Skip to content

view

StructureView

Source code in hdxms_datasets/view.py 
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
class StructureView:
    def __init__(
        self,
        structure: Structure,
        mapping: StructureMapping = StructureMapping(),
        hide_water=True,
        **kwargs: dict,
    ):
        """
        Initialize the PDBeMolstar visualization namespace.
        Can uses a `StructureMapping` which relates peptides to the structure

        Args:
            structure: The structure to visualize.
            mapping: Optional structure mapping information.
            **kwargs: Additional keyword arguments for customization.
        """
        self.structure = structure
        self.mapping = mapping

        from ipymolstar import PDBeMolstar

        self.view = PDBeMolstar(
            custom_data=self.structure.pdbemolstar_custom_data(),
            hide_water=hide_water,
            **kwargs,
        )

    def show(self):
        return self.view

    def highlight(self, resi: int) -> StructureView:
        """
        Highlights a residue in the structure.

        Args:
            resi: Residue number to highlight.

        Returns:
            The updated StructureView object.
        """
        param = self.get_query_param(resi)
        data = self._augment_chain([param])
        self.view.highlight = {"data": data}

        return self

    def color_peptide(
        self,
        start: int,
        end: int,
        color: str = "red",
        non_selected_color: str = "lightgray",
    ) -> StructureView:
        """
        Color a peptide by start and end residue numbers.

        Args:
            start: Start residue number.
            end: End residue number.
            color: Color for the peptide.
            non_selected_color: Color for non-selected regions.

        Returns:
            The updated StructureView object.
        """
        kwargs = {"color": color}
        param = self.get_query_param_range(start, end, **kwargs)
        data = self._augment_chain([param])

        color_data = {
            "data": data,
            "nonSelectedColor": non_selected_color,
        }

        self.view.color_data = color_data
        self.view.tooltips = None

        return self

    def peptide_coverage(
        self,
        peptides: nw.DataFrame,
        color: str = "darkgreen",
        non_selected_color: str = "lightgray",
    ):
        """
        Plots peptide coverage on the structure.

        Args:
            peptides: Peptides object or DataFrame containing peptide data.
            color: Color for the covered regions.
            non_selected_color: Color for non-covered regions.

        Returns:
            The updated StructureView object.
        """
        intervals = contiguous_peptides(peptides)

        data = [self.get_query_param_range(start, end, color=color) for start, end in intervals]
        color_data = {
            "data": self._augment_chain(data),
            "nonSelectedColor": non_selected_color,
        }

        self.view.color_data = color_data
        self.view.tooltips = None
        return self

    def non_overlapping_peptides(
        self,
        peptides: nw.DataFrame,
        colors: list[str] | None = None,
        non_selected_color: str = "lightgray",
    ):
        """Selects a set of non-overlapping peptides to display on the structure. Starts with the first
        peptide and successively adds peptides that do not overlap with already selected peptides.

        Args:
            peptides: Peptides object or DataFrame containing peptide data.
            colors: List of colors to cycle through for different peptides.
            non_selected_color: Color for non-covered regions.

        Returns:
            The updated StructureView object.

        """

        intervals = non_overlapping_peptides(peptides)

        colors = (
            colors
            if colors is not None
            else ["#1B9E77", "#D95F02", "#7570B3", "#E7298A", "#66A61E", "#E6AB02"]
        )

        cdata = []
        tdata = []
        for (start, end), color in zip(intervals, itertools.cycle(colors)):
            cdata.append(self.get_query_param_range(start, end, color=color))
            df_f = peptides.filter((nw.col("start") == start) & (nw.col("end") == end)).to_native()
            sequence = df_f["sequence"].unique().first()
            tdata.append(self.get_query_param_range(start, end, tooltip=f"Peptide: {sequence}"))

        color_data = {
            "data": self._augment_chain(cdata),
            "nonSelectedColor": non_selected_color,
        }

        self.view.color_data = color_data
        self.view.tooltips = {"data": self._augment_chain(tdata)}
        return self

    def peptide_redundancy(
        self,
        peptides: nw.DataFrame,
        colors: list[str] | None = None,
        clip: Optional[int] = None,
        non_selected_color: str = "lightgray",
    ):
        """Colors residues by peptide redundancy.

        Args:
            peptides: Peptides DataFrame containing peptide data.
            colors: List of colors to use for different redundancy levels.
            clip: Optional maximum redundancy value for clipping.
            non_selected_color: Color for non-covered regions.

        Returns:
            The updated StructureView object.

        """
        r_number, redundancy = peptide_redundancy(peptides)

        colors = (
            colors
            if colors is not None
            else ["#C6DBEF", "#9ECAE1", "#6BAED6", "#4292C6", "#2171B5", "#08519C", "#08306B"]
        )

        if clip:
            vals = ((redundancy.clip(None, clip) / clip) * (len(colors) - 1)).astype(int)
        else:
            vals = ((redundancy / redundancy.max()) * (len(colors) - 1)).astype(int)

        data = []
        tooltips = []
        for rn, rv, rv_clip in zip(r_number, redundancy, vals):
            tooltips.append(self.get_query_param(int(rn), tooltip=f"Redundancy: {rv} peptides"))

            if rv == 0:
                continue

            color_elem = self.get_query_param(int(rn), color=colors[rv_clip])
            data.append(color_elem)

        color_data = {
            "data": self._augment_chain(data),
            "nonSelectedColor": non_selected_color,
        }

        self.view.color_data = color_data
        self.view.tooltips = {"data": self._augment_chain(tooltips)}
        return self

    def set_mapping(self, mapping: StructureMapping):
        self.mapping = mapping
        return self

    def get_query_param(self, resi: int, **kwargs):
        resi = self.mapping.map(resi)

        # TODO entity support
        c_dict = {
            self.residue_name: int(resi),
            **kwargs,
        }

        return c_dict

    def get_query_param_range(self, start: int, end: int, **kwargs):
        start = self.mapping.map(start)
        end = self.mapping.map(end)

        # TODO entity support
        c_dict = {
            "start_" + self.residue_name: int(start),
            "end_" + self.residue_name: int(end),
            **kwargs,
        }

        return c_dict

    @property
    def residue_name(self) -> str:
        """
        Returns the residue name based on whether auth residue numbers are used.
        """
        return "auth_residue_number" if self.mapping.auth_residue_numbers else "residue_number"

    @property
    def chain_name(self) -> str:
        """
        Returns the chain name based on whether auth chain labels are used.

        Note that 'struct_asym_id' used in PDBeMolstar is equivalent to
        'label_asym_id' in mmCIF.

        """
        return "auth_asym_id" if self.mapping.auth_chain_labels else "struct_asym_id"

    def _augment_chain(
        self,
        data: list[dict[str, ValueType]],
    ) -> list[dict[str, ValueType]]:
        """Augment a list of data with chain information"""
        if self.mapping.chain:
            aug_data = []
            for elem, chain in itertools.product(data, self.mapping.chain):
                aug_data.append(elem | {self.chain_name: chain})
        else:
            aug_data = data

        return aug_data

    def _repr_mimebundle_(self, include=None, exclude=None):
        return self.show()._repr_mimebundle_(include=include, exclude=exclude)

chain_name property

Returns the chain name based on whether auth chain labels are used.

Note that 'struct_asym_id' used in PDBeMolstar is equivalent to
'label_asym_id' in mmCIF.

residue_name property

Returns the residue name based on whether auth residue numbers are used.

__init__(structure, mapping=StructureMapping(), hide_water=True, **kwargs)

Initialize the PDBeMolstar visualization namespace.
Can uses a StructureMapping which relates peptides to the structure

Parameters:

Name Type Description Default
structure Structure

The structure to visualize.

 required
mapping StructureMapping

Optional structure mapping information.

 StructureMapping()
**kwargs dict

Additional keyword arguments for customization.

 {}
Source code in hdxms_datasets/view.py 
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
def __init__(
    self,
    structure: Structure,
    mapping: StructureMapping = StructureMapping(),
    hide_water=True,
    **kwargs: dict,
):
    """
    Initialize the PDBeMolstar visualization namespace.
    Can uses a `StructureMapping` which relates peptides to the structure

    Args:
        structure: The structure to visualize.
        mapping: Optional structure mapping information.
        **kwargs: Additional keyword arguments for customization.
    """
    self.structure = structure
    self.mapping = mapping

    from ipymolstar import PDBeMolstar

    self.view = PDBeMolstar(
        custom_data=self.structure.pdbemolstar_custom_data(),
        hide_water=hide_water,
        **kwargs,
    )

color_peptide(start, end, color='red', non_selected_color='lightgray')

Color a peptide by start and end residue numbers.

Parameters:

Name Type Description Default
start int

Start residue number.

 required
end int

End residue number.

 required
color str

Color for the peptide.

 'red'
non_selected_color str

Color for non-selected regions.

 'lightgray'

Returns:

Type Description
StructureView

The updated StructureView object.
Source code in hdxms_datasets/view.py 
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
def color_peptide(
    self,
    start: int,
    end: int,
    color: str = "red",
    non_selected_color: str = "lightgray",
) -> StructureView:
    """
    Color a peptide by start and end residue numbers.

    Args:
        start: Start residue number.
        end: End residue number.
        color: Color for the peptide.
        non_selected_color: Color for non-selected regions.

    Returns:
        The updated StructureView object.
    """
    kwargs = {"color": color}
    param = self.get_query_param_range(start, end, **kwargs)
    data = self._augment_chain([param])

    color_data = {
        "data": data,
        "nonSelectedColor": non_selected_color,
    }

    self.view.color_data = color_data
    self.view.tooltips = None

    return self

highlight(resi)

Highlights a residue in the structure.

Parameters:

Name Type Description Default
resi int

Residue number to highlight.

 required

Returns:

Type Description
StructureView

The updated StructureView object.
Source code in hdxms_datasets/view.py 
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
def highlight(self, resi: int) -> StructureView:
    """
    Highlights a residue in the structure.

    Args:
        resi: Residue number to highlight.

    Returns:
        The updated StructureView object.
    """
    param = self.get_query_param(resi)
    data = self._augment_chain([param])
    self.view.highlight = {"data": data}

    return self

non_overlapping_peptides(peptides, colors=None, non_selected_color='lightgray')

Selects a set of non-overlapping peptides to display on the structure. Starts with the first
peptide and successively adds peptides that do not overlap with already selected peptides.

Parameters:

Name Type Description Default
peptides DataFrame

Peptides object or DataFrame containing peptide data.

 required
colors list[str] | None

List of colors to cycle through for different peptides.

 None
non_selected_color str

Color for non-covered regions.

 'lightgray'

Returns:

Type Description

The updated StructureView object.
Source code in hdxms_datasets/view.py 
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
def non_overlapping_peptides(
    self,
    peptides: nw.DataFrame,
    colors: list[str] | None = None,
    non_selected_color: str = "lightgray",
):
    """Selects a set of non-overlapping peptides to display on the structure. Starts with the first
    peptide and successively adds peptides that do not overlap with already selected peptides.

    Args:
        peptides: Peptides object or DataFrame containing peptide data.
        colors: List of colors to cycle through for different peptides.
        non_selected_color: Color for non-covered regions.

    Returns:
        The updated StructureView object.

    """

    intervals = non_overlapping_peptides(peptides)

    colors = (
        colors
        if colors is not None
        else ["#1B9E77", "#D95F02", "#7570B3", "#E7298A", "#66A61E", "#E6AB02"]
    )

    cdata = []
    tdata = []
    for (start, end), color in zip(intervals, itertools.cycle(colors)):
        cdata.append(self.get_query_param_range(start, end, color=color))
        df_f = peptides.filter((nw.col("start") == start) & (nw.col("end") == end)).to_native()
        sequence = df_f["sequence"].unique().first()
        tdata.append(self.get_query_param_range(start, end, tooltip=f"Peptide: {sequence}"))

    color_data = {
        "data": self._augment_chain(cdata),
        "nonSelectedColor": non_selected_color,
    }

    self.view.color_data = color_data
    self.view.tooltips = {"data": self._augment_chain(tdata)}
    return self

peptide_coverage(peptides, color='darkgreen', non_selected_color='lightgray')

Plots peptide coverage on the structure.

Parameters:

Name Type Description Default
peptides DataFrame

Peptides object or DataFrame containing peptide data.

 required
color str

Color for the covered regions.

 'darkgreen'
non_selected_color str

Color for non-covered regions.

 'lightgray'

Returns:

Type Description

The updated StructureView object.
Source code in hdxms_datasets/view.py 
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
def peptide_coverage(
    self,
    peptides: nw.DataFrame,
    color: str = "darkgreen",
    non_selected_color: str = "lightgray",
):
    """
    Plots peptide coverage on the structure.

    Args:
        peptides: Peptides object or DataFrame containing peptide data.
        color: Color for the covered regions.
        non_selected_color: Color for non-covered regions.

    Returns:
        The updated StructureView object.
    """
    intervals = contiguous_peptides(peptides)

    data = [self.get_query_param_range(start, end, color=color) for start, end in intervals]
    color_data = {
        "data": self._augment_chain(data),
        "nonSelectedColor": non_selected_color,
    }

    self.view.color_data = color_data
    self.view.tooltips = None
    return self

peptide_redundancy(peptides, colors=None, clip=None, non_selected_color='lightgray')

Colors residues by peptide redundancy.

Parameters:

Name Type Description Default
peptides DataFrame

Peptides DataFrame containing peptide data.

 required
colors list[str] | None

List of colors to use for different redundancy levels.

 None
clip Optional[int]

Optional maximum redundancy value for clipping.

 None
non_selected_color str

Color for non-covered regions.

 'lightgray'

Returns:

Type Description

The updated StructureView object.
Source code in hdxms_datasets/view.py 
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
def peptide_redundancy(
    self,
    peptides: nw.DataFrame,
    colors: list[str] | None = None,
    clip: Optional[int] = None,
    non_selected_color: str = "lightgray",
):
    """Colors residues by peptide redundancy.

    Args:
        peptides: Peptides DataFrame containing peptide data.
        colors: List of colors to use for different redundancy levels.
        clip: Optional maximum redundancy value for clipping.
        non_selected_color: Color for non-covered regions.

    Returns:
        The updated StructureView object.

    """
    r_number, redundancy = peptide_redundancy(peptides)

    colors = (
        colors
        if colors is not None
        else ["#C6DBEF", "#9ECAE1", "#6BAED6", "#4292C6", "#2171B5", "#08519C", "#08306B"]
    )

    if clip:
        vals = ((redundancy.clip(None, clip) / clip) * (len(colors) - 1)).astype(int)
    else:
        vals = ((redundancy / redundancy.max()) * (len(colors) - 1)).astype(int)

    data = []
    tooltips = []
    for rn, rv, rv_clip in zip(r_number, redundancy, vals):
        tooltips.append(self.get_query_param(int(rn), tooltip=f"Redundancy: {rv} peptides"))

        if rv == 0:
            continue

        color_elem = self.get_query_param(int(rn), color=colors[rv_clip])
        data.append(color_elem)

    color_data = {
        "data": self._augment_chain(data),
        "nonSelectedColor": non_selected_color,
    }

    self.view.color_data = color_data
    self.view.tooltips = {"data": self._augment_chain(tooltips)}
    return self