mandos.search.pubchem.ctd_gene_search.CtdGeneSearch._if_match() - Code Metrics - Inspection of "Bump flake8-bugbear from 20.11.1 to 21.3.2" - dmyersturnbull/mandos - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Push — dependabot/pip/flake8-bugbear-... ( 16d864...b4f9fc )

unknown

created 2021-03-31 03:48 UTC

CtdGeneSearch._if_match() A

↳ Parent: mandos.search.pubchem.ctd_gene_search

Complexity

Conditions

Size

Total Lines	8
Code Lines	8

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
cc	3
eloc	8
nop	4
dl	0
loc	8
rs	10
c	0
b	0
f	0

import re

from dataclasses import dataclass
from typing import Sequence, Optional

from mandos.search.pubchem import PubchemHit, PubchemSearch


@dataclass(frozen=True, order=True, repr=True)

class CtdGeneHit(PubchemHit):
    """"""

    taxon_id: Optional[int]
    taxon_name: Optional[str]


class CtdGeneSearch(PubchemSearch[CtdGeneHit]):

    """"""

    @property
    def data_source(self) -> str:

        return "Comparative Toxicogenomics Database (CTD)"

    def find(self, inchikey: str) -> Sequence[CtdGeneHit]:

        data = self.api.fetch_data(inchikey)
        results = []
        for dd in data.biomolecular_interactions_and_pathways.chemical_gene_interactions:

            for interaction in dd.interactions:
                for predicate in self._predicate(data.name, dd.gene_name, interaction):
                    results.append(
                        CtdGeneHit(
                            record_id=None,
                            origin_inchikey=inchikey,
                            matched_inchikey=data.names_and_identifiers.inchikey,
                            compound_id=str(data.cid),
                            compound_name=data.name,
                            predicate=predicate,
                            object_id=dd.gene_name,
                            object_name=dd.gene_name,
                            search_key=self.key,
                            search_class=self.search_class,
                            data_source=self.data_source,
                            taxon_id=dd.tax_id,
                            taxon_name=dd.tax_name,
                        )
                    )
        return results

    def _predicate(self, compound: str, gene: str, interaction: str) -> Sequence[str]:
        # TODO: Sometimes synonyms of the compound are used (e.g. "Crack Cocaine")

        if (
            "co-treated" in interaction

            or "co-treatment" in interaction

            or "mutant" in interaction

            or "modified form" in interaction

            or "alternative form" in interaction

        ):
            return []
        expression = {
            "results in increased ((?:expression)|(?:activity)|(?:phosphorylation))": "increases $1 of",

            "results in decreased ((?:expression)|(?:activity)|(?:phosphorylation))": "decreases $1 of",

            "affects the ((?:expression)|(?:activity)|(?:phosphorylation))": "affects $1 of",
            "affects the localization": "affects localization",
        }
        results = []
        for txt, effect in expression.items():
            result = self._if_match(
                interaction,
                re.escape(compound)
                + " "
                + txt
                + " "
                + gene
                + "(?: (?:mRNA)|(?:protein)|(?:exon))?",
                effect,
            )
            if result is not None:
                results.append(result)
            else:
                # catches "affects the activity of and affects the expression of"
                # TODO: could this catch something weird:

                if result is None:
                    result = self._if_match(
                        interaction, re.escape(compound) + " " + txt + " of and .+", effect
                    )
                if result is not None:
                    results.append(result)
        if len(results) > 0:
            return results
        result = self._if_match(
            interaction,
            compound + " ((?:affects)|(?:promotes)|(?:inhibits)) the reaction",
            "affects a reaction involving",
        )
        return [] if result is None else [result]

    def _if_match(self, interaction: str, pattern: str, result: str) -> Optional[str]:
class Foo:
    def some_method(self, x, y):
        return x + y;
        pat = re.compile("^" + pattern + "$", flags=re.IGNORECASE)
        match = pat.fullmatch(interaction)
        if match is None:
            return None
        for i, group in enumerate(match.groupdict()):
            result = result.replace("$" + str(i + 1), group)
        return result


__all__ = ["CtdGeneHit", "CtdGeneSearch"]


1			import re
			0 ignored issues – show introduced 2021-03-24 04:52 UTC by Report Bug Copy Issue Report Missing module docstring Loading history...
2			from dataclasses import dataclass
3			from typing import Sequence, Optional
4
5			from mandos.search.pubchem import PubchemHit, PubchemSearch
6
7
8			@dataclass(frozen=True, order=True, repr=True)
			0 ignored issues – show Documentation introduced 2021-03-10 02:41 UTC by Report Bug Copy Issue Report Empty class docstring Loading history...
9			class CtdGeneHit(PubchemHit):
10			""""""
11
12			taxon_id: Optional[int]
13			taxon_name: Optional[str]
14
15
16			class CtdGeneSearch(PubchemSearch[CtdGeneHit]):
			0 ignored issues – show Documentation introduced 2021-03-24 04:52 UTC by Report Bug Copy Issue Report Empty class docstring Loading history...
17			""""""
18
19			@property
20			def data_source(self) -> str:
			0 ignored issues – show introduced 2021-03-24 04:52 UTC by Report Bug Copy Issue Report Missing function or method docstring Loading history...
21			return "Comparative Toxicogenomics Database (CTD)"
22
23			def find(self, inchikey: str) -> Sequence[CtdGeneHit]:
			0 ignored issues – show introduced 2021-03-21 02:08 UTC by Report Bug Copy Issue Report Missing function or method docstring Loading history...
24			data = self.api.fetch_data(inchikey)
25			results = []
26			for dd in data.biomolecular_interactions_and_pathways.chemical_gene_interactions:
			0 ignored issues – show Coding Style Naming introduced 2021-03-31 03:41 UTC by Report Bug Copy Issue Report Variable name "dd" doesn't conform to snake_case naming style ('([^\\W\\dA-Z][^\\WA-Z]2,\|_[^\\WA-Z]*\|__[^\\WA-Z\\d_][^\\WA-Z]+__)$' pattern) This check looks for invalid names for a range of different identifiers. You can set regular expressions to which the identifiers must conform if the defaults do not match your requirements. If your project includes a Pylint configuration file, the settings contained in that file take precedence. To find out more about Pylint, please refer to their site. Loading history...
27			for interaction in dd.interactions:
28			for predicate in self._predicate(data.name, dd.gene_name, interaction):
29			results.append(
30			CtdGeneHit(
31			record_id=None,
32			origin_inchikey=inchikey,
33			matched_inchikey=data.names_and_identifiers.inchikey,
34			compound_id=str(data.cid),
35			compound_name=data.name,
36			predicate=predicate,
37			object_id=dd.gene_name,
38			object_name=dd.gene_name,
39			search_key=self.key,
40			search_class=self.search_class,
41			data_source=self.data_source,
42			taxon_id=dd.tax_id,
43			taxon_name=dd.tax_name,
44			)
45			)
46			return results
47
48			def _predicate(self, compound: str, gene: str, interaction: str) -> Sequence[str]:
49			# TODO: Sometimes synonyms of the compound are used (e.g. "Crack Cocaine")
			0 ignored issues – show Coding Style introduced 2021-03-31 03:41 UTC by Report Bug Copy Issue Report `TODO` and `FIXME` comments should generally be avoided. Loading history...
50			if (
51			"co-treated" in interaction
			0 ignored issues – show Coding Style introduced 2021-03-31 03:41 UTC by Report Bug Copy Issue Report Wrong hanging indentation before block (add 4 spaces). Loading history...
52			or "co-treatment" in interaction
			0 ignored issues – show Coding Style introduced 2021-03-31 03:41 UTC by Report Bug Copy Issue Report Wrong hanging indentation before block (add 4 spaces). Loading history...
53			or "mutant" in interaction
			0 ignored issues – show Coding Style introduced 2021-03-31 03:41 UTC by Report Bug Copy Issue Report Wrong hanging indentation before block (add 4 spaces). Loading history...
54			or "modified form" in interaction
			0 ignored issues – show Coding Style introduced 2021-03-31 03:41 UTC by Report Bug Copy Issue Report Wrong hanging indentation before block (add 4 spaces). Loading history...
55			or "alternative form" in interaction
			0 ignored issues – show Coding Style introduced 2021-03-31 03:41 UTC by Report Bug Copy Issue Report Wrong hanging indentation before block (add 4 spaces). Loading history...
56			):
57			return []
58			expression = {
59			"results in increased ((?:expression)\|(?:activity)\|(?:phosphorylation))": "increases $1 of",
			0 ignored issues – show Coding Style introduced 2021-03-31 03:41 UTC by Report Bug Copy Issue Report This line is too long as per the coding-style (104/100). This check looks for lines that are too long. You can specify the maximum line length. Loading history...
60			"results in decreased ((?:expression)\|(?:activity)\|(?:phosphorylation))": "decreases $1 of",
			0 ignored issues – show Coding Style introduced 2021-03-31 03:41 UTC by Report Bug Copy Issue Report This line is too long as per the coding-style (104/100). This check looks for lines that are too long. You can specify the maximum line length. Loading history...
61			"affects the ((?:expression)\|(?:activity)\|(?:phosphorylation))": "affects $1 of",
62			"affects the localization": "affects localization",
63			}
64			results = []
65			for txt, effect in expression.items():
66			result = self._if_match(
67			interaction,
68			re.escape(compound)
69			+ " "
70			+ txt
71			+ " "
72			+ gene
73			+ "(?: (?:mRNA)\|(?:protein)\|(?:exon))?",
74			effect,
75			)
76			if result is not None:
77			results.append(result)
78			else:
79			# catches "affects the activity of and affects the expression of"
80			# TODO: could this catch something weird:
			0 ignored issues – show Coding Style introduced 2021-03-31 03:41 UTC by Report Bug Copy Issue Report `TODO` and `FIXME` comments should generally be avoided. Loading history...
81			if result is None:
82			result = self._if_match(
83			interaction, re.escape(compound) + " " + txt + " of and .+", effect
84			)
85			if result is not None:
86			results.append(result)
87			if len(results) > 0:
88			return results
89			result = self._if_match(
90			interaction,
91			compound + " ((?:affects)\|(?:promotes)\|(?:inhibits)) the reaction",
92			"affects a reaction involving",
93			)
94			return [] if result is None else [result]
95
96			def _if_match(self, interaction: str, pattern: str, result: str) -> Optional[str]:
			0 ignored issues – show Coding Style introduced 2021-03-31 03:41 UTC by Report Bug Copy Issue Report This method could be written as a function/class method. If a method does not access any attributes of the class, it could also be implemented as a function or static method. This can help improve readability. For example class Foo: def some_method(self, x, y): return x + y; could be written as class Foo: @classmethod def some_method(cls, x, y): return x + y; Loading history...
97			pat = re.compile("^" + pattern + "$", flags=re.IGNORECASE)
98			match = pat.fullmatch(interaction)
99			if match is None:
100			return None
101			for i, group in enumerate(match.groupdict()):
102			result = result.replace("$" + str(i + 1), group)
103			return result
104
105
106			__all__ = ["CtdGeneHit", "CtdGeneSearch"]
107

dmyersturnbull / mandos

Push — dependabot/pip/flake8-bugbear-... ( 16d864...b4f9fc )

CtdGeneSearch._if_match() A

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like