laydi/workflows/go_workflow.py

import gtk
from fluents import dataset, logger, plots, workflow, fluents
import geneontology
#import gostat
from scipy import array, randn, log, ones, zeros
import networkx
import re

EVIDENCE_CODES=[('IMP', 'Inferred from mutant phenotype'),
                ('IGI', 'Inferred from genetic interaction'),
                ('IPI', 'Inferred from physical interaction'),
                ('ISS', 'Inferred from sequence or structure similarity'),
                ('IDA', 'Inferred from direct assay'),
                ('IEP', 'Inferred on expression pattern'),
                ('IEA', 'Inferred from electronic annotation'),
                ('TAS', 'Traceable author statement'),
                ('NAS', 'Non-traceable author statement'),
                ('ND', 'No biological data available'),
                ('RCA', 'Inferred from reviewed computational analysis'),
                ('IC', 'Inferred by curator')]
            
DISTANCE_METRICS = [('resnik', 'Resnik'), 
                    ('jiang', 'Jiang & Conrath'),
                    ('fussimeg', 'FuSSiMeG')]

GO_DATA_DIR = '/home/einarr/data'

evidence = None
go = None

class GoTermView (gtk.Frame):

    def __init__(self):
        gtk.Frame.__init__(self)
        tab = gtk.Table(2, 2, False)
        self._table = tab
        
        self._name = gtk.Label('')
        self._name.set_line_wrap(True)
        self._name.set_alignment(0, 0)
        name_label = gtk.Label('Name:')
        name_label.set_alignment(0, 0)
        tab.attach(name_label, 0, 1, 0, 1, gtk.FILL, gtk.FILL, 5, 5)
        tab.attach(self._name, 1, 2, 0, 1, gtk.FILL|gtk.EXPAND, gtk.FILL, 5, 5)
        
        self._def = gtk.TextBuffer()
        textview = gtk.TextView(self._def)
        textview.set_wrap_mode(gtk.WRAP_WORD)
        scrolled_window = gtk.ScrolledWindow()
        scrolled_window.add(textview)
        def_label = gtk.Label('Def:')
        def_label.set_alignment(0.0, 0.0)
        tab.attach(def_label, 0, 1, 1, 2, gtk.FILL, gtk.FILL, 5, 5)
        tab.attach(scrolled_window, 1, 2, 1, 2, gtk.FILL|gtk.EXPAND, gtk.FILL|gtk.EXPAND, 5, 5)
        
        self.add(tab)
        self.set_go_term(None)

    def set_go_term(self, term):
        if term:
            self.set_label(term['id'])
            self._name.set_text(term['name'])
            self._def.set_text(term['def'])
        else:
            self.set_label('GO Term')
            self._name.set_text('')
            self._def.set_text('')

        
class GeneOntologyTree (gtk.HPaned):
    
    def __init__(self, network):
        gtk.HPaned.__init__(self)
    
        treemodel = geneontology.get_go_treestore(network)
        self._treemodel = treemodel
        self._tree_view = gtk.TreeView(treemodel)

        renderer = gtk.CellRendererText()
        go_column = gtk.TreeViewColumn('GO ID', renderer, text=0)
        self._tree_view.insert_column(go_column, 0)

        renderer = gtk.CellRendererText()
        go_column = gtk.TreeViewColumn('Name', renderer, text=1)
        self._tree_view.insert_column(go_column, 1)

        self._desc_view = GoTermView()

        self._tree_view.connect('cursor-changed', self._on_cursor_changed)

        scrolled_window = gtk.ScrolledWindow()
        scrolled_window.add(self._tree_view)
        self.add1(scrolled_window)
        self.add2(self._desc_view)
        self.show_all()

    def _on_cursor_changed(self, tree):
        path, col = self._tree_view.get_cursor()
        current = self._treemodel.get_iter(path)
        term = self._treemodel.get_value(current, 2)
        self._desc_view.set_go_term(term)        
        

class GoWorkflow (workflow.Workflow):

    name = 'Gene Ontology'
    ident = 'go'
    description = 'Gene Ontology Workflow. For tree distance measures based '\
                + 'on the GO tree.'

    def __init__(self, app):
        workflow.Workflow.__init__(self, app)

        load = workflow.Stage('load', 'Load GO Annotations')
        load.add_function(LoadGOFunction())
        load.add_function(LoadAnnotationsFunction())
        load.add_function(LoadTextDatasetFunction())
        self.add_stage(load)
        
        go = workflow.Stage('go', 'Gene Ontology')
        go.add_function(SelectGoTermsFunction(self))
        go.add_function(GoDistanceFunction())
        go.add_function(SaveDistancesFunction())
        self.add_stage(go)

       
class LoadGOFunction(workflow.Function): 
    def __init__(self):
        workflow.Function.__init__(self, 'load-go', 'Load Gene Ontology')

    def run(self):
        global go
        go = geneontology.read_default_go()
        browser = GeneOntologyTree(go)
        label = gtk.Label('_Gene Ontology')
        label.set_use_underline(True)
        fluents.app['bottom_notebook'].append_page(browser, label)


class LoadTextDatasetFunction(workflow.Function):

    def __init__(self):
        workflow.Function.__init__(self, 'load-text-ds', 'Load GO Evidence')

    def run(self):
        f = open('/home/einarr/data/goa-condensed.ftsv')
        global evidence
        evidence = dataset.read_ftsv(f)
        return [evidence]


class LoadAnnotationsFunction(workflow.Function):

    def __init__(self):
        workflow.Function.__init__(self, 'load-go-ann', 'Load Annotations')
        self.annotations = None
    
    def run(self):
        global evidence
        f = open(GO_DATA_DIR + '/goa-condensed')
        ev_codes = f.readline().split()
        go_terms = []
    
        lines = f.readlines()
        m = zeros((len(lines), len(ev_codes)))

        for i, l in enumerate(lines):
            values = l.split()
            go_terms.append(values[0])
            for j, v in enumerate(values[1:]):
                m[i,j] = float(v.strip())
        
        d = dataset.Dataset(m, 
                            [['go-terms', go_terms], ['evidence', ev_codes]],
                            name='GO evidence')

        evidence = d
        return [d]
            

class EvidenceCodeFrame(gtk.Frame):
    def __init__(self):
        gtk.Frame.__init__(self, 'Evidence Codes')

        self._ec_buttons = {}

        vbox = gtk.VBox(len(EVIDENCE_CODES))
        for code, desc in EVIDENCE_CODES:
            btn = gtk.CheckButton('%s (%s)' % (code, desc))
            self._ec_buttons[code] = btn
            vbox.add(btn)
        self.add(vbox)

    def set_options(self, options):
        for code, desc in EVIDENCE_CODES:
            self._ec_buttons[code].set_active(options[code])

    def update_options(self, options):
        for code, desc in EVIDENCE_CODES:
            options[code] = self._ec_buttons[code].get_active()
        return options


class DistanceMetricFrame(gtk.Frame):
    def __init__(self):
        gtk.Frame.__init__(self, 'Distance Metrics')

        self._metric_buttons = {}

        vbox = gtk.VBox()
        prev = None
        for code, text in DISTANCE_METRICS:
            btn = gtk.RadioButton(prev, '%s' % text)
            self._metric_buttons[code] = btn
            vbox.add(btn)
            prev = btn
        self.add(vbox)

    def set_options(self, options):
        self._metric_buttons[options['metric']].set_active(True)

    def update_options(self, options):
        for code, text in DISTANCE_METRICS:
            if self._metric_buttons[code].get_active():
                options['metric'] = code
                return options
        return options


class GoDistanceDialog(gtk.Dialog):

    def __init__(self):
        gtk.Dialog.__init__(self, 'GO term distance matrix',
                            None,
                            gtk.DIALOG_MODAL | gtk.DIALOG_DESTROY_WITH_PARENT,
                            (gtk.STOCK_OK, gtk.RESPONSE_OK,
                             gtk.STOCK_CANCEL, gtk.RESPONSE_CANCEL))

        self._ec_frame = EvidenceCodeFrame()
        self._metric_frame = DistanceMetricFrame()
        self.vbox.add(self._ec_frame)
        self.vbox.add(self._metric_frame)

    def run(self):
        self.vbox.show_all()
        return gtk.Dialog.run(self)
 
    def set_options(self, options):
        self._ec_frame.set_options(options)
        self._metric_frame.set_options(options)

    def update_options(self, options):
        self._ec_frame.update_options(options)
        self._metric_frame.update_options(options)
        return options
    
    def set_editable(self, editable):
        self._ec_frame.set_sensitive(editable)
        self._metric_frame.set_sensitive(editable)


class NumericDict(dict):
    def __init__(self):
        dict.__init__(self)

    def __getitem__(self, key):
        retval = 0
        try:
            retval = dict.__getitem__(self, key)
        except:
            retval = 0.0
        return retval


class SelectGoTermsFunction(workflow.Function):
    def __init__(self, wf):
        workflow.Function.__init__(self, 'go-select', 'Select GO Terms')
        self.wf = wf

    def run(self):
        self.wf.project.set_selection('go-terms', set(['GO:0007582', 'GO:0008150', 'GO:0051704', 'GO:0044419']))


class GoDistanceFunction(workflow.Function):
    def __init__(self):
        workflow.Function.__init__(self, 'go-dist', 'GO term distance matrix')
        self.options = GoDistanceOptions()
        
    def resnik_distance_matrix(self, selection, ic):
        size = len(selection['go-terms'])
        m = zeros((size, size))
        # Create resnik distance matrix
        ids = list(selection['go-terms'])
        for i, t1 in enumerate(ids):
            for j, t2 in enumerate(ids):
                term1 = go.by_id[t1]
                term2 = go.by_id[t2]
                subsumer = go.subsumer(term1, term2)
                print "%s - %s - %s" % (t1, subsumer['id'], t2)
                m[i, j] = ic[t1] + ic[t2] - 2.0 * ic[subsumer['id']]
        ds = dataset.Dataset(m, (('go-terms', ids), ('_go-terms', ids)), 'Resnik')
        return ds

    def run(self, x, selection):
        global evidence, go
        self.options = self.show_gui(self.options)
        if not selection.has_key('go-terms') or len(selection['go-terms']) == 0:
            logger.log('warning', 'No GO terms selected. Cannot make distance matrix.')

        codes = [c for c, d in EVIDENCE_CODES if self.options[c]]
        ev_indices = evidence.get_indices('evidence', codes)
        ann_count_matrix = evidence._array[:, ev_indices].sum(1)
        total_ann = ann_count_matrix.sum(0)

        annotations = NumericDict()
        ic = NumericDict()

        # Insert annotations into dict
        for i, v in enumerate(evidence.get_identifiers('go-terms')):
            annotations[v] = ann_count_matrix[i]

        # Accumulate annotations
        for term in reversed(networkx.topological_sort(go)):
            for parent in go.in_neighbors(term):
                annotations[parent['id']] += annotations[term['id']]

        # Create information content dictionary
        for term, count in annotations.items():
            ic[term] = -log(count / total_ann)

        return [self.resnik_distance_matrix(selection, ic)]
        
    def show_gui(self, options, edit=True):
        dialog = GoDistanceDialog()
        dialog.set_options(self.options)
        dialog.show_all()
        dialog.set_editable(edit)
        response = dialog.run()
        dialog.hide()
        if response == gtk.RESPONSE_OK:
            return dialog.update_options(self.options)
        else:
            return options


class SaveDistancesFunction(workflow.Function):
    def __init__(self):
        workflow.Function.__init__(self, 'save-matrix', 'Save Matrix')
    
    def run(self, ds):
        filename = '/home/einarr/data/output.ftsv'
        fd = open(filename, 'w')
        dataset.write_ftsv(fd, ds)
        fd.close()


class Options(dict):
    def __init__(self):
        dict.__init__(self)


class GoDistanceOptions(Options):
    def __init__(self):
        Options.__init__(self)
        for code, desc in EVIDENCE_CODES:
            self[code] = True
        self['metric'] = 'fussimeg'