oxo-call 0.11.0

Model-intelligent orchestration for CLI bioinformatics — call any tool with LLM intelligence
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108

# =============================================================================
# ATAC-seq workflow — oxo-call native format
#
# Usage:
#   oxo-call workflow run     atacseq.toml
#   oxo-call workflow dry-run atacseq.toml
#   oxo-call workflow export  atacseq.toml --to snakemake
# =============================================================================

[workflow]
name        = "atacseq"
description = "ATAC-seq: fastp → Bowtie2 → Picard dedup → blacklist filter → MACS3 peaks"
version     = "1.0"

[wildcards]
sample = ["sample1", "sample2"]

# ── Configurable parameters ───────────────────────────────────────────────────
# REQUIRED: update these paths to match your environment before running.
[params]
threads       = "8"
bowtie2_index = "/path/to/bt2_index"    # REQUIRED: Bowtie2 index prefix (e.g. /data/hg38/bt2/hg38)
blacklist     = "/path/to/blacklist.bed"  # REQUIRED: ENCODE blacklist BED for your genome
genome_size   = "hs"                      # macs3 genome size: hs=human, mm=mouse, ce=worm, dm=fly

# =============================================================================

[[step]]
name    = "fastp"
cmd     = """\
fastp \
  --in1  data/{sample}_R1.fastq.gz \
  --in2  data/{sample}_R2.fastq.gz \
  --out1 trimmed/{sample}_R1.fastq.gz \
  --out2 trimmed/{sample}_R2.fastq.gz \
  --html qc/{sample}_fastp.html \
  --json qc/{sample}_fastp.json \
  --thread {params.threads} \
  --detect_adapter_for_pe \
  --length_required 20\
"""
inputs  = ["data/{sample}_R1.fastq.gz", "data/{sample}_R2.fastq.gz"]
outputs = ["trimmed/{sample}_R1.fastq.gz", "trimmed/{sample}_R2.fastq.gz"]

[[step]]
name       = "multiqc"
gather     = true
depends_on = ["fastp"]
cmd        = "multiqc qc/ -o results/multiqc/ --force"
inputs     = []
outputs    = ["results/multiqc/multiqc_report.html"]

[[step]]
name       = "bowtie2"
depends_on = ["fastp"]
cmd        = """\
bowtie2 \
  -x {params.bowtie2_index} \
  -1 trimmed/{sample}_R1.fastq.gz \
  -2 trimmed/{sample}_R2.fastq.gz \
  -p {params.threads} \
  --no-mixed --no-discordant --no-unal \
  | samtools sort -@ 4 -o aligned/{sample}.sorted.bam\
"""
inputs  = ["trimmed/{sample}_R1.fastq.gz", "trimmed/{sample}_R2.fastq.gz"]
outputs = ["aligned/{sample}.sorted.bam"]

[[step]]
name       = "mark_duplicates"
depends_on = ["bowtie2"]
cmd        = """\
picard MarkDuplicates \
  I=aligned/{sample}.sorted.bam \
  O=aligned/{sample}.markdup.bam \
  M=qc/{sample}.markdup_metrics.txt \
  REMOVE_DUPLICATES=false && \
samtools index aligned/{sample}.markdup.bam\
"""
inputs  = ["aligned/{sample}.sorted.bam"]
outputs = ["aligned/{sample}.markdup.bam", "qc/{sample}.markdup_metrics.txt"]

[[step]]
name       = "filter"
depends_on = ["mark_duplicates"]
cmd        = """\
samtools view -@ {params.threads} -b -F 1804 -f 2 -q 30 aligned/{sample}.markdup.bam \
  | bedtools intersect -v -abam stdin -b {params.blacklist} \
  > aligned/{sample}.filtered.bam && \
samtools index aligned/{sample}.filtered.bam\
"""
inputs  = ["aligned/{sample}.markdup.bam"]
outputs = ["aligned/{sample}.filtered.bam"]

[[step]]
name       = "macs3"
depends_on = ["filter"]
cmd        = """\
macs3 callpeak \
  -t aligned/{sample}.filtered.bam \
  -f BAMPE \
  -n {sample} \
  --outdir peaks/ \
  -g {params.genome_size} \
  --nomodel --shift -75 --extsize 150 \
  -B --SPMR --keep-dup all\
"""
inputs  = ["aligned/{sample}.filtered.bam"]
outputs = ["peaks/{sample}_peaks.narrowPeak", "peaks/{sample}_summits.bed"]