Upload solutions for exercises_D

Exercises/solutions/Python_course_2021_exercises_D.ipynb

+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "name": "Python_course_2021_exercises_D.ipynb",
+      "provenance": [],
+      "collapsed_sections": []
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "xqfYLmi0LWEl",
+        "pycharm": {
+          "name": "#%% md\n"
+        }
+      },
+      "source": [
+        "# Python course 2021 - Exercises D"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "LRZcpmP8LaR_",
+        "pycharm": {
+          "name": "#%% md\n"
+        }
+      },
+      "source": [
+        "## Part1 - writing files"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "NDIaKYRcLfz1",
+        "pycharm": {
+          "name": "#%% md\n"
+        }
+      },
+      "source": [
+        "\n",
+        "\n",
+        "---\n",
+        "1.1) Read the file AtCol0_Exons.fasta and write all headers (starting with '>') into a new file!\n",
+        "\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 1,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Mounted at /content/drive\n"
+          ]
+        }
+      ],
+      "source": [
+        "from google.colab import drive\n",
+        "drive.mount('/content/drive')\n",
+        "\n",
+        "with open(\"/content/drive/MyDrive/ColabNotebooks/UniPythonCourse/Exercises/data/AtCol0_Exons.fasta\", 'r') as exons:\n",
+        "    with open(\"/content/drive/MyDrive/ColabNotebooks/UniPythonCourse/Exercises/data/Header_AtCol0_Exons.txt\", 'w') as new_file:\n",
+        "        line = exons.readline()\n",
+        "        while line:\n",
+        "            if line[0] == '>':\n",
+        "                new_file.write(line)\n",
+        "            line = exons.readline()"
+      ],
+      "metadata": {
+        "pycharm": {
+          "name": "#%%\n"
+        },
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "9OMVwvZLzW9A",
+        "outputId": "36f854a7-f0f2-4472-f3e5-081fad69ebe9"
+      }
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "\n",
+        "\n",
+        "---\n",
+        "1.2) Read the file AtCol0_Exons.fasta and write the following:\n",
+        "* Line if it is a header\n",
+        "* Length of line if it is a sequence line\n"
+      ],
+      "metadata": {
+        "collapsed": false,
+        "pycharm": {
+          "name": "#%% md\n"
+        },
+        "id": "4S2i2BAjzW9B"
+      }
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 2,
+      "outputs": [],
+      "source": [
+        "with open(\"/content/drive/MyDrive/ColabNotebooks/UniPythonCourse/Exercises/data/AtCol0_Exons.fasta\", 'r') as exons:\n",
+        "    with open(\"/content/drive/MyDrive/ColabNotebooks/UniPythonCourse/Exercises/data/Summary_AtCol0_Exons.txt\", 'w') as new_file:\n",
+        "        line = exons.readline()\n",
+        "        while line:\n",
+        "            if line[0] == '>':\n",
+        "                new_file.write(line)\n",
+        "            else:\n",
+        "                new_file.write(str(len(line.strip())) + \"\\n\")\n",
+        "            line = exons.readline()"
+      ],
+      "metadata": {
+        "pycharm": {
+          "name": "#%%\n"
+        },
+        "id": "WRHfLJuJzW9C"
+      }
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "\n",
+        "\n",
+        "---\n",
+        "1.3) Calculate the number of sequences, the cumulative length and the average length in a new file! Are they matching the values of the original file?\n"
+      ],
+      "metadata": {
+        "collapsed": false,
+        "pycharm": {
+          "name": "#%% md\n"
+        },
+        "id": "2Uy9-PtVzW9C"
+      }
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 3,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Number of sequences: 217183\n",
+            "Cumulative length: 64867051 bases\n",
+            "Average sequence length: 298.67462462531597 bases\n"
+          ]
+        }
+      ],
+      "source": [
+        "def summarize_seq_info(summary_file):\n",
+        "    with open(summary_file, 'r') as summary:\n",
+        "        seq_count = 0\n",
+        "        cum_len = 0\n",
+        "        line = summary.readline()\n",
+        "        while line:\n",
+        "            if line[0] == '>':\n",
+        "                seq_count += 1\n",
+        "            else:\n",
+        "                cum_len += int(line.strip())\n",
+        "            line = summary.readline()\n",
+        "        print(\"Number of sequences:\", seq_count)\n",
+        "        print(\"Cumulative length:\", cum_len, \"bases\")\n",
+        "        print(\"Average sequence length:\", cum_len / seq_count, \"bases\")\n",
+        "\n",
+        "summarize_seq_info(\"/content/drive/MyDrive/ColabNotebooks/UniPythonCourse/Exercises/data/Summary_AtCol0_Exons.txt\")"
+      ],
+      "metadata": {
+        "pycharm": {
+          "name": "#%%\n"
+        },
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "V5s-M0dSzW9D",
+        "outputId": "212fadb1-dbbc-4929-e53e-d41426830418"
+      }
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "\n",
+        "\n",
+        "---\n",
+        "1.4) Write sequences into a new file if their length is a multiple of 10!\n"
+      ],
+      "metadata": {
+        "collapsed": false,
+        "pycharm": {
+          "name": "#%% md\n"
+        },
+        "id": "KuS83FpyzW9E"
+      }
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 4,
+      "outputs": [],
+      "source": [
+        "def seq_lens_multiple_of_10(fasta_file):\n",
+        "  with open(fasta_file, 'r') as fasta_input:\n",
+        "    with open(\"/content/drive/MyDrive/ColabNotebooks/UniPythonCourse/Exercises/data/AtCol0_mult10.txt\", 'w') as out:\n",
+        "      cum_len = 0\n",
+        "      sequence = \"\"\n",
+        "      line = fasta_input.readline()\n",
+        "      while line:\n",
+        "        if line[0] == '>':    # Reading the next header\n",
+        "          if cum_len % 10 == 0:   # Check if the length is a multiple of 10\n",
+        "              out.write(sequence + '\\n')\n",
+        "          cum_len = 0   # Reset the sequence length and the sequence as we are in the next sequence now\n",
+        "          sequence = \"\"\n",
+        "        else:\n",
+        "          sequence += line.strip()    # Append the sequence to the current one as long as no other header is in between\n",
+        "          cum_len += len(line.strip())    # Update the cumulative length for this sequence\n",
+        "        line = fasta_input.readline()\n",
+        "\n",
+        "seq_lens_multiple_of_10(\"/content/drive/MyDrive/ColabNotebooks/UniPythonCourse/Exercises/data/AtCol0_Exons.fasta\")"
+      ],
+      "metadata": {
+        "pycharm": {
+          "name": "#%%\n"
+        },
+        "id": "m2FZHcpmzW9G"
+      }
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "## Part2 - characters"
+      ],
+      "metadata": {
+        "collapsed": false,
+        "pycharm": {
+          "name": "#%% md\n"
+        },
+        "id": "HAzJAcOAzW9I"
+      }
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "\n",
+        "\n",
+        "---\n",
+        "2.1) Read the file AtCol0_Exons.fasta and write the following:\n",
+        "*   Only Arabidopsis Gene Identifier (e.g. AT1G01010)\n",
+        "*   Gene Identifier, exon name, exon length (tab-delimited)\n",
+        "\n",
+        "\n"
+      ],
+      "metadata": {
+        "collapsed": false,
+        "pycharm": {
+          "name": "#%% md\n"
+        },
+        "id": "hUOOeTCUzW9I"
+      }
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 11,
+      "outputs": [],
+      "source": [
+        "import re\n",
+        "\n",
+        "def arabidopsis_only(fasta_file):\n",
+        "  with open(fasta_file, 'r') as summary:\n",
+        "    with open(\"/content/drive/MyDrive/ColabNotebooks/UniPythonCourse/Exercises/data/Arabidopsis_Exons.txt\", 'w') as arabidopsis:\n",
+        "      line = summary.readline()\n",
+        "      while line:\n",
+        "        if line.startswith('>AT'):\n",
+        "          columns = line.split('|')\n",
+        "          gene_identifier = columns[0].strip('>').split('.')[0]\n",
+        "          if gene_identifier in re.findall(\"AT\\dG\\d{5}\", gene_identifier):\n",
+        "            exon_name = columns[1].strip()\n",
+        "            exon_length = columns[3].strip().split(' ')[2]\n",
+        "            arabidopsis.write(gene_identifier + '\\t' + exon_name + '\\t' + exon_length + '\\n')\n",
+        "        line = summary.readline()\n",
+        "\n",
+        "arabidopsis_only(\"/content/drive/MyDrive/ColabNotebooks/UniPythonCourse/Exercises/data/AtCol0_Exons.fasta\")"
+      ],
+      "metadata": {
+        "pycharm": {
+          "name": "#%%\n"
+        },
+        "id": "YStsUutUzW9I"
+      }
+    }
+  ]
+}
\ No newline at end of file