{
"cells": [
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [],
"source": [
"# Inline matplotlib backend\n",
"%matplotlib inline"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [],
"source": [
"# Import packages\n",
"import os\n",
"import math\n",
"import pandas as pd\n",
"import numpy as np\n",
"import seaborn as sns\n",
"import matplotlib.pyplot as plt\n",
"from sklearn.covariance import MinCovDet\n",
"from scipy.stats import percentileofscore\n",
"from scipy.stats import rankdata\n",
"from scipy.stats import t\n",
"from scipy.spatial.distance import euclidean"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [],
"source": [
"# Set working directory\n",
"os.getcwd()\n",
"os.chdir('Path/To/Data')"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [],
"source": [
"# Read in replicates; using just row-normalized data\n",
"ua = pd.read_csv('UnA/20190517_UnA_rowsum.csv', index_col=0)\n",
"ub = pd.read_csv('UnB/20190517_UnB_rowsum.csv', index_col=0)\n",
"uc = pd.read_csv('UnC/20190517_UnC_rowsum.csv', index_col=0)\n",
"ia = pd.read_csv('IndA/20190517_IndA_rowsum.csv', index_col=0)\n",
"ib = pd.read_csv('IndB/20190517_IndB_rowsum.csv', index_col=0)\n",
"ic = pd.read_csv('IndC/20190517_IndC_rowsum.csv', index_col=0)"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {},
"outputs": [],
"source": [
"# Labeling replicate columns for ease of identification in joined dataframe\n",
"ua.columns = ['Gene_ua', 'Protein information_ua', '3K_ua', '5.4K_ua', '12.2K_ua', \n",
" '24K_ua', '78.4K_ua', '110K_ua', '195.5K_ua']\n",
"ub.columns = ['Gene_ub', 'Protein information_ub', '3K_ub', '5.4K_ub', '12.2K_ub', \n",
" '24K_ub', '78.4K_ub', '110K_ub', '195.5K_ub']\n",
"uc.columns = ['Gene_uc', 'Protein information_uc', '3K_uc', '5.4K_uc', '12.2K_uc', \n",
" '24K_uc', '78.4K_uc', '110K_uc', '195.5K_uc']\n",
"ia.columns = ['Gene_ia', 'Protein information_ia', '3K_ia', '5.4K_ia', '12.2K_ia', \n",
" '24K_ia', '78.4K_ia', '110K_ia', '195.5K_ia']\n",
"ib.columns = ['Gene_ib', 'Protein information_ib', '3K_ib', '5.4K_ib', '12.2K_ib', \n",
" '24K_ib', '78.4K_ib', '110K_ib', '195.5K_ib']\n",
"ic.columns = ['Gene_ic', 'Protein information_ic', '3K_ic', '5.4K_ic', '12.2K_ic', \n",
" '24K_ic', '78.4K_ic', '110K_ic', '195.5K_ic']"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [],
"source": [
"# Pull out proteins common across all six replicates\n",
"dflist = [ua, ub, uc, ia, ib, ic]\n",
"common = pd.concat(dflist, axis=1, join='inner')"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {},
"outputs": [],
"source": [
"# Redefine replicates with only common proteins\n",
"ua = common.loc[:, 'Gene_ua':'195.5K_ua']\n",
"ub = common.loc[:, 'Gene_ub':'195.5K_ub']\n",
"uc = common.loc[:, 'Gene_uc':'195.5K_uc']\n",
"ia = common.loc[:, 'Gene_ia':'195.5K_ia']\n",
"ib = common.loc[:, 'Gene_ib':'195.5K_ib']\n",
"ic = common.loc[:, 'Gene_ic':'195.5K_ic']"
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {},
"outputs": [],
"source": [
"# Changing columns back to replicate invariant names\n",
"ua.columns = ['Gene', 'Protein information', '3K', '5.4K', '12.2K', '24K', '78.4K', '110K', '195.5K']\n",
"ub.columns = ['Gene', 'Protein information', '3K', '5.4K', '12.2K', '24K', '78.4K', '110K', '195.5K']\n",
"uc.columns = ['Gene', 'Protein information', '3K', '5.4K', '12.2K', '24K', '78.4K', '110K', '195.5K']\n",
"ia.columns = ['Gene', 'Protein information', '3K', '5.4K', '12.2K', '24K', '78.4K', '110K', '195.5K']\n",
"ib.columns = ['Gene', 'Protein information', '3K', '5.4K', '12.2K', '24K', '78.4K', '110K', '195.5K']\n",
"ic.columns = ['Gene', 'Protein information', '3K', '5.4K', '12.2K', '24K', '78.4K', '110K', '195.5K']"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {},
"outputs": [],
"source": [
"# Calculate centroid arrays for uninduced and induced\n",
"un_cent = np.zeros((len(common.index), 7))\n",
"ind_cent = np.zeros((len(common.index), 7))\n",
"\n",
"fractlist = ['3K', '5.4K', '12.2K', '24K', '78.4K', '110K', '195.5K']\n",
"\n",
"for protein, row in zip(common.index, range(0, len(common.index))):\n",
" for fraction, col in zip(fractlist, range(0, 7)):\n",
" tempa = ua.at[protein, fraction]\n",
" tempb = ub.at[protein, fraction]\n",
" tempc = uc.at[protein, fraction]\n",
" un_cent[row, col] = np.mean([tempa, tempb, tempc])\n",
"\n",
"for protein, row in zip(common.index, range(0, len(common.index))):\n",
" for fraction, col in zip(fractlist, range(0, 7)):\n",
" tempa = ia.at[protein, fraction]\n",
" tempb = ib.at[protein, fraction]\n",
" tempc = ic.at[protein, fraction]\n",
" ind_cent[row, col] = np.mean([tempa, tempb, tempc])"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {},
"outputs": [],
"source": [
"# Calculate Euclidean distance from each replicate to its respective centroid\n",
"un_stats = np.zeros((len(common.index), 4))\n",
"ind_stats = np.zeros((len(common.index), 4))\n",
"\n",
"unlist = [ua, ub, uc]\n",
"indlist = [ia, ib, ic]\n",
"\n",
"for protein, row in zip(common.index, range(0, len(common.index))):\n",
" for df, col in zip(unlist, range(0,3)):\n",
" temp = df.loc[protein, '3K':'195.5K']\n",
" avg = un_cent[row]\n",
" un_stats[row, col] = euclidean(temp, avg)\n",
"\n",
"for protein, row in zip(common.index, range(0, len(common.index))):\n",
" for df, col in zip(indlist, range(0,3)):\n",
" temp = df.loc[protein, '3K':'195.5K']\n",
" avg = ind_cent[row]\n",
" ind_stats[row, col] = euclidean(temp, avg)"
]
},
{
"cell_type": "code",
"execution_count": 27,
"metadata": {},
"outputs": [],
"source": [
"# Calculate standard deviation of distances for each condition\n",
"un_stats[:, 3] = np.std(un_stats[:, 0:3], axis=1, ddof=1)\n",
"ind_stats[:, 3] = np.std(ind_stats[:, 0:3], axis=1, ddof=1)"
]
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {},
"outputs": [],
"source": [
"# Calculate t-statistic and p-value for each protein\n",
"# Using Benjamini-Hochberg correction for p-values\n",
"mvmt_stats = np.zeros((len(common.index), 5))\n",
"\n",
"# Column 0 will contain the Euclidean distance between the uninduced and induced centroids\n",
"for row in range(0, len(common.index)):\n",
" mvmt_stats[row, 0] = euclidean(un_cent[row], ind_cent[row])\n",
"\n",
"# Column 1 will contain the t-statistic\n",
"for row in range(0, len(common.index)):\n",
" unvar = (un_stats[row, 3])**2\n",
" indvar = (ind_stats[row, 3])**2\n",
" mvmt_stats[row, 1] = ((mvmt_stats[row, 0])/np.sqrt((unvar+indvar)/3))\n",
"\n",
"# Column 2 will contain the p-value\n",
"for row in range(0, len(common.index)):\n",
" tstat = mvmt_stats[row, 1]\n",
" unvar = (un_stats[row, 3])**2\n",
" indvar = (ind_stats[row, 3])**2\n",
" dof = (2*((unvar**2+(2*unvar*indvar)+indvar**2)/(unvar**2+indvar**2)))\n",
" mvmt_stats[row, 2] = t.sf(x=tstat, df=dof)\n",
"\n",
"# Column 3 will contain the rank value for each p-value\n",
"mvmt_stats[:, 3] = rankdata(mvmt_stats[:, 2])\n",
"\n",
"# Column 4 will contain the Benjamini-Hochberg critical values; using an FDR of 0.01 or 1%\n",
"mvmt_stats[:, 4] = (mvmt_stats[:, 3]/len(common.index))*0.01"
]
},
{
"cell_type": "code",
"execution_count": 29,
"metadata": {},
"outputs": [],
"source": [
"# Calculate t-statistic and p-value for each protein\n",
"# Using Benjamini-Hochberg correction for p-values\n",
"mvmt_stats2 = np.zeros((len(common.index), 5))\n",
"\n",
"# Column 0 will contain the Euclidean distance between the uninduced and induced centroids\n",
"for row in range(0, len(common.index)):\n",
" mvmt_stats2[row, 0] = euclidean(un_cent[row], ind_cent[row])\n",
"\n",
"# Column 1 will contain the t-statistic\n",
"for row in range(0, len(common.index)):\n",
" unvar = (un_stats[row, 3])**2\n",
" indvar = (ind_stats[row, 3])**2\n",
" mvmt_stats2[row, 1] = ((mvmt_stats2[row, 0])/np.sqrt((unvar+indvar)/3))\n",
"\n",
"# Column 2 will contain the p-value\n",
"for row in range(0, len(common.index)):\n",
" tstat = mvmt_stats2[row, 1]\n",
" unvar = (un_stats[row, 3])**2\n",
" indvar = (ind_stats[row, 3])**2\n",
" dof = (2*((unvar**2+(2*unvar*indvar)+indvar**2)/(unvar**2+indvar**2)))\n",
" mvmt_stats2[row, 2] = t.sf(tstat, df=dof)\n",
"\n",
"# Column 3 will contain the rank value for each p-value\n",
"mvmt_stats2[:, 3] = rankdata(mvmt_stats2[:, 2])\n",
"\n",
"# Column 4 will contain the Benjamini-Hochberg critical values; using an FDR of 0.015 or 1.5%\n",
"mvmt_stats2[:, 4] = (mvmt_stats2[:, 3]/len(common.index))*0.015"
]
},
{
"cell_type": "code",
"execution_count": 30,
"metadata": {},
"outputs": [],
"source": [
"# Calculate t-statistic and p-value for each protein\n",
"# Using Benjamini-Hochberg correction for p-values\n",
"mvmt_stats3 = np.zeros((len(common.index), 5))\n",
"\n",
"# Column 0 will contain the Euclidean distance between the uninduced and induced centroids\n",
"for row in range(0, len(common.index)):\n",
" mvmt_stats3[row, 0] = euclidean(un_cent[row], ind_cent[row])\n",
"\n",
"# Column 1 will contain the t-statistic\n",
"for row in range(0, len(common.index)):\n",
" unvar = (un_stats[row, 3])**2\n",
" indvar = (ind_stats[row, 3])**2\n",
" mvmt_stats3[row, 1] = ((mvmt_stats3[row, 0])/np.sqrt((unvar+indvar)/3))\n",
"\n",
"# Column 2 will contain the p-value\n",
"for row in range(0, len(common.index)):\n",
" tstat = mvmt_stats3[row, 1]\n",
" unvar = (un_stats[row, 3])**2\n",
" indvar = (ind_stats[row, 3])**2\n",
" dof = (2*((unvar**2+(2*unvar*indvar)+indvar**2)/(unvar**2+indvar**2)))\n",
" mvmt_stats3[row, 2] = t.sf(tstat, df=dof)\n",
"\n",
"# Column 3 will contain the rank value for each p-value\n",
"mvmt_stats3[:, 3] = rankdata(mvmt_stats3[:, 2])\n",
"\n",
"# Column 4 will contain the Benjamini-Hochberg critical values; using an FDR of 0.02 or 2%\n",
"mvmt_stats3[:, 4] = (mvmt_stats3[:, 3]/len(common.index))*0.02"
]
},
{
"cell_type": "code",
"execution_count": 31,
"metadata": {},
"outputs": [],
"source": [
"# Adding the p-value and critical value for each protein, then sorting by p-value; FDR of 1%\n",
"sigmvmt = common.loc[:, 'Gene_ua':'Protein information_ua']\n",
"sigmvmt['p-value'] = mvmt_stats[:, 2]\n",
"sigmvmt['CritValue'] = mvmt_stats[:, 4]\n",
"sigmvmt.sort_values(by='p-value', inplace=True)"
]
},
{
"cell_type": "code",
"execution_count": 32,
"metadata": {},
"outputs": [],
"source": [
"# Adding the p-value and critical value for each protein, then sorting by p-value; FDR of 1.5%\n",
"sigmvmt2 = common.loc[:, 'Gene_ua':'Protein information_ua']\n",
"sigmvmt2['p-value'] = mvmt_stats2[:, 2]\n",
"sigmvmt2['CritValue'] = mvmt_stats2[:, 4]\n",
"sigmvmt2.sort_values(by='p-value', inplace=True)"
]
},
{
"cell_type": "code",
"execution_count": 33,
"metadata": {},
"outputs": [],
"source": [
"# Adding the p-value and critical value for each protein, then sorting by p-value; FDR of 2%\n",
"sigmvmt3 = common.loc[:, 'Gene_ua':'Protein information_ua']\n",
"sigmvmt3['p-value'] = mvmt_stats3[:, 2]\n",
"sigmvmt3['CritValue'] = mvmt_stats3[:, 4]\n",
"sigmvmt3.sort_values(by='p-value', inplace=True)"
]
},
{
"cell_type": "code",
"execution_count": 34,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Gene_ua</th>\n",
" <th>Protein information_ua</th>\n",
" <th>p-value</th>\n",
" <th>CritValue</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Protein IDs</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>P55795</th>\n",
" <td>HNRH2</td>\n",
" <td>Heterogeneous nuclear ribonucleoprotein H2</td>\n",
" <td>0.000002</td>\n",
" <td>0.000002</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P55265</th>\n",
" <td>DSRAD</td>\n",
" <td>Double-stranded RNA-specific adenosine deaminase</td>\n",
" <td>0.000004</td>\n",
" <td>0.000003</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P33241</th>\n",
" <td>LSP1</td>\n",
" <td>Lymphocyte-specific protein 1</td>\n",
" <td>0.000005</td>\n",
" <td>0.000005</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P33121</th>\n",
" <td>ACSL1</td>\n",
" <td>Long-chain-fatty-acid--CoA ligase 1</td>\n",
" <td>0.000010</td>\n",
" <td>0.000007</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P78559</th>\n",
" <td>MAP1A</td>\n",
" <td>Microtubule-associated protein 1A</td>\n",
" <td>0.000012</td>\n",
" <td>0.000008</td>\n",
" </tr>\n",
" <tr>\n",
" <th>A6NFD8</th>\n",
" <td>HELT</td>\n",
" <td>Hairy and enhancer of split-related protein HELT</td>\n",
" <td>0.000013</td>\n",
" <td>0.000010</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9UJX2</th>\n",
" <td>CDC23</td>\n",
" <td>Cell division cycle protein 23 homolog</td>\n",
" <td>0.000013</td>\n",
" <td>0.000012</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P53618</th>\n",
" <td>COPB</td>\n",
" <td>Coatomer subunit beta</td>\n",
" <td>0.000014</td>\n",
" <td>0.000013</td>\n",
" </tr>\n",
" <tr>\n",
" <th>O14733</th>\n",
" <td>MP2K7</td>\n",
" <td>Dual specificity mitogen-activated protein kin...</td>\n",
" <td>0.000020</td>\n",
" <td>0.000015</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q13740</th>\n",
" <td>CD166</td>\n",
" <td>CD166 antigen</td>\n",
" <td>0.000021</td>\n",
" <td>0.000017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q8NG68</th>\n",
" <td>TTL</td>\n",
" <td>Tubulin--tyrosine ligase</td>\n",
" <td>0.000024</td>\n",
" <td>0.000018</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9H0U4</th>\n",
" <td>RAB1B</td>\n",
" <td>Ras-related protein Rab-1B</td>\n",
" <td>0.000025</td>\n",
" <td>0.000020</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q06136</th>\n",
" <td>KDSR</td>\n",
" <td>3-ketodihydrosphingosine reductase</td>\n",
" <td>0.000026</td>\n",
" <td>0.000022</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P26358</th>\n",
" <td>DNMT1</td>\n",
" <td>DNA (cytosine-5)-methyltransferase 1</td>\n",
" <td>0.000026</td>\n",
" <td>0.000023</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P01034</th>\n",
" <td>CYTC</td>\n",
" <td>Cystatin-C</td>\n",
" <td>0.000028</td>\n",
" <td>0.000025</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q6P6C2</th>\n",
" <td>ALKB5</td>\n",
" <td>RNA demethylase ALKBH5</td>\n",
" <td>0.000030</td>\n",
" <td>0.000027</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P35523</th>\n",
" <td>CLCN1</td>\n",
" <td>Chloride channel protein 1</td>\n",
" <td>0.000031</td>\n",
" <td>0.000028</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P41240</th>\n",
" <td>CSK</td>\n",
" <td>Tyrosine-protein kinase CSK</td>\n",
" <td>0.000032</td>\n",
" <td>0.000030</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9NUV9</th>\n",
" <td>GIMA4</td>\n",
" <td>GTPase IMAP family member 4</td>\n",
" <td>0.000032</td>\n",
" <td>0.000032</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9NPE2</th>\n",
" <td>NGRN</td>\n",
" <td>Neugrin</td>\n",
" <td>0.000032</td>\n",
" <td>0.000033</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9Y294</th>\n",
" <td>ASF1A</td>\n",
" <td>Histone chaperone ASF1A</td>\n",
" <td>0.000033</td>\n",
" <td>0.000035</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q8IZ73</th>\n",
" <td>RUSD2</td>\n",
" <td>RNA pseudouridylate synthase domain-containing...</td>\n",
" <td>0.000035</td>\n",
" <td>0.000037</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q15526</th>\n",
" <td>SURF1</td>\n",
" <td>Surfeit locus protein 1</td>\n",
" <td>0.000036</td>\n",
" <td>0.000038</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9Y3T9</th>\n",
" <td>NOC2L</td>\n",
" <td>Nucleolar complex protein 2 homolog</td>\n",
" <td>0.000038</td>\n",
" <td>0.000040</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9Y6I8</th>\n",
" <td>PXMP4</td>\n",
" <td>Peroxisomal membrane protein 4</td>\n",
" <td>0.000038</td>\n",
" <td>0.000042</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9P2C4</th>\n",
" <td>TM181</td>\n",
" <td>Transmembrane protein 181</td>\n",
" <td>0.000039</td>\n",
" <td>0.000043</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P50570</th>\n",
" <td>DYN2</td>\n",
" <td>Dynamin-2</td>\n",
" <td>0.000041</td>\n",
" <td>0.000045</td>\n",
" </tr>\n",
" <tr>\n",
" <th>O75446</th>\n",
" <td>SAP30</td>\n",
" <td>Histone deacetylase complex subunit SAP30</td>\n",
" <td>0.000041</td>\n",
" <td>0.000047</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9NVH1</th>\n",
" <td>DJC11</td>\n",
" <td>DnaJ homolog subfamily C member 11</td>\n",
" <td>0.000042</td>\n",
" <td>0.000048</td>\n",
" </tr>\n",
" <tr>\n",
" <th>O75319</th>\n",
" <td>DUS11</td>\n",
" <td>RNA/RNP complex-1-interacting phosphatase</td>\n",
" <td>0.000043</td>\n",
" <td>0.000050</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q14CB8</th>\n",
" <td>RHG19</td>\n",
" <td>Rho GTPase-activating protein 19</td>\n",
" <td>0.001498</td>\n",
" <td>0.001515</td>\n",
" </tr>\n",
" <tr>\n",
" <th>O60218</th>\n",
" <td>AK1BA</td>\n",
" <td>Aldo-keto reductase family 1 member B10</td>\n",
" <td>0.001499</td>\n",
" <td>0.001517</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P62753</th>\n",
" <td>RS6</td>\n",
" <td>40S ribosomal protein S6</td>\n",
" <td>0.001501</td>\n",
" <td>0.001518</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P31943</th>\n",
" <td>HNRH1</td>\n",
" <td>Heterogeneous nuclear ribonucleoprotein H</td>\n",
" <td>0.001503</td>\n",
" <td>0.001520</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q6NXR4</th>\n",
" <td>TTI2</td>\n",
" <td>TELO2-interacting protein 2</td>\n",
" <td>0.001504</td>\n",
" <td>0.001522</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q6P0Q8</th>\n",
" <td>MAST2</td>\n",
" <td>Microtubule-associated serine/threonine-protei...</td>\n",
" <td>0.001505</td>\n",
" <td>0.001523</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P47736</th>\n",
" <td>RPGP1</td>\n",
" <td>Rap1 GTPase-activating protein 1</td>\n",
" <td>0.001507</td>\n",
" <td>0.001525</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9NTK5</th>\n",
" <td>OLA1</td>\n",
" <td>Obg-like ATPase 1</td>\n",
" <td>0.001515</td>\n",
" <td>0.001527</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P51809</th>\n",
" <td>VAMP7</td>\n",
" <td>Vesicle-associated membrane protein 7</td>\n",
" <td>0.001516</td>\n",
" <td>0.001528</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q6PJW8</th>\n",
" <td>CNST</td>\n",
" <td>Consortin</td>\n",
" <td>0.001518</td>\n",
" <td>0.001530</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q92536</th>\n",
" <td>YLAT2</td>\n",
" <td>Y+L amino acid transporter 2</td>\n",
" <td>0.001519</td>\n",
" <td>0.001532</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9BYG5</th>\n",
" <td>PAR6B</td>\n",
" <td>Partitioning defective 6 homolog beta</td>\n",
" <td>0.001525</td>\n",
" <td>0.001533</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P26641</th>\n",
" <td>EF1G</td>\n",
" <td>Elongation factor 1-gamma</td>\n",
" <td>0.001527</td>\n",
" <td>0.001535</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9H6F5</th>\n",
" <td>CCD86</td>\n",
" <td>Coiled-coil domain-containing protein 86</td>\n",
" <td>0.001528</td>\n",
" <td>0.001537</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9UBD5</th>\n",
" <td>ORC3</td>\n",
" <td>Origin recognition complex subunit 3</td>\n",
" <td>0.001529</td>\n",
" <td>0.001538</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q14738</th>\n",
" <td>2A5D</td>\n",
" <td>Serine/threonine-protein phosphatase 2A 56 kDa...</td>\n",
" <td>0.001534</td>\n",
" <td>0.001540</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q5DX21</th>\n",
" <td>IGS11</td>\n",
" <td>Immunoglobulin superfamily member 11</td>\n",
" <td>0.001536</td>\n",
" <td>0.001542</td>\n",
" </tr>\n",
" <tr>\n",
" <th>O15226</th>\n",
" <td>NKRF</td>\n",
" <td>NF-kappa-B-repressing factor</td>\n",
" <td>0.001538</td>\n",
" <td>0.001543</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9NX47</th>\n",
" <td>MARH5</td>\n",
" <td>E3 ubiquitin-protein ligase MARCH5</td>\n",
" <td>0.001546</td>\n",
" <td>0.001545</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9BVJ6</th>\n",
" <td>UT14A</td>\n",
" <td>U3 small nucleolar RNA-associated protein 14 h...</td>\n",
" <td>0.001546</td>\n",
" <td>0.001547</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P43359</th>\n",
" <td>MAGA5</td>\n",
" <td>Melanoma-associated antigen 5</td>\n",
" <td>0.001546</td>\n",
" <td>0.001548</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q6PCB8</th>\n",
" <td>EMB</td>\n",
" <td>Embigin</td>\n",
" <td>0.001548</td>\n",
" <td>0.001550</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q6ZNE5</th>\n",
" <td>BAKOR</td>\n",
" <td>Beclin 1-associated autophagy-related key regu...</td>\n",
" <td>0.001548</td>\n",
" <td>0.001552</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P13591</th>\n",
" <td>NCAM1</td>\n",
" <td>Neural cell adhesion molecule 1</td>\n",
" <td>0.001549</td>\n",
" <td>0.001554</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q8IXT5</th>\n",
" <td>RB12B</td>\n",
" <td>RNA-binding protein 12B</td>\n",
" <td>0.001550</td>\n",
" <td>0.001555</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q14554</th>\n",
" <td>PDIA5</td>\n",
" <td>Protein disulfide-isomerase A5</td>\n",
" <td>0.001552</td>\n",
" <td>0.001557</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q96GX2</th>\n",
" <td>A7L3B</td>\n",
" <td>Ataxin-7-like protein 3B</td>\n",
" <td>0.001552</td>\n",
" <td>0.001559</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q8WXA9</th>\n",
" <td>SREK1</td>\n",
" <td>Splicing regulatory glutamine/lysine-rich prot...</td>\n",
" <td>0.001558</td>\n",
" <td>0.001560</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9UBI1</th>\n",
" <td>COMD3</td>\n",
" <td>COMM domain-containing protein 3</td>\n",
" <td>0.001560</td>\n",
" <td>0.001562</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q5JSQ8</th>\n",
" <td>KHDCL</td>\n",
" <td>Putative KHDC1-like protein</td>\n",
" <td>0.001563</td>\n",
" <td>0.001564</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>935 rows × 4 columns</p>\n",
"</div>"
],
"text/plain": [
" Gene_ua Protein information_ua \\\n",
"Protein IDs \n",
"P55795 HNRH2 Heterogeneous nuclear ribonucleoprotein H2 \n",
"P55265 DSRAD Double-stranded RNA-specific adenosine deaminase \n",
"P33241 LSP1 Lymphocyte-specific protein 1 \n",
"P33121 ACSL1 Long-chain-fatty-acid--CoA ligase 1 \n",
"P78559 MAP1A Microtubule-associated protein 1A \n",
"A6NFD8 HELT Hairy and enhancer of split-related protein HELT \n",
"Q9UJX2 CDC23 Cell division cycle protein 23 homolog \n",
"P53618 COPB Coatomer subunit beta \n",
"O14733 MP2K7 Dual specificity mitogen-activated protein kin... \n",
"Q13740 CD166 CD166 antigen \n",
"Q8NG68 TTL Tubulin--tyrosine ligase \n",
"Q9H0U4 RAB1B Ras-related protein Rab-1B \n",
"Q06136 KDSR 3-ketodihydrosphingosine reductase \n",
"P26358 DNMT1 DNA (cytosine-5)-methyltransferase 1 \n",
"P01034 CYTC Cystatin-C \n",
"Q6P6C2 ALKB5 RNA demethylase ALKBH5 \n",
"P35523 CLCN1 Chloride channel protein 1 \n",
"P41240 CSK Tyrosine-protein kinase CSK \n",
"Q9NUV9 GIMA4 GTPase IMAP family member 4 \n",
"Q9NPE2 NGRN Neugrin \n",
"Q9Y294 ASF1A Histone chaperone ASF1A \n",
"Q8IZ73 RUSD2 RNA pseudouridylate synthase domain-containing... \n",
"Q15526 SURF1 Surfeit locus protein 1 \n",
"Q9Y3T9 NOC2L Nucleolar complex protein 2 homolog \n",
"Q9Y6I8 PXMP4 Peroxisomal membrane protein 4 \n",
"Q9P2C4 TM181 Transmembrane protein 181 \n",
"P50570 DYN2 Dynamin-2 \n",
"O75446 SAP30 Histone deacetylase complex subunit SAP30 \n",
"Q9NVH1 DJC11 DnaJ homolog subfamily C member 11 \n",
"O75319 DUS11 RNA/RNP complex-1-interacting phosphatase \n",
"... ... ... \n",
"Q14CB8 RHG19 Rho GTPase-activating protein 19 \n",
"O60218 AK1BA Aldo-keto reductase family 1 member B10 \n",
"P62753 RS6 40S ribosomal protein S6 \n",
"P31943 HNRH1 Heterogeneous nuclear ribonucleoprotein H \n",
"Q6NXR4 TTI2 TELO2-interacting protein 2 \n",
"Q6P0Q8 MAST2 Microtubule-associated serine/threonine-protei... \n",
"P47736 RPGP1 Rap1 GTPase-activating protein 1 \n",
"Q9NTK5 OLA1 Obg-like ATPase 1 \n",
"P51809 VAMP7 Vesicle-associated membrane protein 7 \n",
"Q6PJW8 CNST Consortin \n",
"Q92536 YLAT2 Y+L amino acid transporter 2 \n",
"Q9BYG5 PAR6B Partitioning defective 6 homolog beta \n",
"P26641 EF1G Elongation factor 1-gamma \n",
"Q9H6F5 CCD86 Coiled-coil domain-containing protein 86 \n",
"Q9UBD5 ORC3 Origin recognition complex subunit 3 \n",
"Q14738 2A5D Serine/threonine-protein phosphatase 2A 56 kDa... \n",
"Q5DX21 IGS11 Immunoglobulin superfamily member 11 \n",
"O15226 NKRF NF-kappa-B-repressing factor \n",
"Q9NX47 MARH5 E3 ubiquitin-protein ligase MARCH5 \n",
"Q9BVJ6 UT14A U3 small nucleolar RNA-associated protein 14 h... \n",
"P43359 MAGA5 Melanoma-associated antigen 5 \n",
"Q6PCB8 EMB Embigin \n",
"Q6ZNE5 BAKOR Beclin 1-associated autophagy-related key regu... \n",
"P13591 NCAM1 Neural cell adhesion molecule 1 \n",
"Q8IXT5 RB12B RNA-binding protein 12B \n",
"Q14554 PDIA5 Protein disulfide-isomerase A5 \n",
"Q96GX2 A7L3B Ataxin-7-like protein 3B \n",
"Q8WXA9 SREK1 Splicing regulatory glutamine/lysine-rich prot... \n",
"Q9UBI1 COMD3 COMM domain-containing protein 3 \n",
"Q5JSQ8 KHDCL Putative KHDC1-like protein \n",
"\n",
" p-value CritValue \n",
"Protein IDs \n",
"P55795 0.000002 0.000002 \n",
"P55265 0.000004 0.000003 \n",
"P33241 0.000005 0.000005 \n",
"P33121 0.000010 0.000007 \n",
"P78559 0.000012 0.000008 \n",
"A6NFD8 0.000013 0.000010 \n",
"Q9UJX2 0.000013 0.000012 \n",
"P53618 0.000014 0.000013 \n",
"O14733 0.000020 0.000015 \n",
"Q13740 0.000021 0.000017 \n",
"Q8NG68 0.000024 0.000018 \n",
"Q9H0U4 0.000025 0.000020 \n",
"Q06136 0.000026 0.000022 \n",
"P26358 0.000026 0.000023 \n",
"P01034 0.000028 0.000025 \n",
"Q6P6C2 0.000030 0.000027 \n",
"P35523 0.000031 0.000028 \n",
"P41240 0.000032 0.000030 \n",
"Q9NUV9 0.000032 0.000032 \n",
"Q9NPE2 0.000032 0.000033 \n",
"Q9Y294 0.000033 0.000035 \n",
"Q8IZ73 0.000035 0.000037 \n",
"Q15526 0.000036 0.000038 \n",
"Q9Y3T9 0.000038 0.000040 \n",
"Q9Y6I8 0.000038 0.000042 \n",
"Q9P2C4 0.000039 0.000043 \n",
"P50570 0.000041 0.000045 \n",
"O75446 0.000041 0.000047 \n",
"Q9NVH1 0.000042 0.000048 \n",
"O75319 0.000043 0.000050 \n",
"... ... ... \n",
"Q14CB8 0.001498 0.001515 \n",
"O60218 0.001499 0.001517 \n",
"P62753 0.001501 0.001518 \n",
"P31943 0.001503 0.001520 \n",
"Q6NXR4 0.001504 0.001522 \n",
"Q6P0Q8 0.001505 0.001523 \n",
"P47736 0.001507 0.001525 \n",
"Q9NTK5 0.001515 0.001527 \n",
"P51809 0.001516 0.001528 \n",
"Q6PJW8 0.001518 0.001530 \n",
"Q92536 0.001519 0.001532 \n",
"Q9BYG5 0.001525 0.001533 \n",
"P26641 0.001527 0.001535 \n",
"Q9H6F5 0.001528 0.001537 \n",
"Q9UBD5 0.001529 0.001538 \n",
"Q14738 0.001534 0.001540 \n",
"Q5DX21 0.001536 0.001542 \n",
"O15226 0.001538 0.001543 \n",
"Q9NX47 0.001546 0.001545 \n",
"Q9BVJ6 0.001546 0.001547 \n",
"P43359 0.001546 0.001548 \n",
"Q6PCB8 0.001548 0.001550 \n",
"Q6ZNE5 0.001548 0.001552 \n",
"P13591 0.001549 0.001554 \n",
"Q8IXT5 0.001550 0.001555 \n",
"Q14554 0.001552 0.001557 \n",
"Q96GX2 0.001552 0.001559 \n",
"Q8WXA9 0.001558 0.001560 \n",
"Q9UBI1 0.001560 0.001562 \n",
"Q5JSQ8 0.001563 0.001564 \n",
"\n",
"[935 rows x 4 columns]"
]
},
"execution_count": 34,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Determining the maximum p-value < CritValue and subsetting out all p-values less than that cutoff; FDR of 1%\n",
"df = sigmvmt[sigmvmt['p-value'] < sigmvmt['CritValue']]\n",
"cutoff = df['p-value'].max()\n",
"moved = sigmvmt[sigmvmt['p-value'] <= cutoff]\n",
"moved"
]
},
{
"cell_type": "code",
"execution_count": 35,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Gene_ua</th>\n",
" <th>Protein information_ua</th>\n",
" <th>p-value</th>\n",
" <th>CritValue</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Protein IDs</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>P55795</th>\n",
" <td>HNRH2</td>\n",
" <td>Heterogeneous nuclear ribonucleoprotein H2</td>\n",
" <td>0.000002</td>\n",
" <td>0.000003</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P55265</th>\n",
" <td>DSRAD</td>\n",
" <td>Double-stranded RNA-specific adenosine deaminase</td>\n",
" <td>0.000004</td>\n",
" <td>0.000005</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P33241</th>\n",
" <td>LSP1</td>\n",
" <td>Lymphocyte-specific protein 1</td>\n",
" <td>0.000005</td>\n",
" <td>0.000008</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P33121</th>\n",
" <td>ACSL1</td>\n",
" <td>Long-chain-fatty-acid--CoA ligase 1</td>\n",
" <td>0.000010</td>\n",
" <td>0.000010</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P78559</th>\n",
" <td>MAP1A</td>\n",
" <td>Microtubule-associated protein 1A</td>\n",
" <td>0.000012</td>\n",
" <td>0.000013</td>\n",
" </tr>\n",
" <tr>\n",
" <th>A6NFD8</th>\n",
" <td>HELT</td>\n",
" <td>Hairy and enhancer of split-related protein HELT</td>\n",
" <td>0.000013</td>\n",
" <td>0.000015</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9UJX2</th>\n",
" <td>CDC23</td>\n",
" <td>Cell division cycle protein 23 homolog</td>\n",
" <td>0.000013</td>\n",
" <td>0.000018</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P53618</th>\n",
" <td>COPB</td>\n",
" <td>Coatomer subunit beta</td>\n",
" <td>0.000014</td>\n",
" <td>0.000020</td>\n",
" </tr>\n",
" <tr>\n",
" <th>O14733</th>\n",
" <td>MP2K7</td>\n",
" <td>Dual specificity mitogen-activated protein kin...</td>\n",
" <td>0.000020</td>\n",
" <td>0.000023</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q13740</th>\n",
" <td>CD166</td>\n",
" <td>CD166 antigen</td>\n",
" <td>0.000021</td>\n",
" <td>0.000025</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q8NG68</th>\n",
" <td>TTL</td>\n",
" <td>Tubulin--tyrosine ligase</td>\n",
" <td>0.000024</td>\n",
" <td>0.000028</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9H0U4</th>\n",
" <td>RAB1B</td>\n",
" <td>Ras-related protein Rab-1B</td>\n",
" <td>0.000025</td>\n",
" <td>0.000030</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q06136</th>\n",
" <td>KDSR</td>\n",
" <td>3-ketodihydrosphingosine reductase</td>\n",
" <td>0.000026</td>\n",
" <td>0.000033</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P26358</th>\n",
" <td>DNMT1</td>\n",
" <td>DNA (cytosine-5)-methyltransferase 1</td>\n",
" <td>0.000026</td>\n",
" <td>0.000035</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P01034</th>\n",
" <td>CYTC</td>\n",
" <td>Cystatin-C</td>\n",
" <td>0.000028</td>\n",
" <td>0.000038</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q6P6C2</th>\n",
" <td>ALKB5</td>\n",
" <td>RNA demethylase ALKBH5</td>\n",
" <td>0.000030</td>\n",
" <td>0.000040</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P35523</th>\n",
" <td>CLCN1</td>\n",
" <td>Chloride channel protein 1</td>\n",
" <td>0.000031</td>\n",
" <td>0.000043</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P41240</th>\n",
" <td>CSK</td>\n",
" <td>Tyrosine-protein kinase CSK</td>\n",
" <td>0.000032</td>\n",
" <td>0.000045</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9NUV9</th>\n",
" <td>GIMA4</td>\n",
" <td>GTPase IMAP family member 4</td>\n",
" <td>0.000032</td>\n",
" <td>0.000048</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9NPE2</th>\n",
" <td>NGRN</td>\n",
" <td>Neugrin</td>\n",
" <td>0.000032</td>\n",
" <td>0.000050</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9Y294</th>\n",
" <td>ASF1A</td>\n",
" <td>Histone chaperone ASF1A</td>\n",
" <td>0.000033</td>\n",
" <td>0.000053</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q8IZ73</th>\n",
" <td>RUSD2</td>\n",
" <td>RNA pseudouridylate synthase domain-containing...</td>\n",
" <td>0.000035</td>\n",
" <td>0.000055</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q15526</th>\n",
" <td>SURF1</td>\n",
" <td>Surfeit locus protein 1</td>\n",
" <td>0.000036</td>\n",
" <td>0.000058</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9Y3T9</th>\n",
" <td>NOC2L</td>\n",
" <td>Nucleolar complex protein 2 homolog</td>\n",
" <td>0.000038</td>\n",
" <td>0.000060</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9Y6I8</th>\n",
" <td>PXMP4</td>\n",
" <td>Peroxisomal membrane protein 4</td>\n",
" <td>0.000038</td>\n",
" <td>0.000063</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9P2C4</th>\n",
" <td>TM181</td>\n",
" <td>Transmembrane protein 181</td>\n",
" <td>0.000039</td>\n",
" <td>0.000065</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P50570</th>\n",
" <td>DYN2</td>\n",
" <td>Dynamin-2</td>\n",
" <td>0.000041</td>\n",
" <td>0.000068</td>\n",
" </tr>\n",
" <tr>\n",
" <th>O75446</th>\n",
" <td>SAP30</td>\n",
" <td>Histone deacetylase complex subunit SAP30</td>\n",
" <td>0.000041</td>\n",
" <td>0.000070</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9NVH1</th>\n",
" <td>DJC11</td>\n",
" <td>DnaJ homolog subfamily C member 11</td>\n",
" <td>0.000042</td>\n",
" <td>0.000073</td>\n",
" </tr>\n",
" <tr>\n",
" <th>O75319</th>\n",
" <td>DUS11</td>\n",
" <td>RNA/RNP complex-1-interacting phosphatase</td>\n",
" <td>0.000043</td>\n",
" <td>0.000075</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P30825</th>\n",
" <td>CTR1</td>\n",
" <td>High affinity cationic amino acid transporter 1</td>\n",
" <td>0.005781</td>\n",
" <td>0.005804</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q53GS9</th>\n",
" <td>SNUT2</td>\n",
" <td>U4/U6.U5 tri-snRNP-associated protein 2</td>\n",
" <td>0.005781</td>\n",
" <td>0.005807</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P04075</th>\n",
" <td>ALDOA</td>\n",
" <td>Fructose-bisphosphate aldolase A</td>\n",
" <td>0.005782</td>\n",
" <td>0.005809</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q15173</th>\n",
" <td>2A5B</td>\n",
" <td>Serine/threonine-protein phosphatase 2A 56 kDa...</td>\n",
" <td>0.005785</td>\n",
" <td>0.005812</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9P219</th>\n",
" <td>DAPLE</td>\n",
" <td>Protein Daple</td>\n",
" <td>0.005789</td>\n",
" <td>0.005814</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9Y639</th>\n",
" <td>NPTN</td>\n",
" <td>Neuroplastin</td>\n",
" <td>0.005792</td>\n",
" <td>0.005817</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q99439</th>\n",
" <td>CNN2</td>\n",
" <td>Calponin-2</td>\n",
" <td>0.005792</td>\n",
" <td>0.005819</td>\n",
" </tr>\n",
" <tr>\n",
" <th>O95470</th>\n",
" <td>SGPL1</td>\n",
" <td>Sphingosine-1-phosphate lyase 1</td>\n",
" <td>0.005797</td>\n",
" <td>0.005822</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q13303</th>\n",
" <td>KCAB2</td>\n",
" <td>Voltage-gated potassium channel subunit beta-2</td>\n",
" <td>0.005805</td>\n",
" <td>0.005824</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9UKB1</th>\n",
" <td>FBW1B</td>\n",
" <td>F-box/WD repeat-containing protein 11</td>\n",
" <td>0.005806</td>\n",
" <td>0.005827</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9Y608</th>\n",
" <td>LRRF2</td>\n",
" <td>Leucine-rich repeat flightless-interacting pro...</td>\n",
" <td>0.005807</td>\n",
" <td>0.005829</td>\n",
" </tr>\n",
" <tr>\n",
" <th>O43175</th>\n",
" <td>SERA</td>\n",
" <td>D-3-phosphoglycerate dehydrogenase</td>\n",
" <td>0.005810</td>\n",
" <td>0.005832</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P49641</th>\n",
" <td>MA2A2</td>\n",
" <td>Alpha-mannosidase 2x</td>\n",
" <td>0.005811</td>\n",
" <td>0.005834</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9Y262</th>\n",
" <td>EIF3L</td>\n",
" <td>Eukaryotic translation initiation factor 3 sub...</td>\n",
" <td>0.005813</td>\n",
" <td>0.005837</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q7L5N1</th>\n",
" <td>CSN6</td>\n",
" <td>COP9 signalosome complex subunit 6</td>\n",
" <td>0.005816</td>\n",
" <td>0.005839</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q86W56</th>\n",
" <td>PARG</td>\n",
" <td>Poly(ADP-ribose) glycohydrolase</td>\n",
" <td>0.005818</td>\n",
" <td>0.005842</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q86YQ8</th>\n",
" <td>CPNE8</td>\n",
" <td>Copine-8</td>\n",
" <td>0.005820</td>\n",
" <td>0.005844</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q16763</th>\n",
" <td>UBE2S</td>\n",
" <td>Ubiquitin-conjugating enzyme E2 S</td>\n",
" <td>0.005823</td>\n",
" <td>0.005847</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q13615</th>\n",
" <td>MTMR3</td>\n",
" <td>Myotubularin-related protein 3</td>\n",
" <td>0.005835</td>\n",
" <td>0.005849</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9H9A7</th>\n",
" <td>RMI1</td>\n",
" <td>RecQ-mediated genome instability protein 1</td>\n",
" <td>0.005841</td>\n",
" <td>0.005852</td>\n",
" </tr>\n",
" <tr>\n",
" <th>O75874</th>\n",
" <td>IDHC</td>\n",
" <td>Isocitrate dehydrogenase [NADP] cytoplasmic</td>\n",
" <td>0.005846</td>\n",
" <td>0.005855</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9BTU6</th>\n",
" <td>P4K2A</td>\n",
" <td>Phosphatidylinositol 4-kinase type 2-alpha</td>\n",
" <td>0.005848</td>\n",
" <td>0.005857</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q96SK2</th>\n",
" <td>TM209</td>\n",
" <td>Transmembrane protein 209</td>\n",
" <td>0.005851</td>\n",
" <td>0.005860</td>\n",
" </tr>\n",
" <tr>\n",
" <th>O75182</th>\n",
" <td>SIN3B</td>\n",
" <td>Paired amphipathic helix protein Sin3b</td>\n",
" <td>0.005852</td>\n",
" <td>0.005862</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P62249</th>\n",
" <td>RS16</td>\n",
" <td>40S ribosomal protein S16</td>\n",
" <td>0.005856</td>\n",
" <td>0.005865</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q15084</th>\n",
" <td>PDIA6</td>\n",
" <td>Protein disulfide-isomerase A6</td>\n",
" <td>0.005858</td>\n",
" <td>0.005867</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9UFD9</th>\n",
" <td>RIM3A</td>\n",
" <td>RIMS-binding protein 3C</td>\n",
" <td>0.005868</td>\n",
" <td>0.005870</td>\n",
" </tr>\n",
" <tr>\n",
" <th>O15269</th>\n",
" <td>SPTC1</td>\n",
" <td>Serine palmitoyltransferase 1</td>\n",
" <td>0.005869</td>\n",
" <td>0.005872</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9NQS7</th>\n",
" <td>INCE</td>\n",
" <td>Inner centromere protein</td>\n",
" <td>0.005873</td>\n",
" <td>0.005875</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9Y4F3</th>\n",
" <td>MARF1</td>\n",
" <td>Meiosis regulator and mRNA stability factor 1</td>\n",
" <td>0.005874</td>\n",
" <td>0.005877</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>2343 rows × 4 columns</p>\n",
"</div>"
],
"text/plain": [
" Gene_ua Protein information_ua \\\n",
"Protein IDs \n",
"P55795 HNRH2 Heterogeneous nuclear ribonucleoprotein H2 \n",
"P55265 DSRAD Double-stranded RNA-specific adenosine deaminase \n",
"P33241 LSP1 Lymphocyte-specific protein 1 \n",
"P33121 ACSL1 Long-chain-fatty-acid--CoA ligase 1 \n",
"P78559 MAP1A Microtubule-associated protein 1A \n",
"A6NFD8 HELT Hairy and enhancer of split-related protein HELT \n",
"Q9UJX2 CDC23 Cell division cycle protein 23 homolog \n",
"P53618 COPB Coatomer subunit beta \n",
"O14733 MP2K7 Dual specificity mitogen-activated protein kin... \n",
"Q13740 CD166 CD166 antigen \n",
"Q8NG68 TTL Tubulin--tyrosine ligase \n",
"Q9H0U4 RAB1B Ras-related protein Rab-1B \n",
"Q06136 KDSR 3-ketodihydrosphingosine reductase \n",
"P26358 DNMT1 DNA (cytosine-5)-methyltransferase 1 \n",
"P01034 CYTC Cystatin-C \n",
"Q6P6C2 ALKB5 RNA demethylase ALKBH5 \n",
"P35523 CLCN1 Chloride channel protein 1 \n",
"P41240 CSK Tyrosine-protein kinase CSK \n",
"Q9NUV9 GIMA4 GTPase IMAP family member 4 \n",
"Q9NPE2 NGRN Neugrin \n",
"Q9Y294 ASF1A Histone chaperone ASF1A \n",
"Q8IZ73 RUSD2 RNA pseudouridylate synthase domain-containing... \n",
"Q15526 SURF1 Surfeit locus protein 1 \n",
"Q9Y3T9 NOC2L Nucleolar complex protein 2 homolog \n",
"Q9Y6I8 PXMP4 Peroxisomal membrane protein 4 \n",
"Q9P2C4 TM181 Transmembrane protein 181 \n",
"P50570 DYN2 Dynamin-2 \n",
"O75446 SAP30 Histone deacetylase complex subunit SAP30 \n",
"Q9NVH1 DJC11 DnaJ homolog subfamily C member 11 \n",
"O75319 DUS11 RNA/RNP complex-1-interacting phosphatase \n",
"... ... ... \n",
"P30825 CTR1 High affinity cationic amino acid transporter 1 \n",
"Q53GS9 SNUT2 U4/U6.U5 tri-snRNP-associated protein 2 \n",
"P04075 ALDOA Fructose-bisphosphate aldolase A \n",
"Q15173 2A5B Serine/threonine-protein phosphatase 2A 56 kDa... \n",
"Q9P219 DAPLE Protein Daple \n",
"Q9Y639 NPTN Neuroplastin \n",
"Q99439 CNN2 Calponin-2 \n",
"O95470 SGPL1 Sphingosine-1-phosphate lyase 1 \n",
"Q13303 KCAB2 Voltage-gated potassium channel subunit beta-2 \n",
"Q9UKB1 FBW1B F-box/WD repeat-containing protein 11 \n",
"Q9Y608 LRRF2 Leucine-rich repeat flightless-interacting pro... \n",
"O43175 SERA D-3-phosphoglycerate dehydrogenase \n",
"P49641 MA2A2 Alpha-mannosidase 2x \n",
"Q9Y262 EIF3L Eukaryotic translation initiation factor 3 sub... \n",
"Q7L5N1 CSN6 COP9 signalosome complex subunit 6 \n",
"Q86W56 PARG Poly(ADP-ribose) glycohydrolase \n",
"Q86YQ8 CPNE8 Copine-8 \n",
"Q16763 UBE2S Ubiquitin-conjugating enzyme E2 S \n",
"Q13615 MTMR3 Myotubularin-related protein 3 \n",
"Q9H9A7 RMI1 RecQ-mediated genome instability protein 1 \n",
"O75874 IDHC Isocitrate dehydrogenase [NADP] cytoplasmic \n",
"Q9BTU6 P4K2A Phosphatidylinositol 4-kinase type 2-alpha \n",
"Q96SK2 TM209 Transmembrane protein 209 \n",
"O75182 SIN3B Paired amphipathic helix protein Sin3b \n",
"P62249 RS16 40S ribosomal protein S16 \n",
"Q15084 PDIA6 Protein disulfide-isomerase A6 \n",
"Q9UFD9 RIM3A RIMS-binding protein 3C \n",
"O15269 SPTC1 Serine palmitoyltransferase 1 \n",
"Q9NQS7 INCE Inner centromere protein \n",
"Q9Y4F3 MARF1 Meiosis regulator and mRNA stability factor 1 \n",
"\n",
" p-value CritValue \n",
"Protein IDs \n",
"P55795 0.000002 0.000003 \n",
"P55265 0.000004 0.000005 \n",
"P33241 0.000005 0.000008 \n",
"P33121 0.000010 0.000010 \n",
"P78559 0.000012 0.000013 \n",
"A6NFD8 0.000013 0.000015 \n",
"Q9UJX2 0.000013 0.000018 \n",
"P53618 0.000014 0.000020 \n",
"O14733 0.000020 0.000023 \n",
"Q13740 0.000021 0.000025 \n",
"Q8NG68 0.000024 0.000028 \n",
"Q9H0U4 0.000025 0.000030 \n",
"Q06136 0.000026 0.000033 \n",
"P26358 0.000026 0.000035 \n",
"P01034 0.000028 0.000038 \n",
"Q6P6C2 0.000030 0.000040 \n",
"P35523 0.000031 0.000043 \n",
"P41240 0.000032 0.000045 \n",
"Q9NUV9 0.000032 0.000048 \n",
"Q9NPE2 0.000032 0.000050 \n",
"Q9Y294 0.000033 0.000053 \n",
"Q8IZ73 0.000035 0.000055 \n",
"Q15526 0.000036 0.000058 \n",
"Q9Y3T9 0.000038 0.000060 \n",
"Q9Y6I8 0.000038 0.000063 \n",
"Q9P2C4 0.000039 0.000065 \n",
"P50570 0.000041 0.000068 \n",
"O75446 0.000041 0.000070 \n",
"Q9NVH1 0.000042 0.000073 \n",
"O75319 0.000043 0.000075 \n",
"... ... ... \n",
"P30825 0.005781 0.005804 \n",
"Q53GS9 0.005781 0.005807 \n",
"P04075 0.005782 0.005809 \n",
"Q15173 0.005785 0.005812 \n",
"Q9P219 0.005789 0.005814 \n",
"Q9Y639 0.005792 0.005817 \n",
"Q99439 0.005792 0.005819 \n",
"O95470 0.005797 0.005822 \n",
"Q13303 0.005805 0.005824 \n",
"Q9UKB1 0.005806 0.005827 \n",
"Q9Y608 0.005807 0.005829 \n",
"O43175 0.005810 0.005832 \n",
"P49641 0.005811 0.005834 \n",
"Q9Y262 0.005813 0.005837 \n",
"Q7L5N1 0.005816 0.005839 \n",
"Q86W56 0.005818 0.005842 \n",
"Q86YQ8 0.005820 0.005844 \n",
"Q16763 0.005823 0.005847 \n",
"Q13615 0.005835 0.005849 \n",
"Q9H9A7 0.005841 0.005852 \n",
"O75874 0.005846 0.005855 \n",
"Q9BTU6 0.005848 0.005857 \n",
"Q96SK2 0.005851 0.005860 \n",
"O75182 0.005852 0.005862 \n",
"P62249 0.005856 0.005865 \n",
"Q15084 0.005858 0.005867 \n",
"Q9UFD9 0.005868 0.005870 \n",
"O15269 0.005869 0.005872 \n",
"Q9NQS7 0.005873 0.005875 \n",
"Q9Y4F3 0.005874 0.005877 \n",
"\n",
"[2343 rows x 4 columns]"
]
},
"execution_count": 35,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Determining the maximum p-value < CritValue and subsetting out all p-values less than that cutoff; FDR of 1.5%\n",
"df2 = sigmvmt2[sigmvmt2['p-value'] < sigmvmt2['CritValue']]\n",
"cutoff2 = df2['p-value'].max()\n",
"moved2 = sigmvmt2[sigmvmt2['p-value'] <= cutoff2]\n",
"moved2"
]
},
{
"cell_type": "code",
"execution_count": 36,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Gene_ua</th>\n",
" <th>Protein information_ua</th>\n",
" <th>p-value</th>\n",
" <th>CritValue</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Protein IDs</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>P55795</th>\n",
" <td>HNRH2</td>\n",
" <td>Heterogeneous nuclear ribonucleoprotein H2</td>\n",
" <td>0.000002</td>\n",
" <td>0.000003</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P55265</th>\n",
" <td>DSRAD</td>\n",
" <td>Double-stranded RNA-specific adenosine deaminase</td>\n",
" <td>0.000004</td>\n",
" <td>0.000007</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P33241</th>\n",
" <td>LSP1</td>\n",
" <td>Lymphocyte-specific protein 1</td>\n",
" <td>0.000005</td>\n",
" <td>0.000010</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P33121</th>\n",
" <td>ACSL1</td>\n",
" <td>Long-chain-fatty-acid--CoA ligase 1</td>\n",
" <td>0.000010</td>\n",
" <td>0.000013</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P78559</th>\n",
" <td>MAP1A</td>\n",
" <td>Microtubule-associated protein 1A</td>\n",
" <td>0.000012</td>\n",
" <td>0.000017</td>\n",
" </tr>\n",
" <tr>\n",
" <th>A6NFD8</th>\n",
" <td>HELT</td>\n",
" <td>Hairy and enhancer of split-related protein HELT</td>\n",
" <td>0.000013</td>\n",
" <td>0.000020</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9UJX2</th>\n",
" <td>CDC23</td>\n",
" <td>Cell division cycle protein 23 homolog</td>\n",
" <td>0.000013</td>\n",
" <td>0.000023</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P53618</th>\n",
" <td>COPB</td>\n",
" <td>Coatomer subunit beta</td>\n",
" <td>0.000014</td>\n",
" <td>0.000027</td>\n",
" </tr>\n",
" <tr>\n",
" <th>O14733</th>\n",
" <td>MP2K7</td>\n",
" <td>Dual specificity mitogen-activated protein kin...</td>\n",
" <td>0.000020</td>\n",
" <td>0.000030</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q13740</th>\n",
" <td>CD166</td>\n",
" <td>CD166 antigen</td>\n",
" <td>0.000021</td>\n",
" <td>0.000033</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q8NG68</th>\n",
" <td>TTL</td>\n",
" <td>Tubulin--tyrosine ligase</td>\n",
" <td>0.000024</td>\n",
" <td>0.000037</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9H0U4</th>\n",
" <td>RAB1B</td>\n",
" <td>Ras-related protein Rab-1B</td>\n",
" <td>0.000025</td>\n",
" <td>0.000040</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q06136</th>\n",
" <td>KDSR</td>\n",
" <td>3-ketodihydrosphingosine reductase</td>\n",
" <td>0.000026</td>\n",
" <td>0.000043</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P26358</th>\n",
" <td>DNMT1</td>\n",
" <td>DNA (cytosine-5)-methyltransferase 1</td>\n",
" <td>0.000026</td>\n",
" <td>0.000047</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P01034</th>\n",
" <td>CYTC</td>\n",
" <td>Cystatin-C</td>\n",
" <td>0.000028</td>\n",
" <td>0.000050</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q6P6C2</th>\n",
" <td>ALKB5</td>\n",
" <td>RNA demethylase ALKBH5</td>\n",
" <td>0.000030</td>\n",
" <td>0.000054</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P35523</th>\n",
" <td>CLCN1</td>\n",
" <td>Chloride channel protein 1</td>\n",
" <td>0.000031</td>\n",
" <td>0.000057</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P41240</th>\n",
" <td>CSK</td>\n",
" <td>Tyrosine-protein kinase CSK</td>\n",
" <td>0.000032</td>\n",
" <td>0.000060</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9NUV9</th>\n",
" <td>GIMA4</td>\n",
" <td>GTPase IMAP family member 4</td>\n",
" <td>0.000032</td>\n",
" <td>0.000064</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9NPE2</th>\n",
" <td>NGRN</td>\n",
" <td>Neugrin</td>\n",
" <td>0.000032</td>\n",
" <td>0.000067</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9Y294</th>\n",
" <td>ASF1A</td>\n",
" <td>Histone chaperone ASF1A</td>\n",
" <td>0.000033</td>\n",
" <td>0.000070</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q8IZ73</th>\n",
" <td>RUSD2</td>\n",
" <td>RNA pseudouridylate synthase domain-containing...</td>\n",
" <td>0.000035</td>\n",
" <td>0.000074</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q15526</th>\n",
" <td>SURF1</td>\n",
" <td>Surfeit locus protein 1</td>\n",
" <td>0.000036</td>\n",
" <td>0.000077</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9Y3T9</th>\n",
" <td>NOC2L</td>\n",
" <td>Nucleolar complex protein 2 homolog</td>\n",
" <td>0.000038</td>\n",
" <td>0.000080</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9Y6I8</th>\n",
" <td>PXMP4</td>\n",
" <td>Peroxisomal membrane protein 4</td>\n",
" <td>0.000038</td>\n",
" <td>0.000084</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9P2C4</th>\n",
" <td>TM181</td>\n",
" <td>Transmembrane protein 181</td>\n",
" <td>0.000039</td>\n",
" <td>0.000087</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P50570</th>\n",
" <td>DYN2</td>\n",
" <td>Dynamin-2</td>\n",
" <td>0.000041</td>\n",
" <td>0.000090</td>\n",
" </tr>\n",
" <tr>\n",
" <th>O75446</th>\n",
" <td>SAP30</td>\n",
" <td>Histone deacetylase complex subunit SAP30</td>\n",
" <td>0.000041</td>\n",
" <td>0.000094</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9NVH1</th>\n",
" <td>DJC11</td>\n",
" <td>DnaJ homolog subfamily C member 11</td>\n",
" <td>0.000042</td>\n",
" <td>0.000097</td>\n",
" </tr>\n",
" <tr>\n",
" <th>O75319</th>\n",
" <td>DUS11</td>\n",
" <td>RNA/RNP complex-1-interacting phosphatase</td>\n",
" <td>0.000043</td>\n",
" <td>0.000100</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q96GK7</th>\n",
" <td>FAH2A</td>\n",
" <td>Fumarylacetoacetate hydrolase domain-containin...</td>\n",
" <td>0.010581</td>\n",
" <td>0.010726</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q12824</th>\n",
" <td>SNF5</td>\n",
" <td>SWI/SNF-related matrix-associated actin-depend...</td>\n",
" <td>0.010602</td>\n",
" <td>0.010729</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q13614</th>\n",
" <td>MTMR2</td>\n",
" <td>Myotubularin-related protein 2</td>\n",
" <td>0.010612</td>\n",
" <td>0.010732</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q86SX3</th>\n",
" <td>TEDC1</td>\n",
" <td>Tubulin epsilon and delta complex protein 1</td>\n",
" <td>0.010613</td>\n",
" <td>0.010736</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q96QK1</th>\n",
" <td>VPS35</td>\n",
" <td>Vacuolar protein sorting-associated protein 35</td>\n",
" <td>0.010619</td>\n",
" <td>0.010739</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P61247</th>\n",
" <td>RS3A</td>\n",
" <td>40S ribosomal protein S3a</td>\n",
" <td>0.010636</td>\n",
" <td>0.010742</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q71F23</th>\n",
" <td>CENPU</td>\n",
" <td>Centromere protein U</td>\n",
" <td>0.010641</td>\n",
" <td>0.010746</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9BTT0</th>\n",
" <td>AN32E</td>\n",
" <td>Acidic leucine-rich nuclear phosphoprotein 32 ...</td>\n",
" <td>0.010661</td>\n",
" <td>0.010749</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q8WXX5</th>\n",
" <td>DNJC9</td>\n",
" <td>DnaJ homolog subfamily C member 9</td>\n",
" <td>0.010672</td>\n",
" <td>0.010753</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P30419</th>\n",
" <td>NMT1</td>\n",
" <td>Glycylpeptide N-tetradecanoyltransferase 1</td>\n",
" <td>0.010682</td>\n",
" <td>0.010756</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9Y5Y0</th>\n",
" <td>FLVC1</td>\n",
" <td>Feline leukemia virus subgroup C receptor-rela...</td>\n",
" <td>0.010690</td>\n",
" <td>0.010759</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q7Z417</th>\n",
" <td>NUFP2</td>\n",
" <td>Nuclear fragile X mental retardation-interacti...</td>\n",
" <td>0.010699</td>\n",
" <td>0.010763</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q96LR5</th>\n",
" <td>UB2E2</td>\n",
" <td>Ubiquitin-conjugating enzyme E2 E2</td>\n",
" <td>0.010705</td>\n",
" <td>0.010766</td>\n",
" </tr>\n",
" <tr>\n",
" <th>O95619</th>\n",
" <td>YETS4</td>\n",
" <td>YEATS domain-containing protein 4</td>\n",
" <td>0.010706</td>\n",
" <td>0.010769</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q5TAQ9</th>\n",
" <td>DCAF8</td>\n",
" <td>DDB1- and CUL4-associated factor 8</td>\n",
" <td>0.010712</td>\n",
" <td>0.010773</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P13796</th>\n",
" <td>PLSL</td>\n",
" <td>Plastin-2</td>\n",
" <td>0.010712</td>\n",
" <td>0.010776</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9P0U4</th>\n",
" <td>CXXC1</td>\n",
" <td>CXXC-type zinc finger protein 1</td>\n",
" <td>0.010713</td>\n",
" <td>0.010779</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P49354</th>\n",
" <td>FNTA</td>\n",
" <td>Protein farnesyltransferase/geranylgeranyltran...</td>\n",
" <td>0.010724</td>\n",
" <td>0.010783</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9UFF9</th>\n",
" <td>CNOT8</td>\n",
" <td>CCR4-NOT transcription complex subunit 8</td>\n",
" <td>0.010732</td>\n",
" <td>0.010786</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9BVM2</th>\n",
" <td>DPCD</td>\n",
" <td>Protein DPCD</td>\n",
" <td>0.010736</td>\n",
" <td>0.010789</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9NV92</th>\n",
" <td>NFIP2</td>\n",
" <td>NEDD4 family-interacting protein 2</td>\n",
" <td>0.010745</td>\n",
" <td>0.010793</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q8N5G2</th>\n",
" <td>MACOI</td>\n",
" <td>Macoilin</td>\n",
" <td>0.010753</td>\n",
" <td>0.010796</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q92585</th>\n",
" <td>MAML1</td>\n",
" <td>Mastermind-like protein 1</td>\n",
" <td>0.010757</td>\n",
" <td>0.010799</td>\n",
" </tr>\n",
" <tr>\n",
" <th>P55145</th>\n",
" <td>MANF</td>\n",
" <td>Mesencephalic astrocyte-derived neurotrophic f...</td>\n",
" <td>0.010773</td>\n",
" <td>0.010803</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q96JG8</th>\n",
" <td>MAGD4</td>\n",
" <td>Melanoma-associated antigen D4</td>\n",
" <td>0.010777</td>\n",
" <td>0.010806</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q8NFH5</th>\n",
" <td>NUP35</td>\n",
" <td>Nucleoporin NUP35</td>\n",
" <td>0.010783</td>\n",
" <td>0.010809</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Q9Y548</th>\n",
" <td>YIPF1</td>\n",
" <td>Protein YIPF1</td>\n",
" <td>0.010787</td>\n",
" <td>0.010813</td>\n",
" </tr>\n",
" <tr>\n",
" <th>O14776</th>\n",
" <td>TCRG1</td>\n",
" <td>Transcription elongation regulator 1</td>\n",
" <td>0.010792</td>\n",
" <td>0.010816</td>\n",
" </tr>\n",
" <tr>\n",
" <th>O14920</th>\n",
" <td>IKKB</td>\n",
" <td>Inhibitor of nuclear factor kappa-B kinase sub...</td>\n",
" <td>0.010799</td>\n",
" <td>0.010819</td>\n",
" </tr>\n",
" <tr>\n",
" <th>O75093</th>\n",
" <td>SLIT1</td>\n",
" <td>Slit homolog 1 protein</td>\n",
" <td>0.010804</td>\n",
" <td>0.010823</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>3236 rows × 4 columns</p>\n",
"</div>"
],
"text/plain": [
" Gene_ua Protein information_ua \\\n",
"Protein IDs \n",
"P55795 HNRH2 Heterogeneous nuclear ribonucleoprotein H2 \n",
"P55265 DSRAD Double-stranded RNA-specific adenosine deaminase \n",
"P33241 LSP1 Lymphocyte-specific protein 1 \n",
"P33121 ACSL1 Long-chain-fatty-acid--CoA ligase 1 \n",
"P78559 MAP1A Microtubule-associated protein 1A \n",
"A6NFD8 HELT Hairy and enhancer of split-related protein HELT \n",
"Q9UJX2 CDC23 Cell division cycle protein 23 homolog \n",
"P53618 COPB Coatomer subunit beta \n",
"O14733 MP2K7 Dual specificity mitogen-activated protein kin... \n",
"Q13740 CD166 CD166 antigen \n",
"Q8NG68 TTL Tubulin--tyrosine ligase \n",
"Q9H0U4 RAB1B Ras-related protein Rab-1B \n",
"Q06136 KDSR 3-ketodihydrosphingosine reductase \n",
"P26358 DNMT1 DNA (cytosine-5)-methyltransferase 1 \n",
"P01034 CYTC Cystatin-C \n",
"Q6P6C2 ALKB5 RNA demethylase ALKBH5 \n",
"P35523 CLCN1 Chloride channel protein 1 \n",
"P41240 CSK Tyrosine-protein kinase CSK \n",
"Q9NUV9 GIMA4 GTPase IMAP family member 4 \n",
"Q9NPE2 NGRN Neugrin \n",
"Q9Y294 ASF1A Histone chaperone ASF1A \n",
"Q8IZ73 RUSD2 RNA pseudouridylate synthase domain-containing... \n",
"Q15526 SURF1 Surfeit locus protein 1 \n",
"Q9Y3T9 NOC2L Nucleolar complex protein 2 homolog \n",
"Q9Y6I8 PXMP4 Peroxisomal membrane protein 4 \n",
"Q9P2C4 TM181 Transmembrane protein 181 \n",
"P50570 DYN2 Dynamin-2 \n",
"O75446 SAP30 Histone deacetylase complex subunit SAP30 \n",
"Q9NVH1 DJC11 DnaJ homolog subfamily C member 11 \n",
"O75319 DUS11 RNA/RNP complex-1-interacting phosphatase \n",
"... ... ... \n",
"Q96GK7 FAH2A Fumarylacetoacetate hydrolase domain-containin... \n",
"Q12824 SNF5 SWI/SNF-related matrix-associated actin-depend... \n",
"Q13614 MTMR2 Myotubularin-related protein 2 \n",
"Q86SX3 TEDC1 Tubulin epsilon and delta complex protein 1 \n",
"Q96QK1 VPS35 Vacuolar protein sorting-associated protein 35 \n",
"P61247 RS3A 40S ribosomal protein S3a \n",
"Q71F23 CENPU Centromere protein U \n",
"Q9BTT0 AN32E Acidic leucine-rich nuclear phosphoprotein 32 ... \n",
"Q8WXX5 DNJC9 DnaJ homolog subfamily C member 9 \n",
"P30419 NMT1 Glycylpeptide N-tetradecanoyltransferase 1 \n",
"Q9Y5Y0 FLVC1 Feline leukemia virus subgroup C receptor-rela... \n",
"Q7Z417 NUFP2 Nuclear fragile X mental retardation-interacti... \n",
"Q96LR5 UB2E2 Ubiquitin-conjugating enzyme E2 E2 \n",
"O95619 YETS4 YEATS domain-containing protein 4 \n",
"Q5TAQ9 DCAF8 DDB1- and CUL4-associated factor 8 \n",
"P13796 PLSL Plastin-2 \n",
"Q9P0U4 CXXC1 CXXC-type zinc finger protein 1 \n",
"P49354 FNTA Protein farnesyltransferase/geranylgeranyltran... \n",
"Q9UFF9 CNOT8 CCR4-NOT transcription complex subunit 8 \n",
"Q9BVM2 DPCD Protein DPCD \n",
"Q9NV92 NFIP2 NEDD4 family-interacting protein 2 \n",
"Q8N5G2 MACOI Macoilin \n",
"Q92585 MAML1 Mastermind-like protein 1 \n",
"P55145 MANF Mesencephalic astrocyte-derived neurotrophic f... \n",
"Q96JG8 MAGD4 Melanoma-associated antigen D4 \n",
"Q8NFH5 NUP35 Nucleoporin NUP35 \n",
"Q9Y548 YIPF1 Protein YIPF1 \n",
"O14776 TCRG1 Transcription elongation regulator 1 \n",
"O14920 IKKB Inhibitor of nuclear factor kappa-B kinase sub... \n",
"O75093 SLIT1 Slit homolog 1 protein \n",
"\n",
" p-value CritValue \n",
"Protein IDs \n",
"P55795 0.000002 0.000003 \n",
"P55265 0.000004 0.000007 \n",
"P33241 0.000005 0.000010 \n",
"P33121 0.000010 0.000013 \n",
"P78559 0.000012 0.000017 \n",
"A6NFD8 0.000013 0.000020 \n",
"Q9UJX2 0.000013 0.000023 \n",
"P53618 0.000014 0.000027 \n",
"O14733 0.000020 0.000030 \n",
"Q13740 0.000021 0.000033 \n",
"Q8NG68 0.000024 0.000037 \n",
"Q9H0U4 0.000025 0.000040 \n",
"Q06136 0.000026 0.000043 \n",
"P26358 0.000026 0.000047 \n",
"P01034 0.000028 0.000050 \n",
"Q6P6C2 0.000030 0.000054 \n",
"P35523 0.000031 0.000057 \n",
"P41240 0.000032 0.000060 \n",
"Q9NUV9 0.000032 0.000064 \n",
"Q9NPE2 0.000032 0.000067 \n",
"Q9Y294 0.000033 0.000070 \n",
"Q8IZ73 0.000035 0.000074 \n",
"Q15526 0.000036 0.000077 \n",
"Q9Y3T9 0.000038 0.000080 \n",
"Q9Y6I8 0.000038 0.000084 \n",
"Q9P2C4 0.000039 0.000087 \n",
"P50570 0.000041 0.000090 \n",
"O75446 0.000041 0.000094 \n",
"Q9NVH1 0.000042 0.000097 \n",
"O75319 0.000043 0.000100 \n",
"... ... ... \n",
"Q96GK7 0.010581 0.010726 \n",
"Q12824 0.010602 0.010729 \n",
"Q13614 0.010612 0.010732 \n",
"Q86SX3 0.010613 0.010736 \n",
"Q96QK1 0.010619 0.010739 \n",
"P61247 0.010636 0.010742 \n",
"Q71F23 0.010641 0.010746 \n",
"Q9BTT0 0.010661 0.010749 \n",
"Q8WXX5 0.010672 0.010753 \n",
"P30419 0.010682 0.010756 \n",
"Q9Y5Y0 0.010690 0.010759 \n",
"Q7Z417 0.010699 0.010763 \n",
"Q96LR5 0.010705 0.010766 \n",
"O95619 0.010706 0.010769 \n",
"Q5TAQ9 0.010712 0.010773 \n",
"P13796 0.010712 0.010776 \n",
"Q9P0U4 0.010713 0.010779 \n",
"P49354 0.010724 0.010783 \n",
"Q9UFF9 0.010732 0.010786 \n",
"Q9BVM2 0.010736 0.010789 \n",
"Q9NV92 0.010745 0.010793 \n",
"Q8N5G2 0.010753 0.010796 \n",
"Q92585 0.010757 0.010799 \n",
"P55145 0.010773 0.010803 \n",
"Q96JG8 0.010777 0.010806 \n",
"Q8NFH5 0.010783 0.010809 \n",
"Q9Y548 0.010787 0.010813 \n",
"O14776 0.010792 0.010816 \n",
"O14920 0.010799 0.010819 \n",
"O75093 0.010804 0.010823 \n",
"\n",
"[3236 rows x 4 columns]"
]
},
"execution_count": 36,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Determining the maximum p-value < CritValue and subsetting out all p-values less than that cutoff; FDR of 2%\n",
"df3 = sigmvmt3[sigmvmt3['p-value'] < sigmvmt3['CritValue']]\n",
"cutoff3 = df3['p-value'].max()\n",
"moved3 = sigmvmt3[sigmvmt3['p-value'] <= cutoff3]\n",
"moved3"
]
},
{
"cell_type": "code",
"execution_count": 37,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(935, 17)\n",
"(871, 17)\n"
]
}
],
"source": [
"# Reading in full data summary to cross-reference with moved list\n",
"# Saving moved proteins with FDR of 0.01; including copy without markers that are moving\n",
"fulldata = pd.read_csv('20190518_FullExperimentSummary_Thresholding.csv', index_col=0)\n",
"temp = fulldata.loc[moved.index, :]\n",
"temp['pval'] = moved['p-value']\n",
"temp['critval'] = moved['CritValue']\n",
"temp.to_csv('20190518_EuclideanDistance_FDR0.01.csv', sep=',')\n",
"temp_nomrkr = temp[temp.Marker == 'No']\n",
"temp_nomrkr.to_csv('20190518_EuclideanDistance_FDR0.01_nomrkr.csv', sep=',')\n",
"print(temp.shape)\n",
"print(temp_nomrkr.shape)"
]
},
{
"cell_type": "code",
"execution_count": 39,
"metadata": {},
"outputs": [],
"source": [
"# Making IDs only files for each of the FDR=0.01 lists\n",
"temp.reset_index(inplace=True)\n",
"temp['Protein IDs'].to_csv('20190518_EuclideanDistance_FDR0.01_IDs.csv', sep=',', header=False, index=False)\n",
"temp_nomrkr.reset_index(inplace=True)\n",
"temp_nomrkr['Protein IDs'].to_csv('20190518_EuclideanDistance_FDR0.01_nomrkr_IDs.csv', sep=',', header=False, index=False)"
]
},
{
"cell_type": "code",
"execution_count": 40,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(2343, 17)\n",
"(2207, 17)\n"
]
}
],
"source": [
"# Reading in full data summary to cross-reference with moved list\n",
"# Saving moved proteins with FDR of 0.015; including copy without markers that are moving\n",
"temp2 = fulldata.loc[moved2.index, :]\n",
"temp2['pval'] = moved2['p-value']\n",
"temp2['critval'] = moved2['CritValue']\n",
"temp2.to_csv('20190518_EuclideanDistance_FDR0.015.csv', sep=',')\n",
"temp_nomrkr2 = temp2[temp2.Marker == 'No']\n",
"temp_nomrkr2.to_csv('20190518_EuclideanDistance_FDR0.015_nomrkr.csv', sep=',')\n",
"print(temp2.shape)\n",
"print(temp_nomrkr2.shape)"
]
},
{
"cell_type": "code",
"execution_count": 41,
"metadata": {},
"outputs": [],
"source": [
"# Making IDs only files for each of the FDR=0.015 lists\n",
"temp2.reset_index(inplace=True)\n",
"temp2['Protein IDs'].to_csv('20190518_EuclideanDistance_FDR0.015_IDs.csv', sep=',', header=False, index=False)\n",
"temp_nomrkr2.reset_index(inplace=True)\n",
"temp_nomrkr2['Protein IDs'].to_csv('20190518_EuclideanDistance_FDR0.015_nomrkr_IDs.csv', sep=',', header=False, index=False)"
]
},
{
"cell_type": "code",
"execution_count": 42,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(3236, 17)\n",
"(3056, 17)\n"
]
}
],
"source": [
"# Reading in full data summary to cross-reference with moved list\n",
"# Saving moved proteins with FDR of 0.02; including copy without markers that are moving\n",
"temp3 = fulldata.loc[moved3.index, :]\n",
"temp3['pval'] = moved3['p-value']\n",
"temp3['critval'] = moved3['CritValue']\n",
"temp3.to_csv('20190518_EuclideanDistance_FDR0.02.csv', sep=',')\n",
"temp_nomrkr3 = temp3[temp3.Marker == 'No']\n",
"temp_nomrkr3.to_csv('20190518_EuclideanDistance_FDR0.02_nomrkr.csv', sep=',')\n",
"print(temp3.shape)\n",
"print(temp_nomrkr3.shape)"
]
},
{
"cell_type": "code",
"execution_count": 43,
"metadata": {},
"outputs": [],
"source": [
"# Making IDs only files for each of the FDR=0.0075 lists\n",
"temp3.reset_index(inplace=True)\n",
"temp3['Protein IDs'].to_csv('20190518_EuclideanDistance_FDR0.02_IDs.csv', sep=',', header=False, index=False)\n",
"temp_nomrkr3.reset_index(inplace=True)\n",
"temp_nomrkr3['Protein IDs'].to_csv('20190518_EuclideanDistance_FDR0.02_nomrkr_IDs.csv', sep=',', header=False, index=False)"
]
}
],
"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
}