{
  "annotation_id": "315d4637-12ae-4480-83e7-2f53d61f3516",
  "date_created": "2026-03-02T18:01:32.323000Z",
  "date_modified": "2026-03-02T18:01:32.323000Z",
  "file_hash": "f7630ee02b84df336e9b1af6c598584b38b61d3eaa6c4a05bbde97e3e871a961",
  "private": false,
  "record": {
    "abstract": "The presence of neighbor dependencies generated a specific pattern of\ndinucleotide frequencies in all organisms. Especially, the\nCpG-methylation-deamination process is the predominant substitution process in\nvertebrates and needs to be incorporated into a more realistic model for\nnucleotide substitutions. Based on a general framework of nucleotide\nsubstitutions we develop a method that is able to identify the most relevant\nneighbor dependent substitution processes, measure their strength, and judge\ntheir importance to be included into the modeling. Starting from a model for\nneighbor independent nucleotide substitution we successively add neighbor\ndependent substitution processes in the order of their ability to increase the\nlikelihood of the model describing given data. The analysis of neighbor\ndependent nucleotide substitutions in human, zebrafish and fruit fly is\npresented. A web server to perform the presented analysis is publicly\navailable.",
    "arxiv_id": "q-bio/0501018",
    "authors": [
      "Peter F. Arndt",
      "Terence Hwa"
    ],
    "categories": [
      "q-bio.GN"
    ],
    "title": "Identification and Measurement of Neighbor Dependent Nucleotide   Substitution Processes",
    "url": "https://arxiv.org/abs/q-bio/0501018"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "33953928-eeef-452b-bcce-c116a67c7b8b",
    "id": "arXiv Dataset IDs",
    "type": "Model",
    "variant": "snapshot-2026-03-01",
    "version": "0.1.0"
  },
  "user_id": 1000002
}