Last active
June 20, 2020 15:52
-
-
Save genomewalker/1838d616dca101be52c8d970ec43d426 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# From | |
cut -f3 permafrost_pathway_orthologs.txt | grep -v ortho | while read ko; do make ${ko}.kegg.faa; done | |
for i in *kegg.faa; do NAM=$(basename $i .kegg.faa); hmmalign ../profiles/$NAM.hmm $NAM.kegg.faa | awk -vN=$NAM '{if (NR == 2){print "#=GF ID"N"\n#=GF AC "N}else{print $0}}' ; done > alns.stck | |
mmseqs convertmsa faa/alns.stck ko_msa_db | |
mmseqs msa2profile ko_msa_db permafrost_ko_profiles --match-mode 1 | |
# KO | |
seqkit replace --ignore-case --kv-file <(awk '{print $2"\t"$1}' ko_genes.list) --pattern "(.+)" --replacement "{kv}" <(seqkit replace -p "\s.+" test) > ko_seq.faa | |
awk '/^>/{split($1,a,":")}{print >> a[2]".fa"}' ../ko_seq.faa | |
~/opt/uproc-1.2.0/uproc-makedb model ko_seq.faa koDB |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
pathway gene orthology | |
Nitrogen Fixation Nif-specific regulatory protein K02584 | |
Nitrogen Fixation nitrogen fixation protein NifB K02585 | |
Nitrogen Fixation nitrogenase molybdenum-iron protein alpha chain [EC:1.18.6.1] K02586 | |
Nitrogen Fixation nitrogenase molybdenum-cofactor synthesis protein NifE K02587 | |
Nitrogen Fixation nitrogenase iron protein NifH [EC:1.18.6.1] K02588 | |
Nitrogen Fixation nitrogen regulatory protein PII 1 K02589 | |
Nitrogen Fixation nitrogen regulatory protein PII 2 K02590 | |
Nitrogen Fixation nitrogenase molybdenum-iron protein beta chain [EC:1.18.6.1] K02591 | |
Nitrogen Fixation nitrogenase molybdenum-iron protein NifN K02592 | |
Nitrate Reduction nitrate reductase 1, alpha subunit [EC:1.7.99.4] K00370 | |
Nitrate Reduction nitrate reductase 1, beta subunit [EC:1.7.99.4] K00371 | |
Nitrate Reduction nitrate reductase 1, delta subunit [EC:1.7.99.4] K00373 | |
Nitrate Reduction nitrate reductase 1, gamma subunit [EC:1.7.99.4] K00374 | |
Denitrification nitric-oxide reductase, cytochrome b-containing subunit I K04561 | |
Denitrification nitrous-oxide reductase [EC:1.7.99.6] K00376 | |
Denitrification nitrous oxidase accessory protein K07218 | |
Ammonification nitrite reductase (NAD(P)H) large subunit [EC:1.7.1.4] K00362 | |
Ammonification nitrite reductase (NAD(P)H) small subunit [EC:1.7.1.4] K00363 | |
Ammonification formate-dependent nitrite reductase, periplasmic cytochrome c552 K03385 | |
Ammonification formate-dependent nitrite reductase, Fe-S protein K04014 | |
Ammonification ferredoxin-nitrite reductase [EC:1.7.7.1] K00366 | |
NADH Dehydrogenase I NADH dehydrogenase [EC:1.6.5.3] K00329 | |
NADH Dehydrogenase I NADH dehydrogenase I subunit A [EC:1.6.5.3] K00330 | |
NADH Dehydrogenase I NADH dehydrogenase I subunit B [EC:1.6.5.3] K00331 | |
NADH Dehydrogenase I NADH dehydrogenase I subunit C [EC:1.6.5.3] K00332 | |
NADH Dehydrogenase I NADH dehydrogenase I subunit D [EC:1.6.5.3] K00333 | |
NADH Dehydrogenase I NADH dehydrogenase I subunit E [EC:1.6.5.3] K00334 | |
NADH Dehydrogenase I NADH dehydrogenase I subunit F [EC:1.6.5.3] K00335 | |
NADH Dehydrogenase I NADH dehydrogenase I subunit G [EC:1.6.5.3] K00336 | |
NADH Dehydrogenase I NADH dehydrogenase I subunit H [EC:1.6.5.3] K00337 | |
NADH Dehydrogenase I NADH dehydrogenase I subunit I [EC:1.6.5.3] K00338 | |
NADH Dehydrogenase I NADH dehydrogenase I subunit J [EC:1.6.5.3] K00339 | |
NADH Dehydrogenase I NADH dehydrogenase I subunit K [EC:1.6.5.3] K00340 | |
NADH Dehydrogenase I NADH dehydrogenase I subunit L [EC:1.6.5.3] K00341 | |
NADH Dehydrogenase I NADH dehydrogenase I subunit M [EC:1.6.5.3] K00342 | |
NADH Dehydrogenase I NADH dehydrogenase I subunit N [EC:1.6.5.3] K00343 | |
Pyruvate Dehydrogenase E1 & E2 pyruvate dehydrogenase E1 component subunit alpha [EC:1.2.4.1] K00161 | |
Pyruvate Dehydrogenase E1 & E2 pyruvate dehydrogenase E1 component subunit beta [EC:1.2.4.1] K00162 | |
Pyruvate Dehydrogenase E1 & E2 pyruvate dehydrogenase E1 component [EC:1.2.4.1] K00163 | |
Pyruvate Dehydrogenase E1 & E2 pyruvate dehydrogenase E2 component (dihydrolipoamide acetyltransferase) [EC:2.3.1.12] K00627 | |
Pyruvate Ferridoxin Oxidoreductase pyruvate ferredoxin oxidoreductase, alpha subunit [EC:1.2.7.1] K00169 | |
Pyruvate Ferridoxin Oxidoreductase pyruvate ferredoxin oxidoreductase, beta subunit [EC:1.2.7.1] K00170 | |
Pyruvate Ferridoxin Oxidoreductase pyruvate ferredoxin oxidoreductase, delta subunit [EC:1.2.7.1] K00171 | |
Pyruvate Ferridoxin Oxidoreductase pyruvate ferredoxin oxidoreductase, gamma subunit [EC:1.2.7.1] K00172 | |
Cellulose Degradation beta-glucosidase K05349 | |
Cellulose Degradation beta-glucosidase K05350 | |
Cellulose Degradation beta-glucosidase K01188 | |
Cellulose Degradation 6-phospho-beta-glucosidase K01222 | |
Cellulose Degradation 6-phospho-beta-glucosidase K01223 | |
Cellulose Degradation endoglucanase K01179 | |
Cellulose Degradation cellobiose phosphorylase K00702 | |
Cellobiose Transport cellobiose transport system substrate-binding protein K10240 | |
Cellobiose Transport cellobiose transport system permease protein K10241 | |
Cellobiose Transport cellobiose transport system permease protein K10242 | |
Cellobiose Transport cellobiose transport system ATP-binding protein K10243 | |
Hemi-cellulose Degradation mannan endo-1,4-beta-mannosidase [EC:3.2.1.78] K01218 | |
Hemi-cellulose Degradation xylose isomerase [EC:5.3.1.5] K01805 | |
Chitin Degradation putative chitinase K03791 | |
Chitin Degradation chitinase K01183 | |
Chitin Degradation chitin deacetylase [EC:3.5.1.41] K01452 | |
Sugar Utilization L-arabinose isomerase [EC:5.3.1.4] K01804 | |
Sugar Utilization xylose isomerase [EC:5.3.1.5] K01805 | |
Sugar Utilization xylulokinase [EC:2.7.1.17] K00854 | |
Sugar Utilization beta-galactosidase [EC:3.2.1.23] K01190 | |
Sugar Utilization beta-galactosidase [EC:3.2.1.23] K12308 | |
Sugar Utilization galactokinase [EC:2.7.1.6] K00849 | |
Sugar Utilization glucokinase [EC:2.7.1.2] K00845 | |
Sugar Utilization polyphosphate glucokinase [EC:2.7.1.63] K00886 | |
Sugar Utilization mannose-6-phosphate isomerase [EC:5.3.1.8] K02793 | |
Sugar Utilization fructokinase [EC:2.7.1.4] K00847 | |
Sugar Transporters lactose/L-arabinose transport system substrate-binding protein K10188 | |
Sugar Transporters lactose/L-arabinose transport system permease protein K10189 | |
Sugar Transporters lactose/L-arabinose transport system permease protein K10190 | |
Sugar Transporters putative multiple sugar transport system substrate-binding protein K10546 | |
Sugar Transporters putative multiple sugar transport system permease protein K10547 | |
Sugar Transporters putative multiple sugar transport system ATP-binding protein K10548 | |
Sugar Transporters multiple sugar transport system ATP-binding protein K02023 | |
Sugar Transporters multiple sugar transport system permease protein K02025 | |
Sugar Transporters multiple sugar transport system permease protein K02026 | |
Sugar Transporters multiple sugar transport system substrate-binding protein K02027 | |
Sugar Transporters D-xylose transport system substrate-binding protein K10543 | |
Sugar Transporters D-xylose transport system permease protein K10544 | |
Sugar Transporters D-xylose transport system ATP-binding protein [EC:3.6.3.17] K10545 | |
Sugar Transporters fructose transport system substrate-binding protein K10552 | |
Sugar Transporters fructose transport system permease protein K10553 | |
Sugar Transporters fructose transport system ATP-binding protein K10554 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment