From b2324dc0c9b02d01bbd6364a721c9e6535e36a88 Mon Sep 17 00:00:00 2001 From: Keshav Date: Fri, 20 Feb 2026 15:15:14 +0100 Subject: [PATCH] Merged template changes and put into new branch for unique PR. --- config_template/template_neat_config.yml | 96 ++++++++++++------------ 1 file changed, 47 insertions(+), 49 deletions(-) diff --git a/config_template/template_neat_config.yml b/config_template/template_neat_config.yml index 84d2c3af..4bdc8fb1 100644 --- a/config_template/template_neat_config.yml +++ b/config_template/template_neat_config.yml @@ -1,25 +1,27 @@ -## Template for gen_reads parallel +## Template for NEAT's read-simulator (as of version 4.3.5, parallelization-friendly) ## Any parameter that is not required but has a default value will use the ## default value even if the variable is not included in the config. For -## required items, they must be included in the config and the must be given a value. +## required items, they must be included in the config and they must be given a value. ## All other items can be present or not. If present and the value is set to a single ## period, the variable will be treated as though it had been omitted. Please do -## not modify this template, but instead make a copy in your working directory. Done this -## way, you can run without even needing to declare -c. +## not modify this template, but instead make a copy in your working directory. +## Run with this command: neat read-simulator -c -o [-p ] -# Absolute path to input reference fasta file +# Absolute path to input reference FASTA file # type = string | required: yes reference: REQUIRED -# Read length of the reads in the fastq output. Only required if @produce_fastq is set to true -# type = int | required: no | default = 101 +# Read length of the reads in the FASTQ output. Only required if @produce_fastq is set to true +# type = int | required: no | default = 151 read_len: . -# Average Coverage for the entire genome. +# Average coverage for the entire genome # type = float | required: no | default = 10.0 coverage: . -# Absolute path to file with sequencing error model +# Absolute path to file with sequencing error model or quality-score model. +# Error models are typically produced by neat model-seq-err (from FASTQ/BAM-like inputs), while +# quality-score models can be produced by neat model-qual-score (optionally fit with --markov) # type = string | required: no | default: /neat/models/defaults/default_error_model.pickle.gz error_model: . @@ -27,13 +29,12 @@ error_model: . # type = float | required = no | must be between 0.0 and 0.3 avg_seq_error: . -# This scales the quality scores to match the desired average sequencing error rate -# specified by avg_seq_error. +# This scales the quality scores to match the desired average sequencing error rate specified by avg_seq_error # type: boolean | required = no | default = false rescale_qualities: . -# This is the factor to add to the quality scores to get the ascii text version of the -# score. The default follows the sanger quality offset +# This is the factor to add to the quality scores to get the ASCII text version of the +# score. The default follows the Sanger quality offset # type: int | required = no | default = 33 quality_offset: . @@ -41,97 +42,94 @@ quality_offset: . # type = int | required = no | default = 2 ploidy: . -# Absolute path to vcf file containing variants that will always be included, regardless -# of genotype and filter. You can pre-filter your vcf for these fields before inputting it -# if this is not the desired behavior. +# Absolute path to VCF file containing variants that will always be included, regardless +# of genotype and filter. You can pre-filter your VCF for these fields before inputting it +# if this is not the desired behavior # type: string | required = no include_vcf: . -# Absolute path to bed file containing reference regions that the simulation -# should target. +# Absolute path to BED file containing reference regions that the simulation should target # type = string | required = no target_bed: . -# Scalar value for coverage in regions outside the targeted bed. Example 0.5 +# Scalar value for coverage in regions outside the targeted BED. Example: 0.5 # would get you roughly half the coverage as the on target areas. Default is -# 0 coverage in off-target regions. Number should be a float in decimal. +# 0 coverage in off-target regions. Number should be a float in decimal # type: float | required = no | default = 0.00 off_target_scalar: . -# Absolute path to bed file containing reference regions that the simulation -# should discard. +# Absolute path to BED file containing reference regions that the simulation should discard # type = string | required = no discard_bed: . # Absolute path to the mutation model pickle file. Omitting this value will cause -# NEAT to use the default model, with some standard parameters, and generally uniform biases. +# NEAT to use the default model, with some standard parameters, and generally uniform biases # type: string | required = no mutation_model: . -# Average mutation rate per base pair. Overall average is 0.001, or model default -# Use either this value to override the mutation rate for the default or input model. +# Average mutation rate per base pair. Overall average is 0.001, or model default. +# Use either this value to override the mutation rate for the default or input model # type: float | required = no | must be between 0.0 and 0.3 mutation_rate: . -# Absolute path to a bed file with mutation rates by region. -# Rates must be in the fourth column and be of the form "mut_rate=x.xx" -# Rates must be between 0.00 and 0.03 +# Absolute path to a BED file with mutation rates by region. +# Rates must be in the third column and be of the form "mut_rate=x.xx" +# Rates must be between 0.0 and 0.3 # type: string | required = no mutation_bed: . -# Whether the output should be paired ended. For certain conditions (i.e., vcf only or -# fasta only), this will be ignored. If this is true, then there must be an included fragment +# Whether the output should be paired ended. For certain conditions (i.e., VCF only or +# FASTA only), this will be ignored. If this is true, then there must be an included fragment # length model output from runner.py or a mean and standard deviation -# by declaring values for @fragment_mean and @fragment_std_dev. +# by declaring values for @fragment_mean and @fragment_std_dev # type: boolean | required = no | default = false paired_ended: . -# Absolute path to a pickle file containing the fragment length model output -# from runner.py. +# Absolute path to a pickle file containing the fragment length model. +# Typically produced by neat model-fraglen (learned from BAM alignments) # type: string | required = no | default: /neat/models/defaults/default_fraglen_model.pickle.gz fragment_model: . -# Mean for the paired end fragment length. This only applies if paired-ended is set to true. +# Mean for the paired-end fragment length. This only applies if paired-ended is set to true. # This number will form the mean for the sample distribution of the fragment lengths in the simulation # Note: This number is REQUIRED if paired_ended is set to true, unless a fragment length model is used. # type: float | required: no (unless paired-ended) fragment_mean: . -# Standard deviation for the paired end fragment length. This only applies if paired-ended is set to true. +# Standard deviation for the paired-end fragment length. This only applies if paired-ended is set to true. # This number will form the standard deviation about the mean specified above for the sample distribution -# of the fragment lengths in the simulation. +# of the fragment lengths in the simulation # Note: This number is REQUIRED if paired_ended is set to true, unless a fragment length model is used. # type: float | required: no (unless paired-ended) fragment_st_dev: . -# Whether to produce the golden bam file. This file will contain the reads +# Whether to produce the golden BAM file. This file will contain the reads # aligned with the exact region of the genome # type: boolean | required = no | default = false produce_bam: . -# Whether to produce a vcf file containing all the mutation errors added -# by NEAT. +# Whether to produce a VCF file containing all the mutation errors added by NEAT # type: boolean | required = no | default = false produce_vcf: . -# Whether to output the fastq(s) of the reads. This is the default output. NEAT -# will produce 1 fastq for single ended reads or 2 fastqs for paired ended. +# Whether to output the FASTQ(s) of the reads. This is the default output. NEAT +# will produce 1 FASTQ for single-ended reads or 2 FASTQs for paired-ended reads # type: boolean | required = no | default = true produce_fastq: . # If set to true, this will ignore statistical models and force coverage to be -# constant across the genome. This is considered a debugging feature. +# constant across the genome. This is considered a debugging feature # type: boolean | required = no | default = false no_coverage_bias: . # Set an RNG seed value. Runs using identical RNG values should produce identical results # so things like read locations, variant positions, error positions, etc. should be the same. -# Useful for debugging. +# Useful for debugging # type: int | required = no rng_seed: . # Set an absolute minimum number of mutations. The program always adds at least 1 mutation. -# Useful for very small datasets. +# Useful for very small datasets # type: int | required = no min_mutations: . @@ -141,17 +139,17 @@ min_mutations: . overwrite_output: . # How to split the input reference for parallelization -# Note if threads == 1, this option has no effect. +# Note: If threads == 1, this option has no effect. # type = string | required: no | default = contig | values: contig, size parallel_mode: . # Target block size if by = size (overlap = read_len * 2). -# Default is 500000 when by = size. Not used for by = contig. +# Default is 500000 when by = size. Not used for by = contig # type = int | required: no | default = 500000 (when by=size) parallel_block_size: . -# Maximum number of concurrent NEAT jobs (threads or hyperthreads) to run. -# type = int | required: no | default = all available. +# Maximum number of concurrent NEAT jobs (threads or hyperthreads) to run +# type = int | required: no | default = all available threads: . # Delete the 'splits' directory after stitching completes @@ -160,7 +158,7 @@ threads: . cleanup_splits: . # Reuse existing files in '/splits' and skip the split step. -# The directory must contain neat-generated files and must be in the output dir within "splits" +# The directory must contain NEAT-generated files and must be in the output directory within "splits" # Note if threads == 1, this option has no effect. # type = bool | required: no | default = False reuse_splits: . \ No newline at end of file