source_id	enabled	source_label	source_group	module	collection	input_list	fasta_file	metadata_file	options	version	citation	notes	status
FUNGI	true	FUNGI	fungi	mod_I		/projects/academic/kmkauffm/kauffman/ZZ.daysDir/2026.214_maniFasta_AllOralsDB_flavor_builds/maniFasta-dev/99.prepackaged_inputs/MOD-I.AllOralsDB.fungi.v2026.198.tsv						Fungi detected in the oral samples.	enabled
MICROEUK_ENTAMOEBA	true	ENTAMOEBA	microeuks	mod_I		/projects/academic/kmkauffm/kauffman/ZZ.daysDir/2026.214_maniFasta_AllOralsDB_flavor_builds/maniFasta-dev/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.	enabled
VIRUSES_HUMAN	true	VIRUSES_HUMAN	viruses	mod_I		/projects/academic/kmkauffm/kauffman/ZZ.daysDir/2026.214_maniFasta_AllOralsDB_flavor_builds/maniFasta-dev/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/).	enabled
VIRUSES_FUNGAL_MICROEUK	true	VIRUSES_FUNGAL_MICROEUK	viruses	mod_I		/projects/academic/kmkauffm/kauffman/ZZ.daysDir/2026.214_maniFasta_AllOralsDB_flavor_builds/maniFasta-dev/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.)	enabled
VIRUSES_DIETARY	true	VIRUSES_DIETARY	viruses	mod_I		/projects/academic/kmkauffm/kauffman/ZZ.daysDir/2026.214_maniFasta_AllOralsDB_flavor_builds/maniFasta-dev/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).	enabled
VIRUSES_HERVS	true	VIRUSES_HERVS	viruses	mod_II		/projects/academic/kmkauffm/kauffman/ZZ.daysDir/2026.214_maniFasta_AllOralsDB_flavor_builds/maniFasta-dev/99.prepackaged_inputs/MOD-II.AllOralsDB.viruses_HERVs.v2026.198.tsv			lineage_taxid_override=206037			Viruses that are endogenous in the human genome (HERVs).	enabled
ALLERGENONLINE_V24	false	ALLERGENS	allergens	mod_II		/projects/academic/kmkauffm/kauffman/ZZ.daysDir/2026.214_maniFasta_AllOralsDB_flavor_builds/maniFasta-dev/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).	disabled
HSP2	false	HSP2	human_salivary	mod_II		/projects/academic/kmkauffm/kauffman/ZZ.daysDir/2026.214_maniFasta_AllOralsDB_flavor_builds/maniFasta-dev/99.prepackaged_inputs/MOD-II.HSP2.0.v2026.198.tsv				Downloaded manually June 18, 2026.	HSP2.0 (https://salivaryproteome.org/salivary-protein)		disabled
MICROEUK_TTENAX	true	TTENAX	microeuks	mod_III			/projects/academic/kmkauffm/kauffman/ZZ.daysDir/2026.214_maniFasta_AllOralsDB_flavor_builds/maniFasta-dev/99.prepackaged_inputs/MOD-III.Mpeyako2024.trichomonas.v2026.198.fasta	/projects/academic/kmkauffm/kauffman/ZZ.daysDir/2026.214_maniFasta_AllOralsDB_flavor_builds/maniFasta-dev/99.prepackaged_inputs/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).	enabled
OBELISKS_ORAL	true	OBELISKS_ORAL	obelisks	mod_III			/projects/academic/kmkauffm/kauffman/ZZ.daysDir/2026.214_maniFasta_AllOralsDB_flavor_builds/maniFasta-dev/99.prepackaged_inputs/MOD-III.Zheludev2024.obelisks_ORAL.v2026.215.fasta	/projects/academic/kmkauffm/kauffman/ZZ.daysDir/2026.214_maniFasta_AllOralsDB_flavor_builds/maniFasta-dev/99.prepackaged_inputs/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).	enabled
DAIRY_DB	true	DAIRY	food	mod_III			/projects/academic/kmkauffm/kauffman/ZZ.daysDir/2026.214_maniFasta_AllOralsDB_flavor_builds/maniFasta-dev/99.prepackaged_inputs/MOD-III.Dairy_DB.SUBSET-151.fasta	/projects/academic/kmkauffm/kauffman/ZZ.daysDir/2026.214_maniFasta_AllOralsDB_flavor_builds/maniFasta-dev/99.prepackaged_inputs/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.	enabled
OBELISKS	false	OBELISKS	obelisks	mod_III			/projects/academic/kmkauffm/kauffman/ZZ.daysDir/2026.214_maniFasta_AllOralsDB_flavor_builds/maniFasta-dev/99.prepackaged_inputs/MOD-III.Zheludev2024.obelisks.v2026.215.fasta	/projects/academic/kmkauffm/kauffman/ZZ.daysDir/2026.214_maniFasta_AllOralsDB_flavor_builds/maniFasta-dev/99.prepackaged_inputs/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).	disabled
HUMAN_C	false	HUMAN_C	human	mod_IV	human_uniprot				protein_set=canonical				disabled
HUMAN_CI	true	HUMAN_CI	human	mod_IV	human_uniprot				protein_set=canonical_isoform				enabled
HUMAN_CIT	false	HUMAN_CIT	human	mod_IV	human_uniprot				protein_set=canonical_isoform_trembl				disabled
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	disabled
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.	disabled
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.	enabled
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.	disabled
CRAP_CCP	true	CRAP	contaminants	mod_IV	cRAP				set=ccp		10.5281/ZENODO.15115102	Cambridge Centre for Proteomics cRAP set.	enabled
