Solving the second degree neighbor problem with Python 3.10

fasta_graph.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "0e928ad0",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-01-28T23:33:19.195967Z",
     "start_time": "2022-01-28T23:33:19.053420Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      ">s1\r\n",
      "AAA\r\n",
      ">s2\r\n",
      "AAG\r\n",
      ">s3\r\n",
      "AGG\r\n",
      ">s4\r\n",
      "TTT\r\n"
     ]
    }
   ],
   "source": [
    "cat ~/Code/jessime/notebooks/sites.fa"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "b26a63da",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-01-28T23:35:00.772046Z",
     "start_time": "2022-01-28T23:35:00.764197Z"
    }
   },
   "outputs": [],
   "source": [
    "from collections import defaultdict\n",
    "from pathlib import Path\n",
    "from itertools import pairwise\n",
    "\n",
    "\n",
    "def get_sequences(input_fasta):\n",
    "    \"\"\"Returns sequences from a fasta formatted str.\"\"\"\n",
    "    return Path(input_fasta).read_text().splitlines()[1::2]\n",
    "\n",
    "\n",
    "def are_similar(seq1, seq2, limit=5):\n",
    "    \"\"\"Returns True if two sequences are similar above some threshold.\"\"\"\n",
    "    # prewritten\n",
    "    return sum(1 for c1, c2 in zip(seq1, seq2) if c1 == c2) >= limit\n",
    "\n",
    "\n",
    "def build_graph(seqs):\n",
    "    \"\"\"Returns a graph representing which sequences are similar to each other.\"\"\"\n",
    "    graph = defaultdict(set)\n",
    "    for seq1, seq2 in pairwise(seqs):\n",
    "        if are_similar(seq1, seq2, 2):\n",
    "            graph[seq1].add(seq2)\n",
    "            graph[seq2].add(seq1)\n",
    "    return graph\n",
    "\n",
    "\n",
    "def is_second_degree(graph, seq1, seq2):\n",
    "    \"\"\"Returns True if a sequences is a second degree neighbor to another sequence.\"\"\"\n",
    "    if any((seq1 not in graph, seq2 not in graph, seq2 in graph[seq1])):\n",
    "        return False\n",
    "    return bool(graph[seq1] & graph[seq2])\n",
    "\n",
    "\n",
    "def run(input_fasta, seq1, seq2):\n",
    "    seqs = get_sequences(input_fasta)\n",
    "    graph = build_graph(seqs)\n",
    "    return is_second_degree(graph, seq1, seq2)\n",
    "\n",
    "    \n",
    "assert run('sites.fa', \"AAA\", \"AGG\")\n",
    "assert run('sites.fa', \"AGG\", \"AAA\")\n",
    "assert not run('sites.fa', \"AAA\", \"AAG\")\n",
    "assert not run('sites.fa', \"AAG\", \"AGG\")\n",
    "assert not run('sites.fa', \"AAA\", \"TTT\")\n",
    "assert not run('sites.fa', \"HEY\", \"TTT\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9dea57b3",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "6f561ee6",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.10.0"
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": true,
   "sideBar": true,
   "skip_h1_title": false,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": false,
   "toc_position": {},
   "toc_section_display": true,
   "toc_window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}