2a:null 2b:["$","title",null,{"children":"Visualization of RNASeq raw data | Tomaz Mohoric | Observable"}] 30:[] 2e:{"id":"0b50581f49537206","slug":"visualization-of-rnaseq-raw-data","title":"Visualization of RNASeq raw data","thumbnail":"6332f2f8b6b1f024f3248c22e81794dc16479bda02a1db2bfd55e604956a029b","access_level":"public","create_time":"$D2021-02-10T17:50:47.892Z","update_time":"$D2021-03-16T20:51:10.750Z","view_time":null,"first_public_time":"$D2021-02-10T18:09:38.469Z","fork":false,"stars":0,"starred":false,"owner":{"type":"team","id":"e418e540719406f7","login":"tomazm","name":"Tomaz Mohoric","avatar_url":null,"tier":"starter_2024"},"version":385,"publish_version":385,"role":null,"authored":false,"authors":[{"type":"individual","id":"acb80c7d769b3359","login":"tomazm","name":"Tomaz Mohoric","avatar_url":null,"tier":null}],"members":[{"type":"individual","id":"acb80c7d769b3359","login":"tomazm","name":"Tomaz Mohoric","avatar_url":null,"tier":null,"role":"editor"}],"comments":[],"custom_thumbnail":false,"trashed":false,"subscribed":null,"forks":2,"collection":null,"type":"notebook","body":{"title":"Visualization of RNASeq raw data","cells":[{"id":0,"value":"md`# Visualization of RNASeq raw data`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":331,"value":"viewof keyword = Text({label: \"Enter the first gene name to be searched for:\", value: \"CYP\"})","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":376,"value":"viewof keyword2 = Text({label: \"Enter the second gene name to be searched for:\", value: \"CYP\"})","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":364,"value":"md`Below all the genes containing the first OR the second gene name will be listed. Select the genes which will be displayed in the heatmap:`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":338,"value":"viewof selected_gene_objects = Table(gene_objects_with_names, {value: gene_objects_with_names.slice(0, 5), columns: [\"SYMBOL\", \"Ensembl_IDs\", \"24h\", \"48h\", \"72h\"]})","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":212,"value":"viewof width = Range([350, 650], {step: 20, value: 350, label: \"Heatmap width\"})","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":215,"value":"viewof height = Range([250, 650], {step: 20, value: 250, label: \"Heatmap height\"})","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":314,"value":"viewof rescaled_counts = Toggle({label: \"Rescaled counts:\"})","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":64,"value":"html`Selected genes:

${selected_gene_objects.map(item => html`

${item.NAME}`)}`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":232,"value":"md`### Average read counts as a heatmap`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":134,"value":"average_counts_heatmap = {\n var color_column;\n \n if (rescaled_counts) {\n color_column = \"RESCALED_COUNT\";\n } else {\n color_column = \"COUNT\";\n }\n\n return vl.markRect().data(reshaped_rnaseq_data)\n .encode(\n vl.y().fieldN(\"SAMPLE\"),\n vl.x().fieldN(\"TIMEPOINT\").sort(timepoints),\n vl.color().fieldQ(color_column)\n .scale({type: \"linear\", scheme: \"pinkyellowgreen\", zero: false, nice: true})\n .legend({titleOrient: 'right', tickCount: 5}),\n vl.tooltip([\n vl.fieldN(\"SYMBOL\"),\n vl.fieldN(\"ENSEMBL\"),\n vl.fieldN(\"TIMEPOINT\"),\n vl.fieldQ(\"COUNT\"),\n vl.fieldQ(\"RESCALED_COUNT\")]),\n ).width(width).height(height).render()\n}","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":293,"value":"md`### Average read counts as a line chart`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":263,"value":"viewof linechart = {\n const layer_1 = vl.markLine().data(reshaped_rnaseq_data)\n .encode(\n vl.x().fieldN(\"TIMEPOINT\").sort(timepoints),\n vl.y().fieldQ(\"COUNT\"),\n vl.color().fieldN(\"SAMPLE\")\n ).width(width).height(height)\n \n const layer_2 = vl.markPoint().data(reshaped_rnaseq_data)\n .encode(\n vl.x().fieldN(\"TIMEPOINT\").sort(timepoints),\n vl.y().fieldQ(\"COUNT\"),\n vl.color().fieldN(\"SAMPLE\")\n )\n \n return vl.layer(layer_1, layer_2).render()\n}","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":237,"value":"md`### Average normalized read counts as a heatmap`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":250,"value":"vl.markRect().data(reshaped_normalized_rnaseq_data)\n .encode(\n vl.y().fieldN(\"SAMPLE\"),\n vl.x().fieldN(\"TIMEPOINT\").sort(timepoints),\n vl.color().fieldQ(\"COUNT\")\n .scale({type: \"linear\", scheme: \"pinkyellowgreen\", zero: false, nice: true})\n .legend({titleOrient: 'right', tickCount: 5}),\n vl.tooltip([\n vl.fieldN(\"SYMBOL\"),\n vl.fieldN(\"ENSEMBL\"),\n vl.fieldN(\"TIMEPOINT\"),\n vl.fieldQ(\"COUNT\")]),\n ).width(width).height(height).render()","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":126,"value":"reshaped_rnaseq_data = reshape_rnaseq_data(rnaseq_data)","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":245,"value":"reshaped_normalized_rnaseq_data = reshape_normalized_rnaseq_data(normalized_rnaseq_data)","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":114,"value":"timepoints = [\"24h\", \"48h\", \"72h\", \"144h\"]","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":113,"value":"reshape_rnaseq_data = function(data) {\n var i, j;\n var arr = [];\n \n for (i = 0; i < data.length; i++) {\n for (j = 0; j < timepoints.length; j++) {\n var item = data[i];\n var timepoint = timepoints[j];\n var count_column_name = timepoint;\n\n var new_item = {\n \"SYMBOL\": item.SYMBOL,\n \"ENSEMBL\": item.Ensembl_IDs,\n \"TIMEPOINT\": timepoint,\n \"COUNT\": item[count_column_name],\n \"RESCALED_COUNT\": item[count_column_name] / max_count,\n \"SAMPLE\": item.SYMBOL + \", \" + item.Ensembl_IDs,\n };\n\n arr.push(new_item); \n }\n }\n \n return arr;\n}","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":240,"value":"replicates = [1, 2, 3]","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":230,"value":"reshape_normalized_rnaseq_data = function(data) {\n var i, j, k;\n var arr = [];\n \n for (i = 0; i < data.length; i++) {\n for (j = 0; j < timepoints.length; j++) {\n var item = data[i];\n var timepoint = timepoints[j];\n \n var average_count = 0;\n \n for (k = 0; k < replicates.length; k++) {\n var count_column_name = timepoint + \"_Replicate\" + replicates[k];\n average_count = average_count + item[count_column_name];\n }\n \n average_count = average_count / (replicates.length);\n\n var new_item = {\n \"SYMBOL\": item.SYMBOL,\n \"ENSEMBL\": item.Ensembl_IDs,\n \"TIMEPOINT\": timepoint,\n \"COUNT\": average_count,\n \"SAMPLE\": item.SYMBOL + \", \" + item.Ensembl_IDs,\n };\n\n arr.push(new_item); \n }\n }\n \n return arr;\n}","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":228,"value":"normalized_rnaseq_data = fetch_dataset_to_array(normalized_dataset_url, query_options_for_rnaseq_data)","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":110,"value":"rnaseq_data = fetch_dataset_to_array(dataset_url, query_options_for_rnaseq_data)","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":104,"value":"query_options_for_rnaseq_data = {\n return {\n method: 'POST',\n body: JSON.stringify({\n condition: {\n containedIn: [\n {column: [\"Ensembl_IDs\"]}, selected_gene_objects.map(item => item.Ensembl_IDs),\n ]\n },\n \n })\n }\n}","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":77,"value":"//selected_gene_objects = gene_objects_with_names.filter(item => selected_genes.includes(item.NAME))","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":201,"value":"gene_list = gene_objects_with_names.map(item => item.NAME)","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":70,"value":"gene_objects_with_names = gene_objects.map(item => {item.NAME = item.SYMBOL + \", \" + item.Ensembl_IDs; return item})","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":301,"value":"max_count = {\n var maximums = [];\n var i;\n \n for (i = 0; i < timepoints.length; i++) {\n var timepoint = timepoints[i];\n maximums.push(\n Math.max(...gene_objects.map(item => item[timepoint]))\n ) \n }\n\n return Math.max(...maximums);\n}","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":14,"value":"gene_objects = fetch_dataset_to_array(dataset_url, query_options_for_gene_list)","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":50,"value":"function dynamicSort(property) {\n var sortOrder = 1;\n if(property[0] === \"-\") {\n sortOrder = -1;\n property = property.substr(1);\n }\n return function (a,b) {\n /* next line works with strings and numbers, \n * and you may want to customize it to your needs\n */\n var result = (a[property] < b[property]) ? -1 : (a[property] > b[property]) ? 1 : 0;\n return result * sortOrder;\n }\n}","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":4,"value":"function fetch_dataset_to_array(dataset_url, query_options) {\n return fetch(dataset_url, query_options).then(response_dataset => {\n if (!response_dataset.ok) throw new Error(response_dataset.status);\n return response_dataset.json();}).then(json => json.results.map(x => x.data));\n}","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":16,"value":"query_options_for_gene_list = {\n return {\n method: 'POST',\n body: JSON.stringify({\n //columns: [\"Ensembl_IDs\", \"SYMBOL\"],\n condition: { \n or: [\n {fuzzySearch: [{ \"column\": [\"SYMBOL\"] }, keyword]},\n {fuzzySearch: [{ \"column\": [\"SYMBOL\"] }, keyword2]},\n ]\n },\n orderBy: [{ expression: { column: [\"SYMBOL\"] }, ordering: \"ascending\" }],\n })\n }\n}","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":225,"value":"normalized_dataset_url = api_url + dataset_id + \"/versions/3/data\"","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":5,"value":"dataset_url = api_url + dataset_id + \"/versions/4/data\"","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":7,"value":"api_url = \"https://api.edelweissdata.com/datasets/\"","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":10,"value":"dataset_id = \"7bff53eb-7c1a-4875-b6b1-cd002e7e9c4c\"","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":35,"value":"import {Select, Range, Toggle, Search, Table, Text} from \"@observablehq/inputs\"","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":135,"value":"import {vl} from \"@vega/vega-lite-api\"","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"}],"files":"$W30","stdlib":"1","titling":"auto"}} 2f:"$2e:body"