# ══════════════════════════════════════════════════════════════════════════
# maniFasta source registry
# One row = one source. Set enabled=TRUE to include it in the next build.
# ══════════════════════════════════════════════════════════════════════════
#
# WHAT TO CHANGE
#   To use any of the pre-packaged inputs simply set >ENABLED< to TRUE for each input you would like to include
#   To include your own files, add a new row: set source_dir=00.setup, point input_list/fasta_file/metadata_file at your file(s), and pick the module that matches your data
#   (see MODULE below).
#
# HOW TO POPULATE THE COLUMN FIELDS
#
# SOURCE ID    
#   A unique label for the dataset, internal row key only — never appears in the output FASTA/metadata.
#
# ENABLED
#   Indicates whether this input row should be included in the build
#   TRUE or FALSE
#
# SOURCE_LABEL
#   Written into every protein's FASTA header (src_db=) and the metadata >source< column. 
#   Must be unique across any sources that could be enabled together in the same build.
#
# SOURCE_GROUP
#   Written into every protein's FASTA header (group=). 
#   A coarser bucket than source_label — for downstream grouping/summary tables.
#   Safe to share across sources
#
# PATHS
#   source_dir + input_list/fasta_file/metadata_file are joined as: <mainDIR>/<source_dir>/<filename>
#   Common source_dir values: 99.prepackaged_inputs (curated inputs shipped with maniFasta) | 00.setup (your own run-specific files)
#
# MODULE  (what kind of source is this row?)
#   mod_I    proteome / genome accessions  → input_list only
#   mod_II   protein accessions            → input_list only
#   mod_III  ready-made FASTA file         → fasta_file (+ optional metadata_file)
#   mod_IV   built-in supported collection → collection (no input_list/fasta_file)
#
# COLLECTION  (mod_IV rows only — which built-in collection to fetch)
#   human_uniprot | HOMD | cRAP
#
#   collection=human_uniprot options:
#     protein_set=canonical                 SwissProt only, reviewed            (~20k seqs)
#     protein_set=canonical_isoform         + reviewed isoforms                 (~42k seqs)
#     protein_set=canonical_isoform_trembl  + isoforms + TrEMBL (unreviewed)    (~250k+ seqs)
#     [default: canonical]
#     download=true|false                   [default: true]
#
#   collection=HOMD options:
#     genomic_refseq_version=<e.g. V11.02>  required (falls back to the VERSION column if omitted)
#     sites=oral                            body-site filter
#     rank=species|genus|family             1 representative genome per group (omit = no dereplication)
#     download=true|false                   [default: true]
#
#   collection=cRAP options:
#     set=ccp                               [default: ccp]
#
# OPTIONS  (mod_I / mod_II rows — which backend to fetch from)
#   fetch_source=ncbi|uniprot|uniparc|pdb   [default: ncbi]
#   uniparc/pdb are protein-accession-only backends → mod_II rows only
#   A per-row fetch_source column inside the input_list file itself overrides
#   this for individual rows (lets one file mix backends).
#
# FORMAT
#   options column = key=value;key=value  (semicolon-separated)
#   version / citation / notes are free text, for your own reference only
#
# ══════════════════════════════════════════════════════════════════════════

source_id	enabled	source_label	source_group	module	collection	source_dir	input_list	fasta_file	metadata_file	options	version	citation	notes

## Module I inputs
FUNGI	TRUE	FUNGI	fungi	mod_I		99.prepackaged_inputs	MOD-I.AllOralsDB.fungi.v2026.198.tsv						Fungi detected in the oral samples.
MICROEUK_ENTAMOEBA	TRUE	ENTAMOEBA	microeuks	mod_I		99.prepackaged_inputs	MOD-I.AllOralsDB.entamoeba.v2026.198.tsv						Proxy for Entamoeba gingivalis; E. gingivalis genome unavailable in NCBI therefore include genomes of other Entamoeba species.
VIRUSES_HUMAN	TRUE	VIRUSES_HUMAN	viruses	mod_I		99.prepackaged_inputs	MOD-I.AllOralsDB.viruses_humans.v2026.198.tsv						Viruses that infect humans and have been detected in oral samples (sources include data from https://viralzone.expasy.org/ and the Human Virus Database http://computationalbiology.cn/humanVirusBase/).
VIRUSES_FUNGAL_MICROEUK	TRUE	VIRUSES_FUNGAL_MICROEUK	viruses	mod_I		99.prepackaged_inputs	MOD-I.AllOralsDB.viruses_microeuks.v2026.198.tsv						Viruses that infect fungi and other microeukaryotes (sources Kinsella et al. and Keeler et al.)
VIRUSES_DIETARY	TRUE	VIRUSES_DIETARY	viruses	mod_I		99.prepackaged_inputs	MOD-I.AllOralsDB.viruses_dietary.v2026.198.tsv						Viruses infecting plants and tobacco products, detected in oral samples (sources include Aguado-García et al., Rivera-Gutierrez 2023 et al., and literature survey).

## Module II inputs
VIRUSES_HERVS	TRUE	VIRUSES_HERVS	viruses	mod_II		99.prepackaged_inputs	MOD-II.AllOralsDB.viruses_HERVs.v2026.198.tsv			lineage_taxid_override=206037			Viruses that are endogenous in the human genome (HERVs).
ALLERGENONLINE_V24	FALSE	ALLERGENS	allergens	mod_II		99.prepackaged_inputs	MOD-II.AllergenOnlineV24.v2026.215.tsv				V24	10.1002/mnfr.201500769	Source: AllergenOnline v24 (118 proteins with PDB chain accessions currently omitted from final output).
HSP2	FALSE	HSP2	human_salivary	mod_II		99.prepackaged_inputs	MOD-II.HSP2.0.v2026.198.tsv				Downloaded manually June 18, 2026.	HSP2.0 (https://salivaryproteome.org/salivary-protein)	

## Module III inputs
MICROEUK_TTENAX	TRUE	TTENAX	microeuks	mod_III		99.prepackaged_inputs		MOD-III.Mpeyako2024.trichomonas.v2026.198.fasta	MOD-III.Mpeyako2024.trichomonas.v2026.198.tsv		Mpeyako_etal_2024	10.3389/fmicb.2024.1437572	Proteins identified and provided by Mpeyako et al. as Suppl Table 2 and Suppl Data 3).
OBELISKS_ORAL	TRUE	OBELISKS_ORAL	obelisks	mod_III		99.prepackaged_inputs		MOD-III.Zheludev2024.obelisks_ORAL.v2026.215.fasta	MOD-III.Zheludev2024.obelisks_ORAL.v2026.198.tsv		Zheludev_etal_2024	10.25740/WB363NT3637	Subset of proteins from protein calls for Obelisk genomes identified by Zheludev (their Supp Table 2), filtered and reviewed to include only Obelisk proteins from oral/oral-proximal datasets (27 of 11,581 pyrodigal ORFs).
DAIRY_DB	TRUE	DAIRY	food	mod_III		99.prepackaged_inputs		MOD-III.Dairy_DB.SUBSET-151.fasta	MOD-III.Dairy_DB.SUBSET-151.tsv		Hendy_2019	10.15124/589742eb-287a-4576-a00a-30df33d9f52c	Proteins provided by Hendy et al. as curated dairy proteins, developed for their study of ancient dental calculus, Wilkin et al. 2020.
OBELISKS	FALSE	OBELISKS	obelisks	mod_III		99.prepackaged_inputs		MOD-III.Zheludev2024.obelisks.v2026.215.fasta	MOD-III.Zheludev2024.obelisks.v2026.198.tsv		Zheludev_etal_2024	10.25740/WB363NT3637	All protein calls for Obelisk genomes identified in Zheludev (their Supp Table 2).

## Module IV inputs
HUMAN_C	FALSE	HUMAN_C	human	mod_IV	human_uniprot					protein_set=canonical			
HUMAN_CI	TRUE	HUMAN_CI	human	mod_IV	human_uniprot					protein_set=canonical_isoform			
HUMAN_CIT	FALSE	HUMAN_CIT	human	mod_IV	human_uniprot					protein_set=canonical_isoform_trembl			
HOMD_ORAL_A	FALSE	HOMD_ORAL_A	bacteria_archaea	mod_IV	HOMD					genomic_refseq_version=V11.03;sites=oral;download=true	V11.03	homd.org	HOMD PROKKA proteomes filtered to oral body site
HOMD_ORAL_S	FALSE	HOMD_ORAL_S	bacteria_archaea	mod_IV	HOMD					genomic_refseq_version=V11.03;sites=oral;download=true;rank=species	V11.03	homd.org	HOMD PROKKA proteomes filtered to oral body site, only include 1 representative genome from each oral species.
HOMD_ORAL_G	TRUE	HOMD_ORAL_G	bacteria_archaea	mod_IV	HOMD					genomic_refseq_version=V11.03;sites=oral;download=true;rank=genus	V11.03	homd.org	HOMD PROKKA proteomes filtered to oral body site, only include 1 representative genome from each oral genus.
HOMD_ORAL_F	FALSE	HOMD_ORAL_F	bacteria_archaea	mod_IV	HOMD					genomic_refseq_version=V11.03;sites=oral;download=true;rank=family	V11.03	homd.org	HOMD PROKKA proteomes filtered to oral body site, only include 1 representative genome from each oral family.
CRAP_CCP	TRUE	CRAP	contaminants	mod_IV	cRAP					set=ccp		10.5281/ZENODO.15115102	Cambridge Centre for Proteomics cRAP set.