config_example_pdk2.yaml

##### IsoTV Config File

pipeline: "IsoTV"
repo: "https://github.molgen.mpg.de/MayerGroup/IsoTV"

### Ouput directory

outdir: "example"

### General pipeline parameters:

basecalling: FALSE
preprocess: FALSE
annotation: TRUE
quantification: TRUE

###### ONT long read processing config
### Basecalling pipeline parameters

guppy: "/path/to/Guppy324/bin/guppy_basecaller"
flowcell: FLO-MIN106
kit: SQK-DCS109

### Reference Files
genome_fasta: "/path/to/GRCh38.p12.primary_assembly.genome.fa"
genome_annot: "/path/to/gencode.v32.primary_assembly.annotation.gtf"

### Samples
# samples with .bottom extension must be placed in the RawData folder
# condition_replicate
samples:
    A549_1: "A549_r1_r3"
    A549_2: "A549_r2_r1"
    A549_5: "A549_r5_r3"
    HCT116_1: "HCT116_r1_r4"
    HCT116_3: "HCT116_r3_r2"
    HCT116_4: "HCT116_r4_r1"
    HCT116_5: "HCT116_r5_r1"
    HEPG2_1: "HEPG2_r1_r1"
    HEPG2_4: "HEPG2_r4_r2"
    HEPG2_5: "HEPG2_r5_r3"
    K562_1: "K562_r1_r2"
    K562_2: "K562_r2_r1"
    K562_3: "K562_r3_r1"
    K562_4: "K562_r4_r2"
    MCF7_1: "MCF7_r1_r2"
    MCF7_3: "MCF7_r3_r3"
    MCF7_4: "MCF7_r4_r2"

threads: 16

# Use pychopper results
pychopper: TRUE

# Use annotation to improve splice junction mapping (minimap2 --junc_bed parameter)
minimap2_opts_junction: TRUE

# Minimum read quality to keep:
min_mean_q: 5

# Stringency of porechop heuristic:
porechop_heu_stringency: 0.25

# Options passed to minimap2 during indexing:
minimap2_index_opts: "-k14"

# Extra options passed to minimap2:
minimap2_opts: "-uf"  # required for stranded data e.g. when pychopper filtered

# Minmum mapping quality:
minimum_mapping_quality: 5

# Options passed to spliced_bam2gff:
spliced_bam2gff_opts: "-s"  # required for stranded data e.g. when pychopper filtered

# -c parameter:
minimum_cluster_size: 3

# -p parameter:
minimum_isoform_percent: 1

# -d parameter:
exon_boundary_tolerance: 10

# -e parameter:
terminal_exon_boundary_tolerance: 50

# Extra options passed to minimap2 when mapping polished reads:
minimap2_opts_polished: "-uf"   # required for stranded data e.g. when pychopper filtered

# Options passed to spliced_bam2gff when converting alignments of polished reads:
spliced_bam2gff_opts_pol: "-s"  # required for stranded data e.g. when pychopper filtered

# Options passed to collapse_partials when collapsing fragmentation artifacts
# Internal exon boundary tolerance:
collapse_internal_tol: 5

# Five prime boundary tolerance:
collapse_five_tol: 500

# Three prime boundary tolerance:
collapse_three_tol: 50

maximum_secondary: 200
secondary_score_ratio: 1

##### Feature Analysis Config
### Input genes

gene_file: "data/genes.tab"

### Output file and folder

output_plots: "test.pdf"

### Processed file paths - required if not using ONT long read processing workflow

nanopore_gtf: "data/PDK2.nanopore.gtf"
polished_reads: "data/PDK2.transcriptome.fas"
counts_data: "data/PDK2.counts.txt"

# Is data continuous
continuous: FALSE

### External tool paths and functional analysis

aa: TRUE

iupred2a_path: "/path/to/iupred2a/iupred2a.py"
iupred2a: TRUE

brewery_path: "/path/to/Brewery/Brewery.py"
brewery: TRUE

interproScan_path: "/path/to/my_interproscan/interproscan-5.38-76.0/interproscan.sh"
pfam: TRUE

prositeScan_path: "/path/to/ps_scan/ps_scan.pl"
pfScan_path: "/path/to/ps_scan/pfscan"
prositeDat_path: "/path/to/prosite.dat"
pfScan: TRUE

minIsoTPM: 1
maxIsoNum: 8
minIsoPct: 10

### Misc paths

java : "/pkg/openjdk-11.0.3.2-0/profile"

lock1: "/.../lock.txt"
lock2: "/.../lock2.txt"