Created on Tue Jul 12 17:18:19 2016 @author: dan """ import pandas as pd from capacity_usage import CAPACITY_USAGE import matplotlib.pyplot as plt import math import numpy as np from scipy.stats import pearsonr, spearmanr flux = pd.DataFrame.from_csv("../data/mmol_gCDW_h.csv") abundance = pd.DataFrame.from_csv("../data/g_gCDW.csv") cu = CAPACITY_USAGE(flux, abundance) def configure_plot(ax, x_label='', y_label='', fontsize=15): ax.tick_params(right=0, top=0, direction='out', labelsize=fontsize) ax.spines['top'].set_visible(False) ax.spines['right'].set_visible(False) ax.set_xlabel(ax.get_xlabel(), size=15) ax.set_ylabel(ax.get_ylabel(), size=15) ax.xaxis.tick_bottom() ax.yaxis.tick_left() ax.set_xlabel(x_label, size=fontsize*1.3) ax.set_ylabel(y_label, size=fontsize*1.3) ax.set_xscale('log') ax.set_yscale('log') def add_labels(x, y, labels, ax, fig, fontsize=10, hide_overlap=True):
import pandas as pd from capacity_usage import CAPACITY_USAGE import matplotlib.pyplot as plt from scipy.stats import pearsonr, spearmanr import seaborn as sns from cobra.manipulation.modify import revert_to_reversible from itertools import product flux = pd.DataFrame.from_csv("../data/mmol_gCDW_h.csv") copies_fL = pd.read_csv("../data/abundance[copies_fl].csv") copies_fL = copies_fL[['bnumber', 'GLC_BATCH_mu=0.58_S']] abundance = pd.DataFrame.from_csv("../data/g_gCDW.csv") cu = CAPACITY_USAGE(flux, abundance) uni_to_b = {row[48:54]:row[0:5].split(';')[0].strip() for row in open("../data/all_ecoli_genes.txt", 'r')} id_mapper = pd.DataFrame.from_dict(uni_to_b.items()) id_mapper.columns = ["uniprot", "bnumber"] TS = pd.read_csv("../data/thermoal_stability_ecoli.csv") df = TS.merge(id_mapper, on=["uniprot"]) #%% model = cu.model.copy() revert_to_reversible(model) def one2one_mapping(): l = [] for b in cu.model.genes: l+=(list(product([b.id], list(b.reactions)))) df = pd.DataFrame(l) df.columns = ['bnumber', 'reaction']
from scipy.stats import ranksums def despine(ax, fontsize=15): ax.tick_params(right=0, top=0, direction="out", labelsize=fontsize) ax.spines["top"].set_visible(False) ax.spines["right"].set_visible(False) ax.set_xlabel(ax.get_xlabel(), size=15) ax.set_ylabel(ax.get_ylabel(), size=15) ax.xaxis.tick_bottom() ax.yaxis.tick_left() flux = pd.DataFrame.from_csv("../data/mmol_gCDW_h.csv") abundance = pd.DataFrame.from_csv("../data/g_gCDW.csv") cu = CAPACITY_USAGE(flux, abundance, shared_reactions=False) biosyn_mean = [] ccm_mean = [] ranksum_pvalues = {} dists = [] for c in cu.cs: x = cu.CU[c] x.replace(np.inf, np.nan, inplace=True) x.dropna(inplace=True) subsystems = pd.Series(index=x.index, data=[cu.rxns[r].subsystem for r in x.index]) for k, v in cu.get_master_groups().iteritems(): subsystems.replace({i: k for i in v}, inplace=True) s = set(subsystems.values) l = []
""" Created on Mon Sep 26 16:21:32 2016 @author: dan """ from capacity_usage import CAPACITY_USAGE import pandas as pd from itertools import product import numpy as np gene_info = pd.DataFrame.from_csv('../data/ecoli_genome_info.csv', sep='\t') copies_fL = pd.DataFrame.from_csv('../data/copies_fL.csv') flux = pd.DataFrame.from_csv("../data/mmol_gCDW_h.csv") abundance = pd.DataFrame.from_csv("../data/g_gCDW.csv") cu = CAPACITY_USAGE(flux, abundance) x = pd.DataFrame({r:r.metabolites for r in cu.model.reactions}).T.stack() r2stoich = x.reset_index() r2stoich.columns = ['reaction', 'metabolite', 'coefficient'] #%% l = [] for r,v in cu.reactions_to_isozymes().iteritems(): l+=(list(product([r], v, cu.cs))) r2isozymes = pd.DataFrame(l) r2isozymes.columns = ['reaction', 'enzyme', 'condition'] #%% # include abudance of enzyme complexes - take the minimum abudance