Bakta Genome Annotation

# Install Bakta via conda/mamba (recommended)
mamba install -c conda-forge -c bioconda bakta

# Verify installation
bakta --version
# bakta 1.9.4

# Download the light database (~3 GB, faster, fewer functional hits)
bakta_db download --output db/ --type light

# Or full database (~70 GB, comprehensive UniRef100 coverage)
# bakta_db download --output db/ --type full

# Install Python parsing dependencies
pip install biopython pandas matplotlib

decisions:
  - id: D1
    param: database
    kind: required
    source: user
    ask: "Annotate against the light database or the full one? The light database leaves more genes described only generically."
    default: null

  - id: D2
    param: organismMetadata
    kind: required
    source: user
    ask: "Which genus, species, and strain should be recorded in the output?"
    default: null

  - id: D3
    param: repliconTopology
    kind: required
    source: data
    ask: "Are these contigs complete circular replicons, plasmids, or draft fragments?"
    default: "draft fragments - no circularity assumed"

  - id: D4
    param: assemblyOrigin
    kind: required
    source: data
    ask: "Is this an isolate genome, or a bin recovered from a metagenome?"
    default: "isolate - gene prediction trains on the assembly itself"

  - id: D5
    param: translationTable
    kind: required
    source: user
    ask: "Which genetic code does this organism use?"
    default: "11, the bacterial and archaeal code"

  - id: D6
    param: locusTagPrefix
    kind: optional
    source: user
    ask: "Which prefix should locus tags carry, if they will be submitted or cross-referenced?"
    default: "generated automatically"

  - id: D7
    param: minContigLength
    kind: optional_conditional
    source: data
    ask: "Should short contigs be skipped?"
    default: "no minimum"

  - id: D8
    param: threadsAndPlotting
    kind: never_ask
    source: data
    reason: "Thread count and the circular plot affect runtime and output files, not the annotation"
    default: "available cores, plot enabled"

# Annotate a bacterial genome — results in results/ directory
bakta genome.fasta \
    --db db/bakta_db_light \
    --output results/ \
    --prefix sample1 \
    --threads 8

# Inspect the JSON summary for feature counts
python -c "
import json
with open('results/sample1.json') as f:
    d = json.load(f)
print('Genus:', d['genome'].get('genus'))
print('Length:', d['genome']['size'], 'bp')
print('CDS:', sum(1 for f in d['features'] if f['type'] == 'cds'))
print('tRNA:', sum(1 for f in d['features'] if f['type'] == 'tRNA'))
"

# Create a dedicated conda environment (avoids dependency conflicts)
mamba create -n bakta_env -c conda-forge -c bioconda bakta python=3.11 -y
mamba activate bakta_env

# Verify Bakta and its dependencies
bakta --version
# bakta 1.9.4

bakta --help | head -20

# Download the light database (sufficient for routine annotation)
mkdir -p db/
bakta_db download --output db/ --type light
# Downloads ~3 GB; expands to ~5 GB on disk

# Verify the database was extracted correctly
ls db/bakta_db_light/
# antifam.h3f  bakta.db  expert  oric.fna  pfam.h3f  rfam-go.tsv  ...

# (Optional) Update AMRFinderPlus DB used by Bakta for AMR gene calling
amrfinder -u

# Install Python parsing tools
pip install biopython pandas matplotlib

from Bio import SeqIO
import re

input_fasta = "genome.fasta"
records = list(SeqIO.parse(input_fasta, "fasta"))
print(f"Input assembly: {len(records)} contigs")
total_bases = sum(len(r) for r in records)
print(f"Total bases: {total_bases:,}")
print(f"Largest contig: {max(len(r) for r in records):,} bp")

# Bakta preferred: short, alphanumeric, unique IDs
cleaned = []
for i, rec in enumerate(records, 1):
    new_id = f"contig_{i:04d}"
    new_rec = rec.__class__(rec.seq, id=new_id, description="")
    cleaned.append(new_rec)

SeqIO.write(cleaned, "genome_clean.fasta", "fasta")
print(f"Wrote genome_clean.fasta with {len(cleaned)} contigs")

# Filter out short contigs (<200 bp) which contribute little to annotation
awk 'BEGIN{RS=">"; ORS=""} NR>1 {n=split($0, a, "\n"); seq=""; for(i=2;i<=n;i++) seq=seq a[i]; if (length(seq) >= 200) print ">" $0}' \
    genome_clean.fasta > genome_filtered.fasta

echo "Filtered assembly: $(grep -c '>' genome_filtered.fasta) contigs"

# Standard annotation for a draft bacterial genome
bakta genome_clean.fasta \
    --db db/bakta_db_light \
    --output annotation/ \
    --prefix E_coli_K12 \
    --genus Escherichia \
    --species coli \
    --strain K12 \
    --locus-tag ECOLI \
    --threads 8 \
    --keep-contig-headers

# Expected runtime: 5–15 min for ~5 Mb genome on 8 CPUs (light DB)

echo "Bakta annotation outputs:"
ls annotation/
# E_coli_K12.embl   E_coli_K12.faa     E_coli_K12.ffn
# E_coli_K12.fna    E_coli_K12.gbff    E_coli_K12.gff3
# E_coli_K12.hypotheticals.faa  E_coli_K12.hypotheticals.tsv
# E_coli_K12.json   E_coli_K12.log     E_coli_K12.png
# E_coli_K12.svg    E_coli_K12.tsv     E_coli_K12.txt

import json
import pandas as pd
from collections import Counter

with open("annotation/E_coli_K12.json") as f:
    bakta = json.load(f)

# Genome-level metadata
genome = bakta["genome"]
print(f"Organism: {genome.get('genus')} {genome.get('species')} {genome.get('strain')}")
print(f"Size: {genome['size']:,} bp across {len(bakta['sequences'])} sequences")
print(f"GC content: {genome['gc']:.2%}")

# Feature type counts
features = bakta["features"]
type_counts = Counter(f["type"] for f in features)
print("\nFeature counts:")
for ftype, n in sorted(type_counts.items(), key=lambda x: -x[1]):
    print(f"  {ftype:>10}: {n}")

# Build a tidy CDS DataFrame
cds_rows = []
for f in features:
    if f["type"] != "cds":
        continue
    cds_rows.append({
        "locus_tag": f.get("locus", ""),
        "contig":    f.get("contig", ""),
        "start":     f.get("start"),
        "stop":      f.get("stop"),
        "strand":    f.get("strand"),
        "gene":      f.get("gene", ""),
        "product":   f.get("product", ""),
        "length_aa": len(f.get("aa", "")),
    })

cds_df = pd.DataFrame(cds_rows)
print(f"\nTotal CDS: {len(cds_df)}")
print(cds_df.head(5).to_string(index=False))

import pandas as pd

# Bakta TSV begins with comment lines starting with '#'
df = pd.read_csv("annotation/E_coli_K12.tsv", sep="\t", comment="#",
                 names=["sequence_id", "type", "start", "stop", "strand",
                        "locus_tag", "gene", "product", "dbxrefs"])
print(f"Total features: {len(df)}")
print(f"Feature types: {df['type'].value_counts().to_dict()}")

# Hypothetical vs annotated CDS
cds = df[df["type"] == "cds"].copy()
hypothetical = cds["product"].str.contains("hypothetical", case=False, na=True)
print(f"\nCDS with assigned function: {(~hypothetical).sum()} / {len(cds)}")
print(f"Hypothetical proteins: {hypothetical.sum()}")

# Cross-references (UniRef, KEGG, EC, GO, etc.) parsed from the dbxrefs column
def split_xrefs(xref_str):
    if not isinstance(xref_str, str) or xref_str in ("", "-"):
        return []
    return [x.strip() for x in xref_str.split(",")]

cds["dbxref_list"] = cds["dbxrefs"].apply(split_xrefs)
ec_hits = cds[cds["dbxref_list"].apply(lambda xs: any(x.startswith("EC:") for x in xs))]
print(f"CDS with EC numbers: {len(ec_hits)}")
print(ec_hits[["locus_tag", "gene", "product"]].head(5).to_string(index=False))

# Re-render the plot from the existing JSON with a different style
bakta_plot --output annotation/ \
           --prefix E_coli_K12_replot \
           --type cog \
           --dpi 300 \
           annotation/E_coli_K12.json

ls annotation/E_coli_K12_replot.*
# E_coli_K12_replot.png  E_coli_K12_replot.svg

# Display the rendered PNG inline in a Jupyter notebook
python <<'PY'
from pathlib import Path
import matplotlib.pyplot as plt
import matplotlib.image as mpimg

img = mpimg.imread("annotation/E_coli_K12.png")
fig, ax = plt.subplots(figsize=(6, 6))
ax.imshow(img)
ax.axis("off")
ax.set_title("Bakta circular genome annotation")
plt.savefig("bakta_circular_thumbnail.png", dpi=120, bbox_inches="tight")
print("Saved bakta_circular_thumbnail.png")
PY

import json
import pandas as pd
import matplotlib.pyplot as plt

with open("annotation/E_coli_K12.json") as f:
    bakta = json.load(f)

genome_size = bakta["genome"]["size"]
features = bakta["features"]

# Per-feature-type counts and density (per Mb)
counts = {}
for f in features:
    counts[f["type"]] = counts.get(f["type"], 0) + 1
density = {k: v / (genome_size / 1e6) for k, v in counts.items()}

cds = [f for f in features if f["type"] == "cds"]
n_cds = len(cds)
n_hypo = sum(1 for f in cds if "hypothetical" in (f.get("product") or "").lower())
n_known = n_cds - n_hypo
coding_density = sum(abs(f["stop"] - f["start"] + 1) for f in cds) / genome_size

print(f"Genome: {genome_size:,} bp")
print(f"CDS: {n_cds}  ({density.get('cds', 0):.1f} per Mb)")
print(f"  Known function: {n_known}  Hypothetical: {n_hypo}")
print(f"Coding density: {coding_density:.1%}")
print(f"tRNA: {counts.get('tRNA', 0)}   rRNA: {counts.get('rRNA', 0)}")
print(f"ncRNA: {counts.get('ncRNA', 0)}  CRISPR: {counts.get('crispr', 0)}")

# Bar plot of feature type counts
fig, ax = plt.subplots(figsize=(8, 4))
items = sorted(counts.items(), key=lambda x: -x[1])
labels = [k for k, _ in items]
values = [v for _, v in items]
bars = ax.bar(labels, values, color="#2980B9", edgecolor="white")
for bar, v in zip(bars, values):
    ax.text(bar.get_x() + bar.get_width() / 2, v + max(values) * 0.01,
            str(v), ha="center", fontsize=9)
ax.set_ylabel("Count")
ax.set_title("Bakta feature counts by type")
plt.xticks(rotation=20)
plt.tight_layout()
plt.savefig("bakta_feature_counts.png", dpi=150, bbox_inches="tight")
print("Saved bakta_feature_counts.png")

#!/bin/bash
# batch_bakta.sh — annotate all FASTA files in a directory
INPUT_DIR="genomes/"
OUTPUT_DIR="annotations/"
DB="db/bakta_db_light"
mkdir -p "$OUTPUT_DIR"

for FASTA in "$INPUT_DIR"/*.fasta; do
    SAMPLE=$(basename "$FASTA" .fasta)
    echo "Annotating: $SAMPLE"
    bakta "$FASTA" \
        --db "$DB" \
        --output "${OUTPUT_DIR}/${SAMPLE}" \
        --prefix "$SAMPLE" \
        --threads 4 \
        --skip-plot \
        --force
done

echo "Batch annotation complete."

# Aggregate per-genome summaries from each sample's JSON file
from pathlib import Path
import json
import pandas as pd

annotation_dir = Path("annotations/")
rows = []
for json_file in sorted(annotation_dir.glob("*/*.json")):
    with open(json_file) as f:
        bakta = json.load(f)
    sample = json_file.stem
    counts = {}
    for feat in bakta["features"]:
        counts[feat["type"]] = counts.get(feat["type"], 0) + 1
    rows.append({
        "sample":  sample,
        "size":    bakta["genome"]["size"],
        "gc":      bakta["genome"]["gc"],
        "CDS":     counts.get("cds", 0),
        "tRNA":    counts.get("tRNA", 0),
        "rRNA":    counts.get("rRNA", 0),
        "ncRNA":   counts.get("ncRNA", 0),
        "crispr":  counts.get("crispr", 0),
    })

summary_df = pd.DataFrame(rows)
print(f"Annotated genomes: {len(summary_df)}")
print(summary_df.to_string(index=False))
summary_df.to_csv("batch_bakta_summary.csv", index=False)
print("Saved: batch_bakta_summary.csv")

bakta plasmid.fasta \
    --db db/bakta_db_light \
    --output plasmid_annotation/ \
    --prefix pBR322 \
    --plasmid \
    --complete \
    --threads 4

# Inspect plasmid-typing results (incompatibility group, replication initiator)
grep -E "rep|inc" plasmid_annotation/pBR322.tsv | head -10