Gene Classification: Issues and Challenges for Relational Learning Claudia Perlich

1
Gene Classification Issues and Challenges for
Relational LearningClaudia Perlich Srujana
MeruguIBM T.J. Watson Research CenterPresented
by Srujana Merugu
2
Outline

• Objectives
• Problem and Domain Description
• Challenges for Relational Learning
• Potential Solutions using ACORA
• Experimental Results

3
Objectives

• Demonstrate that statistical relational learning
  approaches are suitable for gene-classification
• Motivate the relational learning community to use
  this domain for benchmarking
• Highlight the current limitations of relational
  learning techniques with regard to expressive
  power and motivate further developments

4
Problem Description (ILP Challenge 2005)

• Task Functional annotation of the yeast genome
• Training data
• Functional annotations (class labels) for
  partial set of genes
• Secondary protein structure of each gene
• Intra-gene homology
• Protein-gene homology and protein features

5
Functional Annotations (FunCat Hierarchy)

• FunCat hierarchy - forest of multiple class
  trees
• More than 400 classes
• Each gene can have multiple classes
• 4000 labeled examples and 674 unlabeled

6
Secondary Protein Structure (PROF Predictions)
Protein Sequence
caaaaaaaaaaaaaaaaaaaacccbbbbbcccccccccccaaa
a Alpha helix b Beta sheet c Random coil

• Each gene is associated with a single protein
• Homogeneous components are encoded as multiple
  records

7
Intra-Gene Homology (BLAST Scores)
w15

• Scores probability of match being found by
  chance
• Score lt 1e-6 gt significant match
• 100000 gene homology pairs with highly skewed
  degree distribution
• Missing pairs correspond to unknown scores

8
Protein-Gene Homology and Protein Features

• Yeast-SwissProt homology scores similar to the
  intra-gene scores
• 45000 proteins and 3700000 gene-protein pairs
  with highly skewed degree distribution

9

Summary of Data Components

• Functional Annotations (FunCat)
• Predicted Secondary Structure (PROF)
• Intra-Gene homology (BLAST scores)
• Protein homology (SwissProt database) protein
  features

10
Suitability for Benchmarking

• Highly structured information that is
  intrinsically relational
• Important scientific problem with limited
  predictability so far
• Real-life data that require handling noise and
  sparsity
• Reasonable data set size requiring scalable
  techniques

11
Challenging Data Characteristics

• Weighted Links
• Homology scores do not correspond to the
  uncertainty in relationship
• Sparse data (missing links)
• Missing pairs in homology tables need to be
  treated as links with unknown weights
• Ordered data
• Representing secondary protein structure using
  the order, component and length features
  results in highly dependent features
• Multiple class labels
• Classification problem needs to be posed as
  multiple one vs. all problems Interpretation of
  hierarchy is also important

12
Propositionalization

• Transformation
• Exploration- finding related entities using joins
• Aggregation- constructing features, e.g., mean,
  mode
• Model Estimation
• Logistic regression, Decision trees, Naïve Bayes,
  SVM, etc.
• Require each entity to be feature vector
  (x1,x2,,xn ,class)

13
ACORA Automatic Construction of Relational
Attributes

• Explores using breadth first search over all
  joins on identifier attributes starting from
  target table
• Joins back to target (class) table to create
  attributes based on class labels of related
  objects
• Aggregation
• Traditional aggregates mean, median, mode
• Bayesian aggregates for categorical attributes
  distances to class-conditional distributions,
  counts of discriminative values

14
Assumptions Violations

• Co-occurrence in tables ? existence of
  relationship
• Missing pairs in homology table - unknown scores
  and scores do not also reflect uncertainty in
  relationship
• Further joins with protein features are also
  affected by homology scores
• Bags of related objects are random samples
  (i.i.d.)
• Homogenous components of a single protein
  sequence are not i.i.d.
• Class-conditional independence between attributes
• Protein sequence representation
  (order,component,length) and homology
  information (gene/protein id, score) both involve
  dependent attributes

Most relational learners (including ACORA)
require the above assumptions
15
Potential Solutions

• Parameterize the learner to allow the user to
  specify the search space (e.g., Declarative
  Language Bias )
• Change assumptions of relational learner to match
  domain properties (e.g., PolyFarm)
• Change domain representation to match the
  assumptions of the relational learner

16
Protein Structure Representation
Two choices 1. Counts of sub-sequences
disregarding length 2. Counts of sub-sequences
augmented with log length
17
Homology Representation

• Three choices
• Stochastic aggregation Use score as probability
  to weight evidence
• Subset Keep only the n (n10-50) closest objects
  for each gene
• Subset with Cutoff Discard all links with a
  score above a threshold (1e-6)

18
Experimental Methodology

• Classification problem Class 20 (cellular
  transport) vs. rest prior 0.767
• Training using 3000 genes, testing on 1000
  holdout genes
• ACORA settings using all aggregation operators
  and logistic classification models
• Evaluation metrics Accuracy AUC

19
Classification Performance
a) Naïve aggregation
c) Adjusted protein structure
b) Adjusted homology scores
20
Conclusion

• Gene classification task highlights some
  important limitations of existing relational
  learning methods
• handling ordered sequences, weighted and missing
  links
• common to other domains e.g., time series
  analysis
• ACORA with modified domain representation results
  in better predictions as compared to naïve
  aggregation
• Yeast genome is a good benchmark dataset for
  further exploration and empirical analysis

21
Thank You !
?
22
Performance on 10 Most Common Classes
Large variation in class priors and performance
across classes
23
Joining back to the class

• Make features for the known class labels of
  similar genes
• Ratio of binary class
• Treat it as just another attribute (but ignore
  your own label)

24
Exploration Graph Traversal
25
Aggregation

• ytq0045

• Typical aggregation
• COUNT7
• MEAN(Length)572
• MEAN(Weight)63806
• MODE(Category)chondrus

(7,572,63806,chondrus,class)
(x1,x2,,xn ,class)
26
Aggregating Categorical Attributes

• MODE is often not appropriate for aggregation of
  categorical attributes
• Large loss of information
• Not defined for unique attributes such as
  identifiers
• Known problem text classification
• Naïve Bayes approach
• Class-conditional distributions

27
Bayesian aggregates
1 Class-conditional distributions
2 Case vectors
?
4 Extended feature vector
3 Cosine distances for P1 Cosine(G1, DClass
1) 0.316 Cosine(G1, DClass 0) 0.97