{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "%matplotlib inline\n", "import pandas as pd\n", "import numpy as np\n", "import re\n", "import os\n", "import math\n", "from multiprocessing import Pool\n", "from tqdm import tqdm\n", "from scipy import stats\n", "## init\n", "mySpecie='Homo_sapiens'\n", "#prealigned_dir='/cellar/users/btsui/all_seq_snp/Homo_sapiens_all_merged_snp.TCGA.prealigned.pickle'\n", "targetted_align_dir='/cellar/users/btsui/all_seq_snp/Homo_sapiens_all_merged_snp.TCGA.pickle'\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "targetted_df=pd.read_pickle(targetted_align_dir).loc[\"TCGA\"]" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "all_UUIDs=targetted_df.index.get_level_values('Run_digits').unique()" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "n UUID: 1427\n" ] } ], "source": [ "#883, 1427\n", "print ('n UUID:',len(all_UUIDs))" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [], "source": [ "manifest_dir='/cellar/users/btsui/Project/METAMAP/notebook/RapMapTest/XGS_WGS/./tcga_lgg_wgs_bams.df.wxs_rnaseq.pickle'\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "### use andrea mapping to map from TCGA barcode to UUID. " ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [], "source": [ "manifest_df=pd.read_pickle(manifest_dir)" ] }, { "cell_type": "code", "execution_count": 15, "metadata": { "scrolled": true }, "outputs": [], "source": [ "manifest_df['processed']=manifest_df.file_id.isin(all_UUIDs)" ] }, { "cell_type": "code", "execution_count": 16, "metadata": {}, "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", " \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", " \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", " \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", " \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", " \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", " \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", " \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", " \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", " \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", " \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", " \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", " \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", " \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", " \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", " \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", " \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", " \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", " \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", " \n", " \n", " \n", " \n", " \n", "
accessannotationscasesdata_categorydata_formatdata_typeexperimental_strategyfile_idfile_namefile_sizeplatformprocessed
546controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsRNA-Seq1985b367-00c4-4c25-b049-5858e937cc6d948a7b5a-de83-41db-85f1-93a1a9b109ba_gdc_realn...3293981085IlluminaTrue
1019controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsRNA-Seqa7aff6a7-cea4-42e9-8d56-b211843a03028e4c32f5-1ed2-453b-b029-db7836249d3b_gdc_realn...4070637137IlluminaTrue
860controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsRNA-Seq4038984b-21d1-45d3-a5bb-208f9e71aa78b52aeb27-8d06-4a1c-b322-ee947261e95c_gdc_realn...4195199173IlluminaTrue
791controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsRNA-Seq7b17a5ef-c778-4753-8c30-427af9171f7aa9bfcb6f-ce2b-47e2-a2e2-dd777b6d1344_gdc_realn...4436516715IlluminaTrue
1285controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsRNA-Seq93e20db7-4892-4ef8-9331-ecd665e4cb9133262d51-82cb-4fe6-89d1-b7e1c4673896_gdc_realn...4501820893IlluminaTrue
1412controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsWXSceb1a38c-fc22-4d27-9ada-553c1765f1f6C494.TCGA-HT-A4DV-10A-01D-A26K-08.4_gdc_realn.bam4546249959IlluminaTrue
1395controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsRNA-Seq35a18f9e-0ef8-4e55-b655-33397b63fd1ab2a58478-d5d2-443c-9f20-222d43b6c326_gdc_realn...4601200721IlluminaTrue
1843controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsWXS9ac78029-3c36-4e00-b3e2-06415649ec43C494.TCGA-HT-A4DS-10A-01D-A26K-08.4_gdc_realn.bam4659688085IlluminaTrue
1421controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsWXSbc27f71a-4222-4940-8a64-246e2b9f3d44C494.TCGA-DB-A4XC-01A-11D-A26M-08.3_gdc_realn.bam4709420043IlluminaTrue
1131controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsWXS84943493-e5ef-4099-8706-09afa625b076C494.TCGA-DB-A4X9-01A-11D-A26M-08.5_gdc_realn.bam4720213753IlluminaTrue
697controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsWXSf36d778a-2c49-43aa-a577-7a6a921ad6ccC494.TCGA-HT-A4DV-01A-11D-A26M-08.4_gdc_realn.bam4776368233IlluminaTrue
1363controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsRNA-Seq243e9ccb-7c93-4c6a-9e3e-105c379e7f78de2603fc-4fbd-42bf-8601-5807195e8e58_gdc_realn...4936527695IlluminaTrue
333controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsRNA-Seqf895b46c-7811-4ebb-ac9c-970bbfed657afa9ba06b-49aa-4794-a8a4-458245f0f0d0_gdc_realn...5038123177IlluminaTrue
302controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsWXS3594993e-f65c-434b-a64e-b1873f4b04caC494.TCGA-DB-A4XA-01A-11D-A26M-08.4_gdc_realn.bam5103387809IlluminaTrue
610controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsWXS4522becf-1566-4de8-b760-79bb93513ecfC494.TCGA-FG-A4MY-01A-11D-A26M-08.3_gdc_realn.bam5106736217IlluminaTrue
1593controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsRNA-Seq65c95f19-84f0-4e8b-99c3-186f881181a4eb40595a-e557-40f1-bf04-1d2bced6b1ea_gdc_realn...5119970361IlluminaTrue
567controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsRNA-Seqeb4dda76-4215-458b-b9a0-60f9ff24bd6e450ad55c-9632-4249-9308-0054f93f2c1d_gdc_realn...5199614743IlluminaTrue
398controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsRNA-Seqf4db57f0-ba62-4a60-b65d-d2354612eb7bec7f0c4f-eac0-4aaa-9bc1-6a2116770962_gdc_realn...5227895868IlluminaTrue
933controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsWXSce74f5ce-d92f-4c8d-8234-65a372edb92dC494.TCGA-FG-A4MX-10A-01D-A26K-08.4_gdc_realn.bam5308076839IlluminaTrue
744controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsRNA-Seq00b53e00-d640-49e5-b2bd-3a3bdf867998a13a5da8-86e7-40a1-83b9-d2f42cde39c3_gdc_realn...5493253789IlluminaTrue
1824controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsWXSe55c8de3-3a92-42f2-bc1e-70a21355d696C494.TCGA-HT-A4DS-01A-11D-A26M-08.4_gdc_realn.bam5548625577IlluminaTrue
1345controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsWXS3a0e5ae0-dc79-468d-b459-a6d43b612851C494.TCGA-DB-A4XB-01A-11D-A26M-08.3_gdc_realn.bam5566530125IlluminaTrue
580controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsRNA-Seq3011867e-1c3b-4791-849e-4e7d636ddc8846ac364a-6eee-4ddf-8a86-30d5d93e69d9_gdc_realn...5578347546IlluminaTrue
433controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsWXSfd5d9171-979e-4742-adec-179f19bf6c06C494.TCGA-FG-A4MW-01A-11D-A26M-08.4_gdc_realn.bam5610837831IlluminaTrue
2039controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsRNA-Seqaeebf360-49c4-4db3-bdf4-daffdc5279cc9d7eba88-a95f-475a-a86f-49a42c7b6420_gdc_realn...5640103253IlluminaTrue
2013controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsWXS25650a4b-775b-485b-92c2-3f8f30ba4169C494.TCGA-DU-A6S2-01A-21D-A32B-08.1_gdc_realn.bam5680657764IlluminaTrue
1768controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsWXSd8d284a7-6a45-4938-bdf7-5da558a19c79C494.TCGA-DB-A4XC-10A-01D-A26K-08.3_gdc_realn.bam5745632232IlluminaTrue
1289controlled[{'annotation_id': '1c9a57d0-d4bf-5ecc-bb2a-1d...[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsRNA-Seqb2bd014e-44fe-4d24-9b75-91baf36b3c0aff71a6a7-0752-4a83-b2b8-c4d155b7d8ae_gdc_realn...5811473591IlluminaTrue
1754controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsRNA-Seqdcbaf670-8100-4c98-bd4d-2880a5805f23d5d72a65-f064-43cc-8872-7b08f0a31722_gdc_realn...5858397208IlluminaTrue
684controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsWXSa6218259-7690-4646-9756-eaf97e326cb1C494.TCGA-FG-A4MT-10A-01D-A26K-08.7_gdc_realn.bam5884382571IlluminaTrue
.......................................
350controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsWXSde3dfa71-a490-4344-95dc-99301d1dee08C494.TCGA-S9-A6U6-01A-12D-A33T-08.1_gdc_realn.bam25764491559IlluminaTrue
786controlled[{'annotation_id': '8fce0c90-2c27-5289-bd76-c8...[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsWXSd5c9ab65-7aa8-4efc-a570-f935c861d29dC494.TCGA-S9-A6WG-10A-01D-A33W-08.1_gdc_realn.bam25819033618IlluminaTrue
194controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsWXScdb99f45-9d8a-4f5f-8e10-9b3ef51eac2eC494.TCGA-S9-A6WD-01A-12D-A33T-08.1_gdc_realn.bam25899694434IlluminaTrue
295controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsWXS6bd2f0f6-df8f-4b4e-804b-328923ec382bC494.TCGA-FG-A711-01A-21D-A33T-08.1_gdc_realn.bam25954568773IlluminaTrue
301controlled[{'annotation_id': 'fcaf6ab7-6f32-578f-993e-4c...[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsWXS489cc5f3-9f88-4051-87c8-a242123d9ed9C494.TCGA-S9-A6U6-10A-01D-A33W-08.1_gdc_realn.bam25971722247IlluminaTrue
1572controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsWXS4e30cef6-d1af-4d77-ad93-6e31ec58fc35C494.TCGA-VW-A7QS-01A-12D-A33T-08.1_gdc_realn.bam26077683267IlluminaTrue
1526controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsWXS3772a453-c9cb-4084-b73a-181304516637C494.TCGA-DU-A7TA-01A-11D-A33T-08.1_gdc_realn.bam26276177578IlluminaTrue
404controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsWXS5de82077-8540-474f-a569-c4b3b951f81cC494.TCGA-TQ-A7RG-01A-11D-A33T-08.1_gdc_realn.bam26344403523IlluminaTrue
2077controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsWXS704f5788-ca6e-499f-8d43-47134c5ba275C494.TCGA-S9-A6UA-01A-12D-A33T-08.1_gdc_realn.bam26357408848IlluminaTrue
1585controlled[{'annotation_id': '06c4a1d9-1b68-53ec-af55-65...[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsWXS1f46ad29-0ebf-4882-9e90-09428f6242caC494.TCGA-S9-A6U5-10A-01D-A33W-08.1_gdc_realn.bam26373199753IlluminaTrue
1694controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsWXS3ba871b3-2d7f-4266-922b-627785c9e2e5C494.TCGA-TQ-A7RS-10A-01D-A33W-08.1_gdc_realn.bam26379422195IlluminaTrue
309controlled[{'annotation_id': '47718055-fc95-5478-b8b4-c8...[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsWXS4b6fa49f-791e-45ee-8355-be690c9f127dC494.TCGA-S9-A6WH-10A-01D-A33W-08.1_gdc_realn.bam26381599891IlluminaTrue
1025controlled[{'annotation_id': '28fb238d-7868-547e-b643-a3...[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsWXS1ed49bd2-38ef-4747-b572-76bb16d0cb7bC494.TCGA-S9-A6WI-10A-01D-A33W-08.1_gdc_realn.bam26422463992IlluminaTrue
769controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsWXS2207155d-348a-4ed0-91f1-71b60f179ee2C494.TCGA-R8-A6MO-01A-11D-A33T-08.1_gdc_realn.bam26443229606IlluminaTrue
206controlled[{'annotation_id': 'ca544dc9-4f40-5589-99ab-26...[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsWXSe45b1fae-1a83-438e-a6e3-967813831346C494.TCGA-S9-A6U8-01A-21D-A33T-08.1_gdc_realn.bam26444187783IlluminaTrue
1057controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsWXS67a2edc2-4776-4442-b74c-ff8b9b91867eC494.TCGA-E1-5322-01A-01D-1468-08.9_gdc_realn.bam26715379366IlluminaTrue
1539controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsWXS2d622f8a-a91d-44ed-a818-ea7c2fd698cdC494.TCGA-TQ-A7RO-01A-11D-A33T-08.1_gdc_realn.bam27083238331IlluminaTrue
231controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsWXS06350102-0c44-4846-935d-515a5b0da989C494.TCGA-TQ-A7RS-01A-12D-A33T-08.1_gdc_realn.bam27099567535IlluminaTrue
97controlled[{'annotation_id': '672848f7-5cd4-54d4-b025-fe...[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsWXSd942c172-b9b5-452c-bb0d-83ec7f6a5f33C494.TCGA-S9-A6U1-10A-01D-A33W-08.1_gdc_realn.bam27142848890IlluminaTrue
1348controlled[{'annotation_id': 'e16ce51f-59d8-5b7e-9d90-2c...[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsWXS0831b36d-1b92-4c65-83e4-baba1a37120cC494.TCGA-S9-A6WM-10A-01D-A33W-08.1_gdc_realn.bam27268755793IlluminaTrue
1407controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsWXS86cd60d0-91b1-402a-b900-b3dbdd556efaC494.TCGA-TQ-A7RJ-10A-01D-A33W-08.1_gdc_realn.bam27300150050IlluminaTrue
1716controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsWXS17e5b895-6ec1-4bfc-a55f-a2114adb0af1C494.TCGA-DU-A76K-01A-11D-A33T-08.1_gdc_realn.bam27312491024IlluminaTrue
35controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsWXSdb95c082-fe8d-4c85-a4d8-b63d4a39c1eaC494.TCGA-S9-A6U2-01A-21D-A33T-08.1_gdc_realn.bam27452781065IlluminaTrue
1669controlled[{'annotation_id': '233d4f67-1289-563f-8f18-cf...[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsWXS39ea5309-579b-49a6-a9b7-dc45a935be1fC494.TCGA-S9-A6U8-10A-01D-A33W-08.1_gdc_realn.bam27462233818IlluminaTrue
825controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsWXS5b96100f-1815-453d-b2a4-b32bb747b4adC494.TCGA-DH-A7US-01A-11D-A33T-08.1_gdc_realn.bam27741243341IlluminaTrue
570controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsWXSd1ff8258-be02-44bf-9cbb-0bbc895452bfC494.TCGA-S9-A6WM-01A-12D-A33T-08.1_gdc_realn.bam27769132884IlluminaTrue
197controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsWXSe81ecc22-c399-4d35-b4b0-abcec7f895d5C494.TCGA-TQ-A7RM-01A-11D-A33T-08.1_gdc_realn.bam27972622913IlluminaTrue
983controlled[{'annotation_id': 'b9ac0f52-67e2-56fc-a794-aa...[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsWXS66ffda7b-6998-4690-a9b4-14b29cf52aa8C494.TCGA-S9-A6WE-10A-01D-A33W-08.1_gdc_realn.bam28087416994IlluminaTrue
1063controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsWXS2b0048e0-a062-40d2-a1e1-4bb763ea0eadC494.TCGA-S9-A6U1-01A-21D-A33T-08.1_gdc_realn.bam28910247215IlluminaTrue
631controlledNaN[{'project': {'project_id': 'TCGA-LGG'}, 'case...Raw Sequencing DataBAMAligned ReadsWXS65170c46-a72e-41e7-84bb-2e3fe2f90667C494.TCGA-DU-A7TB-10A-01D-A33W-08.1_gdc_realn.bam30154920343IlluminaTrue
\n", "

1427 rows × 12 columns

\n", "
" ], "text/plain": [ " access annotations \\\n", "546 controlled NaN \n", "1019 controlled NaN \n", "860 controlled NaN \n", "791 controlled NaN \n", "1285 controlled NaN \n", "1412 controlled NaN \n", "1395 controlled NaN \n", "1843 controlled NaN \n", "1421 controlled NaN \n", "1131 controlled NaN \n", "697 controlled NaN \n", "1363 controlled NaN \n", "333 controlled NaN \n", "302 controlled NaN \n", "610 controlled NaN \n", "1593 controlled NaN \n", "567 controlled NaN \n", "398 controlled NaN \n", "933 controlled NaN \n", "744 controlled NaN \n", "1824 controlled NaN \n", "1345 controlled NaN \n", "580 controlled NaN \n", "433 controlled NaN \n", "2039 controlled NaN \n", "2013 controlled NaN \n", "1768 controlled NaN \n", "1289 controlled [{'annotation_id': '1c9a57d0-d4bf-5ecc-bb2a-1d... \n", "1754 controlled NaN \n", "684 controlled NaN \n", "... ... ... \n", "350 controlled NaN \n", "786 controlled [{'annotation_id': '8fce0c90-2c27-5289-bd76-c8... \n", "194 controlled NaN \n", "295 controlled NaN \n", "301 controlled [{'annotation_id': 'fcaf6ab7-6f32-578f-993e-4c... \n", "1572 controlled NaN \n", "1526 controlled NaN \n", "404 controlled NaN \n", "2077 controlled NaN \n", "1585 controlled [{'annotation_id': '06c4a1d9-1b68-53ec-af55-65... \n", "1694 controlled NaN \n", "309 controlled [{'annotation_id': '47718055-fc95-5478-b8b4-c8... \n", "1025 controlled [{'annotation_id': '28fb238d-7868-547e-b643-a3... \n", "769 controlled NaN \n", "206 controlled [{'annotation_id': 'ca544dc9-4f40-5589-99ab-26... \n", "1057 controlled NaN \n", "1539 controlled NaN \n", "231 controlled NaN \n", "97 controlled [{'annotation_id': '672848f7-5cd4-54d4-b025-fe... \n", "1348 controlled [{'annotation_id': 'e16ce51f-59d8-5b7e-9d90-2c... \n", "1407 controlled NaN \n", "1716 controlled NaN \n", "35 controlled NaN \n", "1669 controlled [{'annotation_id': '233d4f67-1289-563f-8f18-cf... \n", "825 controlled NaN \n", "570 controlled NaN \n", "197 controlled NaN \n", "983 controlled [{'annotation_id': 'b9ac0f52-67e2-56fc-a794-aa... \n", "1063 controlled NaN \n", "631 controlled NaN \n", "\n", " cases data_category \\\n", "546 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "1019 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "860 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "791 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "1285 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "1412 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "1395 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "1843 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "1421 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "1131 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "697 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "1363 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "333 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "302 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "610 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "1593 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "567 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "398 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "933 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "744 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "1824 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "1345 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "580 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "433 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "2039 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "2013 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "1768 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "1289 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "1754 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "684 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "... ... ... \n", "350 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "786 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "194 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "295 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "301 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "1572 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "1526 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "404 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "2077 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "1585 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "1694 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "309 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "1025 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "769 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "206 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "1057 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "1539 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "231 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "97 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "1348 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "1407 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "1716 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "35 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "1669 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "825 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "570 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "197 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "983 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "1063 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "631 [{'project': {'project_id': 'TCGA-LGG'}, 'case... Raw Sequencing Data \n", "\n", " data_format data_type experimental_strategy \\\n", "546 BAM Aligned Reads RNA-Seq \n", "1019 BAM Aligned Reads RNA-Seq \n", "860 BAM Aligned Reads RNA-Seq \n", "791 BAM Aligned Reads RNA-Seq \n", "1285 BAM Aligned Reads RNA-Seq \n", "1412 BAM Aligned Reads WXS \n", "1395 BAM Aligned Reads RNA-Seq \n", "1843 BAM Aligned Reads WXS \n", "1421 BAM Aligned Reads WXS \n", "1131 BAM Aligned Reads WXS \n", "697 BAM Aligned Reads WXS \n", "1363 BAM Aligned Reads RNA-Seq \n", "333 BAM Aligned Reads RNA-Seq \n", "302 BAM Aligned Reads WXS \n", "610 BAM Aligned Reads WXS \n", "1593 BAM Aligned Reads RNA-Seq \n", "567 BAM Aligned Reads RNA-Seq \n", "398 BAM Aligned Reads RNA-Seq \n", "933 BAM Aligned Reads WXS \n", "744 BAM Aligned Reads RNA-Seq \n", "1824 BAM Aligned Reads WXS \n", "1345 BAM Aligned Reads WXS \n", "580 BAM Aligned Reads RNA-Seq \n", "433 BAM Aligned Reads WXS \n", "2039 BAM Aligned Reads RNA-Seq \n", "2013 BAM Aligned Reads WXS \n", "1768 BAM Aligned Reads WXS \n", "1289 BAM Aligned Reads RNA-Seq \n", "1754 BAM Aligned Reads RNA-Seq \n", "684 BAM Aligned Reads WXS \n", "... ... ... ... \n", "350 BAM Aligned Reads WXS \n", "786 BAM Aligned Reads WXS \n", "194 BAM Aligned Reads WXS \n", "295 BAM Aligned Reads WXS \n", "301 BAM Aligned Reads WXS \n", "1572 BAM Aligned Reads WXS \n", "1526 BAM Aligned Reads WXS \n", "404 BAM Aligned Reads WXS \n", "2077 BAM Aligned Reads WXS \n", "1585 BAM Aligned Reads WXS \n", "1694 BAM Aligned Reads WXS \n", "309 BAM Aligned Reads WXS \n", "1025 BAM Aligned Reads WXS \n", "769 BAM Aligned Reads WXS \n", "206 BAM Aligned Reads WXS \n", "1057 BAM Aligned Reads WXS \n", "1539 BAM Aligned Reads WXS \n", "231 BAM Aligned Reads WXS \n", "97 BAM Aligned Reads WXS \n", "1348 BAM Aligned Reads WXS \n", "1407 BAM Aligned Reads WXS \n", "1716 BAM Aligned Reads WXS \n", "35 BAM Aligned Reads WXS \n", "1669 BAM Aligned Reads WXS \n", "825 BAM Aligned Reads WXS \n", "570 BAM Aligned Reads WXS \n", "197 BAM Aligned Reads WXS \n", "983 BAM Aligned Reads WXS \n", "1063 BAM Aligned Reads WXS \n", "631 BAM Aligned Reads WXS \n", "\n", " file_id \\\n", "546 1985b367-00c4-4c25-b049-5858e937cc6d \n", "1019 a7aff6a7-cea4-42e9-8d56-b211843a0302 \n", "860 4038984b-21d1-45d3-a5bb-208f9e71aa78 \n", "791 7b17a5ef-c778-4753-8c30-427af9171f7a \n", "1285 93e20db7-4892-4ef8-9331-ecd665e4cb91 \n", "1412 ceb1a38c-fc22-4d27-9ada-553c1765f1f6 \n", "1395 35a18f9e-0ef8-4e55-b655-33397b63fd1a \n", "1843 9ac78029-3c36-4e00-b3e2-06415649ec43 \n", "1421 bc27f71a-4222-4940-8a64-246e2b9f3d44 \n", "1131 84943493-e5ef-4099-8706-09afa625b076 \n", "697 f36d778a-2c49-43aa-a577-7a6a921ad6cc \n", "1363 243e9ccb-7c93-4c6a-9e3e-105c379e7f78 \n", "333 f895b46c-7811-4ebb-ac9c-970bbfed657a \n", "302 3594993e-f65c-434b-a64e-b1873f4b04ca \n", "610 4522becf-1566-4de8-b760-79bb93513ecf \n", "1593 65c95f19-84f0-4e8b-99c3-186f881181a4 \n", "567 eb4dda76-4215-458b-b9a0-60f9ff24bd6e \n", "398 f4db57f0-ba62-4a60-b65d-d2354612eb7b \n", "933 ce74f5ce-d92f-4c8d-8234-65a372edb92d \n", "744 00b53e00-d640-49e5-b2bd-3a3bdf867998 \n", "1824 e55c8de3-3a92-42f2-bc1e-70a21355d696 \n", "1345 3a0e5ae0-dc79-468d-b459-a6d43b612851 \n", "580 3011867e-1c3b-4791-849e-4e7d636ddc88 \n", "433 fd5d9171-979e-4742-adec-179f19bf6c06 \n", "2039 aeebf360-49c4-4db3-bdf4-daffdc5279cc \n", "2013 25650a4b-775b-485b-92c2-3f8f30ba4169 \n", "1768 d8d284a7-6a45-4938-bdf7-5da558a19c79 \n", "1289 b2bd014e-44fe-4d24-9b75-91baf36b3c0a \n", "1754 dcbaf670-8100-4c98-bd4d-2880a5805f23 \n", "684 a6218259-7690-4646-9756-eaf97e326cb1 \n", "... ... \n", "350 de3dfa71-a490-4344-95dc-99301d1dee08 \n", "786 d5c9ab65-7aa8-4efc-a570-f935c861d29d \n", "194 cdb99f45-9d8a-4f5f-8e10-9b3ef51eac2e \n", "295 6bd2f0f6-df8f-4b4e-804b-328923ec382b \n", "301 489cc5f3-9f88-4051-87c8-a242123d9ed9 \n", "1572 4e30cef6-d1af-4d77-ad93-6e31ec58fc35 \n", "1526 3772a453-c9cb-4084-b73a-181304516637 \n", "404 5de82077-8540-474f-a569-c4b3b951f81c \n", "2077 704f5788-ca6e-499f-8d43-47134c5ba275 \n", "1585 1f46ad29-0ebf-4882-9e90-09428f6242ca \n", "1694 3ba871b3-2d7f-4266-922b-627785c9e2e5 \n", "309 4b6fa49f-791e-45ee-8355-be690c9f127d \n", "1025 1ed49bd2-38ef-4747-b572-76bb16d0cb7b \n", "769 2207155d-348a-4ed0-91f1-71b60f179ee2 \n", "206 e45b1fae-1a83-438e-a6e3-967813831346 \n", "1057 67a2edc2-4776-4442-b74c-ff8b9b91867e \n", "1539 2d622f8a-a91d-44ed-a818-ea7c2fd698cd \n", "231 06350102-0c44-4846-935d-515a5b0da989 \n", "97 d942c172-b9b5-452c-bb0d-83ec7f6a5f33 \n", "1348 0831b36d-1b92-4c65-83e4-baba1a37120c \n", "1407 86cd60d0-91b1-402a-b900-b3dbdd556efa \n", "1716 17e5b895-6ec1-4bfc-a55f-a2114adb0af1 \n", "35 db95c082-fe8d-4c85-a4d8-b63d4a39c1ea \n", "1669 39ea5309-579b-49a6-a9b7-dc45a935be1f \n", "825 5b96100f-1815-453d-b2a4-b32bb747b4ad \n", "570 d1ff8258-be02-44bf-9cbb-0bbc895452bf \n", "197 e81ecc22-c399-4d35-b4b0-abcec7f895d5 \n", "983 66ffda7b-6998-4690-a9b4-14b29cf52aa8 \n", "1063 2b0048e0-a062-40d2-a1e1-4bb763ea0ead \n", "631 65170c46-a72e-41e7-84bb-2e3fe2f90667 \n", "\n", " file_name file_size \\\n", "546 948a7b5a-de83-41db-85f1-93a1a9b109ba_gdc_realn... 3293981085 \n", "1019 8e4c32f5-1ed2-453b-b029-db7836249d3b_gdc_realn... 4070637137 \n", "860 b52aeb27-8d06-4a1c-b322-ee947261e95c_gdc_realn... 4195199173 \n", "791 a9bfcb6f-ce2b-47e2-a2e2-dd777b6d1344_gdc_realn... 4436516715 \n", "1285 33262d51-82cb-4fe6-89d1-b7e1c4673896_gdc_realn... 4501820893 \n", "1412 C494.TCGA-HT-A4DV-10A-01D-A26K-08.4_gdc_realn.bam 4546249959 \n", "1395 b2a58478-d5d2-443c-9f20-222d43b6c326_gdc_realn... 4601200721 \n", "1843 C494.TCGA-HT-A4DS-10A-01D-A26K-08.4_gdc_realn.bam 4659688085 \n", "1421 C494.TCGA-DB-A4XC-01A-11D-A26M-08.3_gdc_realn.bam 4709420043 \n", "1131 C494.TCGA-DB-A4X9-01A-11D-A26M-08.5_gdc_realn.bam 4720213753 \n", "697 C494.TCGA-HT-A4DV-01A-11D-A26M-08.4_gdc_realn.bam 4776368233 \n", "1363 de2603fc-4fbd-42bf-8601-5807195e8e58_gdc_realn... 4936527695 \n", "333 fa9ba06b-49aa-4794-a8a4-458245f0f0d0_gdc_realn... 5038123177 \n", "302 C494.TCGA-DB-A4XA-01A-11D-A26M-08.4_gdc_realn.bam 5103387809 \n", "610 C494.TCGA-FG-A4MY-01A-11D-A26M-08.3_gdc_realn.bam 5106736217 \n", "1593 eb40595a-e557-40f1-bf04-1d2bced6b1ea_gdc_realn... 5119970361 \n", "567 450ad55c-9632-4249-9308-0054f93f2c1d_gdc_realn... 5199614743 \n", "398 ec7f0c4f-eac0-4aaa-9bc1-6a2116770962_gdc_realn... 5227895868 \n", "933 C494.TCGA-FG-A4MX-10A-01D-A26K-08.4_gdc_realn.bam 5308076839 \n", "744 a13a5da8-86e7-40a1-83b9-d2f42cde39c3_gdc_realn... 5493253789 \n", "1824 C494.TCGA-HT-A4DS-01A-11D-A26M-08.4_gdc_realn.bam 5548625577 \n", "1345 C494.TCGA-DB-A4XB-01A-11D-A26M-08.3_gdc_realn.bam 5566530125 \n", "580 46ac364a-6eee-4ddf-8a86-30d5d93e69d9_gdc_realn... 5578347546 \n", "433 C494.TCGA-FG-A4MW-01A-11D-A26M-08.4_gdc_realn.bam 5610837831 \n", "2039 9d7eba88-a95f-475a-a86f-49a42c7b6420_gdc_realn... 5640103253 \n", "2013 C494.TCGA-DU-A6S2-01A-21D-A32B-08.1_gdc_realn.bam 5680657764 \n", "1768 C494.TCGA-DB-A4XC-10A-01D-A26K-08.3_gdc_realn.bam 5745632232 \n", "1289 ff71a6a7-0752-4a83-b2b8-c4d155b7d8ae_gdc_realn... 5811473591 \n", "1754 d5d72a65-f064-43cc-8872-7b08f0a31722_gdc_realn... 5858397208 \n", "684 C494.TCGA-FG-A4MT-10A-01D-A26K-08.7_gdc_realn.bam 5884382571 \n", "... ... ... \n", "350 C494.TCGA-S9-A6U6-01A-12D-A33T-08.1_gdc_realn.bam 25764491559 \n", "786 C494.TCGA-S9-A6WG-10A-01D-A33W-08.1_gdc_realn.bam 25819033618 \n", "194 C494.TCGA-S9-A6WD-01A-12D-A33T-08.1_gdc_realn.bam 25899694434 \n", "295 C494.TCGA-FG-A711-01A-21D-A33T-08.1_gdc_realn.bam 25954568773 \n", "301 C494.TCGA-S9-A6U6-10A-01D-A33W-08.1_gdc_realn.bam 25971722247 \n", "1572 C494.TCGA-VW-A7QS-01A-12D-A33T-08.1_gdc_realn.bam 26077683267 \n", "1526 C494.TCGA-DU-A7TA-01A-11D-A33T-08.1_gdc_realn.bam 26276177578 \n", "404 C494.TCGA-TQ-A7RG-01A-11D-A33T-08.1_gdc_realn.bam 26344403523 \n", "2077 C494.TCGA-S9-A6UA-01A-12D-A33T-08.1_gdc_realn.bam 26357408848 \n", "1585 C494.TCGA-S9-A6U5-10A-01D-A33W-08.1_gdc_realn.bam 26373199753 \n", "1694 C494.TCGA-TQ-A7RS-10A-01D-A33W-08.1_gdc_realn.bam 26379422195 \n", "309 C494.TCGA-S9-A6WH-10A-01D-A33W-08.1_gdc_realn.bam 26381599891 \n", "1025 C494.TCGA-S9-A6WI-10A-01D-A33W-08.1_gdc_realn.bam 26422463992 \n", "769 C494.TCGA-R8-A6MO-01A-11D-A33T-08.1_gdc_realn.bam 26443229606 \n", "206 C494.TCGA-S9-A6U8-01A-21D-A33T-08.1_gdc_realn.bam 26444187783 \n", "1057 C494.TCGA-E1-5322-01A-01D-1468-08.9_gdc_realn.bam 26715379366 \n", "1539 C494.TCGA-TQ-A7RO-01A-11D-A33T-08.1_gdc_realn.bam 27083238331 \n", "231 C494.TCGA-TQ-A7RS-01A-12D-A33T-08.1_gdc_realn.bam 27099567535 \n", "97 C494.TCGA-S9-A6U1-10A-01D-A33W-08.1_gdc_realn.bam 27142848890 \n", "1348 C494.TCGA-S9-A6WM-10A-01D-A33W-08.1_gdc_realn.bam 27268755793 \n", "1407 C494.TCGA-TQ-A7RJ-10A-01D-A33W-08.1_gdc_realn.bam 27300150050 \n", "1716 C494.TCGA-DU-A76K-01A-11D-A33T-08.1_gdc_realn.bam 27312491024 \n", "35 C494.TCGA-S9-A6U2-01A-21D-A33T-08.1_gdc_realn.bam 27452781065 \n", "1669 C494.TCGA-S9-A6U8-10A-01D-A33W-08.1_gdc_realn.bam 27462233818 \n", "825 C494.TCGA-DH-A7US-01A-11D-A33T-08.1_gdc_realn.bam 27741243341 \n", "570 C494.TCGA-S9-A6WM-01A-12D-A33T-08.1_gdc_realn.bam 27769132884 \n", "197 C494.TCGA-TQ-A7RM-01A-11D-A33T-08.1_gdc_realn.bam 27972622913 \n", "983 C494.TCGA-S9-A6WE-10A-01D-A33W-08.1_gdc_realn.bam 28087416994 \n", "1063 C494.TCGA-S9-A6U1-01A-21D-A33T-08.1_gdc_realn.bam 28910247215 \n", "631 C494.TCGA-DU-A7TB-10A-01D-A33W-08.1_gdc_realn.bam 30154920343 \n", "\n", " platform processed \n", "546 Illumina True \n", "1019 Illumina True \n", "860 Illumina True \n", "791 Illumina True \n", "1285 Illumina True \n", "1412 Illumina True \n", "1395 Illumina True \n", "1843 Illumina True \n", "1421 Illumina True \n", "1131 Illumina True \n", "697 Illumina True \n", "1363 Illumina True \n", "333 Illumina True \n", "302 Illumina True \n", "610 Illumina True \n", "1593 Illumina True \n", "567 Illumina True \n", "398 Illumina True \n", "933 Illumina True \n", "744 Illumina True \n", "1824 Illumina True \n", "1345 Illumina True \n", "580 Illumina True \n", "433 Illumina True \n", "2039 Illumina True \n", "2013 Illumina True \n", "1768 Illumina True \n", "1289 Illumina True \n", "1754 Illumina True \n", "684 Illumina True \n", "... ... ... \n", "350 Illumina True \n", "786 Illumina True \n", "194 Illumina True \n", "295 Illumina True \n", "301 Illumina True \n", "1572 Illumina True \n", "1526 Illumina True \n", "404 Illumina True \n", "2077 Illumina True \n", "1585 Illumina True \n", "1694 Illumina True \n", "309 Illumina True \n", "1025 Illumina True \n", "769 Illumina True \n", "206 Illumina True \n", "1057 Illumina True \n", "1539 Illumina True \n", "231 Illumina True \n", "97 Illumina True \n", "1348 Illumina True \n", "1407 Illumina True \n", "1716 Illumina True \n", "35 Illumina True \n", "1669 Illumina True \n", "825 Illumina True \n", "570 Illumina True \n", "197 Illumina True \n", "983 Illumina True \n", "1063 Illumina True \n", "631 Illumina True \n", "\n", "[1427 rows x 12 columns]" ] }, "execution_count": 16, "metadata": {}, "output_type": "execute_result" } ], "source": [ "manifest_df[manifest_df['processed']]" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "WXS 1045\n", "RNA-Seq 530\n", "Name: experimental_strategy, dtype: int64" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "pd.read_pickle(manifest_dir)['experimental_strategy'].value_counts()" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "### generate the correlation between the data " ] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.6.5" } }, "nbformat": 4, "nbformat_minor": 2 }