History of tree-of-life
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/tree-of-life/__init__.py b/entries/tree-of-life/__init__.py
index 1069f55..0ac11ad 100644
--- a/entries/tree-of-life/__init__.py
+++ b/entries/tree-of-life/__init__.py
@@ -28,7 +28,7 @@ description = """Protein-protein iteraction networks ("interactome") for 1,840 s
tags = ['Biological', 'Protein interactions']
url = 'http://snap.stanford.edu/tree-of-life/data.html'
citation = [('Marinka Zitnik, Rok Sosic, Marcus W Feldman, and Jure Leskovec. "Evolution of resilience in protein interactomes across the tree of life", Proceedings of the National Academy of Sciences (PNAS), 2019, 116 (10) 4426-4433.', 'https://doi.org/10.1073/pnas.1818013116')]
-icon_hash = None
+date_added = '2021-12-25'
upstream_prefix = 'http://snap.stanford.edu/tree-of-life/data'
files = []
[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/tree-of-life/__init__.py b/entries/tree-of-life/__init__.py
index e142b31..1069f55 100644
--- a/entries/tree-of-life/__init__.py
+++ b/entries/tree-of-life/__init__.py
@@ -52,7 +52,7 @@ def cache_open(fname, mode="r"):
with open(f"{cache}/{fname}", mode) as f:
yield f
-with cache_open(f"treeoflife.species.tsv") as f:
+with cache_open("treeoflife.species.tsv") as f:
for i, line in enumerate(f):
if i == 0:
continue
@@ -64,7 +64,7 @@ with cache_open(f"treeoflife.species.tsv") as f:
def fetch_upstream(force=False):
- with cache_open(f"treeoflife.species.pubmed.count.tsv") as f:
+ with cache_open("treeoflife.species.pubmed.count.tsv") as f:
for i, line in enumerate(f):
if i < 2:
continue
@@ -72,7 +72,7 @@ def fetch_upstream(force=False):
nid = vals[0]
pub_count[nid] = int(vals[2])
- with cache_open(f"treeoflife.species.evolution.tsv") as f:
+ with cache_open("treeoflife.species.evolution.tsv") as f:
for i, line in enumerate(f):
if i == 0:
continue
@@ -82,7 +82,7 @@ def fetch_upstream(force=False):
domain[nid] = vals[2]
tax_level2[nid] = vals[3]
- with cache_open(f"treeoflife.taxonomy.zip", "rb") as f:
+ with cache_open("treeoflife.taxonomy.zip", "rb") as f:
with zipfile.ZipFile(f) as zf:
for net in names.keys():
with zf.open(f"treeoflife.taxonomy/{net}.txt", "r") as myfile:
@@ -93,7 +93,6 @@ def fetch_upstream(force=False):
@coerce_props()
@annotate()
def parse(alts=None):
- global files
name = __name__.split(".")[-1]
for fnames, alt, fmt in files:
if alts is not None and alt not in alts:
[entries] Fix parse bugs and improve descriptions and metadata 6bb6851
- parse fixes from the review of the descriptions, e.g. us_patents (directed), celegans_2019 (synapse direction), ecoli_transcription and yeast_transcription (regulator to target), bitcoin (direction, phantom node), ego_social (Google+ features and circles), scotus_majority, arxiv_authors and social_location (as in SNAP), caida_as, dnc, dom, mist, reuters and bibsonomy (names on the right nodes), uci_zoo - every description now states explicitly what the nodes and edges represent; corrected titles, years, tags, citations and licences - the "Hypergraph" tag is removed; very large entries are marked `huge = True` (see --skip-huge) - ICON ids of partial duplicates added (hiv_transmission, congress_bills, openflights, dutch_school)
diff --git a/entries/tree-of-life/__init__.py b/entries/tree-of-life/__init__.py
index 0baf37c..e142b31 100644
--- a/entries/tree-of-life/__init__.py
+++ b/entries/tree-of-life/__init__.py
@@ -24,7 +24,7 @@ import numpy as np
from .. import *
title = "Protein interactomes across the tree of life (2019)"
-description = """Protein-protein iteraction networks ("interactome") for 1,840 species. An interactome captures all physical protein-protein interactions within one species, from direct biophysical protein-protein interactions to regulatory protein-DNA and metabolic interactions. """
+description = """Protein-protein iteraction networks ("interactome") for 1,840 species. An interactome captures all physical protein-protein interactions within one species, from direct biophysical protein-protein interactions to regulatory protein-DNA and metabolic interactions. In each network, nodes are the proteins of one species, and an undirected edge connects two proteins that interact."""
tags = ['Biological', 'Protein interactions']
url = 'http://snap.stanford.edu/tree-of-life/data.html'
citation = [('Marinka Zitnik, Rok Sosic, Marcus W Feldman, and Jure Leskovec. "Evolution of resilience in protein interactomes across the tree of life", Proceedings of the National Academy of Sciences (PNAS), 2019, 116 (10) 4426-4433.', 'https://doi.org/10.1073/pnas.1818013116')]
Update copyright information 73a4f0d
diff --git a/entries/tree-of-life/__init__.py b/entries/tree-of-life/__init__.py
index 32a4d23..0baf37c 100644
--- a/entries/tree-of-life/__init__.py
+++ b/entries/tree-of-life/__init__.py
@@ -1,7 +1,7 @@
#! /usr/bin/env python
# -*- coding: utf-8 -*-
#
-# Copyright (C) 2020-2024 Tiago de Paula Peixoto <tiago@skewed.de>
+# 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
Update copyright information 3d288ea
diff --git a/entries/tree-of-life/__init__.py b/entries/tree-of-life/__init__.py
index 988ec4d..32a4d23 100644
--- a/entries/tree-of-life/__init__.py
+++ b/entries/tree-of-life/__init__.py
@@ -1,7 +1,7 @@
#! /usr/bin/env python
# -*- coding: utf-8 -*-
#
-# Copyright (C) 2020-2023 Tiago de Paula Peixoto <tiago@skewed.de>
+# Copyright (C) 2020-2024 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
Update copyright information 8d005ae
diff --git a/entries/tree-of-life/__init__.py b/entries/tree-of-life/__init__.py
index 7ca7d44..988ec4d 100644
--- a/entries/tree-of-life/__init__.py
+++ b/entries/tree-of-life/__init__.py
@@ -1,7 +1,7 @@
#! /usr/bin/env python
# -*- coding: utf-8 -*-
#
-# Copyright (C) 2021 Tiago de Paula Peixoto <tiago@skewed.de>
+# Copyright (C) 2020-2023 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
Add entry 'tree-of-life' b8e9761
diff --git a/entries/tree-of-life/__init__.py b/entries/tree-of-life/__init__.py
new file mode 100644
index 0000000..7ca7d44
--- /dev/null
+++ b/entries/tree-of-life/__init__.py
@@ -0,0 +1,122 @@
+#! /usr/bin/env python
+# -*- coding: utf-8 -*-
+#
+# Copyright (C) 2021 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/>.
+
+import os
+import shutil
+from contextlib import contextmanager
+import numpy as np
+
+from .. import *
+
+title = "Protein interactomes across the tree of life (2019)"
+description = """Protein-protein iteraction networks ("interactome") for 1,840 species. An interactome captures all physical protein-protein interactions within one species, from direct biophysical protein-protein interactions to regulatory protein-DNA and metabolic interactions. """
+tags = ['Biological', 'Protein interactions']
+url = 'http://snap.stanford.edu/tree-of-life/data.html'
+citation = [('Marinka Zitnik, Rok Sosic, Marcus W Feldman, and Jure Leskovec. "Evolution of resilience in protein interactomes across the tree of life", Proceedings of the National Academy of Sciences (PNAS), 2019, 116 (10) 4426-4433.', 'https://doi.org/10.1073/pnas.1818013116')]
+icon_hash = None
+upstream_prefix = 'http://snap.stanford.edu/tree-of-life/data'
+
+files = []
+
+names = {}
+long_names = {}
+pub_count = {}
+evo_time = {}
+domain = {}
+tax_level2 = {}
+tax = {}
+
+@contextmanager
+def cache_open(fname, mode="r"):
+ cache = f"{root}/cache/upstream/" + __name__.split(".")[-1]
+ os.makedirs(cache, exist_ok=True)
+ if not os.path.exists(f"{cache}/{fname}"):
+ with urllib.request.urlopen(f"{upstream_prefix}/{fname}") as f_r:
+ with open(f"{cache}/{fname}", "wb") as f_w:
+ shutil.copyfileobj(f_r, f_w)
+ with open(f"{cache}/{fname}", mode) as f:
+ yield f
+
+with cache_open(f"treeoflife.species.tsv") as f:
+ for i, line in enumerate(f):
+ if i == 0:
+ continue
+ vals = line.strip().split("\t")
+ nid = vals[0]
+ names[nid] = vals[1]
+ long_names[nid] = vals[2]
+ files.append((f'treeoflife.interactomes.zip:treeoflife.interactomes/{nid}.txt', nid, None))
+
+def fetch_upstream(force=False):
+
+ with cache_open(f"treeoflife.species.pubmed.count.tsv") as f:
+ for i, line in enumerate(f):
+ if i < 2:
+ continue
+ vals = line.strip().split("\t")
+ nid = vals[0]
+ pub_count[nid] = int(vals[2])
+
+ with cache_open(f"treeoflife.species.evolution.tsv") as f:
+ for i, line in enumerate(f):
+ if i == 0:
+ continue
+ vals = line.strip().split("\t")
+ nid = vals[0]
+ evo_time[nid] = float(vals[1])
+ domain[nid] = vals[2]
+ tax_level2[nid] = vals[3]
+
+ with cache_open(f"treeoflife.taxonomy.zip", "rb") as f:
+ with zipfile.ZipFile(f) as zf:
+ for net in names.keys():
+ with zf.open(f"treeoflife.taxonomy/{net}.txt", "r") as myfile:
+ tax[net] = myfile.read().decode("utf8").strip().split("; ")
+ 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 fnames, alt, fmt in files:
+ if alts is not None and alt not in alts:
+ continue
+ if isinstance(fnames, str):
+ fnames = [fnames]
+ with ExitStack() as stack:
+ fs = [stack.enter_context(open_upstream_file(name, fn, "r")) for fn in fnames]
+ def get_edges():
+ for line in fs[0]:
+ vals = line.strip().split()
+ yield vals
+ g = Graph(directed=False)
+ g.vp.name = g.add_edge_list(get_edges(), hashed=True)
+
+ remove_parallel_edges(g)
+
+ g.gp.name = g.new_gp("string", val=names[alt])
+ g.gp.long_name = g.new_gp("string", val=long_names[alt])
+ g.gp.pub_count = g.new_gp("string", val=pub_count[alt])
+ g.gp.evo_time = g.new_gp("double", val=evo_time.get(alt, np.nan))
+ g.gp.domain = g.new_gp("string", val=domain.get(alt, ""))
+ g.gp.taxonomy_level2 = g.new_gp("string", val=tax_level2.get(alt, ""))
+ g.gp.taxonomy = g.new_gp("vector<string>", val=tax.get(alt, []))
+
+ yield alt, g