Customizing Gene Taggers for BeeSpace

1
Customizing Gene Taggersfor BeeSpace

• Jing Jiang
• jiang4_at_uiuc.edu
• March 9, 2005

2
Entity Recognition in BeeSpace

• Types of entities we are interested in
• Genes
• Sequences
• Proteins
• Organisms
• Behaviors
• Currently, we focus on genes

3
Input and Output

• Input free text (w/ simple XML tags)
• lt?xml version1.0 encodingUTF-8gtltDocument
  id1gtWe have cloned and sequenced a cDNA
  encoding Apis mellifera ultraspiracle (AMUSP) and
  examined its responses to JH. lt/Documentgt
• Output tagged text (XML format)
• lt?xml version1.0 encodingUTF-8gt ltDocument
  id1gt ltSentgtltNPgtWelt/NPgt have ltVPgtclonedlt/VPgt
  and ltVPgtsequencedlt/VPgt ltNPgta cDNA encoding
  ltGenegtApis mellifera ultraspiraclelt/GenegtltNPgt
  (ltGenegtAMUSPlt/Genegt) and ltVPgtexaminedlt/VPgt
  ltNPgtits responses to JHlt/NPgt.lt/Sentgtlt/Documentgt

4
Challenges

• No complete gene dictionary
• Many variations
• Acronyms hyperpolarization-activated ion channel
  (Amih)
• Synonyms octopamine receptor (oa1, oar, amoa1)
• Common English words at (arctops), by (3R-B)
• Different genes or gene and protein may share the
  same name/symbol

5
Automatic Gene RecognitionCharacteristics of
Gene Names

• Capitalization (especially acronyms)
• Numbers (gene families)
• Punctuation -, /, , etc.
• Context
• Local surrounding words such as gene,
  encoding, regulation, expressed, etc.
• Global same noun phrase occurs several times in
  the same article

6
Existing Tools

• KeX (Fukuda)
• Based on hand-crafted rules
• Recognizes proteins and other entities
• Human efforts, not easy to modify
• ABNER YAGI (Settles)
• Based on conditional random fields (CRFs) to
  learn the rules
• ABNER identifies and classifies different
  entities including proteins, DNAs, RNAs, cells
• YAGI recognizes genes and gene products
• No training

7
Existing Tools (cont.)

• LingPipe (Alias-i, Inc.)
• Uses a generative statistical model based on word
  trigrams and tag bigrams
• Can be trained
• Has two trained models
• Others
• NLProt (SVM)
• AbGene (rule-based)
• GeneTaggerCRF (CRFs)

8
Comparison of Existing Tools

• Performance on a few manually annotated, public
  data sets (protein names)
• GENIA (2000 abstracts on human blood cell
  transcription factor)
• Yapex (99 abstracts on protein binding
  interaction molecular)
• UTexas (750 abstracts on human)
• Performance on a honeybee sample data set
• Biosis search apis mellifera gene

9
Comparison of Existing Tools (cont.)
10
Comparison of Existing Tools (cont.)

• KeX on honeybee data
• False positives company name, country name, etc.
• Does not differentiate between genes, proteins,
  and other chemicals
• YAGI on honeybee data
• False negatives occurrences of the same gene
  name are not all tagged
• Entity types and boundary detection
• LingPipe on honeybee data
• Similar to YAGI

11
Lessons Learned

• Machine learning methods outperform hand-crafted
  rule-based system
• Machine learning methods have over-fitting
  problem
• Existing tools need to be customized for BeeSpace
• LingPipe is a good choice
• There is still room for better feature selection
• E.g., global context

12
Customization

• Train LingPipe on a better training data set
• Use fly (Drosophila) genes
• F1 increased from 0.2207 to 0.7226 on held-out
  fly data
• Tested on honeybee data results
• Some gene names are learned (Record 13)
• Some false positives are removed (proteins, RNAs)
• Some false positives are introduced
• The noisy training data can be further cleaned
• E.g., exclude common English words

13
Customization (cont.)

• Exploit more features such as global context
• Occurrences of the same word/phrase should be
  tagged all positive or all negative
• Differentiate between domain-independent features
  and domain-specific features
• E.g., prefix Am is domain-specific for Apis
  mellifera
• Features can be weighted based on their
  contribution across domains

14
Maximum Entropy Modelfor Gene Tagging

• Given an observation (a token or a noun phrase),
  together with its context, denoted as x
• Predict y ? gene, non-gene
• Maximum entropy model
• P(yx) K exp(??ifi(x, y))
• Typical f
• y gene candidate phrase starts with a capital
  letter
• y gene candidate phrase contains digits
• Estimate ?i with training data

15
Plan Customization with Feature Adaptation

• ?i trained on large set of data in domain A
  (e.g., human or fly)
• ?i trained on small set of data in domain B
  (e.g., bee)
• ?i ?i?i (1 - ?i)?i used for domain B
• ?i based on how useful fi is across different
  domains
• Large ?i if fi is domain-independent
• Small ?i if fi is domain-specific

16
Issues to Discuss

• Definition of gene names
• Gene families? (e.g., cb1 gene family)
• Entities with a gene name? (e.g., Ks-1
  transcripts)
• Difference between genes and proteins?
• E.g., CREB (cAMP response element binding
  protein) and AmCREB?
• How to evaluate the performance on honeybee data?

17
The End

• Questions?
• Thank You!