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
class StructureView:
    def __init__(self, structure: Structure, hide_water=True, **kwargs):
        """
        Initialize the PDBeMolstar visualization namespace.

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

        from ipymolstar import PDBeMolstar

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

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

    def rn(self, r: int) -> int:
        """apply residue numbering offset"""
        return r + self.structure.residue_offset

    @property
    def chain_name(self) -> str:
        """
        Returns the chain name based on whether auth chain labels are used.
        """
        return "auth_asym_id" if self.structure.auth_chain_labels else "struct_asym_id"

    @staticmethod
    def resolve_peptides(peptides: Peptides | nw.DataFrame) -> nw.DataFrame:
        """
        Loads peptides as a DataFrame or returns the DataFrame.
        """
        if isinstance(peptides, Peptides):
            df = peptides.load()
        else:
            df = peptides

        return df

    @staticmethod
    def resolve_chain(peptides: Peptides | nw.DataFrame, chain: list[str] | None) -> list[str]:
        """
        Resolves the chain information from a Peptides object or a DataFrame.
        """
        if isinstance(chain, list):
            return chain
        elif isinstance(peptides, Peptides):
            return peptides.chain if peptides.chain else []
        else:
            return []

    def show(self) -> StructureView:
        return self.view

    def color_peptide(
        self,
        start: int,
        end: int,
        chain: list[str] | None = None,
        color: str = "red",
        non_selected_color: str = "lightgray",
    ) -> StructureView:
        c_dict = {
            "start_" + self.residue_name: self.rn(start),
            "end_" + self.residue_name: self.rn(end),
            "color": color,
        }

        data = self._augment_chain([c_dict], chain)

        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: Peptides | nw.DataFrame,
        color="darkgreen",
        chain: list[str] | None = None,
        non_selected_color: str = "lightgray",
    ) -> StructureView:
        df = self.resolve_peptides(peptides)
        chain = self.resolve_chain(peptides, chain)
        intervals = contiguous_peptides(df)

        data = []
        for start, end in intervals:
            elem = {
                f"start_{self.residue_name}": self.rn(start),
                f"end_{self.residue_name}": self.rn(end),
                "color": color,
            }
            data.append(elem)

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

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

    def non_overlapping_peptides(
        self,
        peptides: Peptides | nw.DataFrame,
        colors: list[str] | None = None,
        chain: list[str] | None = None,
        non_selected_color: str = "lightgray",
    ) -> StructureView:
        """selects a set of non-overlapping peptides to display on the structure"""
        df = self.resolve_peptides(peptides)
        chain = self.resolve_chain(peptides, chain)

        intervals = non_overlapping_peptides(df)

        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(
                {
                    f"start_{self.residue_name}": self.rn(start),
                    f"end_{self.residue_name}": self.rn(end),
                    "color": color,
                }
            )
            df_f = df.filter((nw.col("start") == start) & (nw.col("end") == end)).to_native()
            sequence = df_f["sequence"].unique().first()
            tdata.append(
                {
                    f"start_{self.residue_name}": self.rn(start),
                    f"end_{self.residue_name}": self.rn(end),
                    "tooltip": f"Peptide: {sequence}",
                }
            )

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

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

    def peptide_redundancy(
        self,
        peptides: Peptides | nw.DataFrame,
        start="start",
        end="end",
        chain: list[str] | None = None,
        colors: list[str] | None = None,
        non_selected_color: str = "lightgray",
    ) -> StructureView:
        """selects a set of non-overlapping peptides to display on the structure"""
        df = self.resolve_peptides(peptides)
        chain = self.resolve_chain(peptides, chain)

        r_number, redundancy = peptide_redundancy(df, start=start, end=end)

        colors = (
            colors
            if colors is not None
            else ["#C6DBEF", "#9ECAE1", "#6BAED6", "#4292C6", "#2171B5", "#08519C", "#08306B"]
        )
        color_lut = {i + 1: colors[i] for i in range(len(colors))}

        data = []
        tooltips = []
        for rn, rv in zip(r_number, redundancy.clip(0, len(colors) - 1)):
            tooltips.append(
                {
                    f"{self.residue_name}": self.rn(int(rn)),
                    "tooltip": f"Redundancy: {rv} peptides",
                }
            )

            if rv == 0:
                continue
            color_elem = {
                f"{self.residue_name}": self.rn(int(rn)),
                "color": color_lut[rv],
            }
            data.append(color_elem)

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

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

    def _augment_chain(
        self, data: list[dict[str, ValueType]], chains: Sequence[str]
    ) -> list[dict[str, ValueType]]:
        """augment a list of data with chain information"""
        if chains:
            aug_data = []
            for elem, chain in itertools.product(data, chains):
                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: str property

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

residue_name: str property

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

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

Initialize the PDBeMolstar visualization namespace.

Parameters:

Name Type Description Default
structure Structure

The structure to visualize.

 required
**kwargs

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
def __init__(self, structure: Structure, hide_water=True, **kwargs):
    """
    Initialize the PDBeMolstar visualization namespace.

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

    from ipymolstar import PDBeMolstar

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

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

selects a set of non-overlapping peptides to display on the structure

Source code in hdxms_datasets/view.py 
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
def non_overlapping_peptides(
    self,
    peptides: Peptides | nw.DataFrame,
    colors: list[str] | None = None,
    chain: list[str] | None = None,
    non_selected_color: str = "lightgray",
) -> StructureView:
    """selects a set of non-overlapping peptides to display on the structure"""
    df = self.resolve_peptides(peptides)
    chain = self.resolve_chain(peptides, chain)

    intervals = non_overlapping_peptides(df)

    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(
            {
                f"start_{self.residue_name}": self.rn(start),
                f"end_{self.residue_name}": self.rn(end),
                "color": color,
            }
        )
        df_f = df.filter((nw.col("start") == start) & (nw.col("end") == end)).to_native()
        sequence = df_f["sequence"].unique().first()
        tdata.append(
            {
                f"start_{self.residue_name}": self.rn(start),
                f"end_{self.residue_name}": self.rn(end),
                "tooltip": f"Peptide: {sequence}",
            }
        )

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

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

peptide_redundancy(peptides, start='start', end='end', chain=None, colors=None, non_selected_color='lightgray')

selects a set of non-overlapping peptides to display on the structure

Source code in hdxms_datasets/view.py 
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
def peptide_redundancy(
    self,
    peptides: Peptides | nw.DataFrame,
    start="start",
    end="end",
    chain: list[str] | None = None,
    colors: list[str] | None = None,
    non_selected_color: str = "lightgray",
) -> StructureView:
    """selects a set of non-overlapping peptides to display on the structure"""
    df = self.resolve_peptides(peptides)
    chain = self.resolve_chain(peptides, chain)

    r_number, redundancy = peptide_redundancy(df, start=start, end=end)

    colors = (
        colors
        if colors is not None
        else ["#C6DBEF", "#9ECAE1", "#6BAED6", "#4292C6", "#2171B5", "#08519C", "#08306B"]
    )
    color_lut = {i + 1: colors[i] for i in range(len(colors))}

    data = []
    tooltips = []
    for rn, rv in zip(r_number, redundancy.clip(0, len(colors) - 1)):
        tooltips.append(
            {
                f"{self.residue_name}": self.rn(int(rn)),
                "tooltip": f"Redundancy: {rv} peptides",
            }
        )

        if rv == 0:
            continue
        color_elem = {
            f"{self.residue_name}": self.rn(int(rn)),
            "color": color_lut[rv],
        }
        data.append(color_elem)

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

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

resolve_chain(peptides, chain) staticmethod

Resolves the chain information from a Peptides object or a DataFrame.

Source code in hdxms_datasets/view.py 
60
61
62
63
64
65
66
67
68
69
70
@staticmethod
def resolve_chain(peptides: Peptides | nw.DataFrame, chain: list[str] | None) -> list[str]:
    """
    Resolves the chain information from a Peptides object or a DataFrame.
    """
    if isinstance(chain, list):
        return chain
    elif isinstance(peptides, Peptides):
        return peptides.chain if peptides.chain else []
    else:
        return []

resolve_peptides(peptides) staticmethod

Loads peptides as a DataFrame or returns the DataFrame.

Source code in hdxms_datasets/view.py 
48
49
50
51
52
53
54
55
56
57
58
@staticmethod
def resolve_peptides(peptides: Peptides | nw.DataFrame) -> nw.DataFrame:
    """
    Loads peptides as a DataFrame or returns the DataFrame.
    """
    if isinstance(peptides, Peptides):
        df = peptides.load()
    else:
        df = peptides

    return df

rn(r)

apply residue numbering offset

Source code in hdxms_datasets/view.py 
37
38
39
def rn(self, r: int) -> int:
    """apply residue numbering offset"""
    return r + self.structure.residue_offset