{
  "annotation_id": "b922461c-cad7-4ea8-ae02-8d2409080bfa",
  "date_created": "2026-03-02T18:01:31.929000Z",
  "date_modified": "2026-03-02T18:01:31.929000Z",
  "file_hash": "ebe416a42c5fc2aac26f0c9b5190f3e7e32630296da1f718781ff0fbc544ab89",
  "private": false,
  "record": {
    "abstract": "We introduce a new heuristic for the multiple alignment of a set of\nsequences. The heuristic is based on a set cover of the residue alphabet of the\nsequences, and also on the determination of a significant set of blocks\ncomprising subsequences of the sequences to be aligned. These blocks are\nobtained with the aid of a new data structure, called a suffix-set tree, which\nis constructed from the input sequences with the guidance of the\nresidue-alphabet set cover and generalizes the well-known suffix tree of the\nsequence set. We provide performance results on selected BAliBASE amino-acid\nsequences and compare them with those yielded by some prominent approaches.",
    "arxiv_id": "q-bio/0412021",
    "authors": [
      "A. H. L. Porto",
      "V. C. Barbosa"
    ],
    "categories": [
      "q-bio.QM"
    ],
    "doi": "10.1007/11732242_12",
    "journal_ref": "Lecture Notes in Computer Science 3907 (2006), 127-137",
    "title": "Multiple sequence alignment based on set covers",
    "url": "https://arxiv.org/abs/q-bio/0412021"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "cd2ecbbf-8f9f-4b4d-9535-53560381eae7",
    "id": "arXiv Dataset IDs",
    "type": "Model",
    "variant": "snapshot-2026-03-01",
    "version": "0.1.0"
  },
  "user_id": 1000002
}