Predicting Homologous
Signaling Pathways Using Machine Learning
Babak Bostan, Russell Greiner, Duane Szafron and Paul Lu
Bioinformatics 2009; doi:
10.1093/bioinformatics/btp532
Abstract:
Motivation: In general, each cell signaling pathway involves many
proteins, each with one or more specific roles. As they are essential components
of cell activity, it is important to understand how these proteins work - and
in particular, to determine which of a species' proteins participate in each
role. Experimentally determining this mapping of proteins to roles is difficult
and time consuming. Fortunately, many pathways are similar across species, so
we may be able to use known pathway information of one species to understand
the corresponding pathway of another.
Results: We present an automatic approach, Predict Signaling Pathway
(PSP), that uses the signaling pathways in well-studied species to predict the
roles of proteins in less-studied species. We use a machine learning approach
to create a predictor that achieves a generalization F-measure of 78.2% when
applied to 11 different pathways across 14 different species. We also show our
approach is very effective in predicting the pathways that have not yet been
experimentally studied completely.
Training datasets:
á
Homo sapiens (human) (gene list, pathways
(MAPK,
ErbB,
Wnt,
Notch,
Hedgehog,
TGF-beta,
VEGF,
Jak-STAT,
Calcium,
Phosphatidylinositol,
mTOR)
)
á
Pan troglodytes
(chimpanzee) (gene list, pathways
(MAPK,
ErbB,
Wnt,
Notch,
Hedgehog,
TGF-beta,
VEGF,
Jak-STAT,
Calcium,
Phosphatidylinositol,
mTOR)
)
á
Macaca mulatta (monkey) (gene list, pathways
(MAPK,
ErbB,
Wnt,
Notch,
Hedgehog,
TGF-beta,
VEGF,
Jak-STAT,
Calcium,
Phosphatidylinositol,
mTOR)
)
á
Mus musculus (mouse) (gene list, pathways
(MAPK,
ErbB,
Wnt,
Notch,
Hedgehog,
TGF-beta,
VEGF,
Jak-STAT,
Calcium,
Phosphatidylinositol,
mTOR)
)
á
Rattus norvegicus (rat) (gene list, pathways
(MAPK,
ErbB,
Wnt,
Notch,
Hedgehog,
TGF-beta,
VEGF,
Jak-STAT,
Calcium,
Phosphatidylinositol,
mTOR)
)
á
Canis familiaris (dog) (gene list, pathways
(MAPK,
ErbB,
Wnt,
Notch,
Hedgehog,
TGF-beta,
VEGF,
Jak-STAT,
Calcium,
Phosphatidylinositol,
mTOR)
)
á
Bos taurus (cow) (gene list, pathways
(MAPK,
ErbB,
Wnt,
Notch,
Hedgehog,
TGF-beta,
VEGF,
Jak-STAT,
Calcium,
Phosphatidylinositol,
mTOR)
)
á
Sus scrofa (pig) (gene list, pathways
(MAPK,
ErbB,
Wnt,
Notch,
Hedgehog,
TGF-beta,
VEGF,
Jak-STAT,
Calcium,
Phosphatidylinositol,
mTOR)
)
á
Monodelphis domestica
(opossum) (gene
list, pathways
(MAPK,
ErbB,
Wnt,
Notch,
Hedgehog,
TGF-beta,
VEGF,
Jak-STAT,
Calcium,
Phosphatidylinositol,
mTOR)
)
á
Ornithorhynchus anatinus
(platypus) (gene
list, pathways
(MAPK,
ErbB,
Wnt,
Notch,
Hedgehog,
TGF-beta,
VEGF,
Jak-STAT,
Calcium,
Phosphatidylinositol,
mTOR)
)
á
Gallus sallus (chicken) (gene list, pathways
(MAPK,
ErbB,
Wnt,
Notch,
Hedgehog,
TGF-beta,
VEGF,
Jak-STAT,
Calcium,
Phosphatidylinositol,
mTOR)
)
á
Xenopus laevis (African
clawed frog) (gene
list, pathways
(MAPK,
ErbB,
Wnt,
Notch,
Hedgehog,
TGF-beta,
VEGF,
Jak-STAT,
Calcium,
Phosphatidylinositol,
mTOR)
)
á
Xenopus tropicalis
(western clawed frog) (gene list, pathways
(MAPK,
ErbB,
Wnt,
Notch,
Hedgehog,
TGF-beta,
VEGF,
Jak-STAT,
Calcium,
Phosphatidylinositol,
mTOR)
)
á
Danio rerio (zegrafish) (gene list, pathways
(MAPK,
ErbB,
Wnt,
Notch,
Hedgehog,
TGF-beta,
VEGF,
Jak-STAT,
Calcium,
Phosphatidylinositol,
mTOR)
)
Prediction output: