renaud / neuroNER

named entity recognizer for neuronal cells, based on UIMA Ruta rules
GNU Lesser General Public License v3.0
7 stars 8 forks source link

issue with identifying protein names #34

Closed stripathy closed 9 years ago

stripathy commented 9 years ago

Given the following .obo for a protein:

id: NCBI_GENE:14811
name: Grin2a
synonym: "Glutamate receptor ionotropic, NMDA 2A" RELATED ADJECTIVE []
synonym: "NR2A" RELATED ADJECTIVE []
synonym: "Glutamate [NMDA] receptor subunit epsilon-1" RELATED ADJECTIVE []
synonym: "GluN2A" RELATED ADJECTIVE []
synonym: "Grin2a" RELATED ADJECTIVE []
synonym: "N-methyl D-aspartate receptor subtype 2A" RELATED ADJECTIVE []
synonym: "NMDAR2A" RELATED ADJECTIVE []
synonym: "Glutamate [NMDA] receptor subunit ε-1" RELATED ADJECTIVE []

The query: 'Grin2a-expressing neuron' does not have a ProteinProp: [(18, 24, 'neuron', u'Neuron', {}), (18, 24, 'neuron', u'NeuronTrigger', {}), (7, 17, 'expressing', u'ProteinTrigger', {})]

but 'NMDAR2A-expressing neuron' has a ProteinProp: [(0, 25, 'NMDAR2A-expressing neuron', u'Neuron', {}), (19, 25, 'neuron', u'Neuron', {}), (8, 18, 'expressing', u'ProteinTrigger', {}), (0, 18, 'NMDAR2A-expressing', u'PreNeuron', {}), (0, 18, 'NMDAR2A-expressing', u'ProteinProp', {u'ontologyId': u'NCBI_GENE:14811'}), (19, 25, 'neuron', u'NeuronTrigger', {})]

but 'GluN2A-expressing neuron' doesn't have a ProteinProp but has a NeurotransmitterProp: [(0, 3, 'Glu', u'NeurotransmitterProp', {u'ontologyId': u'HBP_NEUROTRANSMITTER:0000004'}), (18, 24, 'neuron', u'Neuron', {}), (18, 24, 'neuron', u'NeuronTrigger', {}), (7, 17, 'expressing', u'ProteinTrigger', {})]

renaud commented 9 years ago

I'm on it, I think I found an issue in Ruta and fixed it yesterday

renaud commented 9 years ago

i created a test with Grin2a-expressing neuron space NMDAR2A-expressing neuron space GluN2A-expressing neuron

{
  "ProteinProp": [
    {
      "begin": 0,
      "end": 17,
      "properties": {
        "ontologyId": "NCBI_GENE:14811"
      }
    },
    {
      "begin": 31,
      "end": 49,
      "properties": {
        "ontologyId": "NCBI_GENE:14811"
      }
    },
    {
      "begin": 63,
      "end": 80,
      "properties": {
        "ontologyId": "NCBI_GENE:14811"
      }
    }
  ],
  "Neuron": [
    {
      "begin": 0,
      "end": 24
    },
    {
      "begin": 31,
      "end": 56
    },
    {
      "begin": 63,
      "end": 87
    }
  ]
}