History of yeast_causal_regulation
The changes to the source code of this entry in the repository, newest first, each with the differences it made to the entry's files. They are also listed on GitLab.
[entries] Add the date when each entry was added, and remove icon_hash beff7c9
The dates are those of the commits that first added the entries' files (2020-08-11 for the entries of the initial commit); renamed entries keep the date of their first name. Changed: none
diff --git a/entries/yeast_causal_regulation/__init__.py b/entries/yeast_causal_regulation/__init__.py
index 82c5739..d600e16 100644
--- a/entries/yeast_causal_regulation/__init__.py
+++ b/entries/yeast_causal_regulation/__init__.py
@@ -30,7 +30,7 @@ tags = ['Biological', 'Gene regulation', 'Weighted', 'Uncertain']
url = ['https://genomebiology.biomedcentral.com/articles/10.1186/gb-2007-8-10-r219',
'https://europepmc.org/article/PMC/PMC2246293']
citation = [('L. S. Chen, F. Emmert-Streib, J. D. Storey, "Harnessing naturally randomized transcription to infer regulatory relationships among genes." Genome Biology 8(10), R219 (2007)', 'https://doi.org/10.1186/gb-2007-8-10-r219')]
-icon_hash = '5bd32fe8197c3f8a0272c879'
+date_added = '2026-10-25'
upstream_license = ('Creative Commons Attribution 2.0 (CC BY 2.0)', 'https://creativecommons.org/licenses/by/2.0/')
# The publisher's and PMC's file servers refuse automated downloads, so the
# supplementary files are obtained from the Europe PMC web service (as a zip
[entries] Prefix the properties in the descriptions with (Node), (Edge) or (Graph) bc3dbbd
The lists of properties at the end of the descriptions marked edge properties with "Edge" but left node properties unmarked, or grouped them in "Nodes: `a`, ...; `b`, ..." items, so the kind of a property was often unclear. Every item now starts with (Node), (Edge) or (Graph), followed by the property names, a colon and the explanation, one item per property or group of properties; qualifications (kinds of nodes, networks) follow the names in parentheses. Properties that were only named got a short explanation, and a few items that named the wrong kind of property were corrected.
diff --git a/entries/yeast_causal_regulation/__init__.py b/entries/yeast_causal_regulation/__init__.py
index 073ac24..82c5739 100644
--- a/entries/yeast_causal_regulation/__init__.py
+++ b/entries/yeast_causal_regulation/__init__.py
@@ -24,8 +24,8 @@ description = """A directed network of inferred causal regulatory relationships
The network has the following properties:
-- `name`: the standard gene name, or the systematic ORF name if there is none.
-- `weight`: the estimated probability of the causal regulatory relationship."""
+- (Node) `name`: the standard gene name, or the systematic ORF name if there is none.
+- (Edge) `weight`: the estimated probability of the causal regulatory relationship."""
tags = ['Biological', 'Gene regulation', 'Weighted', 'Uncertain']
url = ['https://genomebiology.biomedcentral.com/articles/10.1186/gb-2007-8-10-r219',
'https://europepmc.org/article/PMC/PMC2246293']
[entries] Remove unneeded code from the entries 2c69f19
Unneeded "global files" statements, unused imports and variables, f-strings without placeholders, duplicate keys in foodweb_little_rock (keeping the order and the values used), and the second definition of get_lines() in twitter_higgs. Nothing changes in the networks or descriptions. Changed: none
diff --git a/entries/yeast_causal_regulation/__init__.py b/entries/yeast_causal_regulation/__init__.py
index 3fceeee..073ac24 100644
--- a/entries/yeast_causal_regulation/__init__.py
+++ b/entries/yeast_causal_regulation/__init__.py
@@ -46,7 +46,6 @@ def fetch_upstream(force=False):
@coerce_props()
@annotate()
def parse(alts=None):
- global files
name = __name__.split(".")[-1]
for fname, alt, fmt in files:
if alts is not None and alt not in alts:
[entries] New entry: yeast_causal_regulation 77ac87b
diff --git a/entries/yeast_causal_regulation/__init__.py b/entries/yeast_causal_regulation/__init__.py
new file mode 100644
index 0000000..3fceeee
--- /dev/null
+++ b/entries/yeast_causal_regulation/__init__.py
@@ -0,0 +1,68 @@
+#! /usr/bin/env python
+# -*- coding: utf-8 -*-
+#
+# Copyright (C) 2020-2026 Tiago de Paula Peixoto <tiago@skewed.de>
+#
+# This program is free software: you can redistribute it and/or modify it under
+# the terms of the GNU Affero General Public License as published by the Free
+# Software Foundation, either version 3 of the License, or (at your option) any
+# later version.
+#
+# This program is distributed in the hope that it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
+# FOR A PARTICULAR PURPOSE. See the GNU Affero General Public License for more
+# details.
+#
+# You should have received a copy of the GNU Affero General Public License along
+# with this program. If not, see <http://www.gnu.org/licenses/>.
+
+from .. import *
+import pandas
+
+title = "Yeast causal gene regulation probabilities (2007)"
+description = """A directed network of inferred causal regulatory relationships among the genes of the budding yeast *Saccharomyces cerevisiae*, from Chen, Emmert-Streib and Storey. The relationships were inferred with the "Trigger" algorithm from genome-wide expression measurements and genotypes of 112 recombinant segregants of a cross between the laboratory strain BY4716 and the wild isolate RM11-1a: since the segregants inherit the parental alleles at random, a locus $L$ linked to the expression of two genes $i$ and $j$ can be used as a natural randomization to test whether $L \\to i \\to j$, i.e. whether the expression of gene $i$ causally affects that of gene $j$. Nodes are the 6,216 genes (open reading frames) assayed by the microarrays, and a directed edge $i \\to j$ has `weight` equal to the estimated probability that gene $i$ regulates gene $j$ (the regulatory probability matrix $P_{ij}$ of the authors). Only nonzero probabilities (rounded to three decimals in the source) are included as edges; the authors build sparse networks by thresholding the probabilities, e.g. at $P_{ij} \\geq 0.9$ (about 4,400 edges, with an estimated false discovery rate of 6%).
+
+The network has the following properties:
+
+- `name`: the standard gene name, or the systematic ORF name if there is none.
+- `weight`: the estimated probability of the causal regulatory relationship."""
+tags = ['Biological', 'Gene regulation', 'Weighted', 'Uncertain']
+url = ['https://genomebiology.biomedcentral.com/articles/10.1186/gb-2007-8-10-r219',
+ 'https://europepmc.org/article/PMC/PMC2246293']
+citation = [('L. S. Chen, F. Emmert-Streib, J. D. Storey, "Harnessing naturally randomized transcription to infer regulatory relationships among genes." Genome Biology 8(10), R219 (2007)', 'https://doi.org/10.1186/gb-2007-8-10-r219')]
+icon_hash = '5bd32fe8197c3f8a0272c879'
+upstream_license = ('Creative Commons Attribution 2.0 (CC BY 2.0)', 'https://creativecommons.org/licenses/by/2.0/')
+# The publisher's and PMC's file servers refuse automated downloads, so the
+# supplementary files are obtained from the Europe PMC web service (as a zip
+# archive, which contains the zip file of Additional data file 2).
+upstream_prefix = 'https://www.ebi.ac.uk/europepmc/webservices/rest/PMC2246293'
+files = [('supplementaryFiles:zip:gb-2007-8-10-r219-S2.zip:Stable1.txt', None, None)]
+
+def fetch_upstream(force=False):
+ return fetch_upstream_files(__name__.split(".")[-1], upstream_prefix, files,
+ force)
+
+@cache_network()
+@coerce_props()
+@annotate()
+def parse(alts=None):
+ global files
+ name = __name__.split(".")[-1]
+ for fname, alt, fmt in files:
+ if alts is not None and alt not in alts:
+ continue
+ # A header line with the gene names, followed by one line per gene,
+ # with its name and the probabilities that it regulates each gene
+ with open_upstream_file(name, fname, "rb") as f:
+ genes = f.readline().decode().split()
+ df = pandas.read_csv(f, sep=" ", header=None, index_col=0)
+ if list(df.index) != genes:
+ raise ValueError("row and column genes differ")
+ P = df.values
+ i, j = numpy.nonzero(P)
+ g = Graph(directed=True)
+ g.add_vertex(len(genes))
+ g.ep.weight = g.new_ep("double")
+ g.add_edge_list(numpy.column_stack((i, j, P[i, j])), eprops=[g.ep.weight])
+ g.vp.name = g.new_vp("string", vals=genes)
+ yield alt, g