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