " },\n", + "function(Bokeh) {\n", + " }\n", + " ];\n", + "\n", + " function run_inline_js() {\n", + " if (root.Bokeh !== undefined || force === true) {\n", + " try {\n", + " for (let i = 0; i < inline_js.length; i++) {\n", + " inline_js[i].call(root, root.Bokeh);\n", + " }\n", + "\n", + " } catch (error) {throw error;\n", + " }} else if (Date.now() < root._bokeh_timeout) {\n", + " setTimeout(run_inline_js, 100);\n", + " } else if (!root._bokeh_failed_load) {\n", + " console.log(\"Bokeh: BokehJS failed to load within specified timeout.\");\n", + " root._bokeh_failed_load = true;\n", + " } else if (force !== true) {\n", + " const cell = $(document.getElementById(null)).parents('.cell').data().cell;\n", + " cell.output_area.append_execute_result(NB_LOAD_WARNING)\n", + " }\n", + " }\n", + "\n", + " if (root._bokeh_is_loading === 0) {\n", + " console.debug(\"Bokeh: BokehJS loaded, going straight to plotting\");\n", + " run_inline_js();\n", + " } else {\n", + " load_libs(css_urls, js_urls, function() {\n", + " console.debug(\"Bokeh: BokehJS plotting callback run at\", now());\n", + " run_inline_js();\n", + " });\n", + " }\n", + "}(window));" + ], + "application/vnd.bokehjs_load.v0+json": "'use strict';\n(function(root) {\n function now() {\n return new Date();\n }\n\n const force = true;\n\n if (typeof root._bokeh_onload_callbacks === \"undefined\" || force === true) {\n root._bokeh_onload_callbacks = [];\n root._bokeh_is_loading = undefined;\n }\n\n\n if (typeof (root._bokeh_timeout) === \"undefined\" || force === true) {\n root._bokeh_timeout = Date.now() + 5000;\n root._bokeh_failed_load = false;\n }\n\n const NB_LOAD_WARNING = {'data': {'text/html':\n \"
\\n\"+\n \"

\\n\"+\n \"BokehJS does not appear to have successfully loaded. If loading BokehJS from CDN, this \\n\"+\n \"may be due to a slow or bad network connection. Possible fixes:\\n\"+\n \"

\\n\"+\n \"\\n\"+\n \"\\n\"+\n \"from bokeh.resources import INLINE\\n\"+\n \"output_notebook(resources=INLINE)\\n\"+\n \"\\n\"+\n \"
\"}};\n\n function display_loaded(error = null) {\n const el = document.getElementById(null);\n if (el != null) {\n const html = (() => {\n if (typeof root.Bokeh === \"undefined\") {\n if (error == null) {\n return \"BokehJS is loading ...\";\n } else {\n return \"BokehJS failed to load.\";\n }\n } else {\n const prefix = `BokehJS ${root.Bokeh.version}`;\n if (error == null) {\n return `${prefix} successfully loaded.`;\n } else {\n return `${prefix} encountered errors while loading and may not function as expected.`;\n }\n }\n })();\n el.innerHTML = html;\n\n if (error != null) {\n const wrapper = document.createElement(\"div\");\n wrapper.style.overflow = \"auto\";\n wrapper.style.height = \"5em\";\n wrapper.style.resize = \"vertical\";\n const content = document.createElement(\"div\");\n content.style.fontFamily = \"monospace\";\n content.style.whiteSpace = \"pre-wrap\";\n content.style.backgroundColor = \"rgb(255, 221, 221)\";\n content.textContent = error.stack ?? error.toString();\n wrapper.append(content);\n el.append(wrapper);\n }\n } else if (Date.now() < root._bokeh_timeout) {\n setTimeout(() => display_loaded(error), 100);\n }\n }\n\n function run_callbacks() {\n try {\n root._bokeh_onload_callbacks.forEach(function(callback) {\n if (callback != null)\n callback();\n });\n } finally {\n delete root._bokeh_onload_callbacks\n }\n console.debug(\"Bokeh: all callbacks have finished\");\n }\n\n function load_libs(css_urls, js_urls, callback) {\n if (css_urls == null) css_urls = [];\n if (js_urls == null) js_urls = [];\n\n root._bokeh_onload_callbacks.push(callback);\n if (root._bokeh_is_loading > 0) {\n console.debug(\"Bokeh: BokehJS is being loaded, scheduling callback at\", now());\n return null;\n }\n if (js_urls == null || js_urls.length === 0) {\n run_callbacks();\n return null;\n }\n console.debug(\"Bokeh: BokehJS not loaded, scheduling load and callback at\", now());\n root._bokeh_is_loading = css_urls.length + js_urls.length;\n\n function on_load() {\n root._bokeh_is_loading--;\n if (root._bokeh_is_loading === 0) {\n console.debug(\"Bokeh: all BokehJS libraries/stylesheets loaded\");\n run_callbacks()\n }\n }\n\n function on_error(url) {\n console.error(\"failed to load \" + url);\n }\n\n for (let i = 0; i < css_urls.length; i++) {\n const url = css_urls[i];\n const element = document.createElement(\"link\");\n element.onload = on_load;\n element.onerror = on_error.bind(null, url);\n element.rel = \"stylesheet\";\n element.type = \"text/css\";\n element.href = url;\n console.debug(\"Bokeh: injecting link tag for BokehJS stylesheet: \", url);\n document.body.appendChild(element);\n }\n\n for (let i = 0; i < js_urls.length; i++) {\n const url = js_urls[i];\n const element = document.createElement('script');\n element.onload = on_load;\n element.onerror = on_error.bind(null, url);\n element.async = false;\n element.src = url;\n console.debug(\"Bokeh: injecting script tag for BokehJS library: \", url);\n document.head.appendChild(element);\n }\n };\n\n function inject_raw_css(css) {\n const element = document.createElement(\"style\");\n element.appendChild(document.createTextNode(css));\n document.body.appendChild(element);\n }\n\n const js_urls = [\"https://cdn.bokeh.org/bokeh/release/bokeh-3.4.1.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-gl-3.4.1.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-widgets-3.4.1.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-tables-3.4.1.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-mathjax-3.4.1.min.js\"];\n const css_urls = [];\n\n const inline_js = [ function(Bokeh) {\n Bokeh.set_log_level(\"info\");\n },\nfunction(Bokeh) {\n }\n ];\n\n function run_inline_js() {\n if (root.Bokeh !== undefined || force === true) {\n try {\n for (let i = 0; i < inline_js.length; i++) {\n inline_js[i].call(root, root.Bokeh);\n }\n\n } catch (error) {throw error;\n }} else if (Date.now() < root._bokeh_timeout) {\n setTimeout(run_inline_js, 100);\n } else if (!root._bokeh_failed_load) {\n console.log(\"Bokeh: BokehJS failed to load within specified timeout.\");\n root._bokeh_failed_load = true;\n } else if (force !== true) {\n const cell = $(document.getElementById(null)).parents('.cell').data().cell;\n cell.output_area.append_execute_result(NB_LOAD_WARNING)\n }\n }\n\n if (root._bokeh_is_loading === 0) {\n console.debug(\"Bokeh: BokehJS loaded, going straight to plotting\");\n run_inline_js();\n } else {\n load_libs(css_urls, js_urls, function() {\n console.debug(\"Bokeh: BokehJS plotting callback run at\", now());\n run_inline_js();\n });\n }\n}(window));" + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "import malariagen_data\n", + "af1 = malariagen_data.Af1()" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 927 + }, + "id": "qsElasBepk8n", + "outputId": "4bf80a06-c2e8-4d2d-b4a6-99c8c66da7db", + "tags": [ + "remove-input" + ] + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
sample_setsample_count
study_id
1236-VO-TZ-OKUMU1236-VO-TZ-OKUMU-VMF00261193
\n", + "
" + ], + "text/plain": [ + " sample_set sample_count\n", + "study_id \n", + "1236-VO-TZ-OKUMU 1236-VO-TZ-OKUMU-VMF00261 193" + ] + }, + "execution_count": 2, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df_sample_sets = af1.sample_sets(release=\"1.3\")\n", + "df_sample_sets[['study_id','sample_set', 'sample_count']].set_index('study_id')" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "yJ16OQ0Hpk8o" + }, + "source": [ + "Here is a more detailed breakdown of the samples contained within this sample set, summarised by country, year of collection, and species:" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 1000 + }, + "id": "a1OMvuTxUWpJ", + "outputId": "9f872334-fd50-4649-990a-df60ea71c12c", + "tags": [ + "remove-input" + ] + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " \r" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
taxonfunestus
study_idsample_setcountryyear
1236-VO-TZ-OKUMU1236-VO-TZ-OKUMU-VMF00261Tanzania2022138
202355
\n", + "
" + ], + "text/plain": [ + "taxon funestus\n", + "study_id sample_set country year \n", + "1236-VO-TZ-OKUMU 1236-VO-TZ-OKUMU-VMF00261 Tanzania 2022 138\n", + " 2023 55" + ] + }, + "execution_count": 3, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df_samples = af1.sample_metadata(sample_sets=\"1.3\")\n", + "df_summary = df_samples.pivot_table(\n", + " index=[\"study_id\",\"sample_set\", \"country\", \"year\"], \n", + " columns=[\"taxon\"],\n", + " values=\"sample_id\", \n", + " aggfunc=len,\n", + " fill_value=0)\n", + "df_summary" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "dLiU0ulIpk8p" + }, + "source": [ + "Note that there can be multiple sampling sites represented within the same sample set." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "OToX5vhfpk8p" + }, + "source": [ + "## Further reading\n", + "\n", + "We hope this page has provided a useful introduction to the `Af1.3` data resource. If you would like to start working with these data, please visit the [cloud data access guide](cloud) or the [data download guide](download) or continue browsing the other documentation on this site.\n", + "\n", + "If you have any questions about the data and how to use them, please do get in touch by [starting a new discussion](https://github.com/malariagen/vector-data/discussions/new) on the malariagen/vector-data repository on GitHub." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "celltoolbar": "Tags", + "colab": { + "name": "Ag3.0-intro.ipynb", + "provenance": [] + }, + "kernelspec": { + "display_name": "global-global-binder-5.0.0", + "language": "python", + "name": "conda-env-global-global-binder-5.0.0-py" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.10.14" + } + }, + "nbformat": 4, + "nbformat_minor": 4 +}