def main():
db = database.SqliteDatabase('../res/gibbs.sqlite')
html_writer = HtmlWriter("../res/nist/report.html")
gc = GroupContribution(db)
gc.override_gc_with_measurements = True
gc.init()
grad = GradientAscent(gc)
nist = Nist(db, html_writer, gc.kegg())
nist.FromDatabase()
alberty = Alberty()
hatzi = Hatzi()
if True:
grad.load_nist_data(nist,
alberty,
skip_missing_reactions=False,
T_range=(298, 314))
grad.verify_results("Alberty", alberty, html_writer)
#grad.write_pseudoisomers("../res/nist/nist_dG0_f.csv")
#html_writer.write("<h2>Using Group Contribution (Hatzimanikatis' implementation)</h2>")
#html_writer.write("<h3>Correlation with the reduced NIST database (containing only compounds that appear in Alberty's list)</h3>")
#logging.info("calculate the correlation between Hatzimanikatis' predictions and the reduced NIST database")
#grad.verify_results("Hatzimanikatis_Reduced", hatzi, html_writer)
#grad.load_nist_data(nist, hatzi, skip_missing_reactions=True, T_range=(298, 314))
grad.verify_results("Hatzimanikatis", hatzi, html_writer)
#grad.load_nist_data(nist, gc, skip_missing_reactions=True, T_range=(298, 314))
grad.verify_results("Milo", gc, html_writer)
elif False:
# Run the gradient ascent algorithm, where the starting point is the same file used for training the GC algorithm
grad.load_dG0_data("../data/thermodynamics/dG0.csv")
# load the data for the anchors (i.e. compounds whose dG0 should not be changed - usually their value will be 0).
grad.anchors = grad.load_dG0_data(
"../data/thermodynamics/nist_anchors.csv")
grad.load_nist_data(nist, grad, skip_missing_reactions=True)
print "Training %d compounds using %d reactions: " % (len(
grad.cid2pmap_dict.keys()), len(grad.data))
grad.hill_climb(max_i=20000)
grad.save_energies(grad.gc.comm, "gradient_cid2prm")
grad.verify_results("gradient1")
elif False:
# Run the gradient ascent algorithm, where the starting point is Alberty's table from (Mathematica 2006)
grad.load_nist_data(nist, alberty, skip_missing_reactions=True)
print "Training %d compounds using %d reactions: " % (len(
grad.cid2pmap_dict.keys()), len(grad.data))
grad.cid2pmap_dict = alberty.cid2pmap_dict
grad.hill_climb(max_i=20000)
grad.save_energies(grad.gc.comm, "gradient_cid2prm")
grad.verify_results("gradient2")
elif False:
# Run the gradient ascent algorithm, where the starting point is Alberty's table from (Mathematica 2006)
# Use DETERMINISTIC gradient ascent
grad.load_nist_data(nist,
alberty,
skip_missing_reactions=True,
T_range=(24 + 273.15, 40 + 273.15))
print "Training %d compounds using %d reactions: " % (len(
grad.cid2pmap_dict.keys()), len(grad.data))
grad.cid2pmap_dict = alberty.cid2pmap_dict
grad.deterministic_hill_climb(max_i=200)
grad.save_energies(grad.gc.comm, "gradient_cid2prm")
grad.verify_results("gradient_deterministic")
elif False:
# Run the gradient ascent algorithm, where the starting point arbitrary (predict all of the NIST compounds)
grad = GradientAscent(gc)
grad.load_nist_data(nist, skip_missing_reactions=False)
print "Training %d compounds using %d reactions: " % (len(
grad.cid2pmap_dict.keys()), len(grad.data))
grad.hill_climb(max_i=20000)
grad.save_energies(grad.gc.comm, "gradient_cid2prm")
grad.verify_results("gradient3")
elif False: # Use Alberty's table from (Mathematica 2006) to calculate the dG0 of all possible reactions in KEGG
grad = GradientAscent(gc)
grad.cid2pmap_dict = alberty.cid2pmap_dict
(pH, I, T) = (7, 0, 300)
counter = 0
for rid in grad.kegg.get_all_rids():
sparse_reaction = grad.kegg.rid2sparse_reaction(rid)
try:
dG0 = grad.reaction_to_dG0(sparse_reaction, pH, I, T)
print "R%05d: dG0_r = %.2f [kJ/mol]" % (rid, dG0)
counter += 1
except MissingCompoundFormationEnergy as e:
#print "R%05d: missing formation energy of C%05d" % (rid, e.cid)
pass
print "Managed to calculate the dG0 of %d reactions" % counter
elif False:
util._mkdir("../res/nist/fig")
csv_writer = csv.writer(open("../res/nist/pseudoisomers.csv", "w"))
cid_set = set()
for row in nist.data:
sparce_reaction = row['sparse']
cid_set.update(sparce_reaction.keys())
html_writer.write("<table border=1>\n")
for cid in sorted(list(cid_set)):
html_writer.write(" <tr><td>C%05d</td><td>%s</td><td>" %
(cid, grad.kegg.cid2name(cid)))
try:
mol = grad.kegg.cid2mol(cid)
img_fname = '../res/nist/fig/C%05d.png' % cid
html_writer.embed_img(img_fname, "C%05d" % cid)
mol.draw(show=False, filename=img_fname)
except AssertionError as e:
html_writer.write("WARNING: cannot draw C%05d - %s" %
(cid, str(e)))
except KeggParseException as e:
html_writer.write("WARNING: cannot draw C%05d - %s" %
(cid, str(e)))
html_writer.write("</td><td>")
if (cid in alberty.cid2pmap_dict):
for (nH, z) in alberty.cid2pmap_dict[cid].keys():
html_writer.write("(nH=%d, z=%d)<br>" % (nH, z))
csv_writer.writerow((cid, nH, z))
else:
nH = grad.kegg.cid2num_hydrogens(cid)
z = grad.kegg.cid2charge(cid)
html_writer.write("unknown pseudoisomers<br>")
html_writer.write("(nH=%d, z=%d)" % (nH, z))
csv_writer.writerow((cid, nH, z))
html_writer.write("</td></tr>\n")
html_writer.write("</table>\n")
html_writer.close()
def main():
db = database.SqliteDatabase('../res/gibbs.sqlite')
html_writer = HtmlWriter("../res/nist/report.html")
gc = GroupContribution(db)
gc.override_gc_with_measurements = True
gc.init()
grad = GradientAscent(gc)
nist = Nist(db, html_writer, gc.kegg())
nist.FromDatabase()
alberty = Alberty()
hatzi = Hatzi()
if True:
grad.load_nist_data(nist, alberty, skip_missing_reactions=False, T_range=(298, 314))
grad.verify_results("Alberty", alberty, html_writer)
#grad.write_pseudoisomers("../res/nist/nist_dG0_f.csv")
#html_writer.write("<h2>Using Group Contribution (Hatzimanikatis' implementation)</h2>")
#html_writer.write("<h3>Correlation with the reduced NIST database (containing only compounds that appear in Alberty's list)</h3>")
#logging.info("calculate the correlation between Hatzimanikatis' predictions and the reduced NIST database")
#grad.verify_results("Hatzimanikatis_Reduced", hatzi, html_writer)
#grad.load_nist_data(nist, hatzi, skip_missing_reactions=True, T_range=(298, 314))
grad.verify_results("Hatzimanikatis", hatzi, html_writer)
#grad.load_nist_data(nist, gc, skip_missing_reactions=True, T_range=(298, 314))
grad.verify_results("Milo", gc, html_writer)
elif False:
# Run the gradient ascent algorithm, where the starting point is the same file used for training the GC algorithm
grad.load_dG0_data("../data/thermodynamics/dG0.csv")
# load the data for the anchors (i.e. compounds whose dG0 should not be changed - usually their value will be 0).
grad.anchors = grad.load_dG0_data("../data/thermodynamics/nist_anchors.csv")
grad.load_nist_data(nist, grad, skip_missing_reactions=True)
print "Training %d compounds using %d reactions: " % (len(grad.cid2pmap_dict.keys()), len(grad.data))
grad.hill_climb(max_i=20000)
grad.save_energies(grad.gc.comm, "gradient_cid2prm")
grad.verify_results("gradient1")
elif False:
# Run the gradient ascent algorithm, where the starting point is Alberty's table from (Mathematica 2006)
grad.load_nist_data(nist, alberty, skip_missing_reactions=True)
print "Training %d compounds using %d reactions: " % (len(grad.cid2pmap_dict.keys()), len(grad.data))
grad.cid2pmap_dict = alberty.cid2pmap_dict
grad.hill_climb(max_i=20000)
grad.save_energies(grad.gc.comm, "gradient_cid2prm")
grad.verify_results("gradient2")
elif False:
# Run the gradient ascent algorithm, where the starting point is Alberty's table from (Mathematica 2006)
# Use DETERMINISTIC gradient ascent
grad.load_nist_data(nist, alberty, skip_missing_reactions=True, T_range=(24 + 273.15, 40 + 273.15))
print "Training %d compounds using %d reactions: " % (len(grad.cid2pmap_dict.keys()), len(grad.data))
grad.cid2pmap_dict = alberty.cid2pmap_dict
grad.deterministic_hill_climb(max_i=200)
grad.save_energies(grad.gc.comm, "gradient_cid2prm")
grad.verify_results("gradient_deterministic")
elif False:
# Run the gradient ascent algorithm, where the starting point arbitrary (predict all of the NIST compounds)
grad = GradientAscent(gc)
grad.load_nist_data(nist, skip_missing_reactions=False)
print "Training %d compounds using %d reactions: " % (len(grad.cid2pmap_dict.keys()), len(grad.data))
grad.hill_climb(max_i=20000)
grad.save_energies(grad.gc.comm, "gradient_cid2prm")
grad.verify_results("gradient3")
elif False: # Use Alberty's table from (Mathematica 2006) to calculate the dG0 of all possible reactions in KEGG
grad = GradientAscent(gc)
grad.cid2pmap_dict = alberty.cid2pmap_dict
(pH, I, T) = (7, 0, 300)
counter = 0
for rid in grad.kegg.get_all_rids():
sparse_reaction = grad.kegg.rid2sparse_reaction(rid)
try:
dG0 = grad.reaction_to_dG0(sparse_reaction, pH, I, T)
print "R%05d: dG0_r = %.2f [kJ/mol]" % (rid, dG0)
counter += 1
except MissingCompoundFormationEnergy as e:
#print "R%05d: missing formation energy of C%05d" % (rid, e.cid)
pass
print "Managed to calculate the dG0 of %d reactions" % counter
elif False:
util._mkdir("../res/nist/fig")
csv_writer = csv.writer(open("../res/nist/pseudoisomers.csv", "w"))
cid_set = set()
for row in nist.data:
sparce_reaction = row['sparse']
cid_set.update(sparce_reaction.keys())
html_writer.write("<table border=1>\n")
for cid in sorted(list(cid_set)):
html_writer.write(" <tr><td>C%05d</td><td>%s</td><td>" % (cid, grad.kegg.cid2name(cid)))
try:
mol = grad.kegg.cid2mol(cid)
img_fname = '../res/nist/fig/C%05d.png' % cid
html_writer.embed_img(img_fname, "C%05d" % cid)
mol.draw(show=False, filename=img_fname)
except AssertionError as e:
html_writer.write("WARNING: cannot draw C%05d - %s" % (cid, str(e)))
except KeggParseException as e:
html_writer.write("WARNING: cannot draw C%05d - %s" % (cid, str(e)))
html_writer.write("</td><td>")
if (cid in alberty.cid2pmap_dict):
for (nH, z) in alberty.cid2pmap_dict[cid].keys():
html_writer.write("(nH=%d, z=%d)<br>" % (nH, z))
csv_writer.writerow((cid, nH, z))
else:
nH = grad.kegg.cid2num_hydrogens(cid)
z = grad.kegg.cid2charge(cid)
html_writer.write("unknown pseudoisomers<br>")
html_writer.write("(nH=%d, z=%d)" % (nH, z))
csv_writer.writerow((cid, nH, z))
html_writer.write("</td></tr>\n")
html_writer.write("</table>\n")
html_writer.close()
