Transform lengthy academic papers into concise, structured 250-word abstracts.
The English summary is being prepared. Showing the original description.
Use Bio.Phylo to read/write phylogenetic trees and perform visualization and statistics; use when tree parsing/conversion, pruning/rerooting, distance calculation, or plotting is required.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Bio.Phylo with support for common formats (Newick/NEXUS/phyloXML).biopython>=1.80matplotlib>=3.7The following example is runnable end-to-end and follows the conventions:
config/task_config.json.python scripts/phylo_task.py.encoding="utf-8".ensure_ascii=False.config/task_config.json{
"input_tree": "data/input_tree.nwk",
"input_format": "newick",
"output_tree": "artifacts/output_tree.xml",
"output_format": "phyloxml",
"prune_terminals": ["TaxonC"],
"reroot_outgroup": "TaxonB",
"ascii_out": "artifacts/tree_ascii.txt",
"stats_out": "artifacts/tree_stats.json",
"plot_enabled": true,
"plot_out": "artifacts/tree_plot.png"
}
scripts/phylo_task.pyimport json
import os
from typing import Any, Dict, List, Optional
from Bio import Phylo
def ensure_parent_dir(path: str) -> None:
parent = os.path.dirname(path)
if parent:
os.makedirs(parent, exist_ok=True)
def load_config(path: str) -> Dict[str, Any]:
with open(path, "r", encoding="utf-8") as f:
return json.load(f)
def prune_by_names(tree, names: List[str]) -> None:
# Prune terminals by name if present
for n in names:
if tree.find_any(name=n) is not None:
tree.prune(target=n)
def reroot_by_outgroup_name(tree, outgroup_name: str) -> None:
outgroup = tree.find_any(name=outgroup_name)
if outgroup is None:
raise ValueError(f"Outgroup '{outgroup_name}' not found in tree terminals/clades.")
tree.root_with_outgroup(outgroup)
def tree_stats(tree) -> Dict[str, Any]:
terminals = tree.get_terminals()
nonterminals = tree.get_nonterminals()
# Collect branch lengths (may include None)
lengths = []
for clade in tree.find_clades(order="preorder"):
if clade.branch_length is not None:
lengths.append(float(clade.branch_length))
return {
"n_terminals": len(terminals),
"n_nonterminals": len(nonterminals),
"n_clades_total": len(terminals) + len(nonterminals),
"branch_length_count": len(lengths),
"branch_length_sum": sum(lengths) if lengths else 0.0,
"branch_length_min": min(lengths) if lengths else None,
"branch_length_max": max(lengths) if lengths else None,
"branch_length_mean": (sum(lengths) / len(lengths)) if lengths else None,
}
def write_ascii(tree, out_path: str) -> None:
ensure_parent_dir(out_path)
with open(out_path, "w", encoding="utf-8") as f:
Phylo.draw_ascii(tree, file=f)
def plot_tree(tree, out_path: str) -> None:
# Optional dependency: matplotlib
import matplotlib
matplotlib.use("Agg") # headless backend
import matplotlib.pyplot as plt
ensure_parent_dir(out_path)
fig = plt.figure(figsize=(10, 6))
ax = fig.add_subplot(1, 1, 1)
Phylo.draw(tree, do_show=False, axes=ax)
fig.tight_layout()
fig.savefig(out_path, dpi=200)
plt.close(fig)
def main(config_path: str = "config/task_config.json") -> None:
cfg = load_config(config_path)
input_tree = cfg["input_tree"]
input_format = cfg.get("input_format", "newick")
output_tree = cfg["output_tree"]
output_format = cfg.get("output_format", "phyloxml")
prune_terminals: List[str] = cfg.get("prune_terminals", [])
reroot_outgroup: Optional[str] = cfg.get("reroot_outgroup")
ascii_out = cfg.get("ascii_out", "artifacts/tree_ascii.txt")
stats_out = cfg.get("stats_out", "artifacts/tree_stats.json")
plot_enabled = bool(cfg.get("plot_enabled", False))
plot_out = cfg.get("plot_out", "artifacts/tree_plot.png")
# Read
tree = Phylo.read(input_tree, input_format)
# Manipulate
if prune_terminals:
prune_by_names(tree, prune_terminals)
if reroot_outgroup:
reroot_by_outgroup_name(tree, reroot_outgroup)
# Write converted tree
ensure_parent_dir(output_tree)
Phylo.write(tree, output_tree, output_format)
# ASCII visualization
write_ascii(tree, ascii_out)
# Stats
ensure_parent_dir(stats_out)
with open(stats_out, "w", encoding="utf-8") as f:
json.dump(tree_stats(tree), f, ensure_ascii=False, indent=2)
# Plot (optional)
if plot_enabled:
plot_tree(tree, plot_out)
if __name__ == "__main__":
main()
python scripts/phylo_task.py
config/task_config.json as an intermediate artifact; scripts are invoked uniformly via python scripts/<task_name>.py. Avoid stacking many CLI -- arguments; prefer config files.encoding="utf-8".ensure_ascii=False to preserve non-ASCII characters.Phylo.read(...) and Phylo.write(...) (e.g., newick, nexus, phyloxml).tree.prune(target=<name>). Names not found are skipped (or can be treated as errors depending on your policy).tree.root_with_outgroup(outgroup_clade); the outgroup is located via tree.find_any(name=...).None); statistics should ignore missing values.tree.get_terminals() and tree.get_nonterminals().Phylo.draw_ascii(tree, file=...) for deterministic CLI-friendly rendering.Agg) for headless environments and saves to an image file.No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Transform lengthy academic papers into concise, structured 250-word abstracts.
The English summary is being prepared. Showing the original description.
Precision editing tool that reduces abstract word count through intelligent compression techniques, maintaining scientific rigor while meeting strict journal and conference requirements.
The English summary is being prepared. Showing the original description.
Refines long medical academic texts into SCI-style unstructured Chinese and English abstracts; use when you need to condense drafts/reports/summaries into bilingual abstracts and generate Summary_Report.md.
The English summary is being prepared. Showing the original description.
Generates submission-ready Elsevier/SCI Highlights from manuscript text or extracted PDF/DOCX/TXT content. Use when a user needs 3-5 concise, evidence-grounded highlight bullets for a research paper, review, meta-analysis, case report, or bioinformatics manuscript.
The English summary is being prepared. Showing the original description.
Generates complete FAERS pharmacovigilance study designs for multi-drug or class-level safety comparison inside one predefined SOC or AE family using active comparators, disproportionality analysis, subgroup characterization, and reviewer-facing evidence control.
The English summary is being prepared. Showing the original description.
Analyze data with `adme-property-predictor` using a reproducible workflow, explicit validation, and structured outputs for review-ready interpretation.
The English summary is being prepared. Showing the original description.