tsv_times.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "f6f70318",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "14c81e03",
   "metadata": {},
   "outputs": [],
   "source": [
    "import xlrd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "c2370d51",
   "metadata": {},
   "outputs": [],
   "source": [
    "df =  pd.read_csv(\"gerd_instrument_snps_PhenoScanner_GWAS.tsv\", sep=\"\\t\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "1164f895",
   "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>snp</th>\n",
       "      <th>rsid</th>\n",
       "      <th>hg19_coordinates</th>\n",
       "      <th>hg38_coordinates</th>\n",
       "      <th>a1</th>\n",
       "      <th>a2</th>\n",
       "      <th>trait</th>\n",
       "      <th>efo</th>\n",
       "      <th>study</th>\n",
       "      <th>pmid</th>\n",
       "      <th>...</th>\n",
       "      <th>beta</th>\n",
       "      <th>se</th>\n",
       "      <th>p</th>\n",
       "      <th>direction</th>\n",
       "      <th>n</th>\n",
       "      <th>n_cases</th>\n",
       "      <th>n_controls</th>\n",
       "      <th>n_studies</th>\n",
       "      <th>unit</th>\n",
       "      <th>dataset</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>rs2815749</td>\n",
       "      <td>rs2815749</td>\n",
       "      <td>chr1:72814783</td>\n",
       "      <td>chr1:72349100</td>\n",
       "      <td>G</td>\n",
       "      <td>A</td>\n",
       "      <td>Childhood BMI</td>\n",
       "      <td>EFO_0004340</td>\n",
       "      <td>EGGC</td>\n",
       "      <td>26604143</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0579</td>\n",
       "      <td>0.0102</td>\n",
       "      <td>1.560000e-08</td>\n",
       "      <td>+</td>\n",
       "      <td>35661</td>\n",
       "      <td>0</td>\n",
       "      <td>35661</td>\n",
       "      <td>20</td>\n",
       "      <td>SDS</td>\n",
       "      <td>EGGC_Childhood-BMI_EUR_2016</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1 rows × 22 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "         snp       rsid hg19_coordinates hg38_coordinates a1 a2  \\\n",
       "0  rs2815749  rs2815749    chr1:72814783    chr1:72349100  G  A   \n",
       "\n",
       "           trait          efo study      pmid  ...    beta      se  \\\n",
       "0  Childhood BMI  EFO_0004340  EGGC  26604143  ...  0.0579  0.0102   \n",
       "\n",
       "              p  direction      n n_cases n_controls n_studies unit  \\\n",
       "0  1.560000e-08          +  35661       0      35661        20  SDS   \n",
       "\n",
       "                       dataset  \n",
       "0  EGGC_Childhood-BMI_EUR_2016  \n",
       "\n",
       "[1 rows x 22 columns]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head(1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "fc19eacd",
   "metadata": {},
   "outputs": [],
   "source": [
    "thresh1 = 5e-8 # gwas threshold 1\n",
    "thresh2 = 1e-5 # gwas threshold 2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "02c3784f",
   "metadata": {},
   "outputs": [],
   "source": [
    "df.trait = df.trait.str.upper() # capitalize traits"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "b095ada5",
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df[df.trait.str.contains('BMI|FAT|MASS|BODY|OBESITY|HIP|CIRCUMFERENCE')] # select obesity related ones"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "431aa376",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "38"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.snp.nunique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "5284b343",
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df[df.study != 'Neale B'] # lets not include 'Neale B'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "9c1dc257",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "9"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.snp.nunique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "538499a4",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "6"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[df.p < thresh1].snp.nunique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "7ec19f2d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['rs2815749', 'rs13107325', 'rs205262', 'rs1716171', 'rs9940128',\n",
       "       'rs9636202'], dtype=object)"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[df.p < thresh1].snp.unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "e11c157e",
   "metadata": {},
   "outputs": [],
   "source": [
    "pd.DataFrame(df[df.p < thresh1]).to_csv('thresh1_snps_sans_neale_b.csv', index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "4108a863",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "9"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[df.p < thresh2].snp.nunique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "828a813e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['rs2815749', 'rs13107325', 'rs329122', 'rs205262', 'rs2396766',\n",
       "       'rs1716171', 'rs9940128', 'rs7206608', 'rs9636202'], dtype=object)"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[df.p < thresh2].snp.unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "2bf3e50b",
   "metadata": {},
   "outputs": [],
   "source": [
    "pd.DataFrame(df[df.p < thresh2]).to_csv('thresh2_snps_sans_neale_b.csv', index=False)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.9.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}