29:null 2a:["$","title",null,{"children":"Unique and shared phamilies (and their protein functions) for each cluster. | jmu | Observable"}] 2f:T47b,SELECT PhamilyName, ANY_VALUE(genesByCluster.genefunction) as cluster1annotation, ANY_VALUE(genesByCluster2.genefunction) as cluster2annotation, MAX(functionFrequencies.frequency) as freqInFirstCluster, MAX(functionFrequencies2.frequency) as freqInSecondCluster, ANY_VALUE(clusterSharedPhamilies.size) as numberOfPhages, FROM totalPhamsInCluster1and2 INNER JOIN clusterSharedPhamilies ON totalPhamsInCluster1and2.phamilyname = clusterSharedPhamilies.phamname INNER JOIN clusterSharedPhamilies2 ON totalPhamsInCluster1and2.phamilyname = clusterSharedPhamilies2.phamname INNER JOIN genesByCluster ON clusterSharedPhamilies.phamname = genesByCluster.phamname INNER JOIN genesByCluster2 ON clusterSharedPhamilies2.phamname = genesByCluster2.phamname LEFT JOIN functionFrequencies ON genesByCluster.genefunction = functionFrequencies.function LEFT JOIN functionFrequencies2 ON genesByCluster2.genefunction = functionFrequencies2.function WHERE functionFrequencies.function != '' and functionFrequencies2.function != '' GROUP BY PhamilyName ORDER BY PhamilyName ASC30:T52b,**Table 5.** This is a comparison of the phamilies that are shared between clusters ${selectedCluster} and ${selectedCluster2} and are annotated in both clusters. This table will help to get a general idea about the function of the genes in the shared phamily and whether or not these are essential for a phage in either cluster. Remember that there are **${totalPhamsInCluster.length.toLocaleString()} phamilies** in Cluster ${selectedCluster} and **${totalPhamsInCluster2.length.toLocaleString()} phamilies** in Cluster ${selectedCluster2} ** Column Descriptions ** - _cluster1annotation_: represents how the phamily was annotated in Cluster ${selectedCluster} - _freqInCluster1_: represents how many times the phamily was seen in Cluster ${selectedCluster} genomes - _cluster2annotation_: represents how the phamily was annotated in Cluster ${selectedCluster2} - _freqInCluster2_: represents how many times the phamily was seen in Cluster ${selectedCluster2} genomes - _numberOfPhages_ represents the number of phages that have that phamily across many clusters (not just Clusters ${selectedCluster} and ${selectedCluster2}). *Any phamily that was seen in one cluster but not the other was removed from the table, and any phamilies that were annotated in one cluster, but not in the other were removed from the table. 31:T6c7,clusterSpecificPhamilies = { // create a place to store the list of cluster-specific phamilies let clusterSpecificPhamilies = []; // conver the phamilies array of objects into one large object for efficient lookup let phamiliesObj = {}; phamilies.forEach((phamily) => { let phamName = phamily.PhamID; let size = phamily.size; phamiliesObj[phamName] = size; }); // get a list of the genes for the selected cluster let genesByCluster = await getPhameratorData( dataset, `/genesbycluster/${selectedCluster}`, user.email, user.password ); // for each gene get its phamily name and add it to a set let uniqueNames = new Set(genesByCluster.map((gene) => gene.phamName)); // for each phamily name, see if the number of members of the phamily in this cluster is the same as the phamily size: for (let phamName of uniqueNames) { let countPhamMembersThisCluster = genesByCluster.filter( (gene) => gene.phamName === phamName ).length; let phamSize = phamiliesObj[phamName]; // - if yes, then this phamily only exists in the selected cluster if (countPhamMembersThisCluster === phamSize) { let phamColor = genesByCluster.filter( (gene) => gene.phamName === phamName )[0].phamColor; phamName = +phamName; clusterSpecificPhamilies.push({ phamName: phamName, size: phamSize, phamColor: phamColor }); } } // - if no, this phamily exists elsewhere so do nothing // add the pham color to each cluster-specific phamily for (let phamily of clusterSpecificPhamilies) { // to do... } clusterSpecificPhamilies.sort((a, b) => a.phamName - b.phamName); return clusterSpecificPhamilies; }32:T649,clusterSharedPhamilies = { // create a place to store the list of phamilies that are shared in the selected cluster let clusterSharedPhamilies = []; // covert the phamilies array of objects into one large object for looking up let phamiliesObject = {}; phamilies.forEach((phamily) => { let phamName = phamily.PhamID; let size = phamily.size; phamiliesObject[phamName] = size; }); // get a list of genes for the selected cluster let genesByCluster = await getPhameratorData( dataset, `/genesbycluster/${selectedCluster}`, user.email, user.password ); // for each gene get its phamily name and add it to a set let sharedNames = new Set(genesByCluster.map((gene) => gene.phamName)); // for each phamily name, see if the number of members of the phamily in this cluster are than phamily size: for (let phamName of sharedNames) { let countPhamMembersThisCluster = genesByCluster.filter( (gene) => gene.phamName === phamName ).length; let phamSize = phamiliesObject[phamName]; // - if no, then this phamily exists in multiple clusters if (countPhamMembersThisCluster != phamSize) { let phamColor = genesByCluster.filter( (gene) => gene.phamName === phamName )[0].phamColor; phamName = +phamName; clusterSharedPhamilies.push({ phamName: phamName, size: phamSize, phamColor: phamColor, }); } } // - if yes, this phamily is unique to the cluster and can be found under the clusterSpecificPhamilies clusterSharedPhamilies.sort((a, b) => a.phamName - b.phamName); return clusterSharedPhamilies; }33:T6d2,clusterSpecificPhamilies2 = { // create a place to store the list of cluster-specific phamilies let clusterSpecificPhamilies2 = []; // conver the phamilies array of objects into one large object for efficient lookup let phamiliesObj = {}; phamilies.forEach((phamily) => { let phamName = phamily.PhamID; let size = phamily.size; phamiliesObj[phamName] = size; }); // get a list of the genes for the selected cluster let genesByCluster2 = await getPhameratorData( dataset, `/genesbycluster/${selectedCluster2}`, user.email, user.password ); // for each gene get its phamily name and add it to a set let uniqueNames = new Set(genesByCluster2.map((gene) => gene.phamName)); // for each phamily name, see if the number of members of the phamily in this cluster is the same as the phamily size: for (let phamName of uniqueNames) { let countPhamMembersThisCluster = genesByCluster2.filter( (gene) => gene.phamName === phamName ).length; let phamSize = phamiliesObj[phamName]; // - if yes, then this phamily only exists in the selected cluster if (countPhamMembersThisCluster === phamSize) { let phamColor = genesByCluster2.filter( (gene) => gene.phamName === phamName )[0].phamColor; phamName = +phamName; clusterSpecificPhamilies2.push({ phamName: phamName, size: phamSize, phamColor: phamColor }); } } // - if no, this phamily exists elsewhere so do nothing // add the pham color to each cluster-specific phamily for (let phamily of clusterSpecificPhamilies2) { // to do... } clusterSpecificPhamilies2.sort((a, b) => a.phamName - b.phamName); return clusterSpecificPhamilies2; }34:T653,clusterSharedPhamilies2 = { // create a place to store the list of phamilies that are shared in the selected cluster let clusterSharedPhamilies2 = []; // covert the phamilies array of objects into one large object for looking up let phamiliesObject = {}; phamilies.forEach((phamily) => { let phamName = phamily.PhamID; let size = phamily.size; phamiliesObject[phamName] = size; }); // get a list of genes for the selected cluster let genesByCluster2 = await getPhameratorData( dataset, `/genesbycluster/${selectedCluster2}`, user.email, user.password ); // for each gene get its phamily name and add it to a set let sharedNames = new Set(genesByCluster2.map((gene) => gene.phamName)); // for each phamily name, see if the number of members of the phamily in this cluster are than phamily size: for (let phamName of sharedNames) { let countPhamMembersThisCluster = genesByCluster2.filter( (gene) => gene.phamName === phamName ).length; let phamSize = phamiliesObject[phamName]; // - if no, then this phamily exists in multiple clusters if (countPhamMembersThisCluster != phamSize) { let phamColor = genesByCluster2.filter( (gene) => gene.phamName === phamName )[0].phamColor; phamName = +phamName; clusterSharedPhamilies2.push({ phamName: phamName, size: phamSize, phamColor: phamColor, }); } } // - if yes, this phamily is unique to the cluster and can be found under the clusterSpecificPhamilies clusterSharedPhamilies2.sort((a, b) => a.phamName - b.phamName); return clusterSharedPhamilies2; }35:[] 2d:{"id":"d40c050df9b7eee0","slug":null,"title":"Unique and shared phamilies (and their protein functions) for each cluster.","thumbnail":"386b2a113aca44c2de7c8a092cdb8a7dcba83c0ac0389f261a536dcc4928eff6","access_level":"public","create_time":"$D2023-06-01T16:50:20.847Z","update_time":"$D2023-06-01T16:50:20.847Z","view_time":null,"first_public_time":"$D2023-06-01T16:50:20.847Z","fork":{"id":"1ea78bef13b2ba72","slug":null,"title":"Unique and shared phamilies (and their protein functions) for each cluster.","owner":{"id":"3e2509283042eb59","login":"icobb","name":"Isobel Cobb"}},"stars":0,"starred":false,"owner":{"type":"team","id":"e0829639966b8d05","login":"jmu","name":"jmu","avatar_url":"https://avatars-next.observableusercontent.com/cb03e8ef2752ae7ab793227e02781453a58a3c89c8b64632a330bcf788d83ba4","tier":"starter_2024"},"version":2022,"publish_version":null,"role":null,"authored":false,"authors":[{"type":"individual","id":"cb7ded4a1c316f71","login":"zshiff02","name":"Zelda","avatar_url":"https://avatars-next.observableusercontent.com/29ce3190c8bd7d97a9f638ae7a13cd9dbcf41f6028155c086d3367a37b729e86","tier":null}],"members":[{"type":"team","id":"e0829639966b8d05","login":"jmu","name":"jmu","avatar_url":"https://avatars-next.observableusercontent.com/cb03e8ef2752ae7ab793227e02781453a58a3c89c8b64632a330bcf788d83ba4","tier":"starter_2024","role":"editor"},{"type":"individual","id":"cb7ded4a1c316f71","login":"zshiff02","name":"Zelda","avatar_url":"https://avatars-next.observableusercontent.com/29ce3190c8bd7d97a9f638ae7a13cd9dbcf41f6028155c086d3367a37b729e86","tier":null,"role":"editor"}],"comments":[],"custom_thumbnail":false,"trashed":false,"lapsed":null,"subscribed":null,"forks":0,"collection":null,"type":"notebook","body":{"title":"Unique and shared phamilies (and their protein functions) for each cluster.","cells":[{"id":0,"value":"# Unique and shared phamilies (and their protein functions) for each cluster.","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","output":"","database":"$undefined"},{"id":473,"value":"terms","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":75,"value":"md`### *Welcome${user.name ? \", \" + user.name.split(\" \")[0] : \"\"}!* :)`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":27,"value":"viewof formData = {\n let formData = \"Signed In\";\n formData = formWithSubmit(html`\n \n`);\n return formData;\n}","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":815,"value":"## Table of Contents\n- [Select Your Clusters](#selectclusters)\n- [Information about Selected Clusters](#selectedclusterinfo)\n\n### Cluster ${selectedCluster}\n- [Unique Phamily Information](#UniquePhamilyInformation)\n- [Shared Phamily Information](#SharedPhamilyInformation)\n- [Protein Function Information](#proteinFunctionInfo)\n\n### Cluster ${selectedCluster2}\n- [Unique Phamily Information](#UniquePhamilyInformation2)\n- [Shared Phamily Information](#SharedPhamilyInformation2)\n- [Protein Function Information](#proteinFunctionInfo2)\n\n### [Comparing Cluster ${selectedCluster} and Cluster ${selectedCluster2}](#proteinComparison)\n- [Looking at the number of Cluster ${selectedCluster} and Cluster ${selectedCluster2} phages that a specfic shared phamily occurs in](#sharedPhamilyTable)","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","output":"","database":"$undefined"},{"id":848,"value":"selectedcluster = md`\n

\n# Select Your Clusters\nSelect two clusters that you would like to compare from the Actino_Draft Database.\n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":29,"value":"viewof dataset = Inputs.select(user.datasets.sort(), {\n label: \"Select a data set\",\n value: \"Actino_Draft\"\n})","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":31,"value":"viewof selectedCluster = Inputs.select(\n clusters.map((c) => c.name),\n {\n label: \"Select a cluster\", value: \"Q\"\n }\n)","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":731,"value":"viewof selectedCluster2 = Inputs.select(\n clusters.map((c) => c.name),\n {\n label: \"Select a second cluster\", value: \"F\"\n }\n)","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":845,"value":"selectedclusterinfo = md`\n

\n# Information About Selected Clusters\n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":268,"value":"## Cluster ${selectedCluster}:\n- **Cluster ${selectedCluster}** has **${phages.length.toLocaleString()} phages**. Within Cluster ${selectedCluster} genomes there are ${totalPhamsInCluster.length.toLocaleString()} phamilies in total with **${clusterSpecificPhamilies.length.toLocaleString()} phamilies** being unique to Cluster ${selectedCluster}.\n\n## Cluster ${selectedCluster2}:\n- **Cluster ${selectedCluster2}** has **${phages2.length.toLocaleString()} phages**. Within Cluster ${selectedCluster2} genomes there are ${totalPhamsInCluster2.length.toLocaleString()} phamilies in total with **${clusterSpecificPhamilies2.length.toLocaleString()} phamilies** being unique to Cluster ${selectedCluster2}.","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","output":"","database":"$undefined"},{"id":820,"value":"UniquePhamilyInformation = md`\n

\n# Unique Phamily Information: Cluster ${selectedCluster}\n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":881,"value":"_NOTE: it might be interesting to make a bubble chart with all of the phamilies in the cluster and then have one color be the shared phams and one color be the unique phams._","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","output":"","database":"$undefined"},{"id":131,"value":"uniquePhams = BubbleChart(clusterSpecificPhamilies, {\n label: (d) =>\n [d.phamName, `(${d.size})`].join(\"\\n\"),\n value: (d) => d.size,\n stroke: \"black\",\n group: (d) => d.phamName,\n groups: clusterSpecificPhamilies.map((d) => d.phamName),\n strokeWidth: 1,\n fillOpacity: 1,\n colors: clusterSpecificPhamilies.map((d) => d.phamColor),\n title: (d) =>\n `phamily: ${d.phamName.toLocaleString(\"en\")}\\nsize: ${d.size.toLocaleString(\n \"en\"\n )}\\n`,\n width: 1152\n})","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":96,"value":"**Figure 1.** This bubble chart displays the **${clusterSpecificPhamilies.length.toLocaleString()}** phamilies that are found only in **Cluster ${selectedCluster}** genomes. \n\nThe number on top is the phamily name and the number on the bottom is the number of times the phamily is seen in Cluster ${selectedCluster} genomes. The size correlates to the number of phages it is found in, with a larger bubble indicating that the phamily is present in a higher number of phages within the cluster.","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","output":"","database":"$undefined"},{"id":1108,"value":"SELECT * FROM clusterSpecificPhamilies","pinned":false,"hidden":false,"mode":"sql","author":"$undefined","summary":"$undefined","output":"","database":"var:clusterSpecificPhamilies"},{"id":535,"value":"**Table 1.** This table shows the phamilies that are **unique to Cluster ${selectedCluster}**.","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","output":"","database":"$undefined"},{"id":190,"value":"SELECT DISTINCT genesByCluster.phamName AS Phamily, size ,function AS annotatedFunction, frequency AS frequencyAcrossCluster FROM clusterSpecificPhamilies\nINNER JOIN genesByCluster\nON clusterSpecificPhamilies.phamName = genesByCluster.phamName\nINNER JOIN functionFrequencies\nON genesByCluster.geneFunction = functionFrequencies.function\n","pinned":false,"hidden":false,"mode":"sql","author":"$undefined","summary":"$undefined","output":"uniquePhamFunction","database":"var:combinedDB"},{"id":263,"value":"**Table 2.** This table shows the phamilies that are **unique to Cluster ${selectedCluster}** that have an annotated function. The function is listed with its frequency within the entire cluster. Sometimes, the phamily is seen in the genome, but it does not have an annotated function, so this should be taken with a grain of salt. The size column lists the number of phages the phamily is seen in Cluster ${selectedCluster}.","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","output":"","database":"$undefined"},{"id":574,"value":"SharedPhamilyInformation = md`\n

\n# Shared Phamily Information: Cluster ${selectedCluster}\n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":1045,"value":"sharedPhams = BubbleChart(clusterSharedPhamilies, {\n label: (d) =>\n [d.phamName, `(${d.size})`].join(\"\\n\"),\n value: (d) => d.size,\n stroke: \"black\",\n group: (d) => d.phamName,\n groups: clusterSharedPhamilies.map((d) => d.phamName),\n strokeWidth: 1,\n fillOpacity: 1,\n colors: clusterSharedPhamilies.map((d) => d.phamColor),\n title: (d) =>\n `phamily: ${d.phamName.toLocaleString(\"en\")}\\nsize: ${d.size.toLocaleString(\n \"en\"\n )}\\n`,\n width: 1152\n})","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":506,"value":"**Figure 2.** This bubble chart displays the **${clusterSharedPhamilies.length.toLocaleString()}** phamilies that are **not unique** to **Cluster ${selectedCluster}** genomes. \n\nThe number on top is the phamily name and the number on the bottom is the number of times the phamily is seen in Cluster ${selectedCluster} phages. The size correlates to the number of phages it is present in, with a larger bubble indicating that the phamily is present in a higher number of phages across clusters.\n","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","output":"","database":"$undefined"},{"id":1112,"value":"SELECT * FROM clusterSharedPhamilies","pinned":false,"hidden":false,"mode":"sql","author":"$undefined","summary":"$undefined","output":"","database":"var:clusterSharedPhamilies"},{"id":548,"value":"**Table 3.** This table shows the phamilies that are **not unique** to **Cluster ${selectedCluster}** (meaning that these phams are present in other clusters).\n\n","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","output":"","database":"$undefined"},{"id":487,"value":"SELECT Distinct function AS annotatedFunction, genesByCluster.phamName AS Phamily, phamilies.size, frequency AS frequencyAcrossCluster FROM phamilies\nInner join genesByCluster\nON phamilies.PhamID = genesByCluster.phamName\nINNER JOIN functionFrequencies\nON genesByCluster.geneFunction = functionFrequencies.function\nfull outer join clusterSpecificPhamilies\nON phamilies.PhamID = clusterSpecificPhamilies.phamName\nWHERE clusterSpecificPhamilies.phamName is null","pinned":false,"hidden":false,"mode":"sql","author":"$undefined","summary":"$undefined","output":"functionsOfSharedPhams","database":"var:combinedDB"},{"id":551,"value":"**Table 4.** This table shows the phamilies that are **not unique** to **Cluster ${selectedCluster}** that have an annotated function. The function is listed with its frequency within the entire ${selectedCluster} cluster. Sometimes, the phamily is seen in the genome, but it does not have an annotated function, so this should be taken with a grain of salt. The size column lists the number of phages the phamily is seen across various clusters.","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","output":"","database":"$undefined"},{"id":576,"value":"proteinFunctionInfo = md`\n

\n# Protein Function Information: Cluster ${selectedCluster}\n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":128,"value":"Plot.plot({\n width: width,\n marginLeft: 250,\n marks: [\n Plot.barX(functionFrequencies, {\n x: \"frequency\",\n y: \"function\",\n fill: \"frequency\",\n sort: {y: \"x\", reverse: true, limit: 20},\n stroke: \"frequency\",\n title: (d) => `${d.frequency}`\n }),\n Plot.ruleX([0])\n ],\n \n color: { scheme: \"Purples\" }\n})\n ","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":135,"value":"**Figure 3.** This chart shows the top 20 most frequent annotated protein functions in **Cluster ${selectedCluster}**. These include phams that are shared and unique to this cluster. ","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","output":"","database":"$undefined"},{"id":1298,"value":"Plot.plot({\n width: width,\n marginLeft: 250,\n marks: [\n Plot.barX(uniquePhamFunction, {\n x: \"frequencyAcrossCluster\",\n y: \"annotatedFunction\",\n fill: \"frequencyAcrossCluster\",\n sort: {y: \"x\", reverse: true, limit: 20},\n stroke: \"frequencyAcrossCluster\",\n title: (d) => `${d.frequencyAcrossCluster}`\n }),\n Plot.ruleX([0])\n ],\n \n color: { scheme: \"Blues\" }\n})\n ","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":1892,"value":"**Figure 4.** This chart shows the top 20 most frequent annotated protein functions of _phams unique_ to **Cluster ${selectedCluster}**. \n\nThe reason why some bars are segmented when you hover over them is that there are different phamilies that encode for that function. For example, there are three unique phams that are annotated as minor tail proteins.","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","output":"","database":"$undefined"},{"id":304,"value":"Sunburst(dataFlare, {\n // path: (d) => d.name, // e.g. flare/animate/Easing\n label: (d) => d.name, // display text\n value: (d) => d?.value, // angle of each arc\n title: (d, n) => [n.id, n.value.toLocaleString()].join(\"\\n\"), // hover text\n width: 1500,\n height: 1500\n})","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":562,"value":"** Figure 5.** This chart displays annotated protein functions on the inner ring and the phams that encode for those proteins on the outer ring. ","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","output":"","database":"$undefined"},{"id":988,"value":"UniquePhamilyInformation2 = md`\n

\n# Unique Phamily Information: Cluster ${selectedCluster2}\n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":1009,"value":"uniquePhams2 = BubbleChart(clusterSpecificPhamilies2, {\n label: (d) =>\n [d.phamName, `(${d.size})`].join(\"\\n\"),\n value: (d) => d.size,\n stroke: \"black\",\n group: (d) => d.phamName,\n groups: clusterSpecificPhamilies2.map((d) => d.phamName),\n strokeWidth: 1,\n fillOpacity: 1,\n colors: clusterSpecificPhamilies2.map((d) => d.phamColor),\n title: (d) =>\n `phamily: ${d.phamName.toLocaleString(\"en\")}\\nsize: ${d.size.toLocaleString(\n \"en\"\n )}\\n`,\n width: 1152\n})","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":1015,"value":"**Figure 1.** This bubble chart displays the **${clusterSpecificPhamilies2.length.toLocaleString()}** phamilies that are found only in **cluster ${selectedCluster2}** genomes. \n\nThe number on top is the phamily name and the number on the bottom is the number of times the phamily is seen in Cluster ${selectedCluster2} genomes. The size correlates to the number of times it is annotated, with a larger bubble indicating that the phamily is present in a higher number of phages within the cluster.","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","output":"","database":"$undefined"},{"id":1021,"value":"SELECT phamName AS Phamily, size , phamColor FROM clusterSpecificPhamilies2","pinned":false,"hidden":false,"mode":"sql","author":"$undefined","summary":"$undefined","output":"","database":"var:clusterSpecificPhamilies2"},{"id":1025,"value":"**Table 1.** This table shows the phamilies that are **unique to Cluster ${selectedCluster2}**.","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","output":"","database":"$undefined"},{"id":1029,"value":"SELECT DISTINCT genesByCluster2.phamName AS Phamily, size ,function AS annotatedFunction, frequency AS frequencyAcrossCluster2 FROM clusterSpecificPhamilies2\nINNER JOIN genesByCluster2\nON clusterSpecificPhamilies2.phamName = genesByCluster2.phamName\nINNER JOIN functionFrequencies2\nON genesByCluster2.geneFunction = functionFrequencies2.function\n","pinned":false,"hidden":false,"mode":"sql","author":"$undefined","summary":"$undefined","output":"uniquePhamFunction2","database":"var:combinedDB"},{"id":1033,"value":"**Table 2.** This table shows the phamilies that are **unique to Cluster ${selectedCluster2}** that have an annotated function. The function is listed with its frequency within the entire cluster. Sometimes, the phamily is seen in the genome, but it does not have an annotated function, so this should be taken with a grain of salt. The size column lists the number of phages the phamily is seen in Cluster ${selectedCluster2}.","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","output":"","database":"$undefined"},{"id":1054,"value":"SharedPhamilyInformation2 = md`\n

\n# Shared Phamily Information: Cluster ${selectedCluster2}\n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":1051,"value":"sharedPhams2 = BubbleChart(clusterSharedPhamilies2, {\n label: (d) =>\n [d.phamName, `(${d.size})`].join(\"\\n\"),\n value: (d) => d.size,\n stroke: \"black\",\n group: (d) => d.phamName,\n groups: clusterSharedPhamilies2.map((d) => d.phamName),\n strokeWidth: 1,\n fillOpacity: 1,\n colors: clusterSharedPhamilies2.map((d) => d.phamColor),\n title: (d) =>\n `phamily: ${d.phamName.toLocaleString(\"en\")}\\nsize: ${d.size.toLocaleString(\n \"en\"\n )}\\n`,\n width: 1152\n})","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":1085,"value":"**Figure 2.** This bubble chart displays the **${clusterSharedPhamilies2.length.toLocaleString()}** phamilies that are **not unique** to **Cluster ${selectedCluster2}** genomes. \n\nThe number on top is the phamily name and the number on the bottom is the number of times the phamily is seen in Cluster ${selectedCluster2} phages. The size correlates to the number of phages it is present in, with a larger bubble indicating that the phamily is present in a higher number of phages across clusters.\n","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","output":"","database":"$undefined"},{"id":1100,"value":"SELECT * FROM clusterSharedPhamilies","pinned":false,"hidden":false,"mode":"sql","author":"$undefined","summary":"$undefined","output":"","database":"var:clusterSharedPhamilies"},{"id":1136,"value":"SELECT Distinct genesByCluster2.phamName AS PhamilyName, phamilies.size, function AS annotatedFunction, frequency AS frequencyAcrossCluster2 FROM phamilies\nInner join genesByCluster2\nON phamilies.PhamID = genesByCluster2.phamName\nINNER JOIN functionFrequencies2\nON genesByCluster2.geneFunction = functionFrequencies2.function\nfull outer join clusterSpecificPhamilies2\nON phamilies.PhamID = clusterSpecificPhamilies2.phamName\nWHERE clusterSpecificPhamilies2.phamName is null","pinned":false,"hidden":false,"mode":"sql","author":"$undefined","summary":"$undefined","output":"functionsOfSharedPhams2","database":"var:combinedDB"},{"id":1141,"value":"**Table 4.** This table shows the phamilies that are **not unique** to **Cluster ${selectedCluster2}** that have an annotated function. The function is listed with its frequency within the entire ${selectedCluster2} cluster. Sometimes, the phamily is seen in the genome, but it does not have an annotated function, so this should be taken with a grain of salt. The size column lists the number of phages the phamily is seen across various clusters.","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","output":"","database":"$undefined"},{"id":1071,"value":"proteinFunctionInfo2 = md`\n

\n# Protein Function Information: Cluster ${selectedCluster2}\n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":1075,"value":"Plot.plot({\n width: width,\n marginLeft: 250,\n marks: [\n Plot.barX(functionFrequencies2, {\n x: \"frequency\",\n y: \"function\",\n fill: \"frequency\",\n sort: {y: \"x\", reverse: true, limit: 20},\n stroke: \"frequency\",\n title: (d) => `${d.frequency}`\n }),\n Plot.ruleX([0])\n ],\n \n color: { scheme: \"Purples\" }\n})\n ","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":1144,"value":"**Figure 3.** This chart shows the top 20 most frequent annotated protein functions in **Cluster ${selectedCluster2}**. These include phams that are shared and unique to this cluster. ","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","output":"","database":"$undefined"},{"id":1906,"value":"Plot.plot({\n width: width,\n marginLeft: 250,\n marks: [\n Plot.barX(uniquePhamFunction2, {\n x: \"frequencyAcrossCluster2\",\n y: \"annotatedFunction\",\n fill: \"frequencyAcrossCluster2\",\n sort: {y: \"x\", reverse: true, limit: 20},\n stroke: \"frequencyAcrossCluster2\",\n title: (d) => `${d.frequencyAcrossCluster2}`\n }),\n Plot.ruleX([0])\n ],\n \n color: { scheme: \"Blues\" }\n})\n ","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":1912,"value":"**Figure 4.** This chart shows the top 20 most frequent annotated protein functions of _phams unique_ to **Cluster ${selectedCluster2}**\n\nThe reason why some bars are segmented when you hover over them is that there are different phamilies that encode for that function. For example, there are three unique phams that are annotated as minor tail proteins.","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","output":"","database":"$undefined"},{"id":1132,"value":"Sunburst(dataFlare2, {\n // path: (d) => d.name, // e.g. flare/animate/Easing\n label: (d) => d.name, // display text\n value: (d) => d?.value, // angle of each arc\n title: (d, n) => [n.id, n.value.toLocaleString()].join(\"\\n\"), // hover text\n width: 1500,\n height: 1500\n})","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":1147,"value":"** Figure 5.** This chart displays annotated protein functions on the inner ring and the phams that encode for those proteins on the outer ring. ","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","output":"","database":"$undefined"},{"id":1155,"value":"proteinComparison = md`\n

\n# Comparing Cluster ${selectedCluster} and Cluster ${selectedCluster2}\n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":1635,"value":"$2f","pinned":true,"hidden":false,"mode":"sql","author":"$undefined","summary":"$undefined","output":"testTable","database":"var:combinedDB"},{"id":1604,"value":"$30","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","output":"","database":"$undefined"},{"id":1883,"value":"sharedPhamilyTable = md`\n

\n## Look at the number of Cluster ${selectedCluster} and ${selectedCluster2} phages that have a specific shared phamily\nHere you can select a phamily that is shared in both selected clusters and see how many phages it is present in. Remember that **Cluster ${selectedCluster}** has **${phages.length.toLocaleString()} phages** and **Cluster ${selectedCluster2}** has **${phages2.length.toLocaleString()} phages** \n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":1687,"value":"viewof selectedPham = Inputs.select(\n phamilySearch.map((c) => c.name),\n {\n label: \"Select a shared phamily you would like to look at:\", value: \"\"\n }\n)","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":1717,"value":"SELECT phageID, cluster, geneFunction, FROM sharedPhamily\nINNER JOIN totalPhagesInCluster1and2\nON sharedPhamily.PhageId = totalPhagesInCluster1and2.phageName\nORDER BY cluster ASC","pinned":false,"hidden":false,"mode":"sql","author":"$undefined","summary":"$undefined","output":"phagesWithPham","database":"var:sharedPhamDB"},{"id":368,"value":"---\n# Data and API Information\n## Sunburst","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","output":"","database":"$undefined"},{"id":307,"value":"dataFlare = ({\n name: \"Unique Phams and their functions for selected cluster\",\n children: d3\n .groups(uniquePhamFunction , (d) => d.annotatedFunction)\n .map((d) => {\n return {\n name: d[0],\n // value: 1\n children: d[1].map((e) => {\n return { name: e.Phamily.replaceAll(\"-\", \"_\"), value: e.frequencyAcrossCluster};\n })\n };\n })\n})","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":1079,"value":"dataFlare2 = ({\n name: \"Unique Phams and their functions for selected cluster\",\n children: d3\n .groups(uniquePhamFunction2 , (d) => d.annotatedFunction)\n .map((d) => {\n return {\n name: d[0],\n // value: 1\n children: d[1].map((e) => {\n return { name: e.Phamily.replaceAll(\"-\", \"_\"), value: e.frequencyAcrossCluster2};\n })\n };\n })\n})","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":709,"value":"## Data for First Dropdown Menu\n","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","output":"","database":"$undefined"},{"id":60,"value":"phages = getPhameratorData(dataset, `/phagesbycluster/${selectedCluster}`, user.email, user.password)\n// these are the phages for the first selected cluster","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":71,"value":"genesByCluster = getPhameratorData(\n dataset,\n `/genesbycluster/${selectedCluster}`,\n user.email,\n user.password\n)","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":117,"value":"genefunctions = genesByCluster\n .filter((gene) => gene.genefunction != \"\")\n .map((gene) => gene.genefunction)","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":119,"value":"functionFrequencies = {\n const counts = {};\n\n for (const geneFunction of genefunctions) {\n counts[geneFunction] = counts[geneFunction] ? counts[geneFunction] + 1 : 1;\n }\n return Object.entries(counts).map((e) => {\n return { function: e[0], frequency: e[1], cluster: `${selectedCluster}`};\n });\n}","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":434,"value":"totalPhamsInCluster = Array.from(new Set(genesByCluster.map(d => +d.phamName))).map(d => {return {\"PhamilyName\": d,\"Cluster\": `${selectedCluster}`}})","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":68,"value":"$31","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":655,"value":"$32","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":711,"value":"## Data for Second Dropdown Menu\n","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","output":"","database":"$undefined"},{"id":752,"value":"phages2 = getPhameratorData(dataset, `/phagesbycluster/${selectedCluster2}`, user.email, user.password)\n// these are the phages for the second selected cluster","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":686,"value":"genesByCluster2 = getPhameratorData(\n dataset,\n `/genesbycluster/${selectedCluster2}`,\n user.email,\n user.password\n)","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":688,"value":"genefunctions2 = genesByCluster2\n .filter((gene) => gene.genefunction != \"\")\n .map((gene) => gene.genefunction)","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":693,"value":"functionFrequencies2 = {\n const counts = {};\n\n for (const geneFunction of genefunctions2) {\n counts[geneFunction] = counts[geneFunction] ? counts[geneFunction] + 1 : 1;\n }\n return Object.entries(counts).map((e) => {\n return { function: e[0], frequency: e[1], cluster: `${selectedCluster2}`};\n });\n}","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":702,"value":"totalPhamsInCluster2 = Array.from(new Set(genesByCluster2.map(d => +d.phamName))).map(d => {return {\"PhamilyName\": d, \"Cluster\": `${selectedCluster2}`}})","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":696,"value":"$33","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":699,"value":"$34","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":1725,"value":"# Shared Phamily Stuff","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","output":"","database":"$undefined"},{"id":1730,"value":"sharedPhamDB = DuckDBClient.of({\nsharedPhamily, phages, phages2, genesByCluster, genesByCluster2, totalPhamsInCluster1and2, totalPhagesInCluster1and2\n})","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":1664,"value":"dataMap = {\n let rows = Array.from(testTable)\n let rawData = []\n\n // turning the SQL into an array\n for (let row of rows) {\n let entries = Object.entries(row)\n let o = {};\n for (let entry of entries) {\n o[entry[0]] = entry[1]\n }\n rawData.push(o)\n }\n\n let columns = Object.keys(rawData[0])\n return d3.group(rawData, d => d.PhamilyName, e => e.freqInFirstCluster,f => f.freqInSecondCluster)\n}","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":1669,"value":"phamilySearch = {\n let data = [];\n for (let entry of dataMap.entries()) {\n let name = entry[0];\n let children = Array.from(entry[1].entries()).map(e => {return {name : e[0]}})\n data.push({name})\n }\n return data;\n}","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":1661,"value":"sharedPhamily = getPhameratorData(dataset, `/phamily/${selectedPham}`,\n user.email,\n user.password)","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":56,"value":"\n## Data For Whole Notebook\n\nThe data in the cells below were downloaded using the Phamerator.org API based on what you have selected in the menus above.","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","output":"","database":"$undefined"},{"id":1303,"value":"totalPhamsInCluster1and2 = totalPhamsInCluster.concat(totalPhamsInCluster2)","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":1819,"value":"totalPhagesInCluster1and2 = phages.concat(phages2)","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":199,"value":"combinedDB = DuckDBClient.of({\n clusters, phamilies, totalPhamsInCluster1and2,\n //first selected cluster\n phages, genesByCluster, clusterSpecificPhamilies, clusterSharedPhamilies, functionFrequencies, totalPhamsInCluster,\n //second selected cluster\n phages2, genesByCluster2, clusterSpecificPhamilies2, clusterSharedPhamilies2, functionFrequencies2, totalPhamsInCluster2})","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":58,"value":"clusters = getPhameratorData(dataset, \"/clusters\", user.email, user.password)","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":64,"value":"phamilies = getPhameratorData(dataset, \"/phamilies\", user.email, user.password)","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":210,"value":"## Code for looking at individual phage in a cluster","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","output":"","database":"$undefined"},{"id":598,"value":"// viewof selectedPhage = Inputs.select(phages.map((p) => p.phagename).sort(), {\n// label: \"Select a phage\"\n// })","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":595,"value":"// genes = getPhameratorData(\n// dataset,\n// `/genes/${selectedPhage}`,\n// user.email,\n// user.password\n// ).then((value) =>\n// value.map((v) => {\n// v.geneFunction = v.geneFunction === \"\" ? null : v.geneFunction;\n// return v;\n// })\n// )","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":54,"value":"---\n# Appendix","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","output":"","database":"$undefined"},{"id":33,"value":"import {\n terms,\n getPhameratorData,\n user,\n formWithSubmit,\n styles\n} with { formData } from \"@scresawn/phamerator-api-utilities\"","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":37,"value":"import { Plot } from \"@mkfreeman/plot-tooltip\"","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":48,"value":"styles","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":112,"value":"import {BubbleChart} from \"5b71f0d1f28004cd\"","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":305,"value":"import {Sunburst} from \"@d3/sunburst\"","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":1332,"value":"import {SankeyChart} from \"@d3/sankey\"","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"}],"files":"$W35","stdlib":"1","titling":"auto"}} 2e:"$2d:body"

Phamerator.org Login