Machine Learning Challenges in Location Proteomics

1
Machine Learning Challenges in Location Proteomics

• Robert F. Murphy
• Departments of Biological Sciences and Biomedical
  Engineering
• Center for Automated Learning and Discovery
• Carnegie Mellon University

2
Protein characteristics relevant to systems
approach

• sequence
• structure
• expression level
• activity
• partners

• location

3
Subcellular locations from major protein databases

• Giantin
• Entrez /note"a new 376kD Golgi complex outher
  membrane protein"
• SwissProt INTEGRAL MEMBRANE PROTEIN. GOLGI
  MEMBRANE.
• GPP130
• Entrez /note"GPP130 type II Golgi membrane
  protein
• SwissProt nothing

4
More questions than answers

• We learned that Giantin and GPP130 are both Golgi
  proteins, but do we know
• What part (i.e., cis, medial, trans) of the Golgi
  complex they each are found in?
• If they have the same subcellular distribution?
• If they also are found in other compartments?

5
Vocabulary is part of the problem

• Different investigators may use different terms
  to refer to the same pattern or the same term to
  refer to different patterns
• Efforts to create restricted vocabularies (e.g.,
  Gene Ontology consortium) for location have been
  made

6
SWALL entries for giantin and gpp130

• ID GIAN_HUMAN STANDARD PRT 3259 AA.
• AC Q14789 Q14398
• GN GOLGB1.
• DR GO GO0000139 CGolgi membrane TAS.
• DR GO GO0005795 CGolgi stack TAS.
• DR GO GO0016021 Cintegral to membrane TAS.
• DR GO GO0007030 PGolgi organization and
  biogenesis TAS.
• ID O00461 PRELIMINARY PRT 696 AA.
• AC O00461
• GN GPP130.
• DR GO GO0005810 Cendocytotic transport
  vesicle TAS.
• DR GO GO0005801 CGolgi cis-face TAS.
• DR GO GO0005796 CGolgi lumen TAS.
• DR GO GO0016021 Cintegral to membrane TAS.

7
Words are not enough

• Still dont know how similar the locations
  patterns of these proteins are
• Restricted vocabularies do not provide the
  necessary complexity and specificity

8
Needed Systematic Approach

• Need to advance past cartoon view of
  subcellular location
• Need systematic, quantitative approach to protein
  location

• Need new methods for accurately and objectively
  determining the subcellular location pattern of
  all proteins
• Distinct from drug screening by low-resolution
  microscopy

9
First Decision Point

• Classification by direct (pixel-by-pixel)
  comparison of individual images to known patterns
  is not useful, since
• different cells have different shapes, sizes,
  orientations
• organelles within cells are not found in fixed
  locations

• Therefore, use feature-based methods rather than
  (pixel) model-based methods

10
Input Images

• Created 2D image database for HeLa cells
• Ten classes covering all major subcellular
  structures Golgi, ER, mitochondria, lysosomes,
  endosomes, nuclei, nucleoli, microfilaments,
  microtubules
• Included classes that are similar to each other

11
Example 2D Images of HeLa
12
Features SLF

• Developed sets of Subcellular Location Features
  (SLF) containing features of different types
• Motivated in part by descriptions used by
  biologists (e.g., punctate, perinuclear)
• First type of features derived from morphological
  image processing - finding objects by automated
  thresholding

13
Features Morphological

• Number of fluorescent objects per cell
• Variance of the object sizes
• Ratio of the largest object to the smallest
• Average distance of objects to the center of
  fluorescence
• Average roundness of objects

14
Features Haralick texture

• Give information on correlations in intensity
  between adjacent pixels to answer questions like
• is the pattern more like a checkerboard or
  alternating stripes?
• is the pattern highly organized (ordered) or more
  scattered (disordered)?

15
Example Difference detected by texture feature
entropy
16
Features Zernike moment

• Measure degree to which pattern matches a
  particular Zernike polynomial
• Give information on basic nature of pattern
  (e.g., circle, donut) and sizes (frequencies)
  present in pattern

17
Examples of Zernike Polynomials
Z(2,0)
Z(4,4)
Z(10,6)
18
Subcellular Location Features 2D

• Morphological features
• Haralick texture features
• Zernike moment features
• Geometric features
• Edge features

19
2D Classification Results
True Class Output of the Classifier Output of the Classifier Output of the Classifier Output of the Classifier Output of the Classifier Output of the Classifier Output of the Classifier Output of the Classifier Output of the Classifier Output of the Classifier
True Class DNA ER Gia Gpp Lam Mit Nuc Act TfR Tub
DNA 99 1 0 0 0 0 0 0 0 0
ER 0 97 0 0 0 2 0 0 0 1
Gia 0 0 91 7 0 0 0 0 2 0
Gpp 0 0 14 82 0 0 2 0 1 0
Lam 0 0 1 0 88 1 0 0 10 0
Mit 0 3 0 0 0 92 0 0 3 3
Nuc 0 0 0 0 0 0 99 0 1 0
Act 0 0 0 0 0 0 0 100 0 0
TfR 0 1 0 0 12 2 0 1 81 2
Tub 1 2 0 0 0 1 0 0 1 95
Overall accuracy 92 (95 for major patterns)
20
Human Classification Results
Overall accuracy 83 (92 for major patterns)
21
Computer vs. Human
22
Extending to 3D Labeling approach

• Total protein labeled with Cy5 reactive dye
• DNA labeled with PI
• Specific Proteins labeled with primary Ab
  Alexa488 conjugated secondary Ab

23
3D Image Set
Giantin
Nuclear
ER
Lysosomal
gpp130
Actin
Mitoch.
Nucleolar
Tubulin
Endosomal
24
New features to measure z asymmetry

• 2D features treated x and y equivalently
• For 3D images, while it makes sense to treat x
  and y equivalently (cells dont have a left and
  right, z should be treated differently (top
  and bottom are not the same)
• We designed features to separate distance
  measures into x-y component and z component

25
Classification Results for 3D images
Overall accuracy 97
26
How to do even better

• Biologists interpreting images of protein
  localization typically view many cells before
  reaching a conclusion
• Can simulate this by classifying sets of cells
  from the same microscope slide

27
Classification of Sets of 3D Images
Set size 9, Overall accuracy 99.7
28
First Conclusion

• Description of subcellular locations for systems
  biology should be implemented using a data-driven
  approach rather than a knowledge-capture
  approach, but

29
Subcellular Location Image Finder

• (Have automated system for finding images in
  on-line journal articles that match a particular
  pattern - enables connection between new images
  and previously published results)

30
Image Similarity

• Classification power of features implies that
  they capture essential characteristics of protein
  patterns
• Can be used to measure similarity between patterns

31
Clustering by Image Similarity

• Ability to measure similarity of protein patterns
  allows us for the first time to create a
  systematic, objective, framework for describing
  subcellular locations
• Ideal for database references
• One way is by creating a Subcellular Location
  Tree
• Illustration Build hierarchical dendrogram

32
Subcellular Location Tree for 10 classes in HeLa
cells
33
Do this for all proteins Location Proteomics

• Can use CD-tagging (developed by Dr. Jonathan
  Jarvik) to randomly tag many proteins Infect
  population of cells with a retrovirus carrying a
  DNA sequence that will produce a tag in a
  random gene in each cell
• Isolate separate clones, each of which produces
  express one tagged protein
• Use RT-PCR to identify tagged gene in each clone
• Collect images of many cells for each clone using
  fluorescence microscopy

34
Example images of CD-tagged clones

1. Glut1 gene (type 1 glucose transporter)
2. Tmpo gene (thymopoietin ??
3. tuba1 gene (?-tubulin)
4. Cald gene (caldesmon 1)
5. Ncl gene (nucleolin)
6. Rps11 gene (ribosomal protein S11)
7. Hmga1 gene (high mobility group AT-hook 1)
8. Col1a2 gene (procollagen type I ?2)
9. Atp5a1 gene (ATP synthase isoform 1)

35
Proof of principle

• Cluster 46 clones expressing different tagged
  proteins based on their subcellular location
  patterns

36
Feature selection

• Use Stepwise Discriminant Analysis to rank
  features based on their ability to distinguish
  proteins
• Use increasing numbers of features to train
  neural network classifiers and evaluate
  classification accuracy over all 46 clones
• Best performance obtained with 10 features

37
Tree building

• Therefore use these 10 features with z-scored
  Euclidean distance function to build SLT
• Find optimal number of clusters using k-means
  clustering and AIC
• Find consensus hierarchical trees by randomly
  dividing the images for each protein in half and
  keeping branches conserved between both halves
  (repeat for 50 random divisions)

38
Consensus Subcellular Location Tree
39
Examples from major clusters
40
Significance

• Proteins clustered by location analogous to
  proteins clustered by sequence (e.g., PFAM)
• Can subdivide clusters by observing response to
  drugs, oncogenes, etc.
• These represent protein location states
• Base knowledge required for modeling
• Can be used to filter protein interactions

41
From patterns to causes

• Machine learning approaches have been previously
  used to find localization motifs in protein
  sequences, but the set of locations used was
  limited to major organelles
• High-resolution subcellular location trees can be
  used to discover (recursively) new motifs that
  determine location of each group
• Can include post-translational modifications

42
More Conclusions

• Organized data collection approach is required to
  capture high-resolution information on the
  subcellular location of all proteins
• Prohibitive combinatorial complexity make
  colocalization approach infeasible, so major
  effort should focus on one protein at a time

43
Center for Bioimage Informatics

• 2.75 M CMU funding from NSF ITR
• Joint with UCSB and collaborators at Berkeley and
  MIT
• R. Murphy (CALD/Biomed.Eng./Biol.Sci.)
• Jelena Kovacevic (Biomedical Engineering)
• Tom Mitchell (CALD)
• Christos Faloutsos (CALD)

44
Acknowledgments

• Former students
• Michael Boland, Mia Markey, William Dirks,
  Gregory Porreca, Edward Roques, Meel Velliste
• Current grad students
• Kai Huang, Xiang Chen, Ting Zhao, Yanhua Hu,
  Elvira Garcia Osuna, Zhenzhen Kou, Juchang Hua
• Funding
• NSF, NIH, Rockefeller Bros. Fund, PA. Tobacco
  Settlement Fund
• Collaborators/Consultants
• Simon Watkins, David Cassasent, Tom Mitchell,
  Christos Faloutsos, Jon Jarvik, Peter Berget