From 24be76dc081e0ed0352aeb6e80ccfebe25944dbf Mon Sep 17 00:00:00 2001
From: Lee Katz - Aspen <gzu2@cdc.gov>
Date: Mon, 4 Nov 2024 10:46:30 -0500
Subject: [PATCH] another round of provenance

---
 .gitignore                             |   3 +
 paper/mra.md                           |   6 +-
 src/provenance/README.md               |  10 ++
 src/provenance/SME.acc                 |  28 ++++
 src/provenance/chromosomes.insdc.tsv   |  15 +-
 src/provenance/ncbi_ref.acc.gz         | Bin 17925464 -> 17927300 bytes
 src/provenance/ncbi_ref.acc.more       |  68 +++++++++
 src/provenance/quick-ncbi-ref-check.sh |  25 ++++
 src/provenance/sources.tsv             | 187 ++++++++++++-------------
 src/provenance/unknown.tsv             |  94 -------------
 10 files changed, 236 insertions(+), 200 deletions(-)
 create mode 100644 src/provenance/ncbi_ref.acc.more
 create mode 100644 src/provenance/quick-ncbi-ref-check.sh

diff --git a/.gitignore b/.gitignore
index f4453e3..2b2d2b5 100644
--- a/.gitignore
+++ b/.gitignore
@@ -2,3 +2,6 @@ edirect
 share
 paper/paper.html
 paper/paper.doc
+# pixi environments
+.pixi
+*.egg-info
diff --git a/paper/mra.md b/paper/mra.md
index 19ca283..d3ca356 100644
--- a/paper/mra.md
+++ b/paper/mra.md
@@ -47,7 +47,9 @@ Kalamari also contains a custom taxonomy and software for downloading and format
 
 ## Announcement
 
-Public Health laboratories sequence microbial pathogens daily for genomic epidemiology, i.e., to track pathogen spread [@armstrong2019pathogen].
+Public Health laboratories sequence microbial pathogens daily for many applications including genomic epidemiology [@armstrong2019pathogen],
+species identification [@lindsey2023rapid],
+and metagenomic analysis [@huang2017metagenomics].
 Relevant databases exist such as RefSeq [@o2016reference] or The Genome Taxonomy Database (GTDB) [@parks2022gtdb].
 However, due to their so comprehensive nature,
 they are disadvantageous for our specific purposes:
@@ -64,7 +66,7 @@ All chromosomes and plasmids are complete, i.e., no contig breaks,
 and obtained from trusted sources, e.g., FDA-ARGOS [@sichtig2019fda] or the NCTC 3000 collection [@dicks2023nctc3000], or provided and reviewed by a CDC subject matter expert.
 
 We obtained the list of plasmids from the Mob-Suite project [@robertsonMobsuite]
-and clustered them at 97% average nucleotide identity (ANI) [@lindsey2023rapid].
+and clustered them at 97% average nucleotide identity using edlb_ani_mummer v1 with default options [@lindsey2023rapid].
 For each cluster, the taxonomy identifier was raised to the lowest common tier of taxonomy.
 For example, if a cluster of plasmids were identified in both _Escherichia coli_ and _Salmonella enterica_, then taxonomy identifiers for all the plasmids in the cluster were changed to their common family, _Enterobacteriaceae_.
 As a result, any taxonomic signature from these plasmids
diff --git a/src/provenance/README.md b/src/provenance/README.md
index f5e1acf..9abc9af 100644
--- a/src/provenance/README.md
+++ b/src/provenance/README.md
@@ -57,6 +57,16 @@ _NOTE_ This command probably would have saved me time if I turned it into a batc
 datasets summary genome accession GCF_000006945.2 --report sequence --as-json-lines | dataformat tsv genome-seq --fields genbank-seq-acc
 ```
 
+Check the assemblies spreadsheet on whether or not it is retrospecitively part of NCBI references
+
+```bash
+zcat assembly_summary_genbank.txt.gz | perl -F'\t' -lane 'print if($F[11] eq "Complete Genome" || $.==1);' > tmp.tsv
+mv tmp.tsv assembly-complete.tsv
+bash quick-ncbi-ref-check.sh Caulobacter vibrioides CP001340
+# If found, add to ncbi_ref.acc.more
+# If not found, see if there is different reference to add
+```
+
 ## Translate
 
 Translate certain entries into CDC, NCTC3000, FDA, or the NCBI list.
diff --git a/src/provenance/SME.acc b/src/provenance/SME.acc
index 573562a..f350fce 100644
--- a/src/provenance/SME.acc
+++ b/src/provenance/SME.acc
@@ -5,6 +5,8 @@ Betacoronavirus_coronavirus	MT233526	2697049	694009	UNKNOWN
 Borreliella_burgdorferi	AE000783	139	64895	UNKNOWN
 Burkholderia_pseudomallei	BX571965	28450	111527	UNKNOWN
 Burkholderia_pseudomallei	BX571966	28450	111527	UNKNOWN
+
+# A ton of Campy and related genomes from Jim Bono
 Campylobacter_coli	CP028187	195	194	UNKNOWN
 Campylobacter_concisus	CP012541	199	194	NCBI-REF
 Campylobacter_cuniculorum	CP020867	374106	194	NCBI-REF
@@ -22,6 +24,9 @@ Campylobacter_sputorum	CP019683	202	194	UNKNOWN
 Campylobacter_subantarcticus	CP007772	497724	194	UNKNOWN
 Campylobacter_volucris	CP007774	1031542	194	UNKNOWN
 Campylobacter_ureolyticus	CP012195	827	194	UNKNOWN
+Arcobacter_ellisii	CP032097	913109	28196	UNKNOWN
+Arcobacter_cibarius	CP043857	255507	28196	UNKNOWN
+Helicobacter_pylori	AE000511	210	209	UNKNOWN
 
 # We trust Segre's lab for Citrobacter
 Citrobacter_freundii	CP007557	546	544	UNKNOWN
@@ -86,8 +91,31 @@ Yersinia_massiliensis	CP054048	33060	629	UNKNOWN
 Yersinia_pseudotuberculosis	CP009712	502800	633	UNKNOWN
 
 
+Salmonella_enterica_IIIa	CP000880	9000014	28901	UNKNOWN
+Salmonella_enterica_IIIb	CP053583	9000015	28901	UNKNOWN
+Salmonella_enterica_IV	CP053579	59205	28901	UNKNOWN
+Salmonella_enterica_IX	CP054715	9000016	28901	UNKNOWN
+Salmonella_enterica_VII	CP053582	59208	28901	UNKNOWN
+Salmonella_enterica_X	CP053581	9000017	28901	UNKNOWN
+
+
 Neisseria_gonorrhoeae	AE004969	485	482	UNKNOWN
 Neisseria_meningitidis	AE002098	487	482	UNKNOWN
 
 # Gulvik
 Leptospira_biflexa	CP000777	355278	145259	UNKNOWN
+Leptospira_interrogans	CP020414	173	171	UNKNOWN
+
+# Eukie hosts
+Bos_taurus	KC153975	9913	9903	UNKNOWN
+Arripis_trutta	AP006810	270544	163128	UNKNOWN
+Brassica_oleracea	JF920286	3712	3705	UNKNOWN
+Gallus_gallus	HQ857211	9031	9030	UNKNOWN
+Humulus_lupulus	NC_086845	3486	3484	UNKNOWN
+Lactuca_sativa	MK820672	75943	4235	UNKNOWN
+Neomysis_japonica	KR006340	1676841	223649	UNKNOWN
+Pollachius_virens	FR751399	8060	8059	UNKNOWN
+Solanum_lycopersicum	MF034192	4081	49274	UNKNOWN
+Sus_scrofa	FJ236999	9823	9822	UNKNOWN
+Thunnus_alalunga	AB101291	8235	8234	UNKNOWN
+Vicia_faba	KC189947	3906	3904	UNKNOWN
diff --git a/src/provenance/chromosomes.insdc.tsv b/src/provenance/chromosomes.insdc.tsv
index 227bbf5..52b3c51 100644
--- a/src/provenance/chromosomes.insdc.tsv
+++ b/src/provenance/chromosomes.insdc.tsv
@@ -2,15 +2,13 @@ scientificName	nuccoreAcc	taxid	parent
 Acholeplasma_laidlawii	CP000896	2148	2147
 Acinetobacter_baumannii	CP045110	509170	470
 Acinetobacter_pittii	CP002177	48296	909768
-Aeromonas_hydrophila	CP000462	644	642
 Agrobacterium_fabrum	AE007869	1176649	1183400
 Agrobacterium_fabrum	AE007870	1176649	1183400
 Alkaliphilus_transvaalensis	CP000724	208226	114627
 Aliivibrio_fischeri	CP000021	668	511678
 Aliivibrio_fischeri	CP000020	668	511678
-Amycolatopsis_mediterranei	CP002000	33910	1813
+Amycolatopsis_mediterranei	CP002896	33910	1813
 Aquifex_aeolicus	AE000657	63363	2713
-Architeuthis_dux	NC_011581	256136	34555
 Arcobacter_bivalviorum	CP031217	663364	2321115
 Arcobacter_ellisii	CP032097	913109	28196
 Arcobacter_cibarius	CP043857	255507	28196
@@ -26,14 +24,13 @@ Atlantibacter_hermannii	CP042941	565	1903434
 Bacillus_cereus	AP007209	1396	86661
 Bacillus_subtilis	AL009126	1423	653685
 Bacillus_thuringiensis	AE017355	1428	86661
-Bacteroides_fragilis	AP006841	817	816
-Bacteroides_thetaiotaomicron	AE015928	818	816
+Bacteroides_fragilis	CR626927	817	816
+Bacteroides_thetaiotaomicron	CP040530	818	816
 Bartonella_bacilliformis	CP000524	774	773
 Betacoronavirus_coronavirus	MT233526	2697049	694009
-Bifidobacterium_adolenscentis	CP028341	1680	1678
-Bifidobacterium_bifidum	CP001840	1681	1678
-Bifidobacterium_longum	AE014295	216816	1678
-Bordetella_bronchiseptica	HE965806	518	517
+Bifidobacterium_bifidum	CP058603	1681	1678
+Bifidobacterium_longum	AP010888	216816	1678
+Bordetella_bronchiseptica	LR134326	518	517
 Borreliella_burgdorferi	AE000783	139	64895
 Bos_taurus	KC153975	9913	9903
 Brachybacterium_faecium	CP001643	43669	43668
diff --git a/src/provenance/ncbi_ref.acc.gz b/src/provenance/ncbi_ref.acc.gz
index 66a282af0119ae80bbd2f0847d9c62226548219b..038fe8635cb711fbcc4472c4188510f8e7719b1f 100644
GIT binary patch
delta 8283
zcmcgw2~^Wpv#&+Hs7PEuK{V6_tjZ?)P8G#!SX6|72#6pMFd!nbCVwkj(~5$H$_|k#
zpt3|nK(<5#0Sf^&><9soecu8kkh}ouv$fyX_s%=-JCnJ&cXH2N=Fa?PCXF}B1cRc>
z1c79*py2(1?|%XiEQ8=%2m~Nl4#5ftRzkoR3PP|7g4GbLfj|g?wGaqHfP!Eh1nVK#
z0KrBGL?94_U=swJArON=9D*$nNI<X^f^86>A&`XNI|#Nzumggf5bT0L3Ib^ec0=$z
z1bZOZ3&B1JWFU}*Kn?<V2oxaL4}l^CN)RYRpaOv^1ZohdL!beHCIng#XhWa_fi47k
z5c~ka0SFF4pbx<z2o6JF0KpLmeuUsC1jiu2Kwt=g5d_8%m_TqGf)fy&guoPnQxKRz
zU=9Hm0t*N%Avg_z6$ED>u!g_}0$T{qLSP5MISA|_aDd=E1db3mLEsDl4gwblTp_ps
z0UiQ32;3pK2!RI#mmu(j;4%bW5L|)48v-8)d?E0Iz#oDD2nY}mAwVFw3c*hhT!SDG
zf*=SW1lJ)TLGUvKzd&#Uf?x=4LU0R$5C}pcxDCOt5QISx4#95_+<_nhf=CFWAc%$_
z27*`!;vk5JAOQk01a~1wgy44w?m=)Lf+Pr%AxMGX0R#^rcmzQz1ZfbYLy!Rh1%k&A
zWJ2%+f-DH0LXZtX4g|RnJcA$)f_w-HASi^O2m&euGzgwUPz=Ef2udI*h2SLwWe}7@
zPyxX!2>yVe5`roS=nzyxPy@kh2;M;O76JwYwGh-nP!B-^1dR|hLC_3A3k2^VXoa8+
z0wx6Q5OhHB9)eB?K0wd~K{o_F5cERO2SGms0}u>CFa*Ic1S1fPLNErwI0O?AOhPaP
z0Skg@2xcIdg@6qK2ZA{W<{{uh!21O(y9Ji<`CC2<@Oe3(SMYfypBH`;<nt;%ujca_
zJ`3@AEuV$?jN<dUWkq29vX>W-);wi3w_U-0M!eNW-o0#%|G}|-4W_12Nhb_{3!PKg
zcen1c+Q@?>VV!{F`2qKzcHM^T3*}7-KSy6N*mQO7(dq}3ACLW}EUy*T&Hkarel&EX
zfO5iF>Bi0N8*g{q*{CQUeXXj|saxy!S63~c%beY$;HkX4>RZQUSywHK)6SYJAp4?3
zt5!R%$hx*LR#lLQT3fZ!Q6TH5rso$HhXPSw)6S@`X=7A)T13P<;wulMTAk;L*K(18
zhAlPUD_%GJ;X2m1!ogv+qCMHNeoM{AbF7J4v2YIL(?S0E93}nYf_XBi_R!pU*%9%>
zWw%#VjQ+7I`ljIl$3dk^zDVKYn*1dfullDY%@r1gf4bVjO%ValZ~lgsdk&%*9&+67
z)L~a*^UWRh70Vrbx`GT1lD|`8MbGZXEAmzOr|p*3|E$S{;a@b#A9jE9i5zwJEUV%Z
z!f)1pB)YeclteP+ggSMOt{F$Q9bcC~oO{1+6Do`Js^l5<LsSIDU=P|66)SL!)Sc+}
zJz6fnLriCKLtvy>7|8}dy3i>sZP!=uqa7KU?wv;yK9sd5`aVF*NgW&u7NuEyZ0>Zg
z7LFz)Jh4^dcp+H}Ex*xnU~Oo^+;?0ZdjRh@D0Gi(u5A^t3u8*pqN`;}hb!O6$^ETt
ze=a4W>X3st#b-{oG)Z<X&Qhb=-Oo0jIZ4%|^%1;?3{L-C@^sy-(Mak<Y#X*mt%&mP
zCm^3^jBcFKd~h!$_#kyQQ}WbTmb0=>>0hc`$?5o_G5>p&e^NdFTkta>3*Bd@o#y4Q
zTGR4oOliA(41V43@U3FurGwHtO>c{Hs-EofS-Ipg(f780Jj0*fdC7r3d(7u&-}?M-
zsCet2X!*i0a((v=5!1Nhuj$P5uSxrw@A3)3?)6nWqmC$qo<$e)1%uH&lqhGVYfF~8
zLvhh9R#ru>AH0i={BH2>j|<H{fz_zJk<}T#=*Z>_-wprkMkw;VRH9#G``}$CWEom$
z^z2n2pe@#3{0(ZQkHYi7|D*`{4{zB~EQm7jQFsx!9({B4Y!E<pYK#3<_Ma3XOUL;C
z+Hw`zaP;gouu(gzy?8lF+DD-{@XsRTD_N%+rCKlF%63hE|7IDN7ZJ7sTQFieGJLoS
zC(&`m`V+@>L{KCtWs0K>y)edCWx}Pqt|~PetHc)=6~*|e;E^YJ)W?~#n}3tpimV$G
zxj`z~Q1+(eL!xcRWKj|6wf5wI0nJSY-7O_#vjdq~R-6jEEhw7`PhX5{hk=`OSlEmG
za*A}C%6TvG_57XUkZjl03&{DVq&?C0!stFBx@h6(oP?d}1GHvIyVOegcXv@XKBK`Z
z%or=JeRfd@X7A5*Z-&St()*6bK@+XYkQl?p^`|@}OB0*5e>RQMF(k%F-X&gD1?mX9
zFE|W^9Zh>m8^cb!br#y?<quLj)9HT+c+rs^(gKUob}=F?MU0QZ_KS$|DcF97jtggn
z|As=&exlXgjBOurWDz`&uc0HZ_-p7m^Zf6@BT}-(UGd4uq-T366hAW?+o?x|)P6Hx
zLS5=O`w_Nl%8c^IK&s8125iy4n1KA_jDMWakGd|ahB0KsKk}+EJM|Xli3q+dv0GL0
zOjn~uB1io<UlVoMRPw>j^TOzHZDkZdc?nPSmJ1UH@1j)!B1CNNwHs6L@4c<>nKmIz
z$A#!BW1TOCIY~U}K39ygFfuTnU><z6U-)g%XInhO-atwc@UVE$`S@;`-Ka|-R-&-E
zy>2BX=jJ7`$P)?NCk3R19VZohoYDP$XTw6v#!@&Y3)@6#Uoc*Sjv@6Y`aBc*{SXD&
zgaLOVQ&U%>==xK~wa;YeBGyCOCmB^HN_zA;<!v7wVaQ)PbH?3r&gV*7Q{t<?+RD&t
zhcB#TAw_$>kfMD~V|=H&kH=q`2(MNca*ARp8FIvv=Y<%=>o~m<<SE&%x#ny6KZ>)M
z(X2BO;d1+jBBNLsLylDP{00W`7aXnhsqMLD`F|~@O{FVlHjYKE)?R;ob_hv}!k@tB
z9L{dqROcuWV;{Jbpj1~P^@p=9H`h5@pNjQ5f&XIAbl<_6g|$3FF)utl=JGOCbfJS|
zKF1vOBD!mY_%?}#Py^HKMqg{6LM_-qB;I&!FsVtOqUw`foVu2u?(pBss*Gq@+1T*d
z2jM#>+5q)&Tfgl0bvLm4Y|?%H+^MvY_0O)`Y*zP6951NNZp$C}_%k_&yb5yNf-BML
zxTsuf)9=y37_su<4;~u6Tu+4b+MJY>IAgazy`@zC*Z2K}ThBXIa=ZOmYD~{K+6Zsm
z4U)chyl+V~!cai6nna}kJ2w-?sE;5ik9~UU!mzFv!>|||S>NmrbtfBSv$`}l@NdF5
ztTXX(k>M${`McIu<2g^=_Eoxu{r+$s-TzQlwm~^wPc!D=N7RhdD~^5f-j1c<+gm4-
zcGTE=E|lT^i)3zB`9-P&;RIF~k$;R@_*qOxXvr$oebnXZ4sO&enLFAdl7SA!8HdED
zQkp|YqO<WHxbQj&;FY(<q<Wv(kpqjkti6`CeF?0It&DJ@AYFe6sQpx?T>9&3Q&ozN
z(=ymzb>g++_wzC~N7Ows3ng>TmCP;c-p<E$L@KVl!k8=>cTlf>&SJ_wTSJxaBbTrH
zY7b3zl<&E$xUfoT>Mz)h6loiy!WbWwDf_xmGd=TI`*=ev=3vpbZffb}cPHq0sneQ8
z-ip!lPYt%c7_{>)>koCQJrqSt@Tjs=$IY!%ZE8=XC&sDnH1%n|xphe={7WNfwwFn@
zM$r3?cA<NumnDM>=`maMhHc`^LX!q$Ln_7U>ZO;oBV#wt2qQ<#J^hf9)cw?MRp%mf
zL}^dDyh%Mw*;I6Tp|fHkwv4(Ir><D=;E5$y-uiayrR;(|*)x5N*b$m9qbSOCvDR|p
z7hBkk<cT@DEEDmZCD_i5bEq?2(}c0g5zhNa=JZSX0@_}NqoU%9=**fpo1;1Zt7@g&
z+G(jaix|8is`aT}`0{&I)z>6m^%apvQ`RjL-S<W2_$ievPw?e_L!}EUE|!kJRP1u#
zpH*C;Br<d0uA0C*!m7yagLe-j<u&C!Lvy`IzMV|pj8;{f^aRJ6At5!frg@JH#>a0x
zA~@g32%gb*MlXfY_fn;pxHcR0pruzIb9ujL1`>1mfwtbxeuE9$7JH)u!j)c~>V6j5
zRcL9{J<<Y3Hz<X5@1b(pHLbxE>3bDoip#`p5RL8OzwW8HNpOrX4qrsbg_`zLAtpTV
zlYFXP$9@-e;;QCcJv6m<zi*?%M^NDV^%2wpg2>w$)r<eWImAZYucH^<+bnFO?$gmO
zbuH3aQ}W}B^PhexMUhJDOOCWC5<Qu+o$g*>LK8i#`|*sijE_Z_FeWOpI2W}ES+t#o
zU|)6Ojb>@bTh_MkSOYI#;%PQ#{*RqBu0bNILmjcIoL1w_Bul*DYa`9=l*HTq9!hel
zI#Xn9^3BwCL}cuu#X%)ho&KT=2ICgP)a8|H(Vu+yXyEXdKG^Gb^N+NGSa)7qXpxhM
zxW4pvCHr>sU;X?Fbwq*HImvD^R}1M=@WvX~rd&i9j7{DPD}U_sCD39lw5?*&lpLHY
zs&B_5+qLwsTptu_5`ThS1lkXL<ok$viyajm)`piD5&08^hsKsV=Apym0s@SlJls@)
zHv{EXCH-3*mi9<>{&B_J<)fA|%5X@cUvzph@CQ9(rn8pb8h+}wkQP=4mx(M@#g1dE
z7@K8l0#nBxAoQGc8GH))C-v*yi9US%6DU_?(igHev}*ZcXs|2ayoq{wPB<|Kf1!Ci
zUsl-2%A5Y6t)6RGkw}lpNpxLf6nhz;hZ`u<Qzba_k~<R9`}8>{x@sd%S7(guQNdgD
zE-|KSr|c{vQgSjz^7{Py)jb*0EGJcAd?pSVu-sBzd&|<TOvW3Z)Tck(e<vbIVjxpI
z>)jOL!azDZWB1{>=7SCOHcDRjO$9;T>Zg&!Of8E5)ez>vw>db5>cZaP8R^R3B)Lk&
z=6JLw>wD7OE<Zirr<pV_cvJV=a%^XtW4|f(*v1S>bcETfQ~4f8RaNl=Z}$ipS@k2$
z_i+RLEAY)}u35>l-uU8{`qY<&LUGOcx<R#1rwA1bm%}p~JY&z5h!^OVMr27uHeL#`
zwknCv*DbxS<P}#gN-<Jye;A0N-%oNo_x94xpi}w6^8Wn~(*<lJo;RyrnTn9Q=rSOU
zZ`x^sw@!)Z@^BegX>W<<D+5(Ij;LpQbv}^^HMR2gJU`-(_Nz`Fu~(Bz8uC|@I~?PB
zWqx1tQ!jh-G~58&<{+bfigG_WeZck={|!txjWEZg^ckwcbYE*`c{1|WBV?^pu3XZ7
zRs6Qf#>oTux;Kp^?>phTP4Yd&W4V2PZWFI3P0BLT`^YX0^;P6!3k`C*p?=cZp5GiW
zZK!A2>Bw2e=sNc`H|wTxu+2GciF@BpQml60P@cDPzvE)Xpf!>ks%&$gi{jYSHUr$7
zWMm*6gLhRgfHdb4@qDVQC(=!|@kCu2aC(!B%5=hUUf)VlA^e=@>dIMHkmIP$pJ-9i
zgwMR85|`w<W(e`QB9oZ6`;wYtV$p7Pj$>MZto5oP3-8Vi&0H@6%7}MNEjMw<7O_!6
zB{|^|?p5!TQtf=}n^x+0MpG@K@g}B^y*bvSZw`A-NiN<LbD=EhvZn}NP-w{)*w?(h
ziRqzlXz}Q?IH@IP%{1jta>uxoogcEYqIUI@kN~7%KFuojgo9A@RUt~;?N=2d4rRhk
z1)g({5_4o_4kJH!6PG^D1q>T?)x-7;<}s?)xhkBD6Zs(y)@R+9`LAiTdfs+!(0xBE
zSBz6<)gWu^d>qrzojdWMHA=1J$$qa^_nh<g{nyi*B5n<I73Iu!YDREl);jgo1bdbv
z^4xmV!!LoP^#@h|lFZA~7FlZA)H_W%DuIPIEf>VHC7LqDi!x)=J$w(!QOg7gx7M?_
z?3`3F=pDEc)O@m1X(K5y_JJd!5z^}UW^jA?6x&_#sdc5bm8X4LLtS%yeXz9^PQ9U1
z?yc9cfUHfVsg=|mm2Ja_x%98Kw$5jy->?1h<5s8k%#1n5V#rh12M12_UCheFyh?R*
z!EDaRb*K8!i^nQuB03{y<?tS7t_1f@zU(n-xpXAS&bP*OH8%3c{4|H7mx(=u)%+@U
z+2_h3PA?<w#rqDI4`H(2hwu_buX~|65-YifnwM%dSeKQ0=`?Pjg2=&7AF%$*i|Bf?
z)3WG){txtj{uih~6xJQ~Pu@mLuKQ&ob{65fvG1)?G%TLnEir+Jl;&IK$Wv$ZY`LAh
zHYPI5vmx733tOlGv*UKtg`9CB=ZQaiylbqIR6u6AldtIU8d$@_v^JjKg_-vzw(;$g
z!Fok)1fND7Jkw2&&`4`x>a@A5m3J4bc9xwg^YEOf>(ORe9Czx>1goQ!+sf*injNye
zQbU>6)6+$Ys4aT5Rw}iH+Y>p@>Kel-?XS0f{y4f#>rKF%$v7t98Iw3S=SCxN`s}9J
zV`Fx-Ry>tG&_VhRuT&%?8@of_bbN|CmNI1hlE|s#rlibwa$ARIj~|v1ip~G#&IvUQ
zws@!sS@KG`DT^Y>q_!aJ<43x1drz69TJ`UDLv~>jxJPOJ%>xWKf8OkQWSZ?UQ8z25
z9Q1gVIW~Q`Fr}O%K02HkQd8bqQb~NY>vTh#k?6gy=EUz9s-tQqoM%NyK%;R|$Tm!q
zgQjl%o|!;KLN2e3n?FCzwMZKl9ybVHK6}s8#)i!DE+F;HPjtI8OBL`*A$LTabhu6k
zt$@a)&i766Z+9}a)-vqW(+mB<vuqykFk!aRjW_Bu?SoBh)5SA~B$-9Jc*z9RbnB#=
zfU22k=cLK3Wc*3@-WiFMxhXx)G$oV>@RBw;Cf?;*&RcG<4?Z$~;!<j7Z|<E}8I2S$
zxo_iU`er9uNh#&*AKE0{sC|t)kk}HefP3u|GWOSDRt*W~=Uc?o-FBoiRn52gyO7xY
zh+5vjrMZTd6z?fJy{)`T);!nFpQdMQddI!da75LZS8?eDGq)i0NJvjEheRH+^+wU^
z%X?)E$?Nc!2!&bKyL&mwn`@@tqgqn*QI~`doU>kYOtjZPMV-O)p5|yGCna6rP)Uhv
z5x$yM?aR&?G&;`clkA!88SWY*Sg%8~ygAbaq=!}Vl<5)I^3b9OrdiR%_T6Z%*At{|
zgy^T+R^8Idu-BP-dfm|dHU8Z9u~7uNMk*mn^9ha2w&rn$l~<O(OxH}3)AEhu?imO-
zR;wc1nlAU3Iz~9&Z-iJTBLUsjS4O5oQQ&T;rn+b&8l9Qnk+#O@$0=T>1~*$yF0>}Q
zw54Fa(p2aCL}c*sWLuqgwf;JPsJEKFDhOcB`tlyz`i;%?=?~40TNpD3&DR9&4Zn42
zKqe)ABtep_JBSeGa9iFLu&?S2h3*vXSJE*1ITp9Rf-WvEsf(y>L<+fL{Uz%2?QVqI
z;fL@MliZ-riK%fPnwGX5DXEC-Zf~Y@e&hAzTJA7Tyt5&)^`TN&|L>>N#_Cqayfg0!
zH5th*-_P|CoaRWW$8ApTIr_&W(@2JhNkFKsy~Ez*1nDF3P<_5DC!gK0g@Fpn2;p6(
z5x5p>>PEkNfauL1S1Y#HDP)~d+moC)Q#5W})FJ6TWy3dW*RF?~r@F?Z4O$K<1=BN4
zT6R`-yfAaBk#Ff?FOQQx`Di(YASQbRkE#8MeUbM}sG)p_!R?ru^&!>SJ<^wAu%%K>
zleZH%9=7|2d+uzny>)h5JT9oPoT)Qn!_+bNcPFO+q(56uDzt{w;>`|sd=fnzx_5HJ
z2Q`z~N%qOy^|2IcERp`ZaqKMysFsk3SxqJ<Yxtz^Yj0s+EtIM37-QXj{ED&f=llre
z9qa~Dxp!y{nPtMzu^mZmASZNlPNY|#A#B&4?>x?HX3qOhkB@8Pk0hXZ{+t1~ldrMv
zd+C>v-CcgBKN7SJXlimPW_U#Lxa?!CA)j6KZ{l=qwC7WvIt6I!^y}&979wdi3?|p?
zQizwv&vt&q&R$e`7pWB?yEUV-Yin9~TN@@j_01w*^w~$TEgo>|_hcIv9SzwqGcZ|z
zt~-%8Tz0`LAYKM3MTpHsS~{q6Nf|q)64DWhZHt{Xc{CG^c)!CK(RO3W+R?fn;sbO_
znL0g0glCa^*f!pX`Pyd0G*!PPe(YrKT`z0(*2gXR%d~WuQ)V94>%+IAM-}JV#0yNa
zM@%FK<XDXy_DTQzk`#?vZB-|oAzfL_6l<RK_%!)SqFF5Cn5<X0(=E`@6Y!3<6`9`p
z(C`@L#|Yl&OhY82{y;Ltoh-bK*E{3r6cEGO8yJ?|HYrLcj-=J>ro<;4j29M0PWAY5
zM!8<Jv|U$xoCj{E8RtE+>IwDoBGPoyw##!uTYQ<PoL=vZ$*HXC81);9EWz!@*8{@$
zUTSCD+e+l@HQ1zAb18>A+&E(l_2JpBzFpP%sSQVQQ#`KB{OBzABAHi6$k<mwJnd<m
e^HA$$-^i>GgIm!-n|aR@5R=^@QuOfFivI$`q5hTt

delta 5716
zcmc&&d011|w!diY(&7LPC?L{zZA(QUB9nkXm0E8V6a)$~DikTBVwe?<)-F^K(%Q-t
zAVn((G8mM32o3}_N>pT!FesEnKtPBPViLFqwD;Ni-uvUd?|$!F`R#9?m7TTsUVH7e
zekVVqvgfzOvFC$&{QUXf992FJ2yzH>5auF$fG`i?Lj+PeA7KH)M+ou=3lSC}EJj#@
zpn#x=uoPh#!g7Qa2ucVm5mq56Bd8##BCJMGLs)~Lj_@(Ue<1uFVJ*TZ2%jQ+hM<A)
zIl?*wO@#FbS_s+*ItUbm4G6jj8xiyn^brgY3=xbFHX#@zm>`%UY(_9cFh{UJ_yS=I
z!d3)Jgf9`cA$*0f9pN7cUnA^5*ok0;V2!W~VK;&ef-S-x1Um$K1P6p~5F8Pl5cVQC
zBe)>ABDf*ABX}U}L)eetiQt9sErK_~0R$g}?+|<u{1E&R0uTZbf)EZO96|_2IE+9=
z2tf!%2tx=*h(L%$h(b7ma1<dLAqIg!IEHW>;d_J=2tOboLM*~bgi{Eo5#kWy5zZha
zAS5Et5Pn4X3E?cl&j`ODoI^-LNJdCONJU6Ppd+LsWFTZBFc5x4$U-=eZ~@^rgo_B-
z2ssFs5ONXn5H2I+BNQMMA`~H9L0}>jBV0wehERe~icp47j!=P6iBN@5jZlM7i@-vt
zL%5D`1K}pZErfamHbMi!ZG<}rcM&)U_Ym$QG$L>j9w0nKc!bb|@ED;Pp#`B8p$*{)
zLOTKvp#z~4p$nlK;VHs1gdT)mgx?YR5cmiJgy#tT2m=U%2rm$Z5QY&(5MCmTB8(vj
z5ndsTBTOKO5GE1C2(J+&2vP(Y!W6>vX^=|*ITCY7%q8&wiFqVGBr)^dd=d*td_+Q?
z#6l8_NGv9?goJ`z4JgXh2e`LB(Jo8$@_A*x`=$(zC4ZgwDAjJ_Re6B;nnb4l$yx2O
zxy;YPJpxa4$RE44?M`Vx6EBf3oBH0o<*7O=xyUwUed3N^&t7_YZ_&BLyI**FtZ&fs
z%scj^E?}SG2CBhA2K^@mIjyD3?k(VdK>gnMdiuUy8#GeL$IMR@<(98IUh$;w(IWxH
zxOU~R=x>6LVr1N?0^54q1@=o<WL9K7vQ@tH!oRP&<r0IDr68xRCCC38^_X$pYSN0J
z&)~=CbV?nI)sj=K`Ikiq?A%u{bn6u43>k+#73G$$b=_Ck=Uu6OpO6X03@oUBogpH1
z*W2;LzZNOp@%5Xf^5;;GSJb)g%dEY5xqf0&1sP?m&N6{$XH0{j$m3{3R@(}?r`zs|
zGT|@Ymdy3Lmi(jMCS;r4X0ab{MYE?}e8IXrUbYh5IlzzUyCCfTk=E*Pvbj5yyDF|Q
zqV#sw&x<kwo_}kpp=$CZrIGmfc472@$-&mhszzRDSD`R$OIXQszlYh{=}Mt#%vE7(
zhW2XCcXUJTLSKK@qSO*56tC+m5s5qZ{E(V4=wLx$L}E!nhGSwYx7o3Xak<Fd!qKB9
zrm!|j<{CZzy5jY~ICZ>vP%v=$zaF6X-U#UeX|!#4_imI5M?!5Kg6-#=`x1SEE``{C
zs3~zaUg_}0bINm5O`kJ#OBCdk=90(62qyi$Y?JFgoee8f<nPU!b)rt|UKw2B6_rgp
zQx@cH(mcN7{0%)LdlSvM=b{VJlRt2n4I9;z3KfP~HF@5Q;%`YKpU!&!T|0Fh?+b&u
zP*H9LgA%SFw@j<9`a~oM7xUHbnWltq7}?i#om6<F(uz`2*2l(OSbFIbP26F5@xn$M
zIX#9PRZ*@ox$ecU3dGG5i<g*ee*W^;|DVpjfA{psipJQL{IN04OTMh_YM*3+3CSmD
zPR!(EG^Y*8Cx(C3C0+{Xjx>+X8rI5J9CfD-`QRz#2j+(zSI4<A*X=ra(ev}l^Xr0q
z7KX~dC)7}Cs8DP~A2}G%GdcI-ZHC8}N58V`XmqObw0o?a+0B!vS=tJ;Gs<E;Exhu!
z4ansN8Jm66xu<i_rd)O|TX%XvqfCb=RwE2nh&ZRnNj6Vi8&o8J+_A#WR)ZH38)$Mu
zMV(NbI92$0thKhGLFNM^gRYR`ei!P<&m|p+tg}1fd!M{IRrp;TPnqV^w02-a>;A%<
zt|wC$n<|ZxhMM+A9UGK0H~Zo_m$GBZ{6wDNbbYt1E6^gy$-FChB!W)nGQ~e9Gw+Bz
z#!qAlGc<lbh5eBibT$Z^-QLFeqI>TNBTIWGFz>`D$So!2z8jE#M5ySTSXv^>^<3$Y
zW*;eWa`^Xw_-~9?NpD^e-q|xWYBeq~Ydz%8rAtO;yhvrO>7c2WwzGqGPoA0y0GjnS
zyM^`E4{2@TW?@ZUMvm!guJm7V3;sN8+m@gvulg$MlMABhjT@fnJ7^U5f13-gh8N0u
ziL6(7_p?*tvWVw#+2t9d={o}jANZN(`kUJN^BxD<m05QhhVmW{x%PE%9b%+D;q`@W
z%XjLouzXk~-*ipIg4H>FhRm#n_5D}u7jARZucs;&JT73*Y35$7%9)MGOdpHd!U@xX
zD-ZT(-Q0RoT)1gD893<{dbwGw;z>zgDD$R0nYk4Hl)7GQa9~uh739<i@z}Em(L772
z*~jy^GDK;cSQ#LZFO|*XO?@9oTrXw)Z`9M=Qc>`lSBZf{Ln+IP*UcOnX`2WSkeHUr
z)Ob^WQWJmDPltDF+O3V5y7UEhB+{<tHRQIh$?-dqo;Sp_rdhwKEjrVkyPLx-9C$MO
zK#^U^I}gIoE=nSa=4i*VtRTzI*vdtrsso1nB`=++7UnL6HH>hq8vb}>#<wf1gH3xQ
z=~S8}!CX(4s33Y};6Q0E*%7pl47o~<%-;DVPtDl#>(kD^G4wd_63^xx%Pq|XmwA2h
zdBduaQu&&Zz*VhGS@oxt-NSAT1Jw|e*$~*eHmxU&-JX0xBz)T2EsJg_-<%(4x#V(~
znqJ2F=Du?Guq&ZN^kmogvm-^lk}1}ObwQlSMAgQw(q8)gHDt)WEvFrg5gpU!JvR1b
z*+I*8*^#YvXIf>6x3i)kGC$VSF(59~xSRnNQ=$_TFKe$M6T?Q)CpURgv&S@MSf-wI
z^5Mg^GaDfn)2k6dn~e|qvfJzL2$iP^QE$;LB8Wru1mBg=D@SD?N=(D*vz_8*O7wSe
z^q!b7&bqi~lV9`Jy1OgU%*3f3GB*j==YY^D!z)bu^l3~*JEKuGT<zkleSs%2OA5|6
zN{(J68ptKvl-U?LzL7Ftr9xq4<Dlmu-L?>SgHn#e;1n_GrNdOSsFNnn+zzJ;5mVBq
z%HwShyxeHx{Y>)S#XWQ4MohizRo=!Q;13*lNBB|sgUrH)*RPy@68D`wM3}6m=1x$z
zhn`7@n~=WvegA~OV1V39-zknobNR}#$tZS>VB+y)czRy$s_oYV_iwK?Kll|<+iUY8
z&YHR0&Q=g@A}~$s`7Cz!PCM#v%h>;Xp{36%lbhu_&O-u~&h0tmJ$@b+#?HQ(w%Fe!
zzyFG%T4@F|tbT?Dov%FiFS%IxRu;>vDVb=6I6c3j@a_Du!{K_v_Zb#7Vj0(iL$9dl
zx%7di?&*)XN1se~(GCWYYEiep@ICag?%sRLFuCDpsf^w6BtO_H&X?Z+DRb}1{e@l5
zJkC(IKamF4eL?RF<B(86ZaHK9S+do7!xR2U%WsK8(Y=NxPX%#VGYdVvBkPe(|D}cY
zbqkZPzxdUN7#rq1-EsmJt<jHo@PFw@#p20eQ`Vq|(TfW*>7uLb7n9Y4qg(Eb#!e_U
zC^HWBur92T99=f8_U77N$i>`xVJ{LRmx8k25qe`)e>G3vD<ixq(rBhB6IPdu#Lec;
zJy!KLuLcvZdBq<jq@ppt|6d8%>PM-XBx_eqS#<Bi19Pt)pCR!RLzORk$0(b_xD3h`
ziEw0u5)}|<XYe+Aco9Q0w)3`GIq3ePlKfV3R7i3D&DrYb-Jv_*$}C$bIpv$?7cBn#
z_u556lWnq5$KR`ZX5uc`MC%WOf81+>Q2&9J#|61AGm49(gw~`8xVvoyH?o*KUTaiM
zgv7aM<w3$@aJ*;8zs9{fx}Y__tY|!HbfUza(pB3sSpT1+{-;5G#B#p{qF$bJ3^CQq
z;4Iy>Vte1%mk9-KG1CLKZ8VK-W<-cg?f&vIy{|~-vqqJ?Zr_^E)RyHZa?V#06_qpc
z<cGp{4uRilpmK89d|KKaI`l4GX3u*$dA+ThCgKK1_WW?LA!O)l*_np+A+E<c>FIwR
zQOGvaUYk(Tp&@^k(7^#R*}ieeOy-;Q5Rt8Xx!xu|OUY6@)_GycDnDHvN~dt;hifdj
zfyu0zBhnuB{;h+uu^c~|hmx_oo8c~bvmWX3*J>hh{1=2p?Zb%(?agnK;`z~2Z)$AM
z&oqj&xl-%kcDk@_Q$r?e?&vbhhs%xX=a#ca17dEGwK=C@rY!W_Ad)paB;v(ckpT?$
z>(KmC-vDEu3O2ucfp|^4Z-5K?u*y~M{M}xh*RA>|#e_->&6=7**o#;B>j^fBTC$nm
zG0|y9T=<9FlhnO99TI&}>7fbVVc|%?QChQpX|Yv$;NGj|1$#Z%Z2gn9uT=Fo#VwL+
z2clCY=Ax>5os2jlBC&6yA>*pHm+j6i%L<)#U!yEB9Ab0Je!S;po)E}!Vz2|0RhQK{
zu_t^3Sczi84C-Dr#@?i_#g%iazIiI>EN9;+3H7oXjcN>YKX)T=Z?cj^KP<5GFrD4L
z@jz4CBTBSNyth_1v-ZqIcA;Z@@5Yy_UHCr+s<;Rq<mkGv34Vo#sI>XkUe0PizH7_H
z1C7zj^i8~tC(}0ZZiuP%bopfwE>GL9`362o2{TtLPVl}VFdO#@kh7p17cryz!`<hQ
z8_&)V-KH_U_Xzq%bxXC_k&#EwXj3;)Xr#`qk<;rH5P3NCe$B!40)0{R-eg@a+3asJ
zP8Kg>5bPuaRow(_s=9H4wosK^7vJc$e(C0QC;1{_(tZ_QS%10ruteX&Ws~SMwL+()
zCYy=g4E{dO>IvV)q=O|soXQtXQfXybG@b7w*=Ts5OYUHT8#vQ=DbxAGC1<RuFH6td
zr<ND)Ec0D#p2Un?+$v6p45+YKL?`%Vt{Sn{!m2LK&W3Dpb5zGQf-^6uO<yz^_{$Oo
zKfETif@Yo0L1OY&DyJhlDrTaj`_*dKLdMM;<HvV5a`*4$rtodZDFrs1wriQ>z+1N}
zIy@6nHZ^Qa5=QB08JlUmE<Rvvq0z$hEl75${7L9c89XbLCRGUZSxn+ZV5885MxWT9
zuhlg8-RRv*zHUmigtQj#;9j!J-pC@mqun#woJ6v#b;Q1@QmbpVK>??>*lMsig8H~x
zM}8;0)jRbFog6vzT~noNw5p)YRW?o|v{{3Oj;qgo@u}^zR8>v2bI0%2e(Y~z;bEXp
z>wEHwVkMvuB&-BQktV{^{(jD!wiLG1#IQ4bsMP8=$pXo|HcDNL+=RUUG?q-?X!kI$
z%nUxfRgII9*;qyKH}6au3QU~}aVahHev-{AmPJLfX#IVawDI(10w>yKubzX`S9NmV
z{cEH6$EKQR=1GFKkb{##TmEK4LVIkyU5Pi$xjWo6FvJNO60HAyXi5G9b*C(gD_e<u
zIF;h~T~KK40Y6?+LfSAz6dmbiCHhe^{#w2CzTF_F?bWSvcgGPgD$AM8z7^>fe${(V
zHoc_1(CDRz>3f57?oNJzMmslQ65svg3{W;Z5Hg7)i|GF<-_WJuwSHJ<{y?z4L`uzw
z)oe{Z<S)=kWKe`=4Sp6QN<3jaH-{-yZY~w-6>YChKQE5_)Sus=F+w8~3H<i<jdF90
ztN4`VXz^j~MxR^J0ge~k5_F6#3`3~ltoqvOu+B`!cFEl-v0&^(<t%3)DMN>i{7fyL
zC>fLP6}U38u95F)>u3I5N~Ud<js9I0dE7}&oj)yNt(n%pUb;O(%3)8bPmdBQy;i!v
Iq$kY#CsLD7#sB~S

diff --git a/src/provenance/ncbi_ref.acc.more b/src/provenance/ncbi_ref.acc.more
new file mode 100644
index 0000000..fb34909
--- /dev/null
+++ b/src/provenance/ncbi_ref.acc.more
@@ -0,0 +1,68 @@
+# I'll just cat these later to ncbi_ref.acc.gz later
+BA000040.2
+Buchnera_aphidicola	BA000003	9	32199	UNKNOWN
+Candidatus_Desulforudis_audaxviator	CP000860	471827	471826	UNKNOWN
+Chlamydia_pneumoniae	AE001363	83558	810	UNKNOWN
+Caulobacter_vibrioides	CP001340	155892	75	UNKNOWN
+Corynebacterium_diphtheriae	CP091095	1717	1716	UNKNOWN
+Corynebacterium_urealyticum	AM942444	43771	1716	UNKNOWN
+Cronobacter_condimenti	CP012264	1163710	413496	UNKNOWN
+Cronobacter_malonaticus	CP006731	413503	413496	UNKNOWN
+Cronobacter_sakazakii	CP011047	28141	413496	UNKNOWN
+Cronobacter_turicensis	FN543093	413502	413496	UNKNOWN
+Coxiella_burnetii	AE016828	777	776	UNKNOWN
+Cronobacter_malonaticus	CP006731	413503	413496	UNKNOWN
+Cronobacter_sakazakii	CP011047	28141	413496	UNKNOWN
+Cronobacter_turicensis	FN543093	413502	413496	UNKNOWN
+Deinococcus_radiodurans	AE000513	1299	1298	UNKNOWN
+Deinococcus_radiodurans	AE001825	1299	1298	UNKNOWN
+Exiguobacterium_antarcticum	CP003063	132920	33986	UNKNOWN
+Flavobacterium_psychrophilum	AM398681	96345	237	UNKNOWN
+Francisella_tularensis	AJ749949	263	262	UNKNOWN
+Gardnerella_vaginalis	CP002104	2702	2701	UNKNOWN
+Haemophilus_influenzae	L42023	727	724	UNKNOWN
+Halobacterium_salinarum	AM774415	478009	2242	UNKNOWN
+Helianthus_annuus	MG770607	4232	4231	UNKNOWN
+Ketogulonicigenium_vulgare	CP002018	92945	92944	UNKNOWN
+Klebsiella_aerogenes	CP002824	548	570	UNKNOWN
+Lactobacillus_acidophilus	CP000033	1579	1578	UNKNOWN
+Lactococcus_lactis	AE005176	1358	1357	UNKNOWN
+Legionella_pneumophila	AE017354	446	445	UNKNOWN
+Leuconostoc_citreum	DQ489736	349519	33964	UNKNOWN
+Lysinibacillus_sphaericus	CP000817	444177	1421	UNKNOWN
+Mesorhizobium_ciceri	CP002447	39645	68287	UNKNOWN
+Methylobacterium	CP000943	426117	2615210	UNKNOWN
+Methylobacterium_radiotolerans	CP001001	31998	407	UNKNOWN
+Micrococcus_luteus	CP001628	1270	1269	UNKNOWN
+Morganella_morganii_morganii	CP004345	180434	582	UNKNOWN
+Mycobacterium_leprae	AL450380	1769	1763	UNKNOWN
+Mycoplasma_mycoides	BX293980	2102	656088	UNKNOWN
+Pantoea_ananatis	CP001875	553	53335	UNKNOWN
+Parabacteroides_distasonis	CP000140	823	375288	UNKNOWN
+Prochlorococcus_marinus	AE017126	1219	1218	UNKNOWN
+Proteus_mirabilis	CP004022	584	583	UNKNOWN
+Pseudomonas_aeruginosa	AE004091	287	136841	UNKNOWN
+Pseudomonas_putida	AP013070	390235	303	UNKNOWN
+Pyrobaculum_neutrophilum	CP001014	70771	2276	UNKNOWN
+Rhodospirillum_rubrum	CP000230	1085	1081	UNKNOWN
+Rickettsia_prowazekii	AJ235269	782	114292	UNKNOWN
+Salinibacter_ruber	CP000159	146919	146918	UNKNOWN
+Salmonella_bongori	FR877557	54736	590	UNKNOWN
+Shewanella_halifaxensis	CP000931	271098	22	UNKNOWN
+Shewanella_oneidensis	AE014299	70863	22	UNKNOWN
+Sinorhizobium_fredii	CP001389	380	663276	UNKNOWN
+Sinorhizobium_medicae	CP000738	110321	28105	UNKNOWN
+Sinorhizobium_meliloti	AL591688	382	28105	UNKNOWN
+Staphylococcus_aureus	CP009554	46170	1280	UNKNOWN
+Staphylococcus_epidermidis	AE015929	1282	1279	UNKNOWN
+Streptococcus_agalactiae	AE009948	1311	1301	UNKNOWN
+Streptococcus_mitis	FN568063	28037	1301	UNKNOWN
+Streptococcus_mutans	AE014133	1309	1301	UNKNOWN
+Streptococcus_pneumoniae	CP000936	487214	1313	UNKNOWN
+Streptococcus_pyogenes	AE004092	1314	1301	UNKNOWN
+Streptococcus_sanguinis	CP000387	1305	1301	UNKNOWN
+Thermotoga_maritima	AE000512	2336	2335	UNKNOWN
+Thermus_thermophilus	AP008226	274	270	UNKNOWN
+Xanthomonas_campestris	AE008922	339	338	UNKNOWN
+Xylella_fastidiosa	CP000941	405440	2371	UNKNOWN
+
diff --git a/src/provenance/quick-ncbi-ref-check.sh b/src/provenance/quick-ncbi-ref-check.sh
new file mode 100644
index 0000000..56f61f2
--- /dev/null
+++ b/src/provenance/quick-ncbi-ref-check.sh
@@ -0,0 +1,25 @@
+#!/bin/bash
+set -e
+set -o pipefail
+#set -x
+
+#which datasets dataformat
+
+genus=$1
+species=$2
+expected=$3
+spreadsheet=assembly-complete.tsv
+
+acc=($(grep $genus $spreadsheet | grep $species | cut -f 1 | tr '\n' ' '))
+chunk_size=100
+
+for ((i=0; i<${#acc}; i+=chunk_size)); do
+  chunk=("${acc[@]:i:chunk_size}")
+  accs=$(echo "$chunk" | tr '\n' ',' | sed 's/,$//')
+  # Join chunk into a comma-separated list
+  accs=$(IFS=,; echo "${chunk[*]}")
+  echo "ACCESSIONS: $accs"
+  datasets summary genome accession $accs --report sequence --as-json-lines | \
+    dataformat tsv genome-seq --fields accession,genbank-seq-acc | \
+    grep -m 1 $expected || true
+done
\ No newline at end of file
diff --git a/src/provenance/sources.tsv b/src/provenance/sources.tsv
index 223e124..54f9386 100644
--- a/src/provenance/sources.tsv
+++ b/src/provenance/sources.tsv
@@ -1,19 +1,17 @@
 scientificName	nuccoreAcc	taxid	parent	source
 Acholeplasma_laidlawii	CP000896	2148	2147	NCBI-REF
 Acinetobacter_baumannii	CP045110	509170	470	NCBI-REF
-Acinetobacter_pittii	CP002177	48296	909768	UNKNOWN
-Aeromonas_hydrophila	CP000462	644	642	UNKNOWN
+Acinetobacter_pittii	CP002177	48296	909768	NCBI-REF
 Agrobacterium_fabrum	AE007869	1176649	1183400	NCBI-REF
 Agrobacterium_fabrum	AE007870	1176649	1183400	NCBI-REF
 Alkaliphilus_transvaalensis	CP000724	208226	114627	NCBI-REF
 Aliivibrio_fischeri	CP000021	668	511678	NCBI-REF
 Aliivibrio_fischeri	CP000020	668	511678	NCBI-REF
-Amycolatopsis_mediterranei	CP002000	33910	1813	UNKNOWN
+Amycolatopsis_mediterranei	CP002896	33910	1813	NCBI-REF
 Aquifex_aeolicus	AE000657	63363	2713	NCBI-REF
-Architeuthis_dux	NC_011581	256136	34555	UNKNOWN
 Arcobacter_bivalviorum	CP031217	663364	2321115	NCBI-REF
-Arcobacter_ellisii	CP032097	913109	28196	UNKNOWN
-Arcobacter_cibarius	CP043857	255507	28196	UNKNOWN
+Arcobacter_ellisii	CP032097	913109	28196	SME
+Arcobacter_cibarius	CP043857	255507	28196	SME
 Arcobacter_halophilus	CP031218	197482	28196	NCBI-REF
 Arcobacter_molluscorum	CP032098	1032072	28196	NCBI-REF
 Arcobacter_mytili	CP031219	603050	28196	NCBI-REF
@@ -21,25 +19,24 @@ Arcobacter_skirrowii	CP032099	28200	28196	NCBI-REF
 Arcobacter_suis	CP032100	1278212	28196	NCBI-REF
 Arcobacter_thereius	CP035926	544718	28196	NCBI-REF
 Arcobacter_trophiarum	CP031367	708186	28196	NCBI-REF
-Arripis_trutta	AP006810	270544	163128	UNKNOWN
+Arripis_trutta	AP006810	270544	163128	SME
 Atlantibacter_hermannii	CP042941	565	1903434	NCBI-GEN:CDC
 Bacillus_cereus	AP007209	1396	86661	SME
 Bacillus_subtilis	AL009126	1423	653685	SME
 Bacillus_thuringiensis	AE017355	1428	86661	SME
-Bacteroides_fragilis	AP006841	817	816	UNKNOWN
-Bacteroides_thetaiotaomicron	AE015928	818	816	UNKNOWN
+Bacteroides_fragilis	CR626927	817	816	NCBI-REF
+Bacteroides_thetaiotaomicron	CP040530	818	816	NCBI-REF
 Bartonella_bacilliformis	CP000524	774	773	NCBI-REF
 Betacoronavirus_coronavirus	MT233526	2697049	694009	SME
-Bifidobacterium_adolenscentis	CP028341	1680	1678	UNKNOWN
-Bifidobacterium_bifidum	CP001840	1681	1678	UNKNOWN
-Bifidobacterium_longum	AE014295	216816	1678	UNKNOWN
-Bordetella_bronchiseptica	HE965806	518	517	UNKNOWN
+Bifidobacterium_bifidum	CP058603	1681	1678	NCBI-REF
+Bifidobacterium_longum	AP010888	216816	1678	NCBI-REF
+Bordetella_bronchiseptica	LR134326	518	517	NCTC3000
 Borreliella_burgdorferi	AE000783	139	64895	SME
-Bos_taurus	KC153975	9913	9903	UNKNOWN
+Bos_taurus	KC153975	9913	9903	SME
 Brachybacterium_faecium	CP001643	43669	43668	UNKNOWN
-Bradyrhizobium_diazoefficiens	BA000040	1355477	374	UNKNOWN
-Brassica_oleracea	JF920286	3712	3705	UNKNOWN
-Buchnera_aphidicola	BA000003	9	32199	UNKNOWN
+Bradyrhizobium_diazoefficiens	BA000040	1355477	374	NCBI-REF
+Brassica_oleracea	JF920286	3712	3705	SME
+Buchnera_aphidicola	BA000003	9	32199	NCBI-REF
 Burkholderia_pseudomallei	BX571965	28450	111527	SME
 Burkholderia_pseudomallei	BX571966	28450	111527	SME
 Campylobacter_avium	CP022347	522484	522485	NCBI-REF
@@ -60,10 +57,10 @@ Campylobacter_sputorum	CP019683	202	194	SME
 Campylobacter_subantarcticus	CP007772	497724	194	SME
 Campylobacter_volucris	CP007774	1031542	194	SME
 Campylobacter_ureolyticus	CP012195	827	194	SME
-Candidatus_Desulforudis_audaxviator	CP000860	471827	471826	UNKNOWN
+Candidatus_Desulforudis_audaxviator	CP000860	471827	471826	NCBI-REF
 Candidatus_Korarchaeum_cryptofilum	CP000968	374847	498846	NCBI-REF
-Chlamydia_pneumoniae	AE001363	83558	810	UNKNOWN
-Caulobacter_vibrioides	CP001340	155892	75	UNKNOWN
+Chlamydia_pneumoniae	AE001363	83558	810	NCBI-REF
+Caulobacter_vibrioides	CP001340	155892	75	NCBI-REF
 Chlamydomonas_reinhardtii	AF008237	3055	3052	UNKNOWN
 Chlamydia_trachomatis	AE001273	813	810	NCBI-REF
 Chlorobaculum_tepidum	AE006470	1097	256319	NCBI-REF
@@ -78,17 +75,17 @@ Clostridium_baratii	CP014204	1561	1485	SME
 Clostridium_botulinum_groupI	CP001078	9000005	1491	SME
 Clostridium_botulinum_groupII	CP000939	9000004	1491	SME
 Clostridium_butyricum	CP013239	1492	1485	SME
-Corynebacterium_diphtheriae	CP091095	1717	1716	UNKNOWN
+Corynebacterium_diphtheriae	CP091095	1717	1716	NCBI-REF
 Clostridium_perfringens	CP000312	1502	1485	SME
-Corynebacterium_urealyticum	AM942444	43771	1716	UNKNOWN
+Corynebacterium_urealyticum	AM942444	43771	1716	NCBI-REF
 Corynebacterium_glutamicum	BA000036	1718	1716	NCBI-REF
-Cronobacter_condimenti	CP012264	1163710	413496	UNKNOWN
-Coxiella_burnetii	AE016828	777	776	UNKNOWN
+Cronobacter_condimenti	CP012264	1163710	413496	NCBI-REF
+Coxiella_burnetii	AE016828	777	776	NCBI-REF
 Cronobacter_dublinensis_dublinensis	CP012266	413498	413497	NCBI-REF
-Cronobacter_malonaticus	CP006731	413503	413496	UNKNOWN
+Cronobacter_malonaticus	CP006731	413503	413496	NCBI-REF
 Cronobacter_muytjensii	CP012268	413501	413496	NCBI-REF
-Cronobacter_sakazakii	CP011047	28141	413496	UNKNOWN
-Cronobacter_turicensis	FN543093	413502	413496	UNKNOWN
+Cronobacter_sakazakii	CP011047	28141	413496	NCBI-REF
+Cronobacter_turicensis	FN543093	413502	413496	NCBI-REF
 Cronobacter_universalis	CP012257	535744	413496	NCBI-REF
 Cryptosporidium_parvum	CM000430	353152	5806	SME
 Cryptosporidium_parvum	CM000429	353152	5806	SME
@@ -110,8 +107,8 @@ Cupriavidus_taiwanensis	CU633750	164546	106589	NCBI-REF
 Cupriavidus_taiwanensis	CU633749	164546	106589	NCBI-REF
 Cyanothece	CP000806	43989	2546360	NCBI-REF
 Cyanothece	CP000807	43989	2546360	NCBI-REF
-Deinococcus_radiodurans	AE000513	1299	1298	UNKNOWN
-Deinococcus_radiodurans	AE001825	1299	1298	UNKNOWN
+Deinococcus_radiodurans	AE000513	1299	1298	NCBI-REF
+Deinococcus_radiodurans	AE001825	1299	1298	NCBI-REF
 Delftia_acidovorans	CP000884	80866	80865	NCBI-REF
 Desulfovibrio_vulgaris	AE017285	881	872	UNKNOWN
 Dictyoglomus_turgidum	CP001251	513050	13	NCBI-REF
@@ -121,40 +118,40 @@ Enterococcus_faecium	CP003583	1352	1350	SME
 Escherichia_albertii	CP024282	208962	561	SME
 Escherichia_coli	CP027582	562	561	SME
 Escherichia_fergusonii	CP042945	564	561	SME
-Exiguobacterium_antarcticum	CP003063	132920	33986	UNKNOWN
+Exiguobacterium_antarcticum	CP003063	132920	33986	NCBI-REF
 Finegoldia_magna	AP008971	1260	150022	SME
 Francisella_philomiragia	CP063138	28110	262	NCBI-REF
-Flavobacterium_psychrophilum	AM398681	96345	237	UNKNOWN
-Francisella_tularensis	AJ749949	263	262	UNKNOWN
+Flavobacterium_psychrophilum	AM398681	96345	237	NCBI-REF
+Francisella_tularensis	AJ749949	263	262	NCBI-REF
 Fusobacterium_nucleatum	CP028101	851	848	SME
-Gallus_gallus	HQ857211	9031	9030	UNKNOWN
-Gardnerella_vaginalis	CP002104	2702	2701	UNKNOWN
+Gallus_gallus	HQ857211	9031	9030	SME
+Gardnerella_vaginalis	CP002104	2702	2701	NCBI-REF
 Geobacter_sulfurreducens	AE017180	35554	28231	NCBI-REF
 Gloeobacter_violaceus	BA000045	33072	33071	NCBI-REF
 Grimontia_hollisae	CP035690	673	246861	NCBI-GEN:CDC
 Grimontia_hollisae	CP035691	673	246861	NCBI-GEN:CDC
-Haemophilus_influenzae	L42023	727	724	UNKNOWN
+Haemophilus_influenzae	L42023	727	724	NCBI-REF
 Haemophilus_somnus	CP000947	228400	731	NCBI-REF
-Halobacterium_salinarum	AM774415	478009	2242	UNKNOWN
-Helianthus_annuus	MG770607	4232	4231	UNKNOWN
-Helicobacter_pylori	AE000511	210	209	UNKNOWN
+Halobacterium_salinarum	AM774415	478009	2242	NCBI-REF
+Helianthus_annuus	MG770607	4232	4231	NCBI-REF
+Helicobacter_pylori	AE000511	210	209	SME
 Heliobacterium_modesticaldum	CP000930	35701	2697	NCBI-REF
-Humulus_lupulus	NC_086845	3486	3484	UNKNOWN
+Humulus_lupulus	NC_086845	3486	3484	SME
 Homo_sapiens	J01415	9606	9605	NCBI-REF
-Ketogulonicigenium_vulgare	CP002018	92945	92944	UNKNOWN
-Klebsiella_aerogenes	CP002824	548	570	UNKNOWN
+Ketogulonicigenium_vulgare	CP002018	92945	92944	NCBI-REF
+Klebsiella_aerogenes	CP002824	548	570	NCBI-REF
 Klebsiella_pneumoniae	CP003200	573	570	NCBI-REF
-Lactobacillus_acidophilus	CP000033	1579	1578	UNKNOWN
+Lactobacillus_acidophilus	CP000033	1579	1578	NCBI-REF
 Lactobacillus_plantarum	AL935263	1590	1578	UNKNOWN
 Lactobacillus_paracasei	CP000423	1597	655183	UNKNOWN
-Lactococcus_lactis	AE005176	1358	1357	UNKNOWN
+Lactococcus_lactis	AE005176	1358	1357	NCBI-REF
 Lactobacillus_salivarius	CP000233	1624	1578	UNKNOWN
-Lactuca_sativa	MK820672	75943	4235	UNKNOWN
-Legionella_pneumophila	AE017354	446	445	UNKNOWN
+Lactuca_sativa	MK820672	75943	4235	SME
+Legionella_pneumophila	AE017354	446	445	NCBI-REF
 Leptospira_biflexa	CP000777	355278	145259	SME
 Leptothrix_cholodnii	CP001013	34029	88	NCBI-REF
-Leptospira_interrogans	CP020414	173	171	FDA-ARGOS
-Leuconostoc_citreum	DQ489736	349519	33964	UNKNOWN
+Leptospira_interrogans	CP020414	173	171	SME
+Leuconostoc_citreum	DQ489736	349519	33964	NCBI-REF
 Listeria_grayi	LR134483	1641	1637	NCTC3000
 Listeria_innocua	CP045743	1642	1637	SME
 Listeria_ivanovii	FR687253	1638	1637	SME
@@ -165,83 +162,83 @@ Listeria_monocytogenes_III	CP054039	9000002	1639	SME
 Listeria_monocytogenes_IV	CP054041	9000003	1639	SME
 Listeria_seeligeri	FN557490	1640	1637	SME
 Listeria_welshimeri	LT906444	1643	1637	NCTC3000
-Lysinibacillus_sphaericus	CP000817	444177	1421	UNKNOWN
+Lysinibacillus_sphaericus	CP000817	444177	1421	NCBI-REF
 Mesoplasma_florum	AE017263	2151	46239	NCBI-REF
-Mesorhizobium_ciceri	CP002447	39645	68287	UNKNOWN
-Methylobacterium	CP000943	426117	2615210	UNKNOWN
-Methylobacterium_radiotolerans	CP001001	31998	407	UNKNOWN
-Micrococcus_luteus	CP001628	1270	1269	UNKNOWN
+Mesorhizobium_ciceri	CP002447	39645	68287	NCBI-REF
+Methylobacterium	CP000943	426117	2615210	NCBI-REF
+Methylobacterium_radiotolerans	CP001001	31998	407	NCBI-REF
+Micrococcus_luteus	CP001628	1270	1269	NCBI-REF
 Moorella_thermoacetica	CP012370	1525	44260	NCBI-REF
-Morganella_morganii_morganii	CP004345	180434	582	UNKNOWN
+Morganella_morganii_morganii	CP004345	180434	582	NCBI-REF
 Mycobacterium_abscessus	CU458896	36809	670516	NCBI-REF
-Mycobacterium_leprae	AL450380	1769	1763	UNKNOWN
+Mycobacterium_leprae	AL450380	1769	1763	NCBI-REF
 Mycobacterium_smegmatis	CP000480	1772	1866885	UNKNOWN
 Mycobacterium_tuberculosis	AL123456	1773	77643	NCBI-REF
-Mycoplasma_mycoides	BX293980	2102	656088	UNKNOWN
+Mycoplasma_mycoides	BX293980	2102	656088	NCBI-REF
 Mycoplasma_pneumoniae	U00089	2104	2093	UNKNOWN
 Neisseria_gonorrhoeae	AE004969	485	482	SME
 Neisseria_meningitidis	AE002098	487	482	SME
-Neomysis_japonica	KR006340	1676841	223649	UNKNOWN
+Neomysis_japonica	KR006340	1676841	223649	SME
 Ochrobactrum_anthropi	CP000758	529	528	UNKNOWN
 Ochrobactrum_anthropi	CP000759	529	528	UNKNOWN
-Pantoea_ananatis	CP001875	553	53335	UNKNOWN
-Parabacteroides_distasonis	CP000140	823	375288	UNKNOWN
+Pantoea_ananatis	CP001875	553	53335	NCBI-REF
+Parabacteroides_distasonis	CP000140	823	375288	NCBI-REF
 Photobacterium_damselae	CP046752	38293	657	NCBI-GEN:CDC
 Photobacterium_damselae	CP046751	38293	657	NCBI-GEN:CDC
-Pollachius_virens	FR751399	8060	8059	UNKNOWN
+Pollachius_virens	FR751399	8060	8059	SME
 Polynucleobacter_necessarius	LT615228	576610	44013	NCBI-REF
-Prochlorococcus_marinus	AE017126	1219	1218	UNKNOWN
-Proteus_mirabilis	CP004022	584	583	UNKNOWN
-Pseudomonas_aeruginosa	AE004091	287	136841	UNKNOWN
-Pseudomonas_putida	AP013070	390235	303	UNKNOWN
-Pyrobaculum_neutrophilum	CP001014	70771	2276	UNKNOWN
+Prochlorococcus_marinus	AE017126	1219	1218	NCBI-REF
+Proteus_mirabilis	CP004022	584	583	NCBI-REF
+Pseudomonas_aeruginosa	AE004091	287	136841	NCBI-REF
+Pseudomonas_putida	AP013070	390235	303	NCBI-REF
+Pyrobaculum_neutrophilum	CP001014	70771	2276	NCBI-REF
 Pseudomonas_syringae_group_genomosp._3	AE016853	251701	136849	NCBI-REF
 Rhodobacter_sphaeroides	CP000144	1063	1060	UNKNOWN
 Rhodobacter_sphaeroides	CP000143	1063	1060	UNKNOWN
 Rhodopirellula_baltica	BX119912	265606	265488	NCBI-REF
-Rhodospirillum_rubrum	CP000230	1085	1081	UNKNOWN
+Rhodospirillum_rubrum	CP000230	1085	1081	NCBI-REF
 Ruminococcus_sp.	CP039381	1263	541000	NCBI-REF
-Rickettsia_prowazekii	AJ235269	782	114292	UNKNOWN
-Salinibacter_ruber	CP000159	146919	146918	UNKNOWN
-Salmonella_bongori	FR877557	54736	590	UNKNOWN
+Rickettsia_prowazekii	AJ235269	782	114292	NCBI-REF
+Salinibacter_ruber	CP000159	146919	146918	NCBI-REF
+Salmonella_bongori	FR877557	54736	590	NCBI-REF
 Salmonella_enterica_IIa	CP053411	9000010	28901	NCBI-GEN:Centers for Disease Control and Prevention
 Salmonella_enterica_IIb	LR134141	9000011	28901	NCTC3000
-Salmonella_enterica_IIIa	CP000880	9000014	28901	UNKNOWN
-Salmonella_enterica_IIIb	CP053583	9000015	28901	UNKNOWN
+Salmonella_enterica_IIIa	CP000880	9000014	28901	SME
+Salmonella_enterica_IIIb	CP053583	9000015	28901	SME
 Salmonella_enterica_I	AE006468	59201	28901	NCBI-REF
-Salmonella_enterica_IV	CP053579	59205	28901	UNKNOWN
-Salmonella_enterica_IX	CP054715	9000016	28901	UNKNOWN
-Salmonella_enterica_VII	CP053582	59208	28901	UNKNOWN
+Salmonella_enterica_IV	CP053579	59205	28901	SME
+Salmonella_enterica_IX	CP054715	9000016	28901	SME
+Salmonella_enterica_VII	CP053582	59208	28901	SME
 Salmonella_enterica_VIII	CP053318	9000009	28901	NCBI-GEN:EDLB-CDC
 Salmonella_enterica_VI	CP053406	59207	28901	NCBI-GEN:Centers for Disease Control and Prevention
-Salmonella_enterica_X	CP053581	9000017	28901	UNKNOWN
+Salmonella_enterica_X	CP053581	9000017	28901	SME
 Serratia_liquefaciens	CP006252	614	613	NCBI-REF
-Shewanella_halifaxensis	CP000931	271098	22	UNKNOWN
-Shewanella_oneidensis	AE014299	70863	22	UNKNOWN
+Shewanella_halifaxensis	CP000931	271098	22	NCBI-REF
+Shewanella_oneidensis	AE014299	70863	22	NCBI-REF
 Shewanella_woodyi	CP000961	60961	22	NCBI-REF
 Shimwellia_blattae	CP001560	563	1335483	UNKNOWN
-Sinorhizobium_fredii	CP001389	380	663276	UNKNOWN
-Sinorhizobium_medicae	CP000738	110321	28105	UNKNOWN
-Sinorhizobium_meliloti	AL591688	382	28105	UNKNOWN
-Solanum_lycopersicum	MF034192	4081	49274	UNKNOWN
-Staphylococcus_aureus	CP009554	46170	1280	UNKNOWN
-Staphylococcus_epidermidis	AE015929	1282	1279	UNKNOWN
-Streptococcus_agalactiae	AE009948	1311	1301	UNKNOWN
-Streptococcus_mitis	FN568063	28037	1301	UNKNOWN
-Streptococcus_mutans	AE014133	1309	1301	UNKNOWN
-Streptococcus_pneumoniae	CP000936	487214	1313	UNKNOWN
-Streptococcus_pyogenes	AE004092	1314	1301	UNKNOWN
-Streptococcus_sanguinis	CP000387	1305	1301	UNKNOWN
-Sus_scrofa	FJ236999	9823	9822	UNKNOWN
+Sinorhizobium_fredii	CP001389	380	663276	NCBI-REF
+Sinorhizobium_medicae	CP000738	110321	28105	NCBI-REF
+Sinorhizobium_meliloti	AL591688	382	28105	NCBI-REF
+Solanum_lycopersicum	MF034192	4081	49274	SME
+Staphylococcus_aureus	CP009554	46170	1280	NCBI-REF
+Staphylococcus_epidermidis	AE015929	1282	1279	NCBI-REF
+Streptococcus_agalactiae	AE009948	1311	1301	NCBI-REF
+Streptococcus_mitis	FN568063	28037	1301	NCBI-REF
+Streptococcus_mutans	AE014133	1309	1301	NCBI-REF
+Streptococcus_pneumoniae	CP000936	487214	1313	NCBI-REF
+Streptococcus_pyogenes	AE004092	1314	1301	NCBI-REF
+Streptococcus_sanguinis	CP000387	1305	1301	NCBI-REF
+Sus_scrofa	FJ236999	9823	9822	SME
 Streptococcus_suis	FM252032	1307	1301	NCBI-REF
 Synechococcus	CP000951	32049	2626047	UNKNOWN
 Thermanaerovibrio_acidaminovorans	CP001818	81462	81461	NCBI-REF
 Thermoanaerobacter_pseudethanolicus	CP000924	496866	1754	NCBI-REF
 Thermodesulfovibrio_yellowstonii	CP001147	28262	28261	NCBI-REF
 Thermosynechococcus_elongatus	BA000039	146786	146785	NCBI-REF
-Thermotoga_maritima	AE000512	2336	2335	UNKNOWN
-Thermus_thermophilus	AP008226	274	270	UNKNOWN
-Thunnus_alalunga	AB101291	8235	8234	UNKNOWN
+Thermotoga_maritima	AE000512	2336	2335	NCBI-REF
+Thermus_thermophilus	AP008226	274	270	NCBI-REF
+Thunnus_alalunga	AB101291	8235	8234	SME
 Treponema_denticola	AE017226	158	157	NCBI-REF
 Ureaplasma_parvum	CP000942	134821	2129	NCBI-REF
 Vibrio_alginolyticus	CP035699	663	717610	NCBI-GEN:CDC
@@ -270,9 +267,9 @@ Vibrio_parahaemolyticus	CP046828	670	717610	NCBI-GEN:CDC
 Vibrio_parahaemolyticus	CP046827	670	717610	NCBI-GEN:CDC
 Vibrio_vulnificus	CP046832	672	662	NCBI-GEN:CDC
 Vibrio_vulnificus	CP046833	672	662	NCBI-GEN:CDC
-Vicia_faba	KC189947	3906	3904	UNKNOWN
-Xanthomonas_campestris	AE008922	339	338	UNKNOWN
-Xylella_fastidiosa	CP000941	405440	2371	UNKNOWN
+Vicia_faba	KC189947	3906	3904	SME
+Xanthomonas_campestris	AE008922	339	338	NCBI-REF
+Xylella_fastidiosa	CP000941	405440	2371	NCBI-REF
 Yersinia_aldovae	CP009781	29483	629	NCBI-REF
 Yersinia_bercovieri	CP054044	634	629	SME
 Yersinia_enterocolitica	CP002246	630	629	SME
diff --git a/src/provenance/unknown.tsv b/src/provenance/unknown.tsv
index f4dd02a..fe872a9 100644
--- a/src/provenance/unknown.tsv
+++ b/src/provenance/unknown.tsv
@@ -1,108 +1,14 @@
-Acinetobacter_pittii	CP002177	48296	909768	UNKNOWN
-Aeromonas_hydrophila	CP000462	644	642	UNKNOWN
-Amycolatopsis_mediterranei	CP002000	33910	1813	UNKNOWN
-Architeuthis_dux	NC_011581	256136	34555	UNKNOWN
-Arcobacter_ellisii	CP032097	913109	28196	UNKNOWN
-Arcobacter_cibarius	CP043857	255507	28196	UNKNOWN
-Arripis_trutta	AP006810	270544	163128	UNKNOWN
-Bacteroides_fragilis	AP006841	817	816	UNKNOWN
-Bacteroides_thetaiotaomicron	AE015928	818	816	UNKNOWN
-Bifidobacterium_adolenscentis	CP028341	1680	1678	UNKNOWN
-Bifidobacterium_bifidum	CP001840	1681	1678	UNKNOWN
-Bifidobacterium_longum	AE014295	216816	1678	UNKNOWN
-Bordetella_bronchiseptica	HE965806	518	517	UNKNOWN
-Bos_taurus	KC153975	9913	9903	UNKNOWN
 Brachybacterium_faecium	CP001643	43669	43668	UNKNOWN
-Bradyrhizobium_diazoefficiens	BA000040	1355477	374	UNKNOWN
-Brassica_oleracea	JF920286	3712	3705	UNKNOWN
-Buchnera_aphidicola	BA000003	9	32199	UNKNOWN
-Candidatus_Desulforudis_audaxviator	CP000860	471827	471826	UNKNOWN
-Chlamydia_pneumoniae	AE001363	83558	810	UNKNOWN
-Caulobacter_vibrioides	CP001340	155892	75	UNKNOWN
 Chlamydomonas_reinhardtii	AF008237	3055	3052	UNKNOWN
-Corynebacterium_diphtheriae	CP091095	1717	1716	UNKNOWN
-Corynebacterium_urealyticum	AM942444	43771	1716	UNKNOWN
-Cronobacter_condimenti	CP012264	1163710	413496	UNKNOWN
-Coxiella_burnetii	AE016828	777	776	UNKNOWN
-Cronobacter_malonaticus	CP006731	413503	413496	UNKNOWN
-Cronobacter_sakazakii	CP011047	28141	413496	UNKNOWN
-Cronobacter_turicensis	FN543093	413502	413496	UNKNOWN
-Deinococcus_radiodurans	AE000513	1299	1298	UNKNOWN
-Deinococcus_radiodurans	AE001825	1299	1298	UNKNOWN
 Desulfovibrio_vulgaris	AE017285	881	872	UNKNOWN
-Exiguobacterium_antarcticum	CP003063	132920	33986	UNKNOWN
-Flavobacterium_psychrophilum	AM398681	96345	237	UNKNOWN
-Francisella_tularensis	AJ749949	263	262	UNKNOWN
-Gallus_gallus	HQ857211	9031	9030	UNKNOWN
-Gardnerella_vaginalis	CP002104	2702	2701	UNKNOWN
-Haemophilus_influenzae	L42023	727	724	UNKNOWN
-Halobacterium_salinarum	AM774415	478009	2242	UNKNOWN
-Helianthus_annuus	MG770607	4232	4231	UNKNOWN
-Helicobacter_pylori	AE000511	210	209	UNKNOWN
-Humulus_lupulus	NC_086845	3486	3484	UNKNOWN
-Ketogulonicigenium_vulgare	CP002018	92945	92944	UNKNOWN
-Klebsiella_aerogenes	CP002824	548	570	UNKNOWN
-Lactobacillus_acidophilus	CP000033	1579	1578	UNKNOWN
 Lactobacillus_plantarum	AL935263	1590	1578	UNKNOWN
 Lactobacillus_paracasei	CP000423	1597	655183	UNKNOWN
-Lactococcus_lactis	AE005176	1358	1357	UNKNOWN
 Lactobacillus_salivarius	CP000233	1624	1578	UNKNOWN
-Lactuca_sativa	MK820672	75943	4235	UNKNOWN
-Legionella_pneumophila	AE017354	446	445	UNKNOWN
-Leuconostoc_citreum	DQ489736	349519	33964	UNKNOWN
-Lysinibacillus_sphaericus	CP000817	444177	1421	UNKNOWN
-Mesorhizobium_ciceri	CP002447	39645	68287	UNKNOWN
-Methylobacterium	CP000943	426117	2615210	UNKNOWN
-Methylobacterium_radiotolerans	CP001001	31998	407	UNKNOWN
-Micrococcus_luteus	CP001628	1270	1269	UNKNOWN
-Morganella_morganii_morganii	CP004345	180434	582	UNKNOWN
-Mycobacterium_leprae	AL450380	1769	1763	UNKNOWN
 Mycobacterium_smegmatis	CP000480	1772	1866885	UNKNOWN
-Mycoplasma_mycoides	BX293980	2102	656088	UNKNOWN
 Mycoplasma_pneumoniae	U00089	2104	2093	UNKNOWN
-Neomysis_japonica	KR006340	1676841	223649	UNKNOWN
 Ochrobactrum_anthropi	CP000758	529	528	UNKNOWN
 Ochrobactrum_anthropi	CP000759	529	528	UNKNOWN
-Pantoea_ananatis	CP001875	553	53335	UNKNOWN
-Parabacteroides_distasonis	CP000140	823	375288	UNKNOWN
-Pollachius_virens	FR751399	8060	8059	UNKNOWN
-Prochlorococcus_marinus	AE017126	1219	1218	UNKNOWN
-Proteus_mirabilis	CP004022	584	583	UNKNOWN
-Pseudomonas_aeruginosa	AE004091	287	136841	UNKNOWN
-Pseudomonas_putida	AP013070	390235	303	UNKNOWN
-Pyrobaculum_neutrophilum	CP001014	70771	2276	UNKNOWN
 Rhodobacter_sphaeroides	CP000144	1063	1060	UNKNOWN
 Rhodobacter_sphaeroides	CP000143	1063	1060	UNKNOWN
-Rhodospirillum_rubrum	CP000230	1085	1081	UNKNOWN
-Rickettsia_prowazekii	AJ235269	782	114292	UNKNOWN
-Salinibacter_ruber	CP000159	146919	146918	UNKNOWN
-Salmonella_bongori	FR877557	54736	590	UNKNOWN
-Salmonella_enterica_IIIa	CP000880	9000014	28901	UNKNOWN
-Salmonella_enterica_IIIb	CP053583	9000015	28901	UNKNOWN
-Salmonella_enterica_IV	CP053579	59205	28901	UNKNOWN
-Salmonella_enterica_IX	CP054715	9000016	28901	UNKNOWN
-Salmonella_enterica_VII	CP053582	59208	28901	UNKNOWN
-Salmonella_enterica_X	CP053581	9000017	28901	UNKNOWN
-Shewanella_halifaxensis	CP000931	271098	22	UNKNOWN
-Shewanella_oneidensis	AE014299	70863	22	UNKNOWN
 Shimwellia_blattae	CP001560	563	1335483	UNKNOWN
-Sinorhizobium_fredii	CP001389	380	663276	UNKNOWN
-Sinorhizobium_medicae	CP000738	110321	28105	UNKNOWN
-Sinorhizobium_meliloti	AL591688	382	28105	UNKNOWN
-Solanum_lycopersicum	MF034192	4081	49274	UNKNOWN
-Staphylococcus_aureus	CP009554	46170	1280	UNKNOWN
-Staphylococcus_epidermidis	AE015929	1282	1279	UNKNOWN
-Streptococcus_agalactiae	AE009948	1311	1301	UNKNOWN
-Streptococcus_mitis	FN568063	28037	1301	UNKNOWN
-Streptococcus_mutans	AE014133	1309	1301	UNKNOWN
-Streptococcus_pneumoniae	CP000936	487214	1313	UNKNOWN
-Streptococcus_pyogenes	AE004092	1314	1301	UNKNOWN
-Streptococcus_sanguinis	CP000387	1305	1301	UNKNOWN
-Sus_scrofa	FJ236999	9823	9822	UNKNOWN
 Synechococcus	CP000951	32049	2626047	UNKNOWN
-Thermotoga_maritima	AE000512	2336	2335	UNKNOWN
-Thermus_thermophilus	AP008226	274	270	UNKNOWN
-Thunnus_alalunga	AB101291	8235	8234	UNKNOWN
-Vicia_faba	KC189947	3906	3904	UNKNOWN
-Xanthomonas_campestris	AE008922	339	338	UNKNOWN
-Xylella_fastidiosa	CP000941	405440	2371	UNKNOWN