[UPDATE] omics

README.md

@@ -33,7 +33,7 @@ jupyter notebook
 
 ### Credits and License
 
-Vítor Pereira, CEB-UMINHO, 2021
+Vítor Pereira and Lucas Carvalho, CEB-UMINHO, 2022
 
 <a rel="license" href="http://creativecommons.org/licenses/by-sa/4.0/"><img alt="Creative Commons License" style="border-width:0" src="https://i.creativecommons.org/l/by-sa/4.0/88x31.png" /></a>
 

data/e_coli_core_trn.csv

-bNum,Gene,Rule
-b0008,b0008,TRUE
-b0080,FruR,NOT surplusFDP
-b0113,PdhR,NOT surplusPYR
-b0114,aceE, NOT PdhR OR Fis
-b0115,aceF, NOT PdhR OR Fis
-b0116,b0116,TRUE
-b0118,b0118,TRUE
-b0351,b0351,TRUE
-b0356,b0356,TRUE
-b0399,PhoB,PhoR
-b0400,PhoR,(NOT (pi_e > 0))
-b0451,b0451,TRUE
-b0474,b0474,TRUE
-b0485,b0485,TRUE
-b0720,b0720,TRUE
-b0721,sdhC, (NOT (ArcA OR Fnr)) OR Crp OR Fis
-b0722,sdhD, (NOT (ArcA OR Fnr)) OR Crp OR Fis
-b0723,sdhA, (NOT (ArcA OR Fnr)) OR Crp OR Fis
-b0724,sdhB, (NOT (ArcA OR Fnr)) OR Crp OR Fis
-b0726,b0726,TRUE
-b0727,b0727,TRUE
-b0728,b0728,TRUE
-b0729,b0729,TRUE
-b0733,cydA, (NOT Fnr) OR ArcA
-b0734,cydB, (NOT Fnr) OR ArcA
-b0755,b0755,TRUE
-b0767,b0767,TRUE
-b0809,b0809,TRUE
-b0810,b0810,TRUE
-b0811,b0811,TRUE
-b0875,b0875,TRUE
-b0902,pflA, ArcA OR (Fnr AND Crp)
-b0903,pflB, ArcA OR (Fnr AND Crp)
-b0904,focA, ArcA OR (Fnr AND Crp)
-b0978,b0978,TRUE
-b0979,b0979,TRUE
-b1101,ptsG, (NOT Mlc) OR (NOT FruR)
-b1136,b1137,TRUE
-b1187,FadR,(glc__D_e > 0) OR (NOT ((ac_e > 0)))
-b1241,adhE, (NOT (o2_e > 0)) OR (NOT ((o2_e > 0) AND FruR)) OR Fis
-b1276,b1276,TRUE
-b1297,b1297,TRUE
-b1334,Fnr,NOT (o2_e > 0)
-b1380,b1380,TRUE
-b1478,b1478,TRUE
-b1479,b1479,TRUE
-b1524,yneH, (NOT (glc__D_e > 0)) OR ((nh4_e > 0) AND (NOT Crp))
-b1594,Mlc,(NOT (glc__D_e > 0))
-b1602,b1602,TRUE
-b1603,b1603,TRUE
-b1611,fumC, NOT ArcA
-b1612,fumA, NOT (ArcA OR Fnr)
-b1621,b1622,TRUE
-b1676,pykF, NOT FruR
-b1702,pps, FruR
-b1723,b1724,TRUE
-b1761,gdhA,NOT (Nac OR (glu__L_e > 0))
-b1773,b1773,TRUE
-b1779,b1779,TRUE
-b1812,b1812,TRUE
-b1817,manX,CRPnoGLM OR (NOT Mlc)
-b1818,manY,CRPnoGLM OR (NOT Mlc)
-b1819,manZ,CRPnoGLM OR (NOT Mlc)
-b1849,b1849,TRUE
-b1852,b1852,TRUE
-b1854,b1854,TRUE
-b1988,Nac,NRI_low
-b2029,b2029,TRUE
-b2097,b2097,TRUE
-b2133,b2133,TRUE
-b2276,nuoN, (NOT (ArcA OR Fnr))
-b2277,nuoM, (NOT (ArcA OR Fnr))
-b2278,nuoL, (NOT (ArcA OR Fnr))
-b2279,nuoK, (NOT (ArcA OR Fnr))
-b2280,nuoJ, (NOT (ArcA OR Fnr))
-b2281,nuoI, (NOT (ArcA OR Fnr))
-b2282,nuoH, (NOT (ArcA OR Fnr))
-b2283,nuoG, (NOT (ArcA OR Fnr))
-b2284,nuoF, (NOT (ArcA OR Fnr))
-b2285,nuoE, (NOT (ArcA OR Fnr))
-b2286,nuoC, (NOT (ArcA OR Fnr))
-b2287,nuoB, (NOT (ArcA OR Fnr))
-b2288,nuoA, (NOT (ArcA OR Fnr))
-b2296,b2296,TRUE
-b2297,b2297,TRUE
-b2415,b2415,TRUE
-b2416,b2416,TRUE
-b2417,b2417,TRUE
-b2458,b2458,TRUE
-b2463,b2463,TRUE
-b2464,b2464,TRUE
-b2465,b2465,TRUE
-b2492,focB, ArcA OR (Fnr AND Crp)
-b2579,b2579,TRUE
-b2587,b2587,TRUE
-b2779,b2779,TRUE
-b2914,b2914,TRUE
-b2925,b2925,TRUE
-b2926,b2926,TRUE
-b2935,b2935,TRUE
-b2975,glcA, (NOT ArcA) AND GlcC
-b2976,glcB, (NOT ArcA) AND GlcC
-b2980,GlcC,(ac_e > 0)
-b2987,pitB, NOT PhoB
-b3114,tdcE, Crp OR Fnr
-b3115,tdcD, Crp OR Fnr
-b3212,gltB, (NOT (NRI_hi AND (glu__L_e > 0)))
-b3213,gltD, (NOT (NRI_hi AND (glu__L_e > 0)))
-b3236,mdh, NOT ArcA
-b3261,Fis,(Biomass_Ecoli_core > 0)
-b3357,Crp,CRPnoGLC
-b3386,b3386,TRUE
-b3403,b3403,TRUE
-b3493,b3493,TRUE
-b3528,dctA,CRPnoGLM AND (NOT ArcA) AND DcuR
-b3603,lldP, NOT ArcA
-b3612,b3612,TRUE
-b3731,b3731,TRUE
-b3732,b3732,TRUE
-b3733,b3733,TRUE
-b3734,b3734,TRUE
-b3735,b3735,TRUE
-b3736,b3736,TRUE
-b3737,b3737,TRUE
-b3738,b3738,TRUE
-b3739,b3739,TRUE
-b3868,GlnG,NOT (nh4_e > 0)
-b3870,glnA,Crp
-b3916,b3916,TRUE
-b3919,b3919,TRUE
-b3925,b3925,TRUE
-b3951,pflD, ArcA OR Fnr
-b3952,pflC, ArcA OR Fnr
-b3956,b3956,TRUE
-b3962,b3962,TRUE
-b4014,aceB, (NOT IclR) AND ((NOT ArcA) OR FruR)
-b4015,aceA, (NOT IclR) AND ((NOT ArcA) OR FruR)
-b4018,IclR,FadR
-b4025,b4025,TRUE
-b4077,b4077,TRUE
-b4090,b4090,TRUE
-b4122,fumB, Fnr OR Crp OR DcuR
-b4124,DcuR,DcuS
-b4125,DcuS,(succ_e > 0) OR (fum_e > 0) OR (mal__L_e > 0)
-b4151,frdD, Fnr OR DcuR
-b4152,frdC, Fnr OR DcuR
-b4153,frdB, Fnr OR DcuR
-b4154,frdA, Fnr OR DcuR
-b4232,b4232,TRUE
-b4301,b4301,TRUE
-b4395,b4395,TRUE
-b4401,ArcA,NOT (o2_e > 0)
-s0001,s0001,TRUE
-CRPnoGLC,CRPnoGLC,(NOT (glc__D_e > 0))
-CRPnoGLM,CRPnoGLM,NOT ((glc__D_e > 0) OR (mal__L_e > 0) OR (lac__D_e > 0))
-NRI_hi,NRI_hi,NRI_low
-NRI_low,NRI_low,GlnG
-surplusFDP,surplusFDP,((NOT (FBP > 0)) AND (NOT ((TKT2 > 0) OR (TALA > 0) OR (PGI > 0)))) OR (fru_e > 0)
-surplusPYR,surplusPYR,(NOT ((ME2 > 0) OR (ME1 > 0))) AND (NOT ((GLCpts > 0) OR (PYK > 0) OR (PFK > 0) OR (LDH_D > 0) OR (SUCCt2_2 > 0)))

ex3-succ-yeast.ipynb

 %% Cell type:markdown id: tags:
 
 # Exercice 3
 
 In this exercice we will try to increase the production of succinate in Yeast.
 
 %% Cell type:markdown id: tags:
 
 ## GECKO models
 
 We will begin by doing the necessary imports and load a GECKO yeast model.
 
 %% Cell type:code id: tags:
 
 ``` python
-from mewpy.model import GeckoModel
+from geckopy.gecko import GeckoModel
 from mewpy.simulation import get_simulator
 from mewpy.problems import GeckoOUProblem
 from mewpy.optimization import EA
 from mewpy.optimization.evaluation import BPCY,WYIELD, ModificationType
 ```
 
 %% Cell type:code id: tags:
 
 ``` python
 model = GeckoModel('single-pool')
 ```
 
 %% Cell type:markdown id: tags:
 
-Next we define the required identifier, the medium, and create a simulation instance:
+Next we define the required identifiers, the medium, and create a simulation instance:
 
 %% Cell type:code id: tags:
 
 ``` python
 BIOMASS = 'r_2111'
 GLC = 'r_1714_REV'
 O2 = 'r_1992'
 SUCC = 'r_2056'
 
 envcond = {GLC:(-10,10000),O2:(0,0)}
-simul = get_simulator(model,envcond= envcond)
+simul = get_simulator(model,envcond=envcond)
 ```
 
 %% Cell type:markdown id: tags:
 
 We can now idendify the essential proteins
 
 %% Cell type:code id: tags:
 
 ``` python
 simul.essential_proteins()
 ```
 
 %% Cell type:markdown id: tags:
 
-Similarly to the strain optimization task using metabolic model, with or without enzymatic constraint (sMOMENT), we can use GECKO model to find genetic modifications that favor the production of succinate.
+Similarly to strain optimization task using metabolic model, with or without enzymatic constraint (sMOMENT), we can use GECKO model to find genetic modifications that favor the production of succinate. However, instead of applying genetic modifications (deletions / up / down-regulations) by evaluating GPR rules, the modifications are imposed on the enzyme usage pseudo-reactions.
 
 %% Cell type:code id: tags:
 
 ``` python
 from mewpy.problems import GeckoKOProblem, GeckoOUProblem
 ```
 
 %% Cell type:markdown id: tags:
 
 ## Exercice
 
 Build and run a GECKO optimization problem for succinate.
 
 %% Cell type:code id: tags:
 
 ``` python
 ```
 
 %% Cell type:code id: tags:
 
 ``` python
 ```
 
 %% Cell type:markdown id: tags:
 
 ## OptRAM optimization problem
 
-OptRAM requires besides a metabolic model, the regulatory network and the identification of genes and transcription factores. The algorithm treat each differently.
+OptRAM requires besides a metabolic model, the regulatory network and the identification of genes and transcription factores. The algorithm treats each differently.
 
 %% Cell type:code id: tags:
 
 ``` python
 gene_file = 'data/mgene.csv'
-ft_file = 'data/TFnames.csv'
+tf_file = 'data/TFnames.csv'
 matrix_file = 'data/regnet.csv'
 model_file = 'data/yeast_7.6-optram.xml'
 ```
 
 %% Cell type:markdown id: tags:
 
 We may now load the files
 
 %% Cell type:code id: tags:
 
 ``` python
-from mewpy.regulation.optram import load_optram
-# adds the prefix 'G_' to genes. Only for REFRAMED models
-regnet = load_optram(gene_file, ft_file, matrix_file, gene_prefix='G_')
-# the general objective is to maximize the target
-from reframed.io.sbml import load_cbmodel
-model = load_cbmodel(model_file)
+from mewpy.problems import load_optram, OptRamProblem
+from cobra.io.sbml import read_sbml_model
+
+regnet = load_optram(gene_file, tf_file, matrix_file)
+model = read_sbml_model(model_file)
 model.objective= BIOMASS
 ```
 
 %% Cell type:markdown id: tags:
 
 OptRAM problems definition
 
 %% Cell type:code id: tags:
 
 ``` python
-from mewpy.regulation.optram import OptRamProblem
-
 obj =[ BPCY(BIOMASS, SUCC, method='lMOMA'),
        WYIELD(BIOMASS, SUCC)]
 
 # OptRAM problem
 problem = OptRamProblem(model, obj, regnet, envcond=envcond, candidate_max_size=10)
 ```
 
 %% Cell type:markdown id: tags:
 
 ## Exercice
 
 Run an optimization for the optRAM problem.
 
 %% Cell type:code id: tags:
 
 ``` python
 ```
 
 %% Cell type:code id: tags:
 
 ``` python
 ```

ex4-optorf.ipynb

-%% Cell type:markdown id: tags:
-
-# Exercice 4
-
-## OptORF
-
-This exercice illustrates how to use OptORF to optimize succinate production
-
-%% Cell type:code id: tags:
-
-``` python
-import os
-from mewpy.analysis import (FBA, pFBA, fva, single_reaction_deletion, single_gene_deletion, SRFBA, RFBA, ifva,
-                            isingle_reaction_deletion, isingle_gene_deletion, isingle_regulator_deletion)
-from mewpy.io import read_model, Engines, Reader
-from mewpy.optimization import EA
-from mewpy.optimization.evaluation import BPCY, WYIELD
-from mewpy.regulation import OptORFProblem
-from mewpy.simulation import get_simulator
-from mewpy.util.io import population_to_csv
-```
-
-%% Cell type:markdown id: tags:
-
-Create the regulatory-metabolic model by firstly loading the metabolic model and then the regulatory network.
-
-%% Cell type:code id: tags:
-
-``` python
-# E. coli core constraint-based model directory
-cbm_model_f = 'data/e_coli_core.xml'
-
-# E. coli core Transcriptional Regulatory Network directory
-reg_model_f = 'data/e_coli_core_trn.csv'
-
-# reader for the metabolic model
-metabolic_reader = Reader(Engines.MetabolicSBML, cbm_model_f)
-
-# reader for the regulatory model
-regulatory_reader = Reader(Engines.RegulatoryCSV,
-                           reg_model_f,
-                           sep=',',
-                           id_col=1,
-                           rule_col=2,
-                           aliases_cols=[0],
-                           header=0)
-
-# reading the integrated metabolic-regulatory model
-model = read_model(metabolic_reader, regulatory_reader)
-
-```
-
-%% Cell type:markdown id: tags:
-
-Identify the necessary reactions
-
-%% Cell type:code id: tags:
-
-``` python
-# Biomass reaction identifier. The model objective function is set to be the biomass reaction, as regular practice.
-_BIOMASS_ID = 'Biomass_Ecoli_core'
-model.objective = {_BIOMASS_ID: 1}
-
-# glucose-exchange reaction identifier. Glucose is the main carbon source for E. coli.
-# Thus, the glucose exchange reaction bounds are set to -10 and 100000.0
-_GLC = 'EX_glc__D_e'
-model.get(_GLC).bounds = (-10.0, 100000.0)
-
-# setting each metabolic gene state/coefficient to 1 (active state)
-for gene in model.yield_genes():
-    gene.coefficient.coefficients = (1,)
-
-# Succinate is a compound of interest that can be synthesized by E. coli.
-# In this case, it will be the target product for the optimization
-_SUC = 'EX_succ_e'
-```
-
-%% Cell type:markdown id: tags:
-
-Create the optimization problem and run the optimization.
-
-%% Cell type:code id: tags:
-
-``` python
-# The evaluators Biomass-Product Coupled Yield and Weighted Yield will be used as evaluation metrics
-# of each set of candidates
-evaluator_1 = BPCY(_BIOMASS_ID, _SUC)
-evaluator_2 = WYIELD(_BIOMASS_ID, _SUC)
-
-# A OptORFProblem problem is created.
-# The OptORF approach is based on gene and regulator deletion to identify optimization strategies.
-# This problem uses a RFBA-like flux analysis to simulate a model constraints derived
-# from the gene and regulator deletions
-problem = OptORFProblem(model, [evaluator_1, evaluator_2], candidate_max_size=6)
-
-# setting up the Evolutionary Algorithm runner with multiprocessing and maximum of 10 generations
-ea = EA(problem, max_generations=10, mp=True)
-final_pop = ea.run()
-```
-
-%% Cell type:code id: tags:
-
-``` python
-```

logs/ME modelSlackModel iJO1366_ETFL_v_0.12_431_enz_128_bins__20200605_072641.json_20210707_164836.log

-2021-07-07 16:48:36,497 - ME modelSlackModel iJO1366_ETFL_v_0.12_431_enz_128_bins__20200605_072641.json - INFO - # ETFL Model SlackModel iJO1366_ETFL_v_0.12_431_enz_128_bins__20200605_072641.json initialized
-2021-07-07 16:48:36,498 - ME modelSlackModel iJO1366_ETFL_v_0.12_431_enz_128_bins__20200605_072641.json - INFO - Empty model initialized

logs/ME modelSlackModel iJO1366_ETFL_v_0.12_431_enz_128_bins__20200605_072641.json_20210707_165330.log

-2021-07-07 16:53:30,100 - ME modelSlackModel iJO1366_ETFL_v_0.12_431_enz_128_bins__20200605_072641.json - INFO - # ETFL Model SlackModel iJO1366_ETFL_v_0.12_431_enz_128_bins__20200605_072641.json initialized
-2021-07-07 16:53:30,101 - ME modelSlackModel iJO1366_ETFL_v_0.12_431_enz_128_bins__20200605_072641.json - INFO - Empty model initialized