{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "# Importing necessary packages\n", "import numpy as np\n", "import pandas as pd\n", "import matplotlib\n", "matplotlib.use('tkagg')\n", "import os\n", "import matplotlib.pyplot as plt\n", "import seaborn as sns\n", "\n", "from sklearn.decomposition import PCA\n", "from sklearn.manifold import TSNE" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "# Importing in full data set\n", "os.chdir('Path/To/Data')\n", "indA = pd.read_csv('IndA/20190517_IndA_RowSum.csv', index_col=0)\n", "indB = pd.read_csv('IndB/20190517_IndB_RowSum.csv', index_col=0)\n", "indC = pd.read_csv('IndC/20190517_IndC_RowSum.csv', index_col=0)\n", "unA = pd.read_csv('UnA/20190517_UnA_RowSum.csv', index_col=0)\n", "unB = pd.read_csv('UnB/20190517_UnB_RowSum.csv', index_col=0)\n", "unC = pd.read_csv('UnC/20190517_UnC_RowSum.csv', index_col=0)" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "5980\n" ] } ], "source": [ "# Find common proteins across all six sets\n", "# From those common proteins, analyze potential markers and overlap with Itzhak \n", "dflist = [unA, unB, unC, indA, indB, indC]\n", "common = pd.concat(dflist, axis=1, join='inner')\n", "tokeep = list(common.index)\n", "print(len(tokeep))" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "C:\\Users\\Aaron Oom\\Anaconda3\\lib\\site-packages\\ipykernel_launcher.py:3: FutureWarning: The signature of `Series.to_csv` was aligned to that of `DataFrame.to_csv`, and argument 'header' will change its default value from False to True: please pass an explicit value to suppress this warning.\n", " This is separate from the ipykernel package so we can avoid doing imports until\n" ] } ], "source": [ "# Converting common proteins to csv to feed into Metascape\n", "uniprot = pd.Series(tokeep)\n", "uniprot.to_csv('CommonJurkatTREHIVwt2Proteins.csv', index=False)" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Index(['Protein', 'Gene Symbol', 'Description',\n", " 'Subcellular Location (Protein Atlas)'],\n", " dtype='object')\n" ] }, { "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", "
ProteinGene SymbolDescriptionSubcellular Location (Protein Atlas)
0HIVNL43_GAG|gagNoneNoneNone
1P01737NoneNoneNone
2A0A0U1RQE8GLYATL1Bglycine-N-acyltransferase like 1BCytosol;Golgi apparatus(Uncertain)
3A0A0U1RRE5NBDYnegative regulator of P-body associationNaN
4A0A1B0GTK4FAM237Afamily with sequence similarity 237 member ANaN
5A0A1B0GUA9C13orf46chromosome 13 open reading frame 46NaN
6A0A1B0GUY1MARCOLMARCO likeNaN
7A0A1B0GVM5ETDCembryonic testis differentiation homolog CNaN
8A0AVT1UBA6ubiquitin like modifier activating enzyme 6Cytosol;Nucleoplasm(Enhanced)
9A0FGR8ESYT2extended synaptotagmin 2Cytosol(Uncertain)
10A0JLT2MED19mediator complex subunit 19Nuclear bodies(Supported)Nucleus(Approved)
11A0PJZ3GXYLT2glucoside xylosyltransferase 2Cytokinetic bridge;Midbody ring;Nucleoplasm(Ap...
12A0PK00TMEM120Btransmembrane protein 120BCytosol;Nucleoli fibrillar center(Approved)
13A1A5C7SLC22A23solute carrier family 22 member 23Cytosol;Nucleoplasm;Vesicles(Approved)
14A1L020MEX3Amex-3 RNA binding family member ACytosol(Supported)
15A1L0T0ILVBLilvB acetolactate synthase likeGolgi apparatus;Vesicles(Approved)
16A1L190SYCE3synaptonemal complex central element protein 3Golgi apparatus;Nucleoli;Nucleus(Approved)
17A1X283SH3PXD2BSH3 and PX domains 2BNucleoli fibrillar center;Nucleus(Approved)
18A1XBS5FAM92Afamily with sequence similarity 92 member AMitochondria(Approved)
19A2RRP1NBASneuroblastoma amplified sequenceGolgi apparatus;Nuclear membrane;Nucleoli(Appr...
20A2RU30TESPA1thymocyte expressed, positive selection associ...NaN
21A2RU67FAM234Bfamily with sequence similarity 234 member BEndoplasmic reticulum(Approved)
22A2RUS2DENND3DENN domain containing 3Cytosol;Vesicles(Approved)
23A2VDJ0TMEM131Ltransmembrane 131 likeVesicles(Approved)Nucleoli fibrillar center(Un...
24A3KMH1VWA8von Willebrand factor A domain containing 8Lipid droplets;Vesicles(Approved)
25A3KN83SBNO1strawberry notch homolog 1Nucleoplasm(Approved)
26A4D1E9GTPBP10GTP binding protein 10NaN
27A4D1P6WDR91WD repeat domain 91NaN
28A4D1U4KIAA1147KIAA1147Golgi apparatus(Approved)
29A4FU01MTMR11myotubularin related protein 11Centrosome(Approved)
...............
5949Q9Y6D9MAD1L1mitotic arrest deficient 1 like 1Nuclear membrane;Nucleoplasm(Supported)
5950Q9Y6E0STK24serine/threonine kinase 24Cytosol;Nucleoli(Supported)
5951Q9Y6E2BZW2basic leucine zipper and W2 domains 2Actin filaments;Cytosol;Plasma membrane(Approved)
5952Q9Y6G5COMMD10COMM domain containing 10Cytosol(Supported)Plasma membrane(Uncertain)
5953Q9Y6G9DYNC1LI1dynein cytoplasmic 1 light intermediate chain 1Centrosome;Cytosol(Supported)
5954Q9Y6H3ATP23ATP23 metallopeptidase and ATP synthase assemb...Plasma membrane;Vesicles(Enhanced)Cell Junctio...
5955Q9Y6I3EPN1epsin 1Cytosol(Enhanced)
5956Q9Y6I4USP3ubiquitin specific peptidase 3Nucleoplasm(Supported)
5957Q9Y6I8PXMP4peroxisomal membrane protein 4Nucleoli fibrillar center;Peroxisomes(Approved)
5958Q9Y6I9TEX264testis expressed 264Cytosol;Nucleoli(Supported)
5959Q9Y6J0CABIN1calcineurin binding protein 1Aggresome;Cytosol;Nucleoplasm(Approved)
5960Q9Y6J9TAF6LTATA-box binding protein associated factor 6 likeNucleoplasm(Supported)
5961Q9Y6K0CEPT1choline/ethanolamine phosphotransferase 1NaN
5962Q9Y6K5OAS32'-5'-oligoadenylate synthetase 3Cytosol;Nucleoplasm(Supported)Plasma membrane(...
5963Q9Y6M1IGF2BP2insulin like growth factor 2 mRNA binding prot...Cytosol(Enhanced)
5964Q9Y6M4CSNK1G3casein kinase 1 gamma 3NaN
5965Q9Y6M7SLC4A7solute carrier family 4 member 7Focal adhesion sites;Plasma membrane(Supported...
5966Q9Y6M9NDUFB9NADH:ubiquinone oxidoreductase subunit B9Mitochondria(Supported)
5967Q9Y6Q9NCOA3nuclear receptor coactivator 3Cytosol;Nucleoplasm(Supported)
5968Q9Y6R1SLC4A4solute carrier family 4 member 4NaN
5969Q9Y6R4MAP3K4mitogen-activated protein kinase kinase kinase 4Cytosol(Approved)
5970Q9Y6R9CCDC61coiled-coil domain containing 61Nucleus(Approved)
5971Q9Y6W3CAPN7calpain 7NaN
5972Q9Y6W5WASF2WASP family member 2Cytosol;Plasma membrane(Approved)
5973Q9Y6X1SERP1stress associated endoplasmic reticulum protein 1Endoplasmic reticulum(Approved)
5974Q9Y6X4FAM169Afamily with sequence similarity 169 member ANuclear membrane(Enhanced)Cytosol(Uncertain)
5975Q9Y6X5ENPP4ectonucleotide pyrophosphatase/phosphodiestera...NaN
5976Q9Y6X9MORC2MORC family CW-type zinc finger 2Cytosol;Nucleus(Supported)
5977Q9Y6Y0IVNS1ABPinfluenza virus NS1A binding proteinCytosol(Supported)
5978Q9Y6Y8SEC23IPSEC23 interacting proteinVesicles(Enhanced)
\n", "

5979 rows × 4 columns

\n", "
" ], "text/plain": [ " Protein Gene Symbol \\\n", "0 HIVNL43_GAG|gag None \n", "1 P01737 None \n", "2 A0A0U1RQE8 GLYATL1B \n", "3 A0A0U1RRE5 NBDY \n", "4 A0A1B0GTK4 FAM237A \n", "5 A0A1B0GUA9 C13orf46 \n", "6 A0A1B0GUY1 MARCOL \n", "7 A0A1B0GVM5 ETDC \n", "8 A0AVT1 UBA6 \n", "9 A0FGR8 ESYT2 \n", "10 A0JLT2 MED19 \n", "11 A0PJZ3 GXYLT2 \n", "12 A0PK00 TMEM120B \n", "13 A1A5C7 SLC22A23 \n", "14 A1L020 MEX3A \n", "15 A1L0T0 ILVBL \n", "16 A1L190 SYCE3 \n", "17 A1X283 SH3PXD2B \n", "18 A1XBS5 FAM92A \n", "19 A2RRP1 NBAS \n", "20 A2RU30 TESPA1 \n", "21 A2RU67 FAM234B \n", "22 A2RUS2 DENND3 \n", "23 A2VDJ0 TMEM131L \n", "24 A3KMH1 VWA8 \n", "25 A3KN83 SBNO1 \n", "26 A4D1E9 GTPBP10 \n", "27 A4D1P6 WDR91 \n", "28 A4D1U4 KIAA1147 \n", "29 A4FU01 MTMR11 \n", "... ... ... \n", "5949 Q9Y6D9 MAD1L1 \n", "5950 Q9Y6E0 STK24 \n", "5951 Q9Y6E2 BZW2 \n", "5952 Q9Y6G5 COMMD10 \n", "5953 Q9Y6G9 DYNC1LI1 \n", "5954 Q9Y6H3 ATP23 \n", "5955 Q9Y6I3 EPN1 \n", "5956 Q9Y6I4 USP3 \n", "5957 Q9Y6I8 PXMP4 \n", "5958 Q9Y6I9 TEX264 \n", "5959 Q9Y6J0 CABIN1 \n", "5960 Q9Y6J9 TAF6L \n", "5961 Q9Y6K0 CEPT1 \n", "5962 Q9Y6K5 OAS3 \n", "5963 Q9Y6M1 IGF2BP2 \n", "5964 Q9Y6M4 CSNK1G3 \n", "5965 Q9Y6M7 SLC4A7 \n", "5966 Q9Y6M9 NDUFB9 \n", "5967 Q9Y6Q9 NCOA3 \n", "5968 Q9Y6R1 SLC4A4 \n", "5969 Q9Y6R4 MAP3K4 \n", "5970 Q9Y6R9 CCDC61 \n", "5971 Q9Y6W3 CAPN7 \n", "5972 Q9Y6W5 WASF2 \n", "5973 Q9Y6X1 SERP1 \n", "5974 Q9Y6X4 FAM169A \n", "5975 Q9Y6X5 ENPP4 \n", "5976 Q9Y6X9 MORC2 \n", "5977 Q9Y6Y0 IVNS1ABP \n", "5978 Q9Y6Y8 SEC23IP \n", "\n", " Description \\\n", "0 None \n", "1 None \n", "2 glycine-N-acyltransferase like 1B \n", "3 negative regulator of P-body association \n", "4 family with sequence similarity 237 member A \n", "5 chromosome 13 open reading frame 46 \n", "6 MARCO like \n", "7 embryonic testis differentiation homolog C \n", "8 ubiquitin like modifier activating enzyme 6 \n", "9 extended synaptotagmin 2 \n", "10 mediator complex subunit 19 \n", "11 glucoside xylosyltransferase 2 \n", "12 transmembrane protein 120B \n", "13 solute carrier family 22 member 23 \n", "14 mex-3 RNA binding family member A \n", "15 ilvB acetolactate synthase like \n", "16 synaptonemal complex central element protein 3 \n", "17 SH3 and PX domains 2B \n", "18 family with sequence similarity 92 member A \n", "19 neuroblastoma amplified sequence \n", "20 thymocyte expressed, positive selection associ... \n", "21 family with sequence similarity 234 member B \n", "22 DENN domain containing 3 \n", "23 transmembrane 131 like \n", "24 von Willebrand factor A domain containing 8 \n", "25 strawberry notch homolog 1 \n", "26 GTP binding protein 10 \n", "27 WD repeat domain 91 \n", "28 KIAA1147 \n", "29 myotubularin related protein 11 \n", "... ... \n", "5949 mitotic arrest deficient 1 like 1 \n", "5950 serine/threonine kinase 24 \n", "5951 basic leucine zipper and W2 domains 2 \n", "5952 COMM domain containing 10 \n", "5953 dynein cytoplasmic 1 light intermediate chain 1 \n", "5954 ATP23 metallopeptidase and ATP synthase assemb... \n", "5955 epsin 1 \n", "5956 ubiquitin specific peptidase 3 \n", "5957 peroxisomal membrane protein 4 \n", "5958 testis expressed 264 \n", "5959 calcineurin binding protein 1 \n", "5960 TATA-box binding protein associated factor 6 like \n", "5961 choline/ethanolamine phosphotransferase 1 \n", "5962 2'-5'-oligoadenylate synthetase 3 \n", "5963 insulin like growth factor 2 mRNA binding prot... \n", "5964 casein kinase 1 gamma 3 \n", "5965 solute carrier family 4 member 7 \n", "5966 NADH:ubiquinone oxidoreductase subunit B9 \n", "5967 nuclear receptor coactivator 3 \n", "5968 solute carrier family 4 member 4 \n", "5969 mitogen-activated protein kinase kinase kinase 4 \n", "5970 coiled-coil domain containing 61 \n", "5971 calpain 7 \n", "5972 WASP family member 2 \n", "5973 stress associated endoplasmic reticulum protein 1 \n", "5974 family with sequence similarity 169 member A \n", "5975 ectonucleotide pyrophosphatase/phosphodiestera... \n", "5976 MORC family CW-type zinc finger 2 \n", "5977 influenza virus NS1A binding protein \n", "5978 SEC23 interacting protein \n", "\n", " Subcellular Location (Protein Atlas) \n", "0 None \n", "1 None \n", "2 Cytosol;Golgi apparatus(Uncertain) \n", "3 NaN \n", "4 NaN \n", "5 NaN \n", "6 NaN \n", "7 NaN \n", "8 Cytosol;Nucleoplasm(Enhanced) \n", "9 Cytosol(Uncertain) \n", "10 Nuclear bodies(Supported)Nucleus(Approved) \n", "11 Cytokinetic bridge;Midbody ring;Nucleoplasm(Ap... \n", "12 Cytosol;Nucleoli fibrillar center(Approved) \n", "13 Cytosol;Nucleoplasm;Vesicles(Approved) \n", "14 Cytosol(Supported) \n", "15 Golgi apparatus;Vesicles(Approved) \n", "16 Golgi apparatus;Nucleoli;Nucleus(Approved) \n", "17 Nucleoli fibrillar center;Nucleus(Approved) \n", "18 Mitochondria(Approved) \n", "19 Golgi apparatus;Nuclear membrane;Nucleoli(Appr... \n", "20 NaN \n", "21 Endoplasmic reticulum(Approved) \n", "22 Cytosol;Vesicles(Approved) \n", "23 Vesicles(Approved)Nucleoli fibrillar center(Un... \n", "24 Lipid droplets;Vesicles(Approved) \n", "25 Nucleoplasm(Approved) \n", "26 NaN \n", "27 NaN \n", "28 Golgi apparatus(Approved) \n", "29 Centrosome(Approved) \n", "... ... \n", "5949 Nuclear membrane;Nucleoplasm(Supported) \n", "5950 Cytosol;Nucleoli(Supported) \n", "5951 Actin filaments;Cytosol;Plasma membrane(Approved) \n", "5952 Cytosol(Supported)Plasma membrane(Uncertain) \n", "5953 Centrosome;Cytosol(Supported) \n", "5954 Plasma membrane;Vesicles(Enhanced)Cell Junctio... \n", "5955 Cytosol(Enhanced) \n", "5956 Nucleoplasm(Supported) \n", "5957 Nucleoli fibrillar center;Peroxisomes(Approved) \n", "5958 Cytosol;Nucleoli(Supported) \n", "5959 Aggresome;Cytosol;Nucleoplasm(Approved) \n", "5960 Nucleoplasm(Supported) \n", "5961 NaN \n", "5962 Cytosol;Nucleoplasm(Supported)Plasma membrane(... \n", "5963 Cytosol(Enhanced) \n", "5964 NaN \n", "5965 Focal adhesion sites;Plasma membrane(Supported... \n", "5966 Mitochondria(Supported) \n", "5967 Cytosol;Nucleoplasm(Supported) \n", "5968 NaN \n", "5969 Cytosol(Approved) \n", "5970 Nucleus(Approved) \n", "5971 NaN \n", "5972 Cytosol;Plasma membrane(Approved) \n", "5973 Endoplasmic reticulum(Approved) \n", "5974 Nuclear membrane(Enhanced)Cytosol(Uncertain) \n", "5975 NaN \n", "5976 Cytosol;Nucleus(Supported) \n", "5977 Cytosol(Supported) \n", "5978 Vesicles(Enhanced) \n", "\n", "[5979 rows x 4 columns]" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# Reading in Metascape results with annotations\n", "annot_data = pd.read_csv('metascape_result.csv', sep = ',')\n", "print(annot_data.columns)\n", "display(annot_data)" ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " Protein Gene Symbol Description \\\n", "0 A0FGR8 ESYT2 extended synaptotagmin 2 \n", "1 A1L020 MEX3A mex-3 RNA binding family member A \n", "2 A1XBS5 FAM92A family with sequence similarity 92 member A \n", "3 A2RU67 FAM234B family with sequence similarity 234 member B \n", "4 A3KN83 SBNO1 strawberry notch homolog 1 \n", "5 A4D1U4 KIAA1147 KIAA1147 \n", "6 A4FU01 MTMR11 myotubularin related protein 11 \n", "7 A5YKK6 CNOT1 CCR4-NOT transcription complex subunit 1 \n", "8 A6NDG6 PGP phosphoglycolate phosphatase \n", "9 A6NEL2 SOWAHB sosondowah ankyrin repeat domain family member B \n", "10 A6QL63 BTBD11 BTB domain containing 11 \n", "11 P62308 SNRPG small nuclear ribonucleoprotein polypeptide G \n", "12 P0CG08 GPR89B G protein-coupled receptor 89B \n", "13 C9JCN9 HSBP1L1 heat shock factor binding protein 1 like 1 \n", "14 C9JLW8 MCRIP1 MAPK regulated corepressor interacting protein 1 \n", "15 L0R6Q1 SLC35A4 solute carrier family 35 member A4 \n", "16 L0R819 ASNSD1 asparagine synthetase domain containing 1 \n", "17 O00148 DDX39A DExD-box helicase 39A \n", "18 O00161 SNAP23 synaptosome associated protein 23 \n", "19 O00165 HAX1 HCLS1 associated protein X-1 \n", "20 O00170 AIP aryl hydrocarbon receptor interacting protein \n", "21 O00180 KCNK1 potassium two pore domain channel subfamily K ... \n", "22 O00182 LGALS9 galectin 9 \n", "23 O00214 LGALS8 galectin 8 \n", "24 O00267 SUPT5H SPT5 homolog, DSIF elongation factor subunit \n", "25 O00291 HIP1 huntingtin interacting protein 1 \n", "26 O00299 CLIC1 chloride intracellular channel 1 \n", "27 O00400 SLC33A1 solute carrier family 33 member 1 \n", "28 O00418 EEF2K eukaryotic elongation factor 2 kinase \n", "29 O00425 IGF2BP3 insulin like growth factor 2 mRNA binding prot... \n", "... ... ... ... \n", "2191 Q9Y5V3 MAGED1 MAGE family member D1 \n", "2192 Q9Y5W7 SNX14 sorting nexin 14 \n", "2193 Q9Y5W9 SNX11 sorting nexin 11 \n", "2194 Q9Y5X2 SNX8 sorting nexin 8 \n", "2195 Q9Y5Y0 FLVCR1 feline leukemia virus subgroup C cellular rece... \n", "2196 Q9Y5Z9 UBIAD1 UbiA prenyltransferase domain containing 1 \n", "2197 Q9Y613 FHOD1 formin homology 2 domain containing 1 \n", "2198 Q9Y617 PSAT1 phosphoserine aminotransferase 1 \n", "2199 Q9Y618 NCOR2 nuclear receptor corepressor 2 \n", "2200 Q9Y620 RAD54B RAD54 homolog B \n", "2201 Q9Y657 SPIN1 spindlin 1 \n", "2202 Q9Y666 SLC12A7 solute carrier family 12 member 7 \n", "2203 Q9Y673 ALG5 ALG5 dolichyl-phosphate beta-glucosyltransferase \n", "2204 Q9Y680 FKBP7 FKBP prolyl isomerase 7 \n", "2205 Q9Y696 CLIC4 chloride intracellular channel 4 \n", "2206 Q9Y6A4 CFAP20 cilia and flagella associated protein 20 \n", "2207 Q9Y6B6 SAR1B secretion associated Ras related GTPase 1B \n", "2208 Q9Y6B7 AP4B1 adaptor related protein complex 4 subunit beta 1 \n", "2209 Q9Y6C9 MTCH2 mitochondrial carrier 2 \n", "2210 Q9Y6D5 ARFGEF2 ADP ribosylation factor guanine nucleotide exc... \n", "2211 Q9Y6I3 EPN1 epsin 1 \n", "2212 Q9Y6I4 USP3 ubiquitin specific peptidase 3 \n", "2213 Q9Y6J9 TAF6L TATA-box binding protein associated factor 6 like \n", "2214 Q9Y6M1 IGF2BP2 insulin like growth factor 2 mRNA binding prot... \n", "2215 Q9Y6M9 NDUFB9 NADH:ubiquinone oxidoreductase subunit B9 \n", "2216 Q9Y6R4 MAP3K4 mitogen-activated protein kinase kinase kinase 4 \n", "2217 Q9Y6R9 CCDC61 coiled-coil domain containing 61 \n", "2218 Q9Y6X1 SERP1 stress associated endoplasmic reticulum protein 1 \n", "2219 Q9Y6Y0 IVNS1ABP influenza virus NS1A binding protein \n", "2220 Q9Y6Y8 SEC23IP SEC23 interacting protein \n", "\n", " Subcellular Location (Protein Atlas) \n", "0 Cytosol(Uncertain) \n", "1 Cytosol(Supported) \n", "2 Mitochondria(Approved) \n", "3 Endoplasmic reticulum(Approved) \n", "4 Nucleoplasm(Approved) \n", "5 Golgi apparatus(Approved) \n", "6 Centrosome(Approved) \n", "7 Cytosol(Supported) \n", "8 Nuclear bodies(Approved) \n", "9 Nucleoli fibrillar center(Approved) \n", "10 Nucleoplasm(Approved) \n", "11 Nucleoplasm(Approved) \n", "12 Endoplasmic reticulum(Approved) \n", "13 Nucleoplasm(Approved) \n", "14 Cytosol(Approved) \n", "15 Nucleoplasm(Approved) \n", "16 Cytosol(Approved) \n", "17 Nuclear speckles(Approved) \n", "18 Plasma membrane(Supported) \n", "19 Mitochondria(Supported) \n", "20 Cytosol(Supported) \n", "21 Vesicles(Approved) \n", "22 Cytosol(Approved) \n", "23 Plasma membrane(Approved) \n", "24 Nucleoplasm(Enhanced) \n", "25 Vesicles(Enhanced) \n", "26 Cytosol(Supported) \n", "27 Nucleus(Approved) \n", "28 Nucleoplasm(Approved) \n", "29 Cytosol(Enhanced) \n", "... ... \n", "2191 Cytosol(Approved) \n", "2192 Cytosol(Supported) \n", "2193 Cytosol(Approved) \n", "2194 Vesicles(Supported) \n", "2195 Cell Junctions(Approved) \n", "2196 Vesicles(Approved) \n", "2197 Cytosol(Supported) \n", "2198 Cytosol(Enhanced) \n", "2199 Nucleoplasm(Supported) \n", "2200 Nucleus(Supported) \n", "2201 Nucleoplasm(Supported) \n", "2202 Cytosol(Uncertain) \n", "2203 Cytosol(Approved) \n", "2204 Endoplasmic reticulum(Supported) \n", "2205 Cytosol(Supported) \n", "2206 Nucleus(Supported) \n", "2207 Endoplasmic reticulum(Approved) \n", "2208 Vesicles(Approved) \n", "2209 Mitochondria(Supported) \n", "2210 Golgi apparatus(Supported) \n", "2211 Cytosol(Enhanced) \n", "2212 Nucleoplasm(Supported) \n", "2213 Nucleoplasm(Supported) \n", "2214 Cytosol(Enhanced) \n", "2215 Mitochondria(Supported) \n", "2216 Cytosol(Approved) \n", "2217 Nucleus(Approved) \n", "2218 Endoplasmic reticulum(Approved) \n", "2219 Cytosol(Supported) \n", "2220 Vesicles(Enhanced) \n", "\n", "[2221 rows x 4 columns]\n" ] } ], "source": [ "# Filtering out those genes with multiple subcelular localization assignments\n", "tokeep = []\n", "for item in annot_data.index:\n", " if str(annot_data.at[item, 'Subcellular Location (Protein Atlas)']).count(')') == 1:\n", " if str(annot_data.at[item, 'Subcellular Location (Protein Atlas)']).count(';') == 0:\n", " tokeep.append(annot_data.loc[item, :])\n", "putative_markers = pd.DataFrame.from_records(tokeep, columns=annot_data.columns)\n", "print(putative_markers)" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " Protein Gene Symbol Description \\\n", "0 A0FGR8 ESYT2 extended synaptotagmin 2 \n", "1 A1L020 MEX3A mex-3 RNA binding family member A \n", "2 A1XBS5 FAM92A family with sequence similarity 92 member A \n", "3 A2RU67 FAM234B family with sequence similarity 234 member B \n", "4 A4D1U4 KIAA1147 KIAA1147 \n", "5 A4FU01 MTMR11 myotubularin related protein 11 \n", "6 A5YKK6 CNOT1 CCR4-NOT transcription complex subunit 1 \n", "7 P0CG08 GPR89B G protein-coupled receptor 89B \n", "8 C9JLW8 MCRIP1 MAPK regulated corepressor interacting protein 1 \n", "9 L0R819 ASNSD1 asparagine synthetase domain containing 1 \n", "10 O00161 SNAP23 synaptosome associated protein 23 \n", "11 O00165 HAX1 HCLS1 associated protein X-1 \n", "12 O00170 AIP aryl hydrocarbon receptor interacting protein \n", "13 O00180 KCNK1 potassium two pore domain channel subfamily K ... \n", "14 O00182 LGALS9 galectin 9 \n", "15 O00214 LGALS8 galectin 8 \n", "16 O00291 HIP1 huntingtin interacting protein 1 \n", "17 O00299 CLIC1 chloride intracellular channel 1 \n", "18 O00425 IGF2BP3 insulin like growth factor 2 mRNA binding prot... \n", "19 O00459 PIK3R2 phosphoinositide-3-kinase regulatory subunit 2 \n", "20 O00462 MANBA mannosidase beta \n", "21 O00463 TRAF5 TNF receptor associated factor 5 \n", "22 O00481 BTN3A1 butyrophilin subfamily 3 member A1 \n", "23 O00483 NDUFA4 NDUFA4 mitochondrial complex associated \n", "24 O00522 KRIT1 KRIT1 ankyrin repeat containing \n", "25 O00559 EBAG9 estrogen receptor binding site associated anti... \n", "26 O00767 SCD stearoyl-CoA desaturase \n", "27 O14494 PLPP1 phospholipid phosphatase 1 \n", "28 O14530 TXNDC9 thioredoxin domain containing 9 \n", "29 O14578 CIT citron rho-interacting serine/threonine kinase \n", "... ... ... ... \n", "1231 Q9Y5B8 NME7 NME/NM23 family member 7 \n", "1232 Q9Y5J7 TIMM9 translocase of inner mitochondrial membrane 9 \n", "1233 Q9Y5L0 TNPO3 transportin 3 \n", "1234 Q9Y5M8 SRPRB SRP receptor subunit beta \n", "1235 Q9Y5S1 TRPV2 transient receptor potential cation channel su... \n", "1236 Q9Y5U9 IER3IP1 immediate early response 3 interacting protein 1 \n", "1237 Q9Y5V0 ZNF706 zinc finger protein 706 \n", "1238 Q9Y5V3 MAGED1 MAGE family member D1 \n", "1239 Q9Y5W7 SNX14 sorting nexin 14 \n", "1240 Q9Y5W9 SNX11 sorting nexin 11 \n", "1241 Q9Y5X2 SNX8 sorting nexin 8 \n", "1242 Q9Y5Y0 FLVCR1 feline leukemia virus subgroup C cellular rece... \n", "1243 Q9Y5Z9 UBIAD1 UbiA prenyltransferase domain containing 1 \n", "1244 Q9Y613 FHOD1 formin homology 2 domain containing 1 \n", "1245 Q9Y617 PSAT1 phosphoserine aminotransferase 1 \n", "1246 Q9Y666 SLC12A7 solute carrier family 12 member 7 \n", "1247 Q9Y673 ALG5 ALG5 dolichyl-phosphate beta-glucosyltransferase \n", "1248 Q9Y680 FKBP7 FKBP prolyl isomerase 7 \n", "1249 Q9Y696 CLIC4 chloride intracellular channel 4 \n", "1250 Q9Y6B6 SAR1B secretion associated Ras related GTPase 1B \n", "1251 Q9Y6B7 AP4B1 adaptor related protein complex 4 subunit beta 1 \n", "1252 Q9Y6C9 MTCH2 mitochondrial carrier 2 \n", "1253 Q9Y6D5 ARFGEF2 ADP ribosylation factor guanine nucleotide exc... \n", "1254 Q9Y6I3 EPN1 epsin 1 \n", "1255 Q9Y6M1 IGF2BP2 insulin like growth factor 2 mRNA binding prot... \n", "1256 Q9Y6M9 NDUFB9 NADH:ubiquinone oxidoreductase subunit B9 \n", "1257 Q9Y6R4 MAP3K4 mitogen-activated protein kinase kinase kinase 4 \n", "1258 Q9Y6X1 SERP1 stress associated endoplasmic reticulum protein 1 \n", "1259 Q9Y6Y0 IVNS1ABP influenza virus NS1A binding protein \n", "1260 Q9Y6Y8 SEC23IP SEC23 interacting protein \n", "\n", " Subcellular Location (Protein Atlas) \n", "0 Cytosol(Uncertain) \n", "1 Cytosol(Supported) \n", "2 Mitochondria(Approved) \n", "3 Endoplasmic reticulum(Approved) \n", "4 Golgi apparatus(Approved) \n", "5 Centrosome(Approved) \n", "6 Cytosol(Supported) \n", "7 Endoplasmic reticulum(Approved) \n", "8 Cytosol(Approved) \n", "9 Cytosol(Approved) \n", "10 Plasma membrane(Supported) \n", "11 Mitochondria(Supported) \n", "12 Cytosol(Supported) \n", "13 Vesicles(Approved) \n", "14 Cytosol(Approved) \n", "15 Plasma membrane(Approved) \n", "16 Vesicles(Enhanced) \n", "17 Cytosol(Supported) \n", "18 Cytosol(Enhanced) \n", "19 Golgi apparatus(Approved) \n", "20 Vesicles(Supported) \n", "21 Cytosol(Supported) \n", "22 Vesicles(Uncertain) \n", "23 Mitochondria(Supported) \n", "24 Vesicles(Uncertain) \n", "25 Golgi apparatus(Enhanced) \n", "26 Endoplasmic reticulum(Enhanced) \n", "27 Plasma membrane(Supported) \n", "28 Cytosol(Enhanced) \n", "29 Cytosol(Approved) \n", "... ... \n", "1231 Mitochondria(Approved) \n", "1232 Mitochondria(Enhanced) \n", "1233 Vesicles(Enhanced) \n", "1234 Plasma membrane(Approved) \n", "1235 Plasma membrane(Supported) \n", "1236 Endoplasmic reticulum(Supported) \n", "1237 Plasma membrane(Approved) \n", "1238 Cytosol(Approved) \n", "1239 Cytosol(Supported) \n", "1240 Cytosol(Approved) \n", "1241 Vesicles(Supported) \n", "1242 Cell Junctions(Approved) \n", "1243 Vesicles(Approved) \n", "1244 Cytosol(Supported) \n", "1245 Cytosol(Enhanced) \n", "1246 Cytosol(Uncertain) \n", "1247 Cytosol(Approved) \n", "1248 Endoplasmic reticulum(Supported) \n", "1249 Cytosol(Supported) \n", "1250 Endoplasmic reticulum(Approved) \n", "1251 Vesicles(Approved) \n", "1252 Mitochondria(Supported) \n", "1253 Golgi apparatus(Supported) \n", "1254 Cytosol(Enhanced) \n", "1255 Cytosol(Enhanced) \n", "1256 Mitochondria(Supported) \n", "1257 Cytosol(Approved) \n", "1258 Endoplasmic reticulum(Approved) \n", "1259 Cytosol(Supported) \n", "1260 Vesicles(Enhanced) \n", "\n", "[1261 rows x 4 columns]\n" ] } ], "source": [ "# Filtering out nuclear proteins\n", "tokeep = []\n", "for item in putative_markers.index:\n", " if 'nucl' not in putative_markers.at[item, 'Subcellular Location (Protein Atlas)'].lower():\n", " tokeep.append(putative_markers.loc[item, :])\n", "postnucl_markers = pd.DataFrame.from_records(tokeep, columns=annot_data.columns)\n", "print(postnucl_markers)" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " Protein Gene Symbol Description \\\n", "0 A1L020 MEX3A mex-3 RNA binding family member A \n", "1 A1XBS5 FAM92A family with sequence similarity 92 member A \n", "2 A2RU67 FAM234B family with sequence similarity 234 member B \n", "3 A4D1U4 KIAA1147 KIAA1147 \n", "4 A4FU01 MTMR11 myotubularin related protein 11 \n", "5 A5YKK6 CNOT1 CCR4-NOT transcription complex subunit 1 \n", "6 P0CG08 GPR89B G protein-coupled receptor 89B \n", "7 C9JLW8 MCRIP1 MAPK regulated corepressor interacting protein 1 \n", "8 L0R819 ASNSD1 asparagine synthetase domain containing 1 \n", "9 O00161 SNAP23 synaptosome associated protein 23 \n", "10 O00165 HAX1 HCLS1 associated protein X-1 \n", "11 O00170 AIP aryl hydrocarbon receptor interacting protein \n", "12 O00180 KCNK1 potassium two pore domain channel subfamily K ... \n", "13 O00182 LGALS9 galectin 9 \n", "14 O00214 LGALS8 galectin 8 \n", "15 O00291 HIP1 huntingtin interacting protein 1 \n", "16 O00299 CLIC1 chloride intracellular channel 1 \n", "17 O00425 IGF2BP3 insulin like growth factor 2 mRNA binding prot... \n", "18 O00459 PIK3R2 phosphoinositide-3-kinase regulatory subunit 2 \n", "19 O00462 MANBA mannosidase beta \n", "20 O00463 TRAF5 TNF receptor associated factor 5 \n", "21 O00483 NDUFA4 NDUFA4 mitochondrial complex associated \n", "22 O00559 EBAG9 estrogen receptor binding site associated anti... \n", "23 O00767 SCD stearoyl-CoA desaturase \n", "24 O14494 PLPP1 phospholipid phosphatase 1 \n", "25 O14530 TXNDC9 thioredoxin domain containing 9 \n", "26 O14578 CIT citron rho-interacting serine/threonine kinase \n", "27 O14579 COPE coatomer protein complex subunit epsilon \n", "28 O14617 AP3D1 adaptor related protein complex 3 subunit delta 1 \n", "29 O14639 ABLIM1 actin binding LIM protein 1 \n", "... ... ... ... \n", "1186 Q9Y597 KCTD3 potassium channel tetramerization domain conta... \n", "1187 Q9Y5B8 NME7 NME/NM23 family member 7 \n", "1188 Q9Y5J7 TIMM9 translocase of inner mitochondrial membrane 9 \n", "1189 Q9Y5L0 TNPO3 transportin 3 \n", "1190 Q9Y5M8 SRPRB SRP receptor subunit beta \n", "1191 Q9Y5S1 TRPV2 transient receptor potential cation channel su... \n", "1192 Q9Y5U9 IER3IP1 immediate early response 3 interacting protein 1 \n", "1193 Q9Y5V0 ZNF706 zinc finger protein 706 \n", "1194 Q9Y5V3 MAGED1 MAGE family member D1 \n", "1195 Q9Y5W7 SNX14 sorting nexin 14 \n", "1196 Q9Y5W9 SNX11 sorting nexin 11 \n", "1197 Q9Y5X2 SNX8 sorting nexin 8 \n", "1198 Q9Y5Y0 FLVCR1 feline leukemia virus subgroup C cellular rece... \n", "1199 Q9Y5Z9 UBIAD1 UbiA prenyltransferase domain containing 1 \n", "1200 Q9Y613 FHOD1 formin homology 2 domain containing 1 \n", "1201 Q9Y617 PSAT1 phosphoserine aminotransferase 1 \n", "1202 Q9Y673 ALG5 ALG5 dolichyl-phosphate beta-glucosyltransferase \n", "1203 Q9Y680 FKBP7 FKBP prolyl isomerase 7 \n", "1204 Q9Y696 CLIC4 chloride intracellular channel 4 \n", "1205 Q9Y6B6 SAR1B secretion associated Ras related GTPase 1B \n", "1206 Q9Y6B7 AP4B1 adaptor related protein complex 4 subunit beta 1 \n", "1207 Q9Y6C9 MTCH2 mitochondrial carrier 2 \n", "1208 Q9Y6D5 ARFGEF2 ADP ribosylation factor guanine nucleotide exc... \n", "1209 Q9Y6I3 EPN1 epsin 1 \n", "1210 Q9Y6M1 IGF2BP2 insulin like growth factor 2 mRNA binding prot... \n", "1211 Q9Y6M9 NDUFB9 NADH:ubiquinone oxidoreductase subunit B9 \n", "1212 Q9Y6R4 MAP3K4 mitogen-activated protein kinase kinase kinase 4 \n", "1213 Q9Y6X1 SERP1 stress associated endoplasmic reticulum protein 1 \n", "1214 Q9Y6Y0 IVNS1ABP influenza virus NS1A binding protein \n", "1215 Q9Y6Y8 SEC23IP SEC23 interacting protein \n", "\n", " Subcellular Location (Protein Atlas) \n", "0 Cytosol(Supported) \n", "1 Mitochondria(Approved) \n", "2 Endoplasmic reticulum(Approved) \n", "3 Golgi apparatus(Approved) \n", "4 Centrosome(Approved) \n", "5 Cytosol(Supported) \n", "6 Endoplasmic reticulum(Approved) \n", "7 Cytosol(Approved) \n", "8 Cytosol(Approved) \n", "9 Plasma membrane(Supported) \n", "10 Mitochondria(Supported) \n", "11 Cytosol(Supported) \n", "12 Vesicles(Approved) \n", "13 Cytosol(Approved) \n", "14 Plasma membrane(Approved) \n", "15 Vesicles(Enhanced) \n", "16 Cytosol(Supported) \n", "17 Cytosol(Enhanced) \n", "18 Golgi apparatus(Approved) \n", "19 Vesicles(Supported) \n", "20 Cytosol(Supported) \n", "21 Mitochondria(Supported) \n", "22 Golgi apparatus(Enhanced) \n", "23 Endoplasmic reticulum(Enhanced) \n", "24 Plasma membrane(Supported) \n", "25 Cytosol(Enhanced) \n", "26 Cytosol(Approved) \n", "27 Golgi apparatus(Enhanced) \n", "28 Cytosol(Approved) \n", "29 Cytosol(Supported) \n", "... ... \n", "1186 Cytosol(Approved) \n", "1187 Mitochondria(Approved) \n", "1188 Mitochondria(Enhanced) \n", "1189 Vesicles(Enhanced) \n", "1190 Plasma membrane(Approved) \n", "1191 Plasma membrane(Supported) \n", "1192 Endoplasmic reticulum(Supported) \n", "1193 Plasma membrane(Approved) \n", "1194 Cytosol(Approved) \n", "1195 Cytosol(Supported) \n", "1196 Cytosol(Approved) \n", "1197 Vesicles(Supported) \n", "1198 Cell Junctions(Approved) \n", "1199 Vesicles(Approved) \n", "1200 Cytosol(Supported) \n", "1201 Cytosol(Enhanced) \n", "1202 Cytosol(Approved) \n", "1203 Endoplasmic reticulum(Supported) \n", "1204 Cytosol(Supported) \n", "1205 Endoplasmic reticulum(Approved) \n", "1206 Vesicles(Approved) \n", "1207 Mitochondria(Supported) \n", "1208 Golgi apparatus(Supported) \n", "1209 Cytosol(Enhanced) \n", "1210 Cytosol(Enhanced) \n", "1211 Mitochondria(Supported) \n", "1212 Cytosol(Approved) \n", "1213 Endoplasmic reticulum(Approved) \n", "1214 Cytosol(Supported) \n", "1215 Vesicles(Enhanced) \n", "\n", "[1216 rows x 4 columns]\n" ] } ], "source": [ "# Filtering out uncertain assignments\n", "tokeep =[]\n", "for item in postnucl_markers.index:\n", " if 'uncertain' not in postnucl_markers.at[item, 'Subcellular Location (Protein Atlas)'].lower():\n", " tokeep.append(postnucl_markers.loc[item,:])\n", "quality_markers = pd.DataFrame.from_records(tokeep, columns=annot_data.columns)\n", "print(quality_markers)" ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " Gene Symbol Description \\\n", "Protein \n", "O00291 HIP1 huntingtin interacting protein 1 \n", "O00425 IGF2BP3 insulin like growth factor 2 mRNA binding prot... \n", "O00559 EBAG9 estrogen receptor binding site associated anti... \n", "O00767 SCD stearoyl-CoA desaturase \n", "O14530 TXNDC9 thioredoxin domain containing 9 \n", "O14579 COPE coatomer protein complex subunit epsilon \n", "O14662 STX16 syntaxin 16 \n", "O14949 UQCRQ ubiquinol-cytochrome c reductase complex III s... \n", "O14967 CLGN calmegin \n", "O15258 RER1 retention in endoplasmic reticulum sorting rec... \n", "O15392 BIRC5 baculoviral IAP repeat containing 5 \n", "O15400 STX7 syntaxin 7 \n", "O43396 TXNL1 thioredoxin like 1 \n", "O43615 TIMM44 translocase of inner mitochondrial membrane 44 \n", "O43795 MYO1B myosin IB \n", "O75534 CSDE1 cold shock domain containing E1 \n", "O75821 EIF3G eukaryotic translation initiation factor 3 sub... \n", "O75822 EIF3J eukaryotic translation initiation factor 3 sub... \n", "O94822 LTN1 listerin E3 ubiquitin protein ligase 1 \n", "O94826 TOMM70 translocase of outer mitochondrial membrane 70 \n", "O95139 NDUFB6 NADH:ubiquinone oxidoreductase subunit B6 \n", "O95159 ZFPL1 zinc finger protein like 1 \n", "O95202 LETM1 leucine zipper and EF-hand containing transmem... \n", "O95292 VAPB VAMP associated protein B and C \n", "O95613 PCNT pericentrin \n", "O95747 OXSR1 oxidative stress responsive kinase 1 \n", "P00387 CYB5R3 cytochrome b5 reductase 3 \n", "P04843 RPN1 ribophorin I \n", "P07195 LDHB lactate dehydrogenase B \n", "P07814 EPRS glutamyl-prolyl-tRNA synthetase \n", "... ... ... \n", "Q9NTK5 OLA1 Obg like ATPase 1 \n", "Q9NUY8 TBC1D23 TBC1 domain family member 23 \n", "Q9NV92 NDFIP2 Nedd4 family interacting protein 2 \n", "Q9NW68 BSDC1 BSD domain containing 1 \n", "Q9NX74 DUS2 dihydrouridine synthase 2 \n", "Q9NXF8 ZDHHC7 zinc finger DHHC-type containing 7 \n", "Q9NYP7 ELOVL5 ELOVL fatty acid elongase 5 \n", "Q9NZB2 FAM120A family with sequence similarity 120A \n", "Q9P0J0 NDUFA13 NADH:ubiquinone oxidoreductase subunit A13 \n", "Q9P0L0 VAPA VAMP associated protein A \n", "Q9P2E9 RRBP1 ribosome binding protein 1 \n", "Q9P2R3 ANKFY1 ankyrin repeat and FYVE domain containing 1 \n", "Q9UHD8 9-Sep septin 9 \n", "Q9UHV9 PFDN2 prefoldin subunit 2 \n", "Q9UN86 G3BP2 G3BP stress granule assembly factor 2 \n", "Q9UPN7 PPP6R1 protein phosphatase 6 regulatory subunit 1 \n", "Q9Y266 NUDC nuclear distribution C, dynein complex regulator \n", "Q9Y371 SH3GLB1 SH3 domain containing GRB2 like, endophilin B1 \n", "Q9Y3D6 FIS1 fission, mitochondrial 1 \n", "Q9Y3P9 RABGAP1 RAB GTPase activating protein 1 \n", "Q9Y4E8 USP15 ubiquitin specific peptidase 15 \n", "Q9Y4W6 AFG3L2 AFG3 like matrix AAA peptidase subunit 2 \n", "Q9Y512 SAMM50 SAMM50 sorting and assembly machinery component \n", "Q9Y520 PRRC2C proline rich coiled-coil 2C \n", "Q9Y5J7 TIMM9 translocase of inner mitochondrial membrane 9 \n", "Q9Y5L0 TNPO3 transportin 3 \n", "Q9Y617 PSAT1 phosphoserine aminotransferase 1 \n", "Q9Y6I3 EPN1 epsin 1 \n", "Q9Y6M1 IGF2BP2 insulin like growth factor 2 mRNA binding prot... \n", "Q9Y6Y8 SEC23IP SEC23 interacting protein \n", "\n", " Subcellular Location (Protein Atlas) \n", "Protein \n", "O00291 Vesicles(Enhanced) \n", "O00425 Cytosol(Enhanced) \n", "O00559 Golgi apparatus(Enhanced) \n", "O00767 Endoplasmic reticulum(Enhanced) \n", "O14530 Cytosol(Enhanced) \n", "O14579 Golgi apparatus(Enhanced) \n", "O14662 Vesicles(Enhanced) \n", "O14949 Mitochondria(Enhanced) \n", "O14967 Endoplasmic reticulum(Enhanced) \n", "O15258 Golgi apparatus(Enhanced) \n", "O15392 Cytokinetic bridge(Enhanced) \n", "O15400 Lysosomes(Enhanced) \n", "O43396 Cytosol(Enhanced) \n", "O43615 Mitochondria(Enhanced) \n", "O43795 Plasma membrane(Enhanced) \n", "O75534 Cytosol(Enhanced) \n", "O75821 Cytosol(Enhanced) \n", "O75822 Cytosol(Enhanced) \n", "O94822 Cytosol(Enhanced) \n", "O94826 Mitochondria(Enhanced) \n", "O95139 Mitochondria(Enhanced) \n", "O95159 Golgi apparatus(Enhanced) \n", "O95202 Mitochondria(Enhanced) \n", "O95292 Endoplasmic reticulum(Enhanced) \n", "O95613 Centrosome(Enhanced) \n", "O95747 Cytosol(Enhanced) \n", "P00387 Endoplasmic reticulum(Enhanced) \n", "P04843 Endoplasmic reticulum(Enhanced) \n", "P07195 Cytosol(Enhanced) \n", "P07814 Cytosol(Enhanced) \n", "... ... \n", "Q9NTK5 Cytosol(Enhanced) \n", "Q9NUY8 Golgi apparatus(Enhanced) \n", "Q9NV92 Vesicles(Enhanced) \n", "Q9NW68 Golgi apparatus(Enhanced) \n", "Q9NX74 Cytosol(Enhanced) \n", "Q9NXF8 Golgi apparatus(Enhanced) \n", "Q9NYP7 Endoplasmic reticulum(Enhanced) \n", "Q9NZB2 Cytosol(Enhanced) \n", "Q9P0J0 Mitochondria(Enhanced) \n", "Q9P0L0 Endoplasmic reticulum(Enhanced) \n", "Q9P2E9 Endoplasmic reticulum(Enhanced) \n", "Q9P2R3 Endosomes(Enhanced) \n", "Q9UHD8 Actin filaments(Enhanced) \n", "Q9UHV9 Cytosol(Enhanced) \n", "Q9UN86 Cytosol(Enhanced) \n", "Q9UPN7 Cytosol(Enhanced) \n", "Q9Y266 Cytosol(Enhanced) \n", "Q9Y371 Cytosol(Enhanced) \n", "Q9Y3D6 Mitochondria(Enhanced) \n", "Q9Y3P9 Cytosol(Enhanced) \n", "Q9Y4E8 Cytosol(Enhanced) \n", "Q9Y4W6 Mitochondria(Enhanced) \n", "Q9Y512 Mitochondria(Enhanced) \n", "Q9Y520 Cytosol(Enhanced) \n", "Q9Y5J7 Mitochondria(Enhanced) \n", "Q9Y5L0 Vesicles(Enhanced) \n", "Q9Y617 Cytosol(Enhanced) \n", "Q9Y6I3 Cytosol(Enhanced) \n", "Q9Y6M1 Cytosol(Enhanced) \n", "Q9Y6Y8 Vesicles(Enhanced) \n", "\n", "[249 rows x 3 columns]\n", "Cytosol(Enhanced) 95\n", "Mitochondria(Enhanced) 41\n", "Endoplasmic reticulum(Enhanced) 35\n", "Vesicles(Enhanced) 23\n", "Golgi apparatus(Enhanced) 20\n", "Plasma membrane(Enhanced) 14\n", "Peroxisomes(Enhanced) 6\n", "Centrosome(Enhanced) 5\n", "Actin filaments(Enhanced) 2\n", "Endosomes(Enhanced) 2\n", "Cytokinetic bridge(Enhanced) 1\n", "Focal adhesion sites(Enhanced) 1\n", "Microtubule organizing center(Enhanced) 1\n", "Microtubules(Enhanced) 1\n", "Lysosomes(Enhanced) 1\n", "Cell Junctions(Enhanced) 1\n", "Name: Subcellular Location (Protein Atlas), dtype: int64\n" ] } ], "source": [ "# Checking how many proteins have an Enhanced reliability score\n", "enhanced = []\n", "enhanced_supported = []\n", "for item in quality_markers.index:\n", " if 'Enhanced' in quality_markers.at[item, 'Subcellular Location (Protein Atlas)']:\n", " enhanced.append(quality_markers.loc[item,:])\n", " enhanced_supported.append(quality_markers.loc[item,:])\n", " elif 'Supported' in quality_markers.at[item, 'Subcellular Location (Protein Atlas)']:\n", " enhanced_supported.append(quality_markers.loc[item,:])\n", "enhancedprot = pd.DataFrame.from_records(enhanced, index = 'Protein', columns=annot_data.columns)\n", "enh_supprot = pd.DataFrame.from_records(enhanced_supported, index = 'Protein', columns=annot_data.columns)\n", "print((enhancedprot))\n", "print(enhancedprot['Subcellular Location (Protein Atlas)'].value_counts())" ] }, { "cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " Gene Symbol Description \\\n", "Protein \n", "O00291 HIP1 huntingtin interacting protein 1 \n", "O00425 IGF2BP3 insulin like growth factor 2 mRNA binding prot... \n", "O00559 EBAG9 estrogen receptor binding site associated anti... \n", "O00767 SCD stearoyl-CoA desaturase \n", "O14530 TXNDC9 thioredoxin domain containing 9 \n", "O14579 COPE coatomer protein complex subunit epsilon \n", "O14662 STX16 syntaxin 16 \n", "O14949 UQCRQ ubiquinol-cytochrome c reductase complex III s... \n", "O14967 CLGN calmegin \n", "O15258 RER1 retention in endoplasmic reticulum sorting rec... \n", "O15392 BIRC5 baculoviral IAP repeat containing 5 \n", "O15400 STX7 syntaxin 7 \n", "O43396 TXNL1 thioredoxin like 1 \n", "O43615 TIMM44 translocase of inner mitochondrial membrane 44 \n", "O43795 MYO1B myosin IB \n", "O75534 CSDE1 cold shock domain containing E1 \n", "O75821 EIF3G eukaryotic translation initiation factor 3 sub... \n", "O75822 EIF3J eukaryotic translation initiation factor 3 sub... \n", "O94822 LTN1 listerin E3 ubiquitin protein ligase 1 \n", "O94826 TOMM70 translocase of outer mitochondrial membrane 70 \n", "O95139 NDUFB6 NADH:ubiquinone oxidoreductase subunit B6 \n", "O95159 ZFPL1 zinc finger protein like 1 \n", "O95202 LETM1 leucine zipper and EF-hand containing transmem... \n", "O95292 VAPB VAMP associated protein B and C \n", "O95613 PCNT pericentrin \n", "O95747 OXSR1 oxidative stress responsive kinase 1 \n", "P00387 CYB5R3 cytochrome b5 reductase 3 \n", "P04843 RPN1 ribophorin I \n", "P07195 LDHB lactate dehydrogenase B \n", "P07814 EPRS glutamyl-prolyl-tRNA synthetase \n", "... ... ... \n", "Q9NTK5 OLA1 Obg like ATPase 1 \n", "Q9NUY8 TBC1D23 TBC1 domain family member 23 \n", "Q9NV92 NDFIP2 Nedd4 family interacting protein 2 \n", "Q9NW68 BSDC1 BSD domain containing 1 \n", "Q9NX74 DUS2 dihydrouridine synthase 2 \n", "Q9NXF8 ZDHHC7 zinc finger DHHC-type containing 7 \n", "Q9NYP7 ELOVL5 ELOVL fatty acid elongase 5 \n", "Q9NZB2 FAM120A family with sequence similarity 120A \n", "Q9P0J0 NDUFA13 NADH:ubiquinone oxidoreductase subunit A13 \n", "Q9P0L0 VAPA VAMP associated protein A \n", "Q9P2E9 RRBP1 ribosome binding protein 1 \n", "Q9P2R3 ANKFY1 ankyrin repeat and FYVE domain containing 1 \n", "Q9UHD8 9-Sep septin 9 \n", "Q9UHV9 PFDN2 prefoldin subunit 2 \n", "Q9UN86 G3BP2 G3BP stress granule assembly factor 2 \n", "Q9UPN7 PPP6R1 protein phosphatase 6 regulatory subunit 1 \n", "Q9Y266 NUDC nuclear distribution C, dynein complex regulator \n", "Q9Y371 SH3GLB1 SH3 domain containing GRB2 like, endophilin B1 \n", "Q9Y3D6 FIS1 fission, mitochondrial 1 \n", "Q9Y3P9 RABGAP1 RAB GTPase activating protein 1 \n", "Q9Y4E8 USP15 ubiquitin specific peptidase 15 \n", "Q9Y4W6 AFG3L2 AFG3 like matrix AAA peptidase subunit 2 \n", "Q9Y512 SAMM50 SAMM50 sorting and assembly machinery component \n", "Q9Y520 PRRC2C proline rich coiled-coil 2C \n", "Q9Y5J7 TIMM9 translocase of inner mitochondrial membrane 9 \n", "Q9Y5L0 TNPO3 transportin 3 \n", "Q9Y617 PSAT1 phosphoserine aminotransferase 1 \n", "Q9Y6I3 EPN1 epsin 1 \n", "Q9Y6M1 IGF2BP2 insulin like growth factor 2 mRNA binding prot... \n", "Q9Y6Y8 SEC23IP SEC23 interacting protein \n", "\n", " Subcellular Location (Protein Atlas) Subcellular_Loc \n", "Protein \n", "O00291 Vesicles(Enhanced) Vesicles \n", "O00425 Cytosol(Enhanced) Cytosol \n", "O00559 Golgi apparatus(Enhanced) Golgi apparatus \n", "O00767 Endoplasmic reticulum(Enhanced) Endoplasmic reticulum \n", "O14530 Cytosol(Enhanced) Cytosol \n", "O14579 Golgi apparatus(Enhanced) Golgi apparatus \n", "O14662 Vesicles(Enhanced) Vesicles \n", "O14949 Mitochondria(Enhanced) Mitochondria \n", "O14967 Endoplasmic reticulum(Enhanced) Endoplasmic reticulum \n", "O15258 Golgi apparatus(Enhanced) Golgi apparatus \n", "O15392 Cytokinetic bridge(Enhanced) Cytokinetic bridge \n", "O15400 Lysosomes(Enhanced) Lysosomes \n", "O43396 Cytosol(Enhanced) Cytosol \n", "O43615 Mitochondria(Enhanced) Mitochondria \n", "O43795 Plasma membrane(Enhanced) Plasma membrane \n", "O75534 Cytosol(Enhanced) Cytosol \n", "O75821 Cytosol(Enhanced) Cytosol \n", "O75822 Cytosol(Enhanced) Cytosol \n", "O94822 Cytosol(Enhanced) Cytosol \n", "O94826 Mitochondria(Enhanced) Mitochondria \n", "O95139 Mitochondria(Enhanced) Mitochondria \n", "O95159 Golgi apparatus(Enhanced) Golgi apparatus \n", "O95202 Mitochondria(Enhanced) Mitochondria \n", "O95292 Endoplasmic reticulum(Enhanced) Endoplasmic reticulum \n", "O95613 Centrosome(Enhanced) Centrosome \n", "O95747 Cytosol(Enhanced) Cytosol \n", "P00387 Endoplasmic reticulum(Enhanced) Endoplasmic reticulum \n", "P04843 Endoplasmic reticulum(Enhanced) Endoplasmic reticulum \n", "P07195 Cytosol(Enhanced) Cytosol \n", "P07814 Cytosol(Enhanced) Cytosol \n", "... ... ... \n", "Q9NTK5 Cytosol(Enhanced) Cytosol \n", "Q9NUY8 Golgi apparatus(Enhanced) Golgi apparatus \n", "Q9NV92 Vesicles(Enhanced) Vesicles \n", "Q9NW68 Golgi apparatus(Enhanced) Golgi apparatus \n", "Q9NX74 Cytosol(Enhanced) Cytosol \n", "Q9NXF8 Golgi apparatus(Enhanced) Golgi apparatus \n", "Q9NYP7 Endoplasmic reticulum(Enhanced) Endoplasmic reticulum \n", "Q9NZB2 Cytosol(Enhanced) Cytosol \n", "Q9P0J0 Mitochondria(Enhanced) Mitochondria \n", "Q9P0L0 Endoplasmic reticulum(Enhanced) Endoplasmic reticulum \n", "Q9P2E9 Endoplasmic reticulum(Enhanced) Endoplasmic reticulum \n", "Q9P2R3 Endosomes(Enhanced) Endosomes \n", "Q9UHD8 Actin filaments(Enhanced) Actin filaments \n", "Q9UHV9 Cytosol(Enhanced) Cytosol \n", "Q9UN86 Cytosol(Enhanced) Cytosol \n", "Q9UPN7 Cytosol(Enhanced) Cytosol \n", "Q9Y266 Cytosol(Enhanced) Cytosol \n", "Q9Y371 Cytosol(Enhanced) Cytosol \n", "Q9Y3D6 Mitochondria(Enhanced) Mitochondria \n", "Q9Y3P9 Cytosol(Enhanced) Cytosol \n", "Q9Y4E8 Cytosol(Enhanced) Cytosol \n", "Q9Y4W6 Mitochondria(Enhanced) Mitochondria \n", "Q9Y512 Mitochondria(Enhanced) Mitochondria \n", "Q9Y520 Cytosol(Enhanced) Cytosol \n", "Q9Y5J7 Mitochondria(Enhanced) Mitochondria \n", "Q9Y5L0 Vesicles(Enhanced) Vesicles \n", "Q9Y617 Cytosol(Enhanced) Cytosol \n", "Q9Y6I3 Cytosol(Enhanced) Cytosol \n", "Q9Y6M1 Cytosol(Enhanced) Cytosol \n", "Q9Y6Y8 Vesicles(Enhanced) Vesicles \n", "\n", "[249 rows x 4 columns]\n", " Gene Symbol Description \\\n", "Protein \n", "O00291 HIP1 huntingtin interacting protein 1 \n", "O00425 IGF2BP3 insulin like growth factor 2 mRNA binding prot... \n", "O00559 EBAG9 estrogen receptor binding site associated anti... \n", "O00767 SCD stearoyl-CoA desaturase \n", "O14530 TXNDC9 thioredoxin domain containing 9 \n", "O14579 COPE coatomer protein complex subunit epsilon \n", "O14662 STX16 syntaxin 16 \n", "O14949 UQCRQ ubiquinol-cytochrome c reductase complex III s... \n", "O14967 CLGN calmegin \n", "O15258 RER1 retention in endoplasmic reticulum sorting rec... \n", "O15392 BIRC5 baculoviral IAP repeat containing 5 \n", "O15400 STX7 syntaxin 7 \n", "O43396 TXNL1 thioredoxin like 1 \n", "O43615 TIMM44 translocase of inner mitochondrial membrane 44 \n", "O43795 MYO1B myosin IB \n", "O75534 CSDE1 cold shock domain containing E1 \n", "O75821 EIF3G eukaryotic translation initiation factor 3 sub... \n", "O75822 EIF3J eukaryotic translation initiation factor 3 sub... \n", "O94822 LTN1 listerin E3 ubiquitin protein ligase 1 \n", "O94826 TOMM70 translocase of outer mitochondrial membrane 70 \n", "O95139 NDUFB6 NADH:ubiquinone oxidoreductase subunit B6 \n", "O95159 ZFPL1 zinc finger protein like 1 \n", "O95202 LETM1 leucine zipper and EF-hand containing transmem... \n", "O95292 VAPB VAMP associated protein B and C \n", "O95613 PCNT pericentrin \n", "O95747 OXSR1 oxidative stress responsive kinase 1 \n", "P00387 CYB5R3 cytochrome b5 reductase 3 \n", "P04843 RPN1 ribophorin I \n", "P07195 LDHB lactate dehydrogenase B \n", "P07814 EPRS glutamyl-prolyl-tRNA synthetase \n", "... ... ... \n", "Q9NTK5 OLA1 Obg like ATPase 1 \n", "Q9NUY8 TBC1D23 TBC1 domain family member 23 \n", "Q9NV92 NDFIP2 Nedd4 family interacting protein 2 \n", "Q9NW68 BSDC1 BSD domain containing 1 \n", "Q9NX74 DUS2 dihydrouridine synthase 2 \n", "Q9NXF8 ZDHHC7 zinc finger DHHC-type containing 7 \n", "Q9NYP7 ELOVL5 ELOVL fatty acid elongase 5 \n", "Q9NZB2 FAM120A family with sequence similarity 120A \n", "Q9P0J0 NDUFA13 NADH:ubiquinone oxidoreductase subunit A13 \n", "Q9P0L0 VAPA VAMP associated protein A \n", "Q9P2E9 RRBP1 ribosome binding protein 1 \n", "Q9P2R3 ANKFY1 ankyrin repeat and FYVE domain containing 1 \n", "Q9UHD8 9-Sep septin 9 \n", "Q9UHV9 PFDN2 prefoldin subunit 2 \n", "Q9UN86 G3BP2 G3BP stress granule assembly factor 2 \n", "Q9UPN7 PPP6R1 protein phosphatase 6 regulatory subunit 1 \n", "Q9Y266 NUDC nuclear distribution C, dynein complex regulator \n", "Q9Y371 SH3GLB1 SH3 domain containing GRB2 like, endophilin B1 \n", "Q9Y3D6 FIS1 fission, mitochondrial 1 \n", "Q9Y3P9 RABGAP1 RAB GTPase activating protein 1 \n", "Q9Y4E8 USP15 ubiquitin specific peptidase 15 \n", "Q9Y4W6 AFG3L2 AFG3 like matrix AAA peptidase subunit 2 \n", "Q9Y512 SAMM50 SAMM50 sorting and assembly machinery component \n", "Q9Y520 PRRC2C proline rich coiled-coil 2C \n", "Q9Y5J7 TIMM9 translocase of inner mitochondrial membrane 9 \n", "Q9Y5L0 TNPO3 transportin 3 \n", "Q9Y617 PSAT1 phosphoserine aminotransferase 1 \n", "Q9Y6I3 EPN1 epsin 1 \n", "Q9Y6M1 IGF2BP2 insulin like growth factor 2 mRNA binding prot... \n", "Q9Y6Y8 SEC23IP SEC23 interacting protein \n", "\n", " Subcellular_Loc \n", "Protein \n", "O00291 Vesicles \n", "O00425 Cytosol \n", "O00559 Golgi apparatus \n", "O00767 Endoplasmic reticulum \n", "O14530 Cytosol \n", "O14579 Golgi apparatus \n", "O14662 Vesicles \n", "O14949 Mitochondria \n", "O14967 Endoplasmic reticulum \n", "O15258 Golgi apparatus \n", "O15392 Cytokinetic bridge \n", "O15400 Lysosomes \n", "O43396 Cytosol \n", "O43615 Mitochondria \n", "O43795 Plasma membrane \n", "O75534 Cytosol \n", "O75821 Cytosol \n", "O75822 Cytosol \n", "O94822 Cytosol \n", "O94826 Mitochondria \n", "O95139 Mitochondria \n", "O95159 Golgi apparatus \n", "O95202 Mitochondria \n", "O95292 Endoplasmic reticulum \n", "O95613 Centrosome \n", "O95747 Cytosol \n", "P00387 Endoplasmic reticulum \n", "P04843 Endoplasmic reticulum \n", "P07195 Cytosol \n", "P07814 Cytosol \n", "... ... \n", "Q9NTK5 Cytosol \n", "Q9NUY8 Golgi apparatus \n", "Q9NV92 Vesicles \n", "Q9NW68 Golgi apparatus \n", "Q9NX74 Cytosol \n", "Q9NXF8 Golgi apparatus \n", "Q9NYP7 Endoplasmic reticulum \n", "Q9NZB2 Cytosol \n", "Q9P0J0 Mitochondria \n", "Q9P0L0 Endoplasmic reticulum \n", "Q9P2E9 Endoplasmic reticulum \n", "Q9P2R3 Endosomes \n", "Q9UHD8 Actin filaments \n", "Q9UHV9 Cytosol \n", "Q9UN86 Cytosol \n", "Q9UPN7 Cytosol \n", "Q9Y266 Cytosol \n", "Q9Y371 Cytosol \n", "Q9Y3D6 Mitochondria \n", "Q9Y3P9 Cytosol \n", "Q9Y4E8 Cytosol \n", "Q9Y4W6 Mitochondria \n", "Q9Y512 Mitochondria \n", "Q9Y520 Cytosol \n", "Q9Y5J7 Mitochondria \n", "Q9Y5L0 Vesicles \n", "Q9Y617 Cytosol \n", "Q9Y6I3 Cytosol \n", "Q9Y6M1 Cytosol \n", "Q9Y6Y8 Vesicles \n", "\n", "[249 rows x 3 columns]\n", " Gene Symbol Description \\\n", "Protein \n", "A1L020 MEX3A mex-3 RNA binding family member A \n", "A5YKK6 CNOT1 CCR4-NOT transcription complex subunit 1 \n", "O00161 SNAP23 synaptosome associated protein 23 \n", "O00165 HAX1 HCLS1 associated protein X-1 \n", "O00170 AIP aryl hydrocarbon receptor interacting protein \n", "O00291 HIP1 huntingtin interacting protein 1 \n", "O00299 CLIC1 chloride intracellular channel 1 \n", "O00425 IGF2BP3 insulin like growth factor 2 mRNA binding prot... \n", "O00462 MANBA mannosidase beta \n", "O00463 TRAF5 TNF receptor associated factor 5 \n", "O00483 NDUFA4 NDUFA4 mitochondrial complex associated \n", "O00559 EBAG9 estrogen receptor binding site associated anti... \n", "O00767 SCD stearoyl-CoA desaturase \n", "O14494 PLPP1 phospholipid phosphatase 1 \n", "O14530 TXNDC9 thioredoxin domain containing 9 \n", "O14579 COPE coatomer protein complex subunit epsilon \n", "O14639 ABLIM1 actin binding LIM protein 1 \n", "O14662 STX16 syntaxin 16 \n", "O14828 SCAMP3 secretory carrier membrane protein 3 \n", "O14925 TIMM23 translocase of inner mitochondrial membrane 23 \n", "O14949 UQCRQ ubiquinol-cytochrome c reductase complex III s... \n", "O14967 CLGN calmegin \n", "O15078 CEP290 centrosomal protein 290 \n", "O15121 DEGS1 delta 4-desaturase, sphingolipid 1 \n", "O15182 CETN3 centrin 3 \n", "O15258 RER1 retention in endoplasmic reticulum sorting rec... \n", "O15269 SPTLC1 serine palmitoyltransferase long chain base su... \n", "O15371 EIF3D eukaryotic translation initiation factor 3 sub... \n", "O15392 BIRC5 baculoviral IAP repeat containing 5 \n", "O15400 STX7 syntaxin 7 \n", "... ... ... \n", "Q9Y285 FARSA phenylalanyl-tRNA synthetase subunit alpha \n", "Q9Y2Q0 ATP8A1 ATPase phospholipid transporting 8A1 \n", "Q9Y2Q3 GSTK1 glutathione S-transferase kappa 1 \n", "Q9Y371 SH3GLB1 SH3 domain containing GRB2 like, endophilin B1 \n", "Q9Y3C4 TPRKB TP53RK binding protein \n", "Q9Y3D6 FIS1 fission, mitochondrial 1 \n", "Q9Y3P9 RABGAP1 RAB GTPase activating protein 1 \n", "Q9Y3Q3 TMED3 transmembrane p24 trafficking protein 3 \n", "Q9Y4E8 USP15 ubiquitin specific peptidase 15 \n", "Q9Y4P3 TBL2 transducin beta like 2 \n", "Q9Y4W6 AFG3L2 AFG3 like matrix AAA peptidase subunit 2 \n", "Q9Y512 SAMM50 SAMM50 sorting and assembly machinery component \n", "Q9Y520 PRRC2C proline rich coiled-coil 2C \n", "Q9Y5J7 TIMM9 translocase of inner mitochondrial membrane 9 \n", "Q9Y5L0 TNPO3 transportin 3 \n", "Q9Y5S1 TRPV2 transient receptor potential cation channel su... \n", "Q9Y5U9 IER3IP1 immediate early response 3 interacting protein 1 \n", "Q9Y5W7 SNX14 sorting nexin 14 \n", "Q9Y5X2 SNX8 sorting nexin 8 \n", "Q9Y613 FHOD1 formin homology 2 domain containing 1 \n", "Q9Y617 PSAT1 phosphoserine aminotransferase 1 \n", "Q9Y680 FKBP7 FKBP prolyl isomerase 7 \n", "Q9Y696 CLIC4 chloride intracellular channel 4 \n", "Q9Y6C9 MTCH2 mitochondrial carrier 2 \n", "Q9Y6D5 ARFGEF2 ADP ribosylation factor guanine nucleotide exc... \n", "Q9Y6I3 EPN1 epsin 1 \n", "Q9Y6M1 IGF2BP2 insulin like growth factor 2 mRNA binding prot... \n", "Q9Y6M9 NDUFB9 NADH:ubiquinone oxidoreductase subunit B9 \n", "Q9Y6Y0 IVNS1ABP influenza virus NS1A binding protein \n", "Q9Y6Y8 SEC23IP SEC23 interacting protein \n", "\n", " Subcellular Location (Protein Atlas) Subcellular_Loc \n", "Protein \n", "A1L020 Cytosol(Supported) Cytosol \n", "A5YKK6 Cytosol(Supported) Cytosol \n", "O00161 Plasma membrane(Supported) Plasma membrane \n", "O00165 Mitochondria(Supported) Mitochondria \n", "O00170 Cytosol(Supported) Cytosol \n", "O00291 Vesicles(Enhanced) Vesicles \n", "O00299 Cytosol(Supported) Cytosol \n", "O00425 Cytosol(Enhanced) Cytosol \n", "O00462 Vesicles(Supported) Vesicles \n", "O00463 Cytosol(Supported) Cytosol \n", "O00483 Mitochondria(Supported) Mitochondria \n", "O00559 Golgi apparatus(Enhanced) Golgi apparatus \n", "O00767 Endoplasmic reticulum(Enhanced) Endoplasmic reticulum \n", "O14494 Plasma membrane(Supported) Plasma membrane \n", "O14530 Cytosol(Enhanced) Cytosol \n", "O14579 Golgi apparatus(Enhanced) Golgi apparatus \n", "O14639 Cytosol(Supported) Cytosol \n", "O14662 Vesicles(Enhanced) Vesicles \n", "O14828 Vesicles(Supported) Vesicles \n", "O14925 Mitochondria(Supported) Mitochondria \n", "O14949 Mitochondria(Enhanced) Mitochondria \n", "O14967 Endoplasmic reticulum(Enhanced) Endoplasmic reticulum \n", "O15078 Centrosome(Supported) Centrosome \n", "O15121 Mitochondria(Supported) Mitochondria \n", "O15182 Centrosome(Supported) Centrosome \n", "O15258 Golgi apparatus(Enhanced) Golgi apparatus \n", "O15269 Endoplasmic reticulum(Supported) Endoplasmic reticulum \n", "O15371 Cytosol(Supported) Cytosol \n", "O15392 Cytokinetic bridge(Enhanced) Cytokinetic bridge \n", "O15400 Lysosomes(Enhanced) Lysosomes \n", "... ... ... \n", "Q9Y285 Cytosol(Supported) Cytosol \n", "Q9Y2Q0 Vesicles(Supported) Vesicles \n", "Q9Y2Q3 Peroxisomes(Supported) Peroxisomes \n", "Q9Y371 Cytosol(Enhanced) Cytosol \n", "Q9Y3C4 Cytosol(Supported) Cytosol \n", "Q9Y3D6 Mitochondria(Enhanced) Mitochondria \n", "Q9Y3P9 Cytosol(Enhanced) Cytosol \n", "Q9Y3Q3 Golgi apparatus(Supported) Golgi apparatus \n", "Q9Y4E8 Cytosol(Enhanced) Cytosol \n", "Q9Y4P3 Cytosol(Supported) Cytosol \n", "Q9Y4W6 Mitochondria(Enhanced) Mitochondria \n", "Q9Y512 Mitochondria(Enhanced) Mitochondria \n", "Q9Y520 Cytosol(Enhanced) Cytosol \n", "Q9Y5J7 Mitochondria(Enhanced) Mitochondria \n", "Q9Y5L0 Vesicles(Enhanced) Vesicles \n", "Q9Y5S1 Plasma membrane(Supported) Plasma membrane \n", "Q9Y5U9 Endoplasmic reticulum(Supported) Endoplasmic reticulum \n", "Q9Y5W7 Cytosol(Supported) Cytosol \n", "Q9Y5X2 Vesicles(Supported) Vesicles \n", "Q9Y613 Cytosol(Supported) Cytosol \n", "Q9Y617 Cytosol(Enhanced) Cytosol \n", "Q9Y680 Endoplasmic reticulum(Supported) Endoplasmic reticulum \n", "Q9Y696 Cytosol(Supported) Cytosol \n", "Q9Y6C9 Mitochondria(Supported) Mitochondria \n", "Q9Y6D5 Golgi apparatus(Supported) Golgi apparatus \n", "Q9Y6I3 Cytosol(Enhanced) Cytosol \n", "Q9Y6M1 Cytosol(Enhanced) Cytosol \n", "Q9Y6M9 Mitochondria(Supported) Mitochondria \n", "Q9Y6Y0 Cytosol(Supported) Cytosol \n", "Q9Y6Y8 Vesicles(Enhanced) Vesicles \n", "\n", "[681 rows x 4 columns]\n", " Gene Symbol Description \\\n", "Protein \n", "A1L020 MEX3A mex-3 RNA binding family member A \n", "A5YKK6 CNOT1 CCR4-NOT transcription complex subunit 1 \n", "O00161 SNAP23 synaptosome associated protein 23 \n", "O00165 HAX1 HCLS1 associated protein X-1 \n", "O00170 AIP aryl hydrocarbon receptor interacting protein \n", "O00291 HIP1 huntingtin interacting protein 1 \n", "O00299 CLIC1 chloride intracellular channel 1 \n", "O00425 IGF2BP3 insulin like growth factor 2 mRNA binding prot... \n", "O00462 MANBA mannosidase beta \n", "O00463 TRAF5 TNF receptor associated factor 5 \n", "O00483 NDUFA4 NDUFA4 mitochondrial complex associated \n", "O00559 EBAG9 estrogen receptor binding site associated anti... \n", "O00767 SCD stearoyl-CoA desaturase \n", "O14494 PLPP1 phospholipid phosphatase 1 \n", "O14530 TXNDC9 thioredoxin domain containing 9 \n", "O14579 COPE coatomer protein complex subunit epsilon \n", "O14639 ABLIM1 actin binding LIM protein 1 \n", "O14662 STX16 syntaxin 16 \n", "O14828 SCAMP3 secretory carrier membrane protein 3 \n", "O14925 TIMM23 translocase of inner mitochondrial membrane 23 \n", "O14949 UQCRQ ubiquinol-cytochrome c reductase complex III s... \n", "O14967 CLGN calmegin \n", "O15078 CEP290 centrosomal protein 290 \n", "O15121 DEGS1 delta 4-desaturase, sphingolipid 1 \n", "O15182 CETN3 centrin 3 \n", "O15258 RER1 retention in endoplasmic reticulum sorting rec... \n", "O15269 SPTLC1 serine palmitoyltransferase long chain base su... \n", "O15371 EIF3D eukaryotic translation initiation factor 3 sub... \n", "O15392 BIRC5 baculoviral IAP repeat containing 5 \n", "O15400 STX7 syntaxin 7 \n", "... ... ... \n", "Q9Y285 FARSA phenylalanyl-tRNA synthetase subunit alpha \n", "Q9Y2Q0 ATP8A1 ATPase phospholipid transporting 8A1 \n", "Q9Y2Q3 GSTK1 glutathione S-transferase kappa 1 \n", "Q9Y371 SH3GLB1 SH3 domain containing GRB2 like, endophilin B1 \n", "Q9Y3C4 TPRKB TP53RK binding protein \n", "Q9Y3D6 FIS1 fission, mitochondrial 1 \n", "Q9Y3P9 RABGAP1 RAB GTPase activating protein 1 \n", "Q9Y3Q3 TMED3 transmembrane p24 trafficking protein 3 \n", "Q9Y4E8 USP15 ubiquitin specific peptidase 15 \n", "Q9Y4P3 TBL2 transducin beta like 2 \n", "Q9Y4W6 AFG3L2 AFG3 like matrix AAA peptidase subunit 2 \n", "Q9Y512 SAMM50 SAMM50 sorting and assembly machinery component \n", "Q9Y520 PRRC2C proline rich coiled-coil 2C \n", "Q9Y5J7 TIMM9 translocase of inner mitochondrial membrane 9 \n", "Q9Y5L0 TNPO3 transportin 3 \n", "Q9Y5S1 TRPV2 transient receptor potential cation channel su... \n", "Q9Y5U9 IER3IP1 immediate early response 3 interacting protein 1 \n", "Q9Y5W7 SNX14 sorting nexin 14 \n", "Q9Y5X2 SNX8 sorting nexin 8 \n", "Q9Y613 FHOD1 formin homology 2 domain containing 1 \n", "Q9Y617 PSAT1 phosphoserine aminotransferase 1 \n", "Q9Y680 FKBP7 FKBP prolyl isomerase 7 \n", "Q9Y696 CLIC4 chloride intracellular channel 4 \n", "Q9Y6C9 MTCH2 mitochondrial carrier 2 \n", "Q9Y6D5 ARFGEF2 ADP ribosylation factor guanine nucleotide exc... \n", "Q9Y6I3 EPN1 epsin 1 \n", "Q9Y6M1 IGF2BP2 insulin like growth factor 2 mRNA binding prot... \n", "Q9Y6M9 NDUFB9 NADH:ubiquinone oxidoreductase subunit B9 \n", "Q9Y6Y0 IVNS1ABP influenza virus NS1A binding protein \n", "Q9Y6Y8 SEC23IP SEC23 interacting protein \n", "\n", " Subcellular_Loc \n", "Protein \n", "A1L020 Cytosol \n", "A5YKK6 Cytosol \n", "O00161 Plasma membrane \n", "O00165 Mitochondria \n", "O00170 Cytosol \n", "O00291 Vesicles \n", "O00299 Cytosol \n", "O00425 Cytosol \n", "O00462 Vesicles \n", "O00463 Cytosol \n", "O00483 Mitochondria \n", "O00559 Golgi apparatus \n", "O00767 Endoplasmic reticulum \n", "O14494 Plasma membrane \n", "O14530 Cytosol \n", "O14579 Golgi apparatus \n", "O14639 Cytosol \n", "O14662 Vesicles \n", "O14828 Vesicles \n", "O14925 Mitochondria \n", "O14949 Mitochondria \n", "O14967 Endoplasmic reticulum \n", "O15078 Centrosome \n", "O15121 Mitochondria \n", "O15182 Centrosome \n", "O15258 Golgi apparatus \n", "O15269 Endoplasmic reticulum \n", "O15371 Cytosol \n", "O15392 Cytokinetic bridge \n", "O15400 Lysosomes \n", "... ... \n", "Q9Y285 Cytosol \n", "Q9Y2Q0 Vesicles \n", "Q9Y2Q3 Peroxisomes \n", "Q9Y371 Cytosol \n", "Q9Y3C4 Cytosol \n", "Q9Y3D6 Mitochondria \n", "Q9Y3P9 Cytosol \n", "Q9Y3Q3 Golgi apparatus \n", "Q9Y4E8 Cytosol \n", "Q9Y4P3 Cytosol \n", "Q9Y4W6 Mitochondria \n", "Q9Y512 Mitochondria \n", "Q9Y520 Cytosol \n", "Q9Y5J7 Mitochondria \n", "Q9Y5L0 Vesicles \n", "Q9Y5S1 Plasma membrane \n", "Q9Y5U9 Endoplasmic reticulum \n", "Q9Y5W7 Cytosol \n", "Q9Y5X2 Vesicles \n", "Q9Y613 Cytosol \n", "Q9Y617 Cytosol \n", "Q9Y680 Endoplasmic reticulum \n", "Q9Y696 Cytosol \n", "Q9Y6C9 Mitochondria \n", "Q9Y6D5 Golgi apparatus \n", "Q9Y6I3 Cytosol \n", "Q9Y6M1 Cytosol \n", "Q9Y6M9 Mitochondria \n", "Q9Y6Y0 Cytosol \n", "Q9Y6Y8 Vesicles \n", "\n", "[681 rows x 3 columns]\n" ] } ], "source": [ "# Rewriting subcellular location column to remove reliability score\n", "for item in enhancedprot.index:\n", " string = enhancedprot.at[item, 'Subcellular Location (Protein Atlas)'].split('(')[0]\n", " enhancedprot.at[item, 'Subcellular_Loc'] = string\n", "print(enhancedprot)\n", "enhancedprot.drop(columns=['Subcellular Location (Protein Atlas)'], inplace=True)\n", "print(enhancedprot)\n", "\n", "for item in enh_supprot.index:\n", " string = enh_supprot.at[item, 'Subcellular Location (Protein Atlas)'].split('(')[0]\n", " enh_supprot.at[item, 'Subcellular_Loc'] = string\n", "print(enh_supprot)\n", "enh_supprot.drop(columns=['Subcellular Location (Protein Atlas)'], inplace=True)\n", "print(enh_supprot)" ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Cytosol 95\n", "Mitochondria 41\n", "Endoplasmic reticulum 35\n", "Vesicles 23\n", "Golgi apparatus 20\n", "Plasma membrane 14\n", "Peroxisomes 6\n", "Centrosome 5\n", "Endosomes 2\n", "Actin filaments 2\n", "Microtubule organizing center 1\n", "Microtubules 1\n", "Lysosomes 1\n", "Cell Junctions 1\n", "Focal adhesion sites 1\n", "Cytokinetic bridge 1\n", "Name: Subcellular_Loc, dtype: int64\n", "['Actin filaments', 'Cell Junctions', 'Centrosome', 'Cytokinetic bridge', 'Cytosol', 'Endoplasmic reticulum', 'Endosomes', 'Focal adhesion sites', 'Golgi apparatus', 'Lysosomes', 'Microtubule organizing center', 'Microtubules', 'Mitochondria', 'Peroxisomes', 'Plasma membrane', 'Vesicles']\n", "Cytosol 256\n", "Mitochondria 100\n", "Vesicles 87\n", "Endoplasmic reticulum 78\n", "Plasma membrane 49\n", "Golgi apparatus 48\n", "Centrosome 19\n", "Peroxisomes 10\n", "Microtubules 9\n", "Cell Junctions 4\n", "Cytoplasmic bodies 3\n", "Actin filaments 3\n", "Lipid droplets 3\n", "Focal adhesion sites 3\n", "Microtubule organizing center 3\n", "Lysosomes 2\n", "Endosomes 2\n", "Cytokinetic bridge 1\n", "Intermediate filaments 1\n", "Name: Subcellular_Loc, dtype: int64\n", "['Actin filaments', 'Cell Junctions', 'Centrosome', 'Cytokinetic bridge', 'Cytoplasmic bodies', 'Cytosol', 'Endoplasmic reticulum', 'Endosomes', 'Focal adhesion sites', 'Golgi apparatus', 'Intermediate filaments', 'Lipid droplets', 'Lysosomes', 'Microtubule organizing center', 'Microtubules', 'Mitochondria', 'Peroxisomes', 'Plasma membrane', 'Vesicles']\n" ] } ], "source": [ "# Counting unique values in Subcellular_Loc column\n", "print(enhancedprot.Subcellular_Loc.value_counts())\n", "compartment_list = list(enhancedprot.Subcellular_Loc.unique())\n", "compartment_list.sort()\n", "print(compartment_list)\n", "\n", "print(enh_supprot.Subcellular_Loc.value_counts())\n", "compartment_list2 = list(enh_supprot.Subcellular_Loc.unique())\n", "compartment_list2.sort()\n", "print(compartment_list2)" ] }, { "cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "There are 60 common proteins between the Itzhak et al. reference markers and our putative markers (enh only)\n", "There are 147 common proteins between the Itzhak et al. reference markers and our putative markers (enh_sup)\n", "There are 725 common proteins between the Itzhak et al. reference markers and replicate common proteins\n" ] } ], "source": [ "# Checking concordance between Itzhak markers and putative markers\n", "Itzhakmarkers = pd.read_csv('Itzhak_HelaOrganelleMarkers.csv', index_col=3)\n", "Itzindex = Itzhakmarkers.index\n", "concordance = Itzindex.intersection(enhancedprot.index)\n", "concordance3 = Itzindex.intersection(enh_supprot.index)\n", "concordance2 = Itzindex.intersection(uniprot)\n", "print(\"There are {:d} common proteins between the Itzhak et al. reference markers and our putative markers (enh only)\".format(len(concordance)))\n", "print(\"There are {:d} common proteins between the Itzhak et al. reference markers and our putative markers (enh_sup)\".format(len(concordance3)))\n", "print(\"There are {:d} common proteins between the Itzhak et al. reference markers and replicate common proteins\".format(len(concordance2)))" ] }, { "cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "189\n", "['O00291', 'O00425', 'O00559', 'O14530', 'O14662', 'O14967', 'O15392', 'O43396', 'O43615', 'O43795', 'O75534', 'O75822', 'O94822', 'O95139', 'O95159', 'O95613', 'O95747', 'P00387', 'P07195', 'P07900', 'P08243', 'P12235', 'P13798', 'P14314', 'P14618', 'P14635', 'P15311', 'P18031', 'P18206', 'P19367', 'P22307', 'P23921', 'P26038', 'P26640', 'P28161', 'P29353', 'P30566', 'P34913', 'P35222', 'P35241', 'P36871', 'P36896', 'P40306', 'P40855', 'P43034', 'P47897', 'P48147', 'P49815', 'P50502', 'P51114', 'P51148', 'P51572', 'P51970', 'P52565', 'P54886', 'P55283', 'P61221', 'P62072', 'P62166', 'P62879', 'P63279', 'P80303', 'P83436', 'P98196', 'Q01433', 'Q04206', 'Q04637', 'Q04759', 'Q06787', 'Q07820', 'Q12792', 'Q12849', 'Q12933', 'Q13283', 'Q13310', 'Q13561', 'Q13586', 'Q14764', 'Q14789', 'Q15276', 'Q15293', 'Q15388', 'Q15785', 'Q15833', 'Q16543', 'Q16667', 'Q16891', 'Q460N5', 'Q49A88', 'Q49B96', 'Q56VL3', 'Q5PRF9', 'Q5T5C0', 'Q5T8D3', 'Q66K74', 'Q6IA69', 'Q6IQ20', 'Q6NXE6', 'Q6NXR4', 'Q6NXT4', 'Q6Y7W6', 'Q70UQ0', 'Q71RC2', 'Q7KZF4', 'Q86UE4', 'Q86UP2', 'Q86XZ4', 'Q8IUH4', 'Q8N0Z8', 'Q8N183', 'Q8N1F8', 'Q8N3C7', 'Q8N490', 'Q8N5M1', 'Q8NC51', 'Q8NE71', 'Q8TB72', 'Q8TEW0', 'Q8WU90', 'Q8WUF5', 'Q8WUM4', 'Q8WV92', 'Q8WWM7', 'Q8WXE0', 'Q92520', 'Q92530', 'Q92574', 'Q92616', 'Q92890', 'Q92934', 'Q969Z0', 'Q96A33', 'Q96A57', 'Q96AG4', 'Q96H55', 'Q96H79', 'Q96II8', 'Q96K37', 'Q96MW1', 'Q96NW4', 'Q96RD7', 'Q96S66', 'Q96TC7', 'Q99614', 'Q99623', 'Q99700', 'Q99961', 'Q9BQE4', 'Q9BQS8', 'Q9BSH4', 'Q9BSQ5', 'Q9BUN8', 'Q9BWM7', 'Q9BX10', 'Q9BX67', 'Q9BXI6', 'Q9H0X9', 'Q9H9B4', 'Q9HBM1', 'Q9HBR0', 'Q9NPB0', 'Q9NQW7', 'Q9NSI8', 'Q9NTK5', 'Q9NUY8', 'Q9NV92', 'Q9NW68', 'Q9NX74', 'Q9NXF8', 'Q9NYP7', 'Q9NZB2', 'Q9P0J0', 'Q9P0L0', 'Q9UN86', 'Q9UPN7', 'Q9Y266', 'Q9Y371', 'Q9Y3D6', 'Q9Y3P9', 'Q9Y4E8', 'Q9Y4W6', 'Q9Y512', 'Q9Y520', 'Q9Y5J7', 'Q9Y5L0', 'Q9Y617', 'Q9Y6I3', 'Q9Y6M1', 'Q9Y6Y8']\n", "534\n", "['A1L020', 'O00165', 'O00170', 'O00291', 'O00299', 'O00425', 'O00462', 'O00463', 'O00483', 'O00559', 'O14494', 'O14530', 'O14662', 'O14967', 'O15078', 'O15121', 'O15182', 'O15392', 'O43164', 'O43303', 'O43396', 'O43402', 'O43488', 'O43615', 'O43795', 'O43852', 'O60337', 'O60343', 'O60502', 'O60518', 'O60566', 'O75116', 'O75323', 'O75354', 'O75534', 'O75822', 'O94822', 'O94874', 'O94986', 'O95139', 'O95159', 'O95182', 'O95208', 'O95298', 'O95433', 'O95470', 'O95476', 'O95613', 'O95684', 'O95747', 'O95772', 'O95786', 'O95793', 'O95900', 'O95980', 'P00374', 'P00387', 'P00491', 'P00492', 'P04075', 'P04350', 'P06396', 'P07195', 'P07203', 'P07384', 'P07737', 'P07900', 'P08236', 'P08238', 'P08243', 'P10721', 'P11172', 'P11940', 'P12235', 'P12429', 'P13164', 'P13693', 'P13798', 'P14314', 'P14618', 'P14635', 'P14854', 'P15311', 'P15813', 'P16591', 'P16949', 'P16989', 'P18031', 'P18206', 'P19367', 'P19634', 'P20290', 'P21266', 'P21580', 'P22061', 'P22307', 'P22681', 'P23526', 'P23921', 'P26038', 'P26640', 'P28065', 'P28161', 'P28328', 'P28907', 'P29353', 'P29597', 'P30086', 'P30566', 'P31350', 'P32121', 'P33241', 'P33527', 'P34913', 'P35222', 'P35241', 'P35475', 'P36507', 'P36871', 'P36896', 'P36915', 'P37173', 'P40306', 'P40855', 'P41250', 'P43007', 'P43034', 'P43307', 'P43487', 'P46459', 'P46976', 'P47897', 'P48147', 'P49281', 'P49642', 'P49815', 'P49914', 'P50502', 'P51114', 'P51116', 'P51148', 'P51149', 'P51530', 'P51572', 'P51957', 'P51970', 'P52306', 'P52565', 'P52566', 'P52594', 'P52888', 'P53004', 'P53384', 'P53611', 'P53990', 'P54578', 'P54886', 'P55145', 'P55283', 'P55786', 'P55957', 'P60033', 'P61020', 'P61221', 'P61599', 'P62072', 'P62166', 'P62879', 'P63010', 'P63279', 'P78381', 'P80303', 'P82094', 'P83436', 'P98095', 'P98172', 'P98194', 'P98196', 'Q00341', 'Q00688', 'Q01433', 'Q01518', 'Q02833', 'Q03113', 'Q04206', 'Q04637', 'Q04759', 'Q05469', 'Q06787', 'Q06830', 'Q07617', 'Q07820', 'Q07960', 'Q08257', 'Q12792', 'Q12802', 'Q12849', 'Q12893', 'Q12933', 'Q12981', 'Q13283', 'Q13310', 'Q13371', 'Q13438', 'Q13459', 'Q13492', 'Q13496', 'Q13505', 'Q13561', 'Q13586', 'Q13614', 'Q13795', 'Q13885', 'Q14344', 'Q14653', 'Q14764', 'Q14789', 'Q147X3', 'Q14C86', 'Q14CB8', 'Q15004', 'Q15018', 'Q15036', 'Q15172', 'Q15181', 'Q15276', 'Q15293', 'Q15388', 'Q15599', 'Q155Q3', 'Q15785', 'Q15833', 'Q15942', 'Q16204', 'Q16537', 'Q16543', 'Q16667', 'Q16760', 'Q16891', 'Q1MSJ5', 'Q2VPK5', 'Q32MZ4', 'Q3T906', 'Q460N5', 'Q49A88', 'Q49B96', 'Q53FA7', 'Q53GL0', 'Q56VL3', 'Q5BJF6', 'Q5JSH3', 'Q5JTJ3', 'Q5PRF9', 'Q5SXH7', 'Q5T0N5', 'Q5T5C0', 'Q5T8D3', 'Q5T9A4', 'Q5VSL9', 'Q5VT06', 'Q5VWZ2', 'Q63HN8', 'Q63HQ0', 'Q66K74', 'Q6FI81', 'Q6IA69', 'Q6IBS0', 'Q6IQ20', 'Q6NXE6', 'Q6NXR4', 'Q6NXT4', 'Q6P1K1', 'Q6P1M0', 'Q6P4A7', 'Q6P4E1', 'Q6PJW8', 'Q6RW13', 'Q6Y7W6', 'Q6YN16', 'Q6ZUT1', 'Q70UQ0', 'Q71RC2', 'Q765P7', 'Q7KZF4', 'Q7L099', 'Q7L3B6', 'Q7Z6I6', 'Q7Z6L1', 'Q86TB9', 'Q86TI2', 'Q86TP1', 'Q86UB9', 'Q86UE4', 'Q86UP2', 'Q86V86', 'Q86VX2', 'Q86WA6', 'Q86XZ4', 'Q8IUH4', 'Q8IWF6', 'Q8IWR0', 'Q8IYD1', 'Q8IZ07', 'Q8IZ83', 'Q8N0U8', 'Q8N0Z3', 'Q8N0Z8', 'Q8N183', 'Q8N1F8', 'Q8N2F6', 'Q8N3C7', 'Q8N490', 'Q8N4S9', 'Q8N573', 'Q8N5K1', 'Q8N5M1', 'Q8N6H7', 'Q8N8J7', 'Q8NBN3', 'Q8NBQ5', 'Q8NC51', 'Q8NC60', 'Q8NCA5', 'Q8NCG7', 'Q8NCM8', 'Q8NE71', 'Q8NEW0', 'Q8NFV4', 'Q8NG11', 'Q8TAE8', 'Q8TAF3', 'Q8TB03', 'Q8TB72', 'Q8TCT8', 'Q8TCY9', 'Q8TCZ2', 'Q8TD31', 'Q8TDM6', 'Q8TE02', 'Q8TEW0', 'Q8WU90', 'Q8WUF5', 'Q8WUI4', 'Q8WUK0', 'Q8WUM4', 'Q8WV92', 'Q8WWM7', 'Q8WWP7', 'Q8WXE0', 'Q8WZA9', 'Q92520', 'Q92530', 'Q92538', 'Q92543', 'Q92574', 'Q92581', 'Q92616', 'Q92743', 'Q92834', 'Q92882', 'Q92890', 'Q92896', 'Q92934', 'Q93063', 'Q969J3', 'Q969Z0', 'Q96A33', 'Q96A57', 'Q96AG3', 'Q96AG4', 'Q96B36', 'Q96B97', 'Q96BD8', 'Q96CU9', 'Q96D31', 'Q96DH6', 'Q96F86', 'Q96GZ6', 'Q96H55', 'Q96H79', 'Q96II8', 'Q96JB5', 'Q96JJ3', 'Q96K37', 'Q96KG9', 'Q96LW7', 'Q96MW1', 'Q96NW4', 'Q96NY8', 'Q96RD7', 'Q96RG2', 'Q96RR4', 'Q96S66', 'Q96T83', 'Q96TC7', 'Q99426', 'Q99543', 'Q99614', 'Q99623', 'Q99700', 'Q99704', 'Q99707', 'Q99942', 'Q99961', 'Q9BPZ3', 'Q9BQE4', 'Q9BQP7', 'Q9BQS8', 'Q9BRQ6', 'Q9BSH4', 'Q9BSJ8', 'Q9BSQ5', 'Q9BT17', 'Q9BTT6', 'Q9BUN8', 'Q9BUT1', 'Q9BV73', 'Q9BVN2', 'Q9BWM7', 'Q9BX10', 'Q9BX67', 'Q9BXI6', 'Q9BXK5', 'Q9BY32', 'Q9BY49', 'Q9BYG5', 'Q9BZ72', 'Q9GZP9', 'Q9GZY4', 'Q9H0X9', 'Q9H2C0', 'Q9H2D1', 'Q9H3G5', 'Q9H3K2', 'Q9H3P7', 'Q9H425', 'Q9H4A3', 'Q9H4G0', 'Q9H5Y7', 'Q9H6L5', 'Q9H6X4', 'Q9H8H3', 'Q9H9B4', 'Q9HBD1', 'Q9HBF4', 'Q9HBM1', 'Q9HBR0', 'Q9HCM4', 'Q9HCP0', 'Q9NPB0', 'Q9NPI6', 'Q9NPQ8', 'Q9NQ48', 'Q9NQW7', 'Q9NR31', 'Q9NSI8', 'Q9NSU2', 'Q9NTK5', 'Q9NUY8', 'Q9NV92', 'Q9NV96', 'Q9NVI7', 'Q9NVT9', 'Q9NW68', 'Q9NWS8', 'Q9NX47', 'Q9NX74', 'Q9NXF8', 'Q9NXR7', 'Q9NXS2', 'Q9NXW2', 'Q9NYL2', 'Q9NYP7', 'Q9NZ52', 'Q9NZB2', 'Q9NZD2', 'Q9NZI8', 'Q9P032', 'Q9P0J0', 'Q9P0L0', 'Q9P0S3', 'Q9P209', 'Q9UBB6', 'Q9UBF8', 'Q9UBS0', 'Q9UBS8', 'Q9UEY8', 'Q9UG63', 'Q9UGJ1', 'Q9UHD1', 'Q9UHY1', 'Q9UI09', 'Q9UKG9', 'Q9UKK3', 'Q9UL15', 'Q9ULA0', 'Q9UM00', 'Q9UN86', 'Q9UNY4', 'Q9UP38', 'Q9UPN7', 'Q9UPU7', 'Q9UPY3', 'Q9UQN3', 'Q9Y223', 'Q9Y243', 'Q9Y266', 'Q9Y285', 'Q9Y2Q0', 'Q9Y2Q3', 'Q9Y371', 'Q9Y3C4', 'Q9Y3D6', 'Q9Y3P9', 'Q9Y4E8', 'Q9Y4P3', 'Q9Y4W6', 'Q9Y512', 'Q9Y520', 'Q9Y5J7', 'Q9Y5L0', 'Q9Y5S1', 'Q9Y5U9', 'Q9Y5W7', 'Q9Y613', 'Q9Y617', 'Q9Y680', 'Q9Y696', 'Q9Y6D5', 'Q9Y6I3', 'Q9Y6M1', 'Q9Y6M9', 'Q9Y6Y0', 'Q9Y6Y8']\n" ] } ], "source": [ "# Pulling out enhanced proteins that aren't already in Itzhak to concatenate with detected Itzhak proteins\n", "exclusive_enhprot = [x for x in enhancedprot.index if x not in concordance2]\n", "print(len(exclusive_enhprot))\n", "print(exclusive_enhprot)\n", "\n", "exclusive_enh_supprot = [x for x in enh_supprot.index if x not in concordance2]\n", "print(len(exclusive_enh_supprot))\n", "print(exclusive_enh_supprot)" ] }, { "cell_type": "code", "execution_count": 16, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "914\n", "1259\n" ] } ], "source": [ "# Appending exclusively enhanced proteins to concordance2, the list of Itzhak markers in common replicate proteins\n", "# (concordance2 also contains enhanced proteins common to Itzhak)\n", "concordance2 = list(concordance2)\n", "exclusive_enhprot = list(exclusive_enhprot)\n", "fullmarkers = concordance2 + exclusive_enhprot\n", "print(len(fullmarkers))\n", "\n", "exclusive_enh_supprot = list(exclusive_enh_supprot)\n", "fullmarkers_plus = concordance2 + exclusive_enh_supprot\n", "print(len(fullmarkers_plus))" ] }, { "cell_type": "code", "execution_count": 17, "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", "
OrganelleHPA
ProteinID
O14639NA
P12814NA
O43707NA
Q9BR76NA
Q92828NA
Q14247NA
Q16643NA
P21333NA
P35579NA
Q8WX93NA
Q9NR12NA
Q14651NA
Q6NYC8NA
Q96SB3NA
Q9Y490NA
P46939NA
Q9P2R3NA
O00203NA
Q9Y2T2NA
P05067NA
Q96BM9NA
Q9NVJ2NA
Q7Z3C6NA
Q15904NA
Q9Y487NA
P61421NA
P38606NA
P21283NA
P36543NA
O75348NA
.........
Q9Y223NA
Q9Y243NA
Q9Y266NA
Q9Y285NA
Q9Y2Q0NA
Q9Y2Q3NA
Q9Y371NA
Q9Y3C4NA
Q9Y3D6NA
Q9Y3P9NA
Q9Y4E8NA
Q9Y4P3NA
Q9Y4W6NA
Q9Y512NA
Q9Y520NA
Q9Y5J7NA
Q9Y5L0NA
Q9Y5S1NA
Q9Y5U9NA
Q9Y5W7NA
Q9Y613NA
Q9Y617NA
Q9Y680NA
Q9Y696NA
Q9Y6D5NA
Q9Y6I3NA
Q9Y6M1NA
Q9Y6M9NA
Q9Y6Y0NA
Q9Y6Y8NA
\n", "

1259 rows × 2 columns

\n", "
" ], "text/plain": [ " Organelle HPA\n", "ProteinID \n", "O14639 NA\n", "P12814 NA\n", "O43707 NA\n", "Q9BR76 NA\n", "Q92828 NA\n", "Q14247 NA\n", "Q16643 NA\n", "P21333 NA\n", "P35579 NA\n", "Q8WX93 NA\n", "Q9NR12 NA\n", "Q14651 NA\n", "Q6NYC8 NA\n", "Q96SB3 NA\n", "Q9Y490 NA\n", "P46939 NA\n", "Q9P2R3 NA\n", "O00203 NA\n", "Q9Y2T2 NA\n", "P05067 NA\n", "Q96BM9 NA\n", "Q9NVJ2 NA\n", "Q7Z3C6 NA\n", "Q15904 NA\n", "Q9Y487 NA\n", "P61421 NA\n", "P38606 NA\n", "P21283 NA\n", "P36543 NA\n", "O75348 NA\n", "... ... ..\n", "Q9Y223 NA\n", "Q9Y243 NA\n", "Q9Y266 NA\n", "Q9Y285 NA\n", "Q9Y2Q0 NA\n", "Q9Y2Q3 NA\n", "Q9Y371 NA\n", "Q9Y3C4 NA\n", "Q9Y3D6 NA\n", "Q9Y3P9 NA\n", "Q9Y4E8 NA\n", "Q9Y4P3 NA\n", "Q9Y4W6 NA\n", "Q9Y512 NA\n", "Q9Y520 NA\n", "Q9Y5J7 NA\n", "Q9Y5L0 NA\n", "Q9Y5S1 NA\n", "Q9Y5U9 NA\n", "Q9Y5W7 NA\n", "Q9Y613 NA\n", "Q9Y617 NA\n", "Q9Y680 NA\n", "Q9Y696 NA\n", "Q9Y6D5 NA\n", "Q9Y6I3 NA\n", "Q9Y6M1 NA\n", "Q9Y6M9 NA\n", "Q9Y6Y0 NA\n", "Q9Y6Y8 NA\n", "\n", "[1259 rows x 2 columns]" ] }, "execution_count": 17, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Generate df from fullmarkers list\n", "markerdf = pd.DataFrame({'ProteinID':fullmarkers})\n", "markerdf['Organelle'] = ''\n", "markerdf['HPA'] = 'NA'\n", "markerdf.set_index('ProteinID', inplace=True)\n", "markerdf\n", "\n", "markerdf_plus = pd.DataFrame({'ProteinID':fullmarkers_plus})\n", "markerdf_plus['Organelle'] = ''\n", "markerdf_plus['HPA'] = 'NA'\n", "markerdf_plus.set_index('ProteinID', inplace=True)\n", "markerdf_plus" ] }, { "cell_type": "code", "execution_count": 18, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Enh+Itzhak:\n", "Large Protein Complex 281\n", "ER 104\n", "Cytosol 88\n", "Endosome 78\n", "Plasma membrane 77\n", "Mitochondrion 51\n", "Lysosome 37\n", "Mitochondria 27\n", "Golgi 25\n", "Ergic/cisGolgi 25\n", "Endoplasmic reticulum 19\n", "Peroxisome 17\n", "Nuclear pore complex 17\n", "Actin binding proteins 16\n", "Vesicles 16\n", "Golgi apparatus 13\n", "ER_high_curvature 9\n", "Centrosome 5\n", "Peroxisomes 3\n", "Cell Junctions 1\n", "Focal adhesion sites 1\n", "Cytokinetic bridge 1\n", "Actin filaments 1\n", "Endosomes 1\n", "Microtubule organizing center 1\n", "Name: Organelle, dtype: int64\n", "--------------------------------\n", "Enh+Itzhak w/ HPA annotation:\n", "NA 665\n", "Cytosol 95\n", "Mitochondria 41\n", "Endoplasmic reticulum 35\n", "Vesicles 23\n", "Golgi apparatus 20\n", "Plasma membrane 14\n", "Peroxisomes 6\n", "Centrosome 5\n", "Endosomes 2\n", "Actin filaments 2\n", "Cytokinetic bridge 1\n", "Lysosomes 1\n", "Microtubules 1\n", "Cell Junctions 1\n", "Focal adhesion sites 1\n", "Microtubule organizing center 1\n", "Name: HPA, dtype: int64\n", "--------------------------------\n", "Enh_Supp+Itzhak:\n", "Large Protein Complex 281\n", "Cytosol 231\n", "Plasma membrane 105\n", "ER 104\n", "Endosome 78\n", "Mitochondria 72\n", "Vesicles 63\n", "Mitochondrion 51\n", "Endoplasmic reticulum 43\n", "Lysosome 37\n", "Golgi apparatus 36\n", "Ergic/cisGolgi 25\n", "Golgi 25\n", "Centrosome 19\n", "Nuclear pore complex 17\n", "Peroxisome 17\n", "Actin binding proteins 16\n", "ER_high_curvature 9\n", "Peroxisomes 5\n", "Microtubules 4\n", "Focal adhesion sites 3\n", "Cell Junctions 3\n", "Microtubule organizing center 3\n", "Lipid droplets 3\n", "Cytoplasmic bodies 3\n", "Actin filaments 2\n", "Cytokinetic bridge 1\n", "Intermediate filaments 1\n", "Lysosomes 1\n", "Endosomes 1\n", "Name: Organelle, dtype: int64\n", "--------------------------------\n", "Enh_Supp+Itzhak w/ HPA annotation:\n", "NA 578\n", "Cytosol 256\n", "Mitochondria 100\n", "Vesicles 87\n", "Endoplasmic reticulum 78\n", "Plasma membrane 49\n", "Golgi apparatus 48\n", "Centrosome 19\n", "Peroxisomes 10\n", "Microtubules 9\n", "Cell Junctions 4\n", "Cytoplasmic bodies 3\n", "Microtubule organizing center 3\n", "Focal adhesion sites 3\n", "Actin filaments 3\n", "Lipid droplets 3\n", "Endosomes 2\n", "Lysosomes 2\n", "Cytokinetic bridge 1\n", "Intermediate filaments 1\n", "Name: HPA, dtype: int64\n", "--------------------------------\n" ] } ], "source": [ "# Adding on organelle assignment from Itzhak then from Metascape for those beyond\n", "for item in markerdf.index:\n", " if item in Itzhakmarkers.index:\n", " markerdf.at[item, 'Organelle'] = Itzhakmarkers.at[item, 'Compartment']\n", " elif item in enhancedprot.index:\n", " markerdf.at[item, 'Organelle'] = enhancedprot.at[item, 'Subcellular_Loc']\n", "\n", "for item in markerdf.index:\n", " if item in enhancedprot.index:\n", " markerdf.at[item, 'HPA'] = enhancedprot.at[item, 'Subcellular_Loc']\n", "\n", "print(\"Enh+Itzhak:\")\n", "print(markerdf.Organelle.value_counts(), end='\\n--------------------------------\\n')\n", "print(\"Enh+Itzhak w/ HPA annotation:\")\n", "print(markerdf.HPA.value_counts(), end='\\n--------------------------------\\n')\n", "\n", "for item in markerdf_plus.index:\n", " if item in Itzhakmarkers.index:\n", " markerdf_plus.at[item, 'Organelle'] = Itzhakmarkers.at[item, 'Compartment']\n", " elif item in enh_supprot.index:\n", " markerdf_plus.at[item, 'Organelle'] = enh_supprot.at[item, 'Subcellular_Loc']\n", "\n", "for item in markerdf_plus.index:\n", " if item in enh_supprot.index:\n", " markerdf_plus.at[item, 'HPA'] = enh_supprot.at[item, 'Subcellular_Loc']\n", "\n", "print(\"Enh_Supp+Itzhak:\")\n", "print(markerdf_plus.Organelle.value_counts(), end='\\n--------------------------------\\n')\n", "print(\"Enh_Supp+Itzhak w/ HPA annotation:\")\n", "print(markerdf_plus.HPA.value_counts(), end='\\n--------------------------------\\n')" ] }, { "cell_type": "code", "execution_count": 19, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Large Protein Complex 369\n", "ER 132\n", "Endosome 79\n", "Plasma membrane 79\n", "Mitochondrion 78\n", "Golgi 38\n", "Lysosome 37\n", "Ergic/cisGolgi 25\n", "Peroxisome 20\n", "Actin binding proteins 17\n", "Nuclear pore complex 17\n", "Vesicles 16\n", "Microtubule proteins 6\n", "Cytokinetic bridge 1\n", "Name: Organelle, dtype: int64\n", "\n", "\n", "Large Protein Complex 518\n", "ER 156\n", "Mitochondrion 123\n", "Plasma membrane 111\n", "Endosome 79\n", "Vesicles 63\n", "Golgi 61\n", "Lysosome 38\n", "Microtubule proteins 26\n", "Ergic/cisGolgi 25\n", "Peroxisome 22\n", "Actin binding proteins 18\n", "Nuclear pore complex 17\n", "Cytokinetic bridge 1\n", "Name: Organelle, dtype: int64\n" ] } ], "source": [ "# Reclassify cytosol as large protein complex\n", "# Reclassify mitochondria as mitochondrion\n", "# Reclassify endoplasmic reticulum and ER_high_curvature as ER\n", "# Reclassify golgi apparatus as golgi\n", "# Reclassify actin filaments as actin binding proteins\n", "# Reclassify centrosome, MTOC, and microtubules as Microtubule Proteins\n", "# Reclassify peroxisomes as peroxisome\n", "# Reclassify endosomes as endosome\n", "# Reclassify cell junctions and focal adhesion sites as plasma membrane\n", "markerdf.at[markerdf['Organelle'] == 'Cytosol', 'Organelle'] = 'Large Protein Complex'\n", "markerdf.at[markerdf['Organelle'] == 'Mitochondria', 'Organelle'] = 'Mitochondrion'\n", "markerdf.at[((markerdf['Organelle'] == 'Endoplasmic reticulum') | (markerdf['Organelle'] == 'ER_high_curvature')), 'Organelle'] = 'ER'\n", "markerdf.at[markerdf['Organelle'] == 'Golgi apparatus', 'Organelle'] = 'Golgi'\n", "markerdf.at[markerdf['Organelle'] == 'Actin filaments', 'Organelle'] = 'Actin binding proteins'\n", "markerdf.at[((markerdf['Organelle'] == 'Centrosome') | (markerdf['Organelle'] == 'Microtubule organizing center') | \n", " (markerdf['Organelle'] == 'Microtubules')), 'Organelle'] = 'Microtubule proteins'\n", "markerdf.at[markerdf['Organelle'] == 'Peroxisomes', 'Organelle'] = 'Peroxisome'\n", "markerdf.at[markerdf['Organelle'] == 'Endosomes', 'Organelle'] = 'Endosome'\n", "markerdf.at[((markerdf['Organelle'] == 'Cell Junctions') | \n", " (markerdf['Organelle'] == 'Focal adhesion sites')), 'Organelle'] = 'Plasma membrane'\n", "\n", "markerdf.at[markerdf['HPA'] == 'Cytosol', 'HPA'] = 'Large Protein Complex'\n", "markerdf.at[markerdf['HPA'] == 'Mitochondria', 'HPA'] = 'Mitochondrion'\n", "markerdf.at[((markerdf['HPA'] == 'Endoplasmic reticulum') | (markerdf['HPA'] == 'ER_high_curvature')), 'HPA'] = 'ER'\n", "markerdf.at[markerdf['HPA'] == 'Golgi apparatus', 'HPA'] = 'Golgi'\n", "markerdf.at[markerdf['HPA'] == 'Actin filaments', 'HPA'] = 'Actin binding proteins'\n", "markerdf.at[((markerdf['HPA'] == 'Centrosome') | (markerdf['HPA'] == 'Microtubule organizing center') | \n", " (markerdf['HPA'] == 'Microtubules')), 'HPA'] = 'Microtubule proteins'\n", "markerdf.at[markerdf['HPA'] == 'Peroxisomes', 'HPA'] = 'Peroxisome'\n", "markerdf.at[markerdf['HPA'] == 'Endosomes', 'HPA'] = 'Endosome'\n", "markerdf.at[((markerdf['HPA'] == 'Cell Junctions') | \n", " (markerdf['HPA'] == 'Focal adhesion sites')), 'HPA'] = 'Plasma membrane'\n", "\n", "print(markerdf.Organelle.value_counts(), end='\\n\\n\\n')\n", "\n", "#-----------------------------------------------------------------------------------------\n", "markerdf_plus.at[((markerdf_plus['Organelle'] == 'Cytosol') | (markerdf_plus['Organelle'] == 'Cytoplasmic bodies') | \n", " (markerdf_plus['Organelle'] == 'Lipid droplets')), 'Organelle'] = 'Large Protein Complex'\n", "markerdf_plus.at[markerdf_plus['Organelle'] == 'Mitochondria', 'Organelle'] = 'Mitochondrion'\n", "markerdf_plus.at[((markerdf_plus['Organelle'] == 'Endoplasmic reticulum') | \n", " (markerdf_plus['Organelle'] == 'ER_high_curvature')), 'Organelle'] = 'ER'\n", "markerdf_plus.at[markerdf_plus['Organelle'] == 'Golgi apparatus', 'Organelle'] = 'Golgi'\n", "markerdf_plus.at[markerdf_plus['Organelle'] == 'Actin filaments', 'Organelle'] = 'Actin binding proteins'\n", "markerdf_plus.at[((markerdf_plus['Organelle'] == 'Centrosome') | (markerdf_plus['Organelle'] == 'Microtubule organizing center') | \n", " (markerdf_plus['Organelle'] == 'Microtubules')), 'Organelle'] = 'Microtubule proteins'\n", "markerdf_plus.at[markerdf_plus['Organelle'] == 'Peroxisomes', 'Organelle'] = 'Peroxisome'\n", "markerdf_plus.at[markerdf_plus['Organelle'] == 'Endosomes', 'Organelle'] = 'Endosome'\n", "markerdf_plus.at[((markerdf_plus['Organelle'] == 'Cell Junctions') | \n", " (markerdf_plus['Organelle'] == 'Focal adhesion sites')), 'Organelle'] = 'Plasma membrane'\n", "markerdf_plus.at[markerdf_plus['Organelle'] == 'Lysosomes', 'Organelle'] = 'Lysosome'\n", "markerdf_plus.drop('O43164', inplace=True)\n", "\n", "markerdf_plus.at[((markerdf_plus['HPA'] == 'Cytosol') | (markerdf_plus['HPA'] == 'Cytoplasmic bodies') | \n", " (markerdf_plus['HPA'] == 'Lipid droplets')), 'HPA'] = 'Large Protein Complex'\n", "markerdf_plus.at[markerdf_plus['HPA'] == 'Mitochondria', 'HPA'] = 'Mitochondrion'\n", "markerdf_plus.at[((markerdf_plus['HPA'] == 'Endoplasmic reticulum') | \n", " (markerdf_plus['HPA'] == 'ER_high_curvature')), 'HPA'] = 'ER'\n", "markerdf_plus.at[markerdf_plus['HPA'] == 'Golgi apparatus', 'HPA'] = 'Golgi'\n", "markerdf_plus.at[markerdf_plus['HPA'] == 'Actin filaments', 'HPA'] = 'Actin binding proteins'\n", "markerdf_plus.at[((markerdf_plus['HPA'] == 'Centrosome') | (markerdf_plus['HPA'] == 'Microtubule organizing center') | \n", " (markerdf_plus['HPA'] == 'Microtubules')), 'HPA'] = 'Microtubule proteins'\n", "markerdf_plus.at[markerdf_plus['HPA'] == 'Peroxisomes', 'HPA'] = 'Peroxisome'\n", "markerdf_plus.at[markerdf_plus['HPA'] == 'Endosomes', 'HPA'] = 'Endosome'\n", "markerdf_plus.at[((markerdf_plus['HPA'] == 'Cell Junctions') | \n", " (markerdf_plus['HPA'] == 'Focal adhesion sites')), 'HPA'] = 'Plasma membrane'\n", "markerdf_plus.at[markerdf_plus['HPA'] == 'Lysosomes', 'HPA'] = 'Lysosome'\n", "\n", "print(markerdf_plus.Organelle.value_counts())" ] }, { "cell_type": "code", "execution_count": 20, "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", "
OrganelleHPA
ProteinID
P86791EndosomeVesicles
Q6WKZ4EndosomeVesicles
O15400EndosomeLysosomes
Q5JRA6ERVesicles
O15258Ergic/cisGolgiGolgi
O14579Large Protein ComplexGolgi
Q9NRA8Large Protein ComplexVesicles
P49720Large Protein ComplexMitochondrion
Q9UHD8Large Protein ComplexActin binding proteins
P68366Large Protein ComplexMicrotubule proteins
P10619LysosomeVesicles
Q0VGL1LysosomeVesicles
Q9H8M5Plasma membraneVesicles
\n", "
" ], "text/plain": [ " Organelle HPA\n", "ProteinID \n", "P86791 Endosome Vesicles\n", "Q6WKZ4 Endosome Vesicles\n", "O15400 Endosome Lysosomes\n", "Q5JRA6 ER Vesicles\n", "O15258 Ergic/cisGolgi Golgi\n", "O14579 Large Protein Complex Golgi\n", "Q9NRA8 Large Protein Complex Vesicles\n", "P49720 Large Protein Complex Mitochondrion\n", "Q9UHD8 Large Protein Complex Actin binding proteins\n", "P68366 Large Protein Complex Microtubule proteins\n", "P10619 Lysosome Vesicles\n", "Q0VGL1 Lysosome Vesicles\n", "Q9H8M5 Plasma membrane Vesicles" ] }, "execution_count": 20, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Checking agreement between Human Protein Atlas enhanced annotations and Itzhak annotations\n", "nonempty = markerdf[markerdf['HPA'] != 'NA']\n", "nonempty[nonempty['Organelle'] != nonempty['HPA']]" ] }, { "cell_type": "code", "execution_count": 21, "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", "
OrganelleHPA
ProteinID
O14639Actin binding proteinsLarge Protein Complex
Q7Z3C6EndosomeVesicles
P86791EndosomeVesicles
Q15075EndosomeVesicles
Q9H4M9EndosomePlasma membrane
Q6WKZ4EndosomeVesicles
P61106EndosomeVesicles
O14828EndosomeVesicles
Q9Y5X2EndosomeVesicles
Q92783EndosomeVesicles
O15400EndosomeLysosome
P51809EndosomeVesicles
Q5JRA6ERVesicles
O15258Ergic/cisGolgiGolgi
P49755Ergic/cisGolgiGolgi
Q15363Ergic/cisGolgiVesicles
Q9Y3Q3Ergic/cisGolgiGolgi
O14579Large Protein ComplexGolgi
Q9NRA8Large Protein ComplexVesicles
Q96KP1Large Protein ComplexVesicles
P49720Large Protein ComplexMitochondrion
Q15437Large Protein ComplexVesicles
P53992Large Protein ComplexVesicles
Q9UHD8Large Protein ComplexActin binding proteins
P68363Large Protein ComplexMicrotubule proteins
Q9BQE3Large Protein ComplexMicrotubule proteins
P68366Large Protein ComplexMicrotubule proteins
P07437Large Protein ComplexMicrotubule proteins
P68371Large Protein ComplexMicrotubule proteins
P10619LysosomeVesicles
P53634LysosomeVesicles
Q0VGL1LysosomeVesicles
O43504LysosomeLarge Protein Complex
P38571LysosomeVesicles
P07602LysosomeVesicles
Q8IXI1MitochondrionLarge Protein Complex
Q92968PeroxisomeVesicles
P78536Plasma membraneLarge Protein Complex
O95782Plasma membraneVesicles
Q9H8M5Plasma membraneVesicles
Q14118Plasma membraneVesicles
\n", "
" ], "text/plain": [ " Organelle HPA\n", "ProteinID \n", "O14639 Actin binding proteins Large Protein Complex\n", "Q7Z3C6 Endosome Vesicles\n", "P86791 Endosome Vesicles\n", "Q15075 Endosome Vesicles\n", "Q9H4M9 Endosome Plasma membrane\n", "Q6WKZ4 Endosome Vesicles\n", "P61106 Endosome Vesicles\n", "O14828 Endosome Vesicles\n", "Q9Y5X2 Endosome Vesicles\n", "Q92783 Endosome Vesicles\n", "O15400 Endosome Lysosome\n", "P51809 Endosome Vesicles\n", "Q5JRA6 ER Vesicles\n", "O15258 Ergic/cisGolgi Golgi\n", "P49755 Ergic/cisGolgi Golgi\n", "Q15363 Ergic/cisGolgi Vesicles\n", "Q9Y3Q3 Ergic/cisGolgi Golgi\n", "O14579 Large Protein Complex Golgi\n", "Q9NRA8 Large Protein Complex Vesicles\n", "Q96KP1 Large Protein Complex Vesicles\n", "P49720 Large Protein Complex Mitochondrion\n", "Q15437 Large Protein Complex Vesicles\n", "P53992 Large Protein Complex Vesicles\n", "Q9UHD8 Large Protein Complex Actin binding proteins\n", "P68363 Large Protein Complex Microtubule proteins\n", "Q9BQE3 Large Protein Complex Microtubule proteins\n", "P68366 Large Protein Complex Microtubule proteins\n", "P07437 Large Protein Complex Microtubule proteins\n", "P68371 Large Protein Complex Microtubule proteins\n", "P10619 Lysosome Vesicles\n", "P53634 Lysosome Vesicles\n", "Q0VGL1 Lysosome Vesicles\n", "O43504 Lysosome Large Protein Complex\n", "P38571 Lysosome Vesicles\n", "P07602 Lysosome Vesicles\n", "Q8IXI1 Mitochondrion Large Protein Complex\n", "Q92968 Peroxisome Vesicles\n", "P78536 Plasma membrane Large Protein Complex\n", "O95782 Plasma membrane Vesicles\n", "Q9H8M5 Plasma membrane Vesicles\n", "Q14118 Plasma membrane Vesicles" ] }, "execution_count": 21, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Checking agreement between Human Protein Atlas enh_supp annotations and Itzhak annotations\n", "nonempty_plus = markerdf_plus[markerdf_plus['HPA'] != 'NA']\n", "nonempty_plus[nonempty_plus['Organelle'] != nonempty_plus['HPA']]" ] }, { "cell_type": "code", "execution_count": 22, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Index(['O00291', 'O14662', 'P98196', 'Q15276', 'Q8IUH4', 'Q8N0Z8', 'Q8N1F8',\n", " 'Q8N3C7', 'Q8WV92', 'Q9BQS8', 'Q9BX10', 'Q9H0X9', 'Q9NPB0', 'Q9NV92',\n", " 'Q9Y5L0', 'Q9Y6Y8'],\n", " dtype='object', name='ProteinID')\n", "Index(['O15155', 'Q969X5', 'Q96RQ1', 'Q9Y282', 'Q9BS26', 'Q9Y3E0', 'O14653',\n", " 'P24390', 'P49257', 'Q12907', 'Q9H0V9', 'P61019', 'Q8WUD1', 'O15258',\n", " 'Q13190', 'O15260', 'Q13445', 'P49755', 'Q15363', 'Q9Y3Q3', 'Q7Z7H5',\n", " 'Q9Y3A6', 'Q9Y3B3', 'Q9BVK6', 'Q969M3'],\n", " dtype='object', name='ProteinID')\n" ] } ], "source": [ "# Examining Vesicles proteins to sort into more articulated organelles\n", "# Also examined Ergic/cisGolgi proteins but didn't appear to be easily differentiable one way or the other\n", "print(markerdf[markerdf['Organelle'] == 'Vesicles'].index)\n", "print(markerdf[markerdf['Organelle'] == 'Ergic/cisGolgi'].index)" ] }, { "cell_type": "code", "execution_count": 23, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Large Protein Complex 369\n", "ER 135\n", "Endosome 81\n", "Plasma membrane 79\n", "Mitochondrion 78\n", "Golgi 43\n", "Lysosome 38\n", "Ergic/cisGolgi 21\n", "Peroxisome 20\n", "Actin binding proteins 17\n", "Nuclear pore complex 17\n", "Microtubule proteins 6\n", "Cytokinetic bridge 1\n", "Name: Organelle, dtype: int64" ] }, "execution_count": 23, "metadata": {}, "output_type": "execute_result" } ], "source": [ "## Itzhak+Enhanced only proteins\n", "\n", "# Proteins for Endosome:\n", "# Q15276, Q8WV92\n", "markerdf.at['Q15276', 'Organelle'] = 'Endosome'\n", "markerdf.at['Q8WV92', 'Organelle'] = 'Endosome'\n", "\n", "# Proteins for Lysosome:\n", "# Q8N1F8\n", "markerdf.at['Q8N1F8', 'Organelle'] = 'Lysosome'\n", "\n", "# Proteins for ER:\n", "# Q9H0X9, Q9Y6Y8, Q9BS26\n", "markerdf.at['Q9H0X9', 'Organelle'] = 'ER'\n", "markerdf.at['Q9Y6Y8', 'Organelle'] = 'ER'\n", "markerdf.at['Q9BS26', 'Organelle'] = 'ER'\n", "\n", "# Proteins for Golgi:\n", "# O14662, Q8IUH4, Q9Y3E0, O15258, Q13190\n", "markerdf.at['O14662', 'Organelle'] = 'Golgi'\n", "markerdf.at['Q8IUH4', 'Organelle'] = 'Golgi'\n", "markerdf.at['Q9Y3E0', 'Organelle'] = 'Golgi'\n", "markerdf.at['O15258', 'Organelle'] = 'Golgi'\n", "markerdf.at['Q13190', 'Organelle'] = 'Golgi'\n", "\n", "# Proteins to discard:\n", "# O00291, P98196, Q8N0Z8, Q9BQS8, Q9BX10, Q9NPB0, Q9NV92, Q9Y5L0\n", "markerdf.drop(['O00291', 'P98196', 'Q8N0Z8', 'Q8N3C7', 'Q9BQS8', 'Q9BX10', 'Q9NPB0', 'Q9NV92', 'Q9Y5L0'], inplace=True)\n", "\n", "markerdf.Organelle.value_counts()" ] }, { "cell_type": "code", "execution_count": 24, "metadata": {}, "outputs": [], "source": [ "# Dropping microtubule proteins as the class is too small\n", "# Saving Itzhak+enhanced markers csv file\n", "markerdf = markerdf[markerdf['Organelle'] != 'Microtubule proteins']\n", "markerdf = markerdf[markerdf['Organelle'] != 'Ergic/cisGolgi']\n", "markerdf = markerdf[markerdf['Organelle'] != 'Actin binding proteins']\n", "markerdf = markerdf[markerdf['Organelle'] != 'Nuclear pore complex']\n", "markerdf = markerdf[markerdf['Organelle'] != 'Cytokinetic bridge']\n", "markerdf.drop(columns='HPA', inplace=True)\n", "markerdf.to_csv('ExpandedMarkerSet_ItzhakWithEnhanced.csv')" ] }, { "cell_type": "code", "execution_count": 26, "metadata": {}, "outputs": [], "source": [ "# Saving just Itzhak markers and just enhanced markers\n", "intersect = markerdf.index.intersection(Itzhakmarkers.index)\n", "itzmark = markerdf.loc[intersect, :]\n", "itzmark.to_csv('DetectedItzhakMarkerSet.csv')\n", "intersect2 = markerdf.index.intersection(enhancedprot.index)\n", "enhmark = markerdf.loc[intersect2, :]\n", "enhmark.to_csv('EnhancedMarkerSet.csv')" ] }, { "cell_type": "code", "execution_count": 27, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Large Protein Complex 369\n", "ER 135\n", "Endosome 81\n", "Plasma membrane 79\n", "Mitochondrion 78\n", "Golgi 43\n", "Lysosome 38\n", "Peroxisome 20\n", "Name: Organelle, dtype: int64" ] }, "execution_count": 27, "metadata": {}, "output_type": "execute_result" } ], "source": [ "markerdf.Organelle.value_counts()" ] } ], "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": "3.7.4" } }, "nbformat": 4, "nbformat_minor": 4 }