BED3:  chr  start  end
BED4:  chr  start  end  name
BED5:  chr  start  end  name  score
BED6:  chr  start  end  name  score  strand
BED12: chr  start  end  name  score  strand  thickStart  thickEnd  rgb  blockCount  blockSizes  blockStarts

# Create simple BED3
echo -e "chr1\t100\t200\nchr1\t300\t400" > regions.bed

# Create BED6 with name and strand
echo -e "chr1\t100\t200\tpeak1\t100\t+" > peaks.bed

import pybedtools

# From string
bed_string = '''chr1\t100\t200\tpeak1\t100\t+
chr1\t300\t400\tpeak2\t200\t-'''
bed = pybedtools.BedTool(bed_string, from_string=True)

# From list of tuples
intervals = [
    ('chr1', 100, 200, 'peak1', 100, '+'),
    ('chr1', 300, 400, 'peak2', 200, '-'),
]
bed = pybedtools.BedTool(intervals)

# From pandas DataFrame
import pandas as pd
df = pd.DataFrame({
    'chrom': ['chr1', 'chr1'],
    'start': [100, 300],
    'end': [200, 400],
    'name': ['peak1', 'peak2'],
    'score': [100, 200],
    'strand': ['+', '-']
})
bed = pybedtools.BedTool.from_dataframe(df)

# Save to file
bed.saveas('output.bed')

# Sort by chromosome and position
sort -k1,1 -k2,2n input.bed > sorted.bed

# Using bedtools
bedtools sort -i input.bed > sorted.bed

# Sort by chromosome, start, then end
sort -k1,1 -k2,2n -k3,3n input.bed > sorted.bed

import pybedtools

bed = pybedtools.BedTool('input.bed')
sorted_bed = bed.sort()
sorted_bed.saveas('sorted.bed')

# Check column count
awk -F'\t' '{print NF}' input.bed | sort -u

# Check for invalid coordinates (start >= end)
awk '$2 >= $3' input.bed

# Check for negative coordinates
awk '$2 < 0 || $3 < 0' input.bed

# Validate with bedtools
bedtools sort -i input.bed > /dev/null 2>&1 && echo "Valid" || echo "Invalid"

import pybedtools

def validate_bed(filepath):
    try:
        bed = pybedtools.BedTool(filepath)
        for interval in bed:
            if interval.start < 0 or interval.end < 0:
                return False, 'Negative coordinates'
            if interval.start >= interval.end:
                return False, f'Invalid interval: {interval.start} >= {interval.end}'
        return True, 'Valid'
    except Exception as e:
        return False, str(e)

valid, msg = validate_bed('input.bed')
print(f'{msg}')

import pybedtools

# Load BED file
bed = pybedtools.BedTool('input.bed')

# Iterate over intervals
for interval in bed:
    print(f'{interval.chrom}:{interval.start}-{interval.end}')
    print(f'Name: {interval.name}, Score: {interval.score}, Strand: {interval.strand}')

# Count intervals
n_intervals = bed.count()

# Convert to pandas DataFrame
df = bed.to_dataframe()

# Access specific columns
df = bed.to_dataframe(names=['chrom', 'start', 'end', 'name', 'score', 'strand'])

# Single chromosome
grep "^chr1\t" input.bed > chr1.bed

# Multiple chromosomes
grep -E "^(chr1|chr2)\t" input.bed > chr1_2.bed

# Exclude chromosome
grep -v "^chrM\t" input.bed > no_chrM.bed

# Intervals >= 100bp
awk '($3 - $2) >= 100' input.bed > large.bed

# Intervals between 100-500bp
awk '($3 - $2) >= 100 && ($3 - $2) <= 500' input.bed > medium.bed

import pybedtools

bed = pybedtools.BedTool('input.bed')

# Filter by chromosome
chr1 = bed.filter(lambda x: x.chrom == 'chr1')

# Filter by size
large = bed.filter(lambda x: len(x) >= 100)

# Filter by strand
plus_strand = bed.filter(lambda x: x.strand == '+')

# Filter by score
high_score = bed.filter(lambda x: float(x.score) >= 500)

# Chain filters
result = bed.filter(lambda x: x.chrom == 'chr1' and len(x) >= 100)
result.saveas('filtered.bed')

# BED to GFF
bedtools bed12togff -i input.bed > output.gff

# BED to FASTA (extract sequences)
bedtools getfasta -fi reference.fa -bed input.bed -fo output.fa

# BED to FASTA with names
bedtools getfasta -fi reference.fa -bed input.bed -name -fo output.fa

# Extract variant positions
bcftools query -f '%CHROM\t%POS0\t%END\n' input.vcf > variants.bed

# Or using awk (simpler for SNPs)
grep -v "^#" input.vcf | awk '{print $1"\t"$2-1"\t"$2}' > snps.bed

# Convert alignments to BED
bedtools bamtobed -i input.bam > alignments.bed

# BED12 for spliced alignments
bedtools bamtobed -i input.bam -split > spliced.bed

import pybedtools

interval = pybedtools.create_interval_from_list(['chr1', '100', '200', 'peak1', '0', '+'])

# Access fields
print(interval.chrom)   # chr1
print(interval.start)   # 100 (int)
print(interval.end)     # 200 (int)
print(interval.name)    # peak1
print(interval.score)   # 0
print(interval.strand)  # +

# Get length
print(len(interval))    # 100

# Get fields list
print(interval.fields)  # ['chr1', '100', '200', 'peak1', '0', '+']

# Fixed-size windows across genome
bedtools makewindows -g genome.txt -w 10000 > windows_10kb.bed

# Windows with step size (sliding windows)
bedtools makewindows -g genome.txt -w 10000 -s 5000 > sliding_10kb.bed

# Fixed number of windows per chromosome
bedtools makewindows -g genome.txt -n 100 > 100_windows_per_chr.bed

# Windows within BED regions
bedtools makewindows -b regions.bed -w 1000 > windows_in_regions.bed

# Add window ID
bedtools makewindows -g genome.txt -w 10000 -i winnum > numbered_windows.bed

# Source chromosome in name
bedtools makewindows -g genome.txt -w 10000 -i srcwinnum > windows_with_source.bed

import pybedtools

# From genome file
windows = pybedtools.BedTool().window_maker(g='genome.txt', w=10000)

# Sliding windows
windows = pybedtools.BedTool().window_maker(g='genome.txt', w=10000, s=5000)

# From BED regions
bed = pybedtools.BedTool('regions.bed')
windows = pybedtools.BedTool().window_maker(b=bed.fn, w=1000)

windows.saveas('windows.bed')

import pybedtools

# At end of script
pybedtools.cleanup()

# Or use context manager (auto-cleanup)
pybedtools.set_tempdir('/tmp/pybedtools')