Explore gapseq biochemistry • gapseq.biochem

Before you start

This package (gapseq.biochem) is a small tool to explore the biochemistry database behind gapseq. It is not the gapseq software itself. You can find all information on gapseq here:

Publication: Genome Biology
Documentation: ReadTheDocs
Source code: GitHub

Important note: The biochemistry database in gapseq is derived from ModelSEED (https://modelseed.org/). In order to give credits to the developers and curators of ModelSEED, we strongly encourage you to cite also the publication for the ModelSEED database when you are using gapseq.

Initialization

With the function initDB(), the database can be initialized from different sources and or different versions.

library(gapseq.biochem)
#> Loading required package: data.table
#> Loading required package: hms
#> Loading required package: CHNOSZ
#> CHNOSZ version 1.4.3 (2022-02-20)
#> reset: creating "thermo" object
#> OBIGT: loading default database with 1904 aqueous, 3445 total species

# Latest version from github
db <- initDB()

# Version at a specific commit
#db <- initDB("c1761254bf65f2789e012fd6ae2da3e45f2b6bae") 

# Database from a local gapseq installation
#db <- initDB("~/Software/gapseq/")

Exploring the biochemistry database

Summary of a specific reaction

summary(db, "rxn10132")
#> rxn10132 – Cyanate transport via proton symport 
#> 
#> Abbreviation:     CYNTt2 
#> gapseq status:    approved 
#> EC:       NA 
#> Charge balance:   0 
#> Mass balance:     Ok 
#> 
#> Equation:
#>  (1) H+[e] + (1) Cyanate[e] <=> (1) H+[c] + (1) Cyanate[c] 
#> 
#> Equation (IDs):
#>  (1) cpd00067[e] + (1) cpd01015[e] <=> (1) cpd00067[c] + (1) cpd01015[c] 
#> 
#> LHS:
#> cpd00067 (+1 * 1 = 1)    H
#> cpd01015 (-1 * 1 = -1)   CNO 
#> 
#> RHS:
#> cpd00067 (+1 * 1 = 1)    H
#> cpd01015 (-1 * 1 = -1)   CNO

Summary of a specific compound

Example: Summary for Lactose

summary(db, "cpd00208")
#> cpd00208 – Lactose 
#> 
#> Mol. formula:     C12H22O11 
#> Charge:   0 
#> Abbreviation:     lcts 
#> 
#> Reactions consuming cpd00208:
#> rxn00816: (1) H2O[c] + (1) Lactose[c] ––> (1) D-Glucose[c] + (1) Galactose[c]
#> rxn06677: (1) Lactose[c] + (1) Protein N-pros-phosphohistidine[c] ––> (1) Lactose-6-phosphate[c] + (1) Protein histidine[c]
#> rxn10865: (1) Phosphoenolpyruvate[c] + (1) Lactose[e] ––> (1) Pyruvate[c] + (1) Lactose-6-phosphate[c]
#> rxn11244: (1) Lactose[c] ––> (1) D-Glucose[c] + (1) Galactose[c]
#> rxn15230: (1) H2O[c] + (1) Lactose[c] ––> (1) Galactose[c] + (1) alpha-D-Glucose[c]
#> rxn15582: (1) H2O[c] + (1) Lactose[c] ––> (1) beta D-Galactose[c] + (1) alpha-D-Glucose[c]
#> rxn15588: (1) H2O[c] + (1) Lactose[c] ––> (1) beta-D-Glucose[c] + (1) beta D-Galactose[c]
#> rxn20022: (1) Lactose[c] + (1) Protein-3-phospho-L-histidines[c] ––> (1) Lactose-6-phosphate[c] + (1) Protein-Histidines[c]
#> rxn29965: (1) H2O[c] + (1) Lactose[c] ––> (1) D-Glucose[c] + (1) Galactose[c]
#> rxn30623: (1) Lactose[c] ––> (1) beta-D-Glucose[c] + (1) Galactose[c]
#> rxn31422: (1) H2O[c] + (1) Lactose[c] ––> (1) Galactose[c] + (1) alpha-D-Glucose[c]
#> rxn32517: (1) H2O[c] + (1) Lactose[c] ––> (1) beta D-Galactose[c] + (1) alpha-D-Glucose[c]
#> rxn38052: (1) H2O[c] + (1) Lactose[c] ––> (1) beta-D-Glucose[c] + (1) beta D-Galactose[c]
#> 
#> Reactions producing cpd00208:
#> rxn01228: (1) H2O[c] + (1) Lactose-6-phosphate[c] ––> (1) Phosphate[c] + (1) Lactose[c]
#> rxn90002: (1) 2-fucosyllactose[c] + (1) H2O[c] ––> (1) Lactose[c] + (1) L-Fucose[c]
#> 
#> Reactions consuming+producing cpd00208:
#> rxn00356: (1) D-Glucose[c] + (1) UDP-galactose[c] <=> (1) UDP[c] + (1) Lactose[c]
#> rxn01229: (1) FAD[c] + (1) H+[c] + (1) Lactose[c] <=> (1) FADH2[c] + (1) 3-Ketolactose[c]
#> rxn11290: (1) Lactose[c] <=> (1) beta-Lactose[c]
#> rxn14171: (1) Lactose[c] + (1) A[c] <=> (1) 3-Ketolactose[c] + (1) AH2[c]
#> rxn15570: (1) UDP-galactose[c] + (1) beta-D-Glucose[c] <=> (1) UDP[c] + (1) Lactose[c]
#> rxn15571: (1) UDP-galactose[c] + (1) alpha-D-Glucose[c] <=> (1) UDP[c] + (1) Lactose[c]
#> rxn20021: (1) Lactose[c] + (1) Acceptor[c] <=> (1) 3-Ketolactose[c] + (1) Donor-H2[c]
#> rxn26312: (1) Lactose[c] <=> (1) allolactose[c]
#> 
#> Transporters of cpd00208:
#> rxn05598: (1) H2O[c] + (1) ATP[c] + (1) Lactose[e] ––> (1) ADP[c] + (1) Phosphate[c] + (1) H+[c] + (1) Lactose[c]
#> rxn08779: (1) H+[e] + (1) Lactose[c] ––> (1) H+[c] + (1) Lactose[e]
#> rxn08780: (1) Lactose[c] <=> (1) Lactose[e]
#> rxn08781: (1) H+[e] + (1) Lactose[e] <=> (1) H+[c] + (1) Lactose[c]
#> rxn10169: (1) H+[e] + (1) Lactose[e] <=> (1) H+[c] + (1) Lactose[c]
#> rxn28585: (1) Lactose[e] <=> (1) Lactose[c]
#> rxn32685: (1) Lactose[c] <=> (1) Lactose[e]

Find reactions

There are different ways to search for specific reactions, e.g. via specific compound IDs (if they are known), via regular expressions/search terms for compound names and/or by EC-numbers. Everything can be done with a single function: findRxns(). Here are a few example cases:

Example: Find reactions with the compound cpd00211 (Butyrate)

findRxns(db, cpd = "cpd00211")
#> rxn00873: (1) ATP[c] + (1) CoA[c] + (1) Butyrate[c] ––> (1) Pyrophosphate[c] + (1) AMP[c] + (1) H+[c] + (1) Butyryl-CoA[c]
#> rxn00875: (1) Acetate[c] + (1) Butyryl-CoA[c] <=> (1) Acetyl-CoA[c] + (1) Butyrate[c]
#> rxn00994: (1) Butyryl-CoA[c] + (1) Acetoacetate[c] <=> (1) Butyrate[c] + (1) Acetoacetyl-CoA[c]
#> rxn01236: (1) ATP[c] + (1) Butyrate[c] <=> (1) ADP[c] + (1) Butanoylphosphate[c]
#> rxn01237: (1) NAD[c] + (1) Butyrate[c] <–– (1) NADH[c] + (1) H+[c] + (1) 2-Butenoate[c]
#> rxn01238: (1) H2O[c] + (1) 5'-Butyrylphosphoinosine[c] ––> (1) IMP[c] + (1) Butyrate[c] + (2) H+[c]
#> rxn02683: (1) H2O[c] + (1) Nonane-4,6-dione[c] ––> (1) H+[c] + (1) Butyrate[c] + (1) 2-Pentanone[c]
#> rxn02879: (1) H2O[c] + (1) Phorbol-12,13-dibutyrate[c] <=> (1) H+[c] + (1) Butyrate[c] + (1) Phorbol 13-butanoate[c]
#> rxn05683: (1) H+[e] + (1) Butyrate[e] <=> (1) H+[c] + (1) Butyrate[c]
#> rxn08111: (1) H2O[c] + (1) NAD[c] + (1) Butanal[c] ––> (1) NADH[c] + (1) Butyrate[c] + (2) H+[c]
#> rxn08183: (1) H+[e] + (1) Butyrate[e] <=> (1) H+[c] + (1) Butyrate[c]
#> rxn08184: (1) Butyrate[c] <=> (1) Butyrate[e]
#> rxn11378: (1) Acetyl-CoA[c] + (1) H+[c] + (1) Butyrate[c] <–– (1) Acetate[c] + (1) M_Butyrate_Coa[c]
#> rxn11382: (1) Butyrate[e] <=> (1) Butyrate[c]
#> rxn13427: (1) Acetyl-CoA[c] + (1) H+[c] + (1) Butyrate[c] <=> (1) Acetate[c] + (1) Butyrate-Coa[c]
#> rxn13713: (1) Butyryl-CoA[c] + (1) 4-Hydroxybutanoate[c] <=> (1) Butyrate[c] + (1) 4-Hydroxybutyryl-CoA[c]
#> rxn13813: (1) H2O[c] + (1) N-Butyryl-L-homoserine lactone[c] <=> (1) H+[c] + (1) Butyrate[c] + (1) homoserine lactone[c]
#> rxn20048: (1) H2O[c] + (1) Tributyrin[c] <=> (1) H+[c] + (1) Butyrate[c] + (1) 1,2-dibutyrin[c]
#> rxn23428: (1) H2O[c] + (1) (2Z,4Z)-2-hydroxy-6-oxonona-2,4-dienoic acid[c] ––> (1) H+[c] + (1) Butyrate[c] + (1) 2-keto-4-pentenoate[c]
#> rxn36389: (1) H2O[c] + (1) NADP[c] + (1) Butanal[c] <=> (1) NADPH[c] + (1) Butyrate[c] + (2) H+[c]
#> rxn36390: (1) H2O[c] + (1) NADP[c] + (1) (Z)-2-buten-1-ol[c] ––> (1) NADPH[c] + (1) Butyrate[c] + (2) H+[c]
#> rxn36391: (1) H2O[c] + (1) NAD[c] + (1) (Z)-2-buten-1-ol[c] ––> (1) NADH[c] + (1) Butyrate[c] + (2) H+[c]
#> rxn36392: (1) H2O[c] + (1) NADP[c] + (1) isobutanal[c] <=> (1) NADPH[c] + (1) Butyrate[c] + (2) H+[c]
#> rxn36393: (1) H2O[c] + (1) NAD[c] + (1) isobutanal[c] <=> (1) NADH[c] + (1) Butyrate[c] + (2) H+[c]
#> rxn36394: (1) H2O[c] + (1) NADP[c] + (1) (Z)-but-2-enal[c] ––> (1) NADPH[c] + (1) Butyrate[c]
#> rxn36395: (1) H2O[c] + (1) NAD[c] + (1) (Z)-but-2-enal[c] ––> (1) NADH[c] + (1) Butyrate[c]
#> rxn37573: (1) H2O[c] + (1) Tributyrin[c] <=> (1) H+[c] + (1) Butyrate[c] + (1) 1,2-dibutyrin[c]
#> rxn37646: (1) H2O[c] + (1) Tributyrin[c] <=> (1) H+[c] + (1) Butyrate[c] + (1) 1,2-dibutyrin[c]
#> rxn38354: (1) H2O[c] + (1) Tributyrin[c] <=> (1) H+[c] + (1) Butyrate[c] + (1) 1,2-dibutyrin[c]

Example: Find reactions with the both compound ids: cpd00100 (Glycerol) and cpd22614 (sulfoquinovose)

findRxns(db, cpd = c("cpd00100","cpd22614"))
#> rxn47991: (1) H2O[c] + (1) 1-(6-sulfo-alpha-D-quinovosyl)glycerol[c] ––> (1) Glycerol[c] + (1) sulfoquinovose[c]

Example: Find reactions with at least one of the compound ids: cpd22614 (sulfoquinovose) or cpd01337 (Romicil).

findRxns(db, cpd = c("cpd22614","cpd01337"), cpd.link = "OR")
#> rxn02682: (1) ATP[c] + (1) Romicil[c] ––> (1) ADP[c] + (1) H+[c] + (1) Oleandomycin 2'-O-phosphate[c]
#> rxn04318: (1) dTDP-D-desosamine[c] + (1) L-Oleandrosyl-oleandolide[c] <=> (1) dTDP[c] + (1) Romicil[c]
#> rxn18889: (1) H2O[c] + (1) ATP[c] + (1) Romicil[c] ––> (1) ADP[c] + (1) Phosphate[c] + (1) H+[c] + (1) Romicil[e]
#> rxn23249: (1) UDP-glucose[c] + (1) Romicil[c] <=> (1) UDP[c] + (1) glucosyl-oleandomycin[c]
#> rxn23250: (1) H2O[c] + (1) glucosyl-oleandomycin[c] ––> (1) beta-D-Glucose[c] + (1) Romicil[c]
#> rxn23251: (1) H2O[c] + (1) glucosyl-oleandomycin[c] ––> (1) beta-D-Glucose[c] + (1) Romicil[c]
#> rxn47991: (1) H2O[c] + (1) 1-(6-sulfo-alpha-D-quinovosyl)glycerol[c] ––> (1) Glycerol[c] + (1) sulfoquinovose[c]
#> rxn48462: (1) sulfoquinovose[c] <=> (1) 6-deoxy-6-sulfo-D-fructose[c]
#> rxn90101: (1) sulfoquinovose[e] + (1) H+[e] <=> (1) sulfoquinovose[c] + (1) H+[c]

Example: Find reactions for EC 4.2.1.22.

findRxns(db, ec = "4.2.1.22")
#> rxn00953: (1) L-Serine[c] + (1) Homocysteine[c] <=> (1) H2O[c] + (1) Cystathionine[c]
#> rxn03380: (1) L-Serine[c] + (1) Selenohomocysteine[c] <=> (1) H2O[c] + (1) Selenocystathionine[c]
#> rxn05909: (1) L-Serine[c] + (1) H+[c] + (1) H2S[c] <=> (1) H2O[c] + (1) L-Cysteine[c]
#> rxn15167: (1) L-Serine[c] + (1) Homocysteine[c] <=> (1) H2O[c] + (1) L-Cystathionine[c]
#> rxn32860: (1) L-Serine[c] + (1) Selenohomocysteine[c] <=> (1) H2O[c] + (1) Selenocystathionine[c]

Example: Find reactions, where the on participating metabolite contains the term “sulfoquinovose”

findRxns(db, grep.str = "sulfoquinovose")
#> rxn04027: (1) UDP-glucose[c] + (1) Sulfite[c] ––> (1) H2O[c] + (1) UDP-6-sulfoquinovose[c]
#> rxn07172: (1) UDP-6-sulfoquinovose[c] + (1) 1,2-Diacyl-sn-glycerol[c] <=> (1) UDP[c] + (1) SQDG[c]
#> rxn22637: (1) UDP-glucose[c] + (1) Sulfite[c] ––> (1) H2O[c] + (1) UDP-6-sulfoquinovose[c]
#> rxn22649: (1) UDP-6-sulfoquinovose[c] + (1) DIACYLGLYCEROL[c] <=> (1) UDP[c] + (1) SULFOQUINOVOSYLDIACYLGLYCEROL[c]
#> rxn22650: (1) UDP-6-sulfoquinovose[c] + (1) DIACYLGLYCEROL[c] <=> (1) UDP[c] + (1) SULFOQUINOVOSYLDIACYLGLYCEROL[c]
#> rxn29915: (1) UDP-6-sulfoquinovose[e] <=> (1) UDP-6-sulfoquinovose[c]
#> rxn30780: (1) UDP-glucose[c] + (1) Sulfite[c] <–– (1) UDP-6-sulfoquinovose[c]
#> rxn31311: (1) UDP-6-sulfoquinovose[c] + (1) 1,2-Diacyl-sn-glycerol[c] <=> (1) UDP[c] + (1) SQDG[c]
#> rxn33924: (2) d[c] + (1) H2O[c] + (1) Glycerol-3-phosphate[c] + (1) UDP-6-sulfoquinovose[c] ––> (1) Phosphate[c] + (1) Sulfoquinovosyldiacyglycerol[c] + (1) Uracil Diphosphate[c] + (2) CoA[c]
#> rxn35088: (1) UDP-6-sulfoquinovose[c] + (1) 1,2-Diacyl-sn-glycerol dihexadecanoyl[c] <–– (1) UDP[c] + (1) H+[c] + (1) Sulfoquinovosyldiacylglycerol (dihexadecanoyl, n-C16:0)[c]
#> rxn35089: (1) UDP-6-sulfoquinovose[c] + (1) 1,2-Diacyl-sn-glycerol (1-(11Z)-octadecenoyl,2-hexadecanoyl, 18:1(11Z)/16:0)[c] <–– (1) UDP[c] + (1) H+[c] + (1) Sulfoquinovosyldiacylglycerol (1-(11Z)-octadecenoyl,2-hexadecanoyl, 18:1(11Z)/16:0)[c]
#> rxn35090: (1) UDP-6-sulfoquinovose[c] + (1) 1,2-Diacyl-sn-glycerol (1-(9Z)-octadecenoyl,2-hexadecanoyl, 18:1(9Z)/16:0)[c] <–– (1) UDP[c] + (1) H+[c] + (1) Sulfoquinovosyldiacylglycerol (1-(9Z)-octadecenoyl,2-hexadecanoyl, 18:1(9Z)/16:0)[c]
#> rxn38784: (1) UDP-6-sulfoquinovose[c] <=> (1) UDP-6-sulfoquinovose[e]
#> rxn47991: (1) H2O[c] + (1) 1-(6-sulfo-alpha-D-quinovosyl)glycerol[c] ––> (1) Glycerol[c] + (1) sulfoquinovose[c]
#> rxn48462: (1) sulfoquinovose[c] <=> (1) 6-deoxy-6-sulfo-D-fructose[c]
#> rxn90101: (1) sulfoquinovose[e] + (1) H+[e] <=> (1) sulfoquinovose[c] + (1) H+[c]

Example: Find all reactions that include NADH (cpd00008) as co-factor and where at least one compound matches the term “L-Lactate” or “D-Lactate”:

findRxns(db, cpd = "cpd00004", grep.str = "(D|L)-Lactate")
#> rxn00499: (1) NAD[c] + (1) L-Lactate[c] <=> (1) NADH[c] + (1) Pyruvate[c] + (1) H+[c]
#> rxn00500: (1) NAD[c] + (1) D-Lactate[c] <=> (1) NADH[c] + (1) Pyruvate[c] + (1) H+[c]
#> rxn01053: (1) H2O[c] + (1) NAD[c] + (1) L-Lactaldehyde[c] ––> (1) NADH[c] + (1) L-Lactate[c] + (2) H+[c]
#> rxn01273: (1) H2O[c] + (1) NAD[c] + (1) D-Lactaldehyde[c] ––> (1) NADH[c] + (1) D-Lactate[c] + (2) H+[c]
#> rxn30087: (1) H2O[c] + (1) NAD[c] + (1) L-Lactaldehyde[c] ––> (1) NADH[c] + (1) L-Lactate[c] + (2) H+[c]
#> rxn30724: (1) NAD[c] + (1) L-Lactaldehyde[c] ––> (1) NADH[c] + (1) L-Lactate[c]
#> rxn33559: (1) H2O[c] + (1) NAD[c] + (1) D-Lactaldehyde[c] ––> (1) NADH[c] + (1) D-Lactate[c] + (2) H+[c]
#> rxn34235: (1) NAD[c] + (1) D-Lactate[c] <=> (1) NADH[c] + (1) Pyruvate[c] + (1) H+[c]
#> rxn34239: (1) NAD[c] + (1) L-Lactate[c] <=> (1) NADH[c] + (1) Pyruvate[c] + (1) H+[c]
#> rxn34240: (1) NAD[c] + (1) L-Lactate[c] <=> (1) NADH[c] + (1) Pyruvate[c] + (1) H+[c]
#> rxn36500: (1) H2O[c] + (1) NAD[c] + (1) D-Lactaldehyde[c] <=> (1) NADH[c] + (1) L-Lactate[c] + (2) H+[c]
#> rxn36645: (1) H2O[c] + (1) NAD[c] + (1) L-Lactaldehyde[c] <=> (1) NADH[c] + (1) D-Lactate[c] + (2) H+[c]
#> rxn36647: (1) H2O[c] + (1) NAD[c] + (1) 2-Oxopropanal[c] <=> (1) NADH[c] + (1) D-Lactate[c]
#> rxn36652: (1) H2O[c] + (1) NAD[c] + (1) 2-Oxopropanal[c] <=> (1) NADH[c] + (1) L-Lactate[c]
#> rxn38860: (1) H2O[c] + (1) NAD[c] + (1) 2-Oxopropanal[c] <=> (1) NADH[c] + (1) D-Lactate[c]
#> rxn38861: (1) H2O[c] + (1) NAD[c] + (1) 2-Oxopropanal[c] <=> (1) NADH[c] + (1) L-Lactate[c]
#> rxn90054: (2) Reducedferredoxin[c] + (2) NAD[c] + (1) L-Lactate[c] ––> (1) Pyruvate[c] + (2) Oxidizedferredoxin[c] + (2) NADH[c]
#> rxn90056: (2) Reducedferredoxin[c] + (2) NAD[c] + (1) D-Lactate[c] ––> (1) Pyruvate[c] + (2) Oxidizedferredoxin[c] + (2) NADH[c]