Lipase-catalyzed synthesis of dilauryl azelate ester: Process optimization by artificial neural networks and reusability study

Article abstract of DOI:10.1039/c5ra16623c

An application of artificial neural networks (ANNs) to predict the performance of a lipase-catalyzed synthesis for esterification of dilauryl azelate ester was carried out. The central composite rotatable design (CCRD) experimental data were utilized for

Full text of DOI:10.1039/c5ra16623c

RSC Advances
View Article Online
View Journal | View Issue
PAPER
Lipase-catalyzed synthesis of dilauryl azelate ester:
process optimization by artificial neural networks
and reusability study
Cite this: RSC Adv., 2015, 5, 94909
*
*
Nurshafira Khairudin, Mahiran Basri, Hamid Reza Fard Masoumi, Wan Sarah Samiun
and Shazwani Samson
An application of artificial neural networks (ANNs) to predict the performance of a lipase-catalyzed synthesis
for esterification of dilauryl azelate ester was carried out. The central composite rotatable design (CCRD)
experimental data were utilized for training and testing of the proposed ANN model. The model was
applied to predict various performance parameters of the enzymatic reaction conditions, namely
enzyme amount (0.05–0.45 g), reaction time (90–450 min), reaction temperature (40–64 ꢀC) and molar
ratio of substrates (AzA : LA, 1 : 3–1 : 9 mol). The incremental back propagation (IBP), batch back
propagation (BBP), quick propagation (QP), genetic algorithm (GA), and the Levenberg–Marguardt (LM)
algorithms were used in the network. It was found that the optimal algorithm and topology were the
incremental back propagation (IBP) and the configuration with 4 inputs, 14 hidden, and 1 output nodes,
respectively.
Received 18th August 2015
Accepted 29th October 2015
DOI: 10.1039/c5ra16623c
www.rsc.org/advances
investigated by Charnock and collaborators.6 Hsieh et al. also
introduced a co-drug of conjugated hydroquinone and aze-
Introduction
laic acid to enhance topical skin targeting and decrease
penetration through the skin. Their studies demonstrated
that esterication of azelaic acid by hydroquinone contains
two hydroxyl functionalities was allowed to formation an
ester co-drug.7
In this work, the synthesis of dilauryl azelate ester was
studied using immobilized lipase (Novozym 435) as biocatalyst
has not been reported. Therefore, the optimization of process
parameters was carried out based on the investigations relating
to the inuence of enzyme amount, reaction time, reaction
temperature, and substrates molar ratio by using articial
neural network. In fact, this works aims to locate the optimum
reaction conditions for lipase catalyzed synthesis of dilauryl
azelate ester through CCRD as an experimental design and ANN
as a statistical tool for optimization.
An articial neural network (ANN) inspired by biological
neural networks process input information using an inter-
connected group of articial neurons and a connectionist
approach to computation.8 This work is concerned with ANNs
that have proven to be a powerful tool successfully used for
several real world applications over the past few years.9–14
Articial neural networks have been used for representing
non-linear functional relationships between variables. The
ability of an ANN to learn and generalize the behavior of any
Azelaic acid is a naturally occurring saturated dicarboxylic acid
which, on pharmacological application, has been shown to be
effective in the treatment of comedonal acnes, and inamma-
tory (papulopustular, nodulocystic and nodular) acne, as well as
various cutaneous hyperpigmentary disorders.1 But its usage is
limited in cosmetics and pharmaceutical products because of
insolubility, high melting point and large dosage requirement.
In addition, due to its crystalline form which melts at high
temperature (103 ꢀC), incorporation of azelaic acid into product
formulation is difficult at standard conditions. However, effi-
cacy was only observed when amount $15% of azelaic acid was
incorporated.2,3 Different derivatives of azelaic acid have also
been proven to be an effective topical treatment for human
inammatory skin disorders.4
Tamarkin and Maccabim (2004) reported that modica-
tion of azelaic acid by attachment of different steroidal
hormones through covalent ester linkages and converting at
least, one of the carboxylic acid groups into ester group has
enhanced not only the technical property of azelaic acid, but
also the functional performance of the resulting modied
azelaic acid. Their studies showed that the modied azelaic
acid exhibited anti-acne, sebum regulatory and skin light-
ening properties on the treated skin at low dosage.5 The
antibacterial properties of some azelaic acid diesters were
complex and non-linear process makes it
a powerful
modeling tool.15 Solving and modeling the complex relation
between input and output variable can be simply performed
by an ANN model imitated by biological neuron processing.
Department of Chemistry, Faculty of Science, Universiti Putra Malaysia, 43400
Serdang, Selangor, Malaysia. E-mail: mahiran@upm.edu.my; nursharakhairudin@
yahoo.com
This journal is © The Royal Society of Chemistry 2015
RSC Adv., 2015, 5, 94909–94918 | 94909

View Article Online
RSC Advances
Paper
ANNs have been used to study a wide variety of chemical where Vcontrol and Vtest are volumes of NaOH solution required
problems.16
to neutralize the excess acid for control (without enzyme) and
test (with enzyme) experiments, respectively.
Methodology
Materials
The ANN description
Articial neural networks that contain input, hidden and
output layers are mathematic free functionalization of the
complicated practical process. The layers which consist of
several nodes, are connected by multilayer normal feed-
forward or feed-back connection formula.20 The hidden
layer could be more than one parallel layer however the single
hidden layer is universally suggested. The connection is that
the nodes of particular layer are connected to the nodes of the
next layer. The nodes are simple articial neurons which
simulate the behavior of biological neural networks. The
nodes of input layer are qualify by sending data via the
special weights to the nodes of hidden layer and then to the
output layer.20–23 The qualication is carried out by associ-
ated weights during learning process by well known learning
algorithms.
Novozym 435 (lipase B from Candida Antarctica) was obtained
from Novo Nordisk A/S (Denmark). Azelaic acid and lauryl
alcohol were purchased from Merck (Germany). n-Hexane ob-
tained from J.T.Baker (USA) was used as the organic solvent. All
other chemicals used in this study were of analytical reagent
grade.
Enzymatic esterication of azelaic acid and analysis of
samples
To optimize the reaction conditions, enzymatic reactions
were usually performed in screw-capped glass vials on
a shaker. In a typical reaction, a certain amount of azelaic
acid and proportional amount of lauryl alcohol were added
into 5 ml solvent (n-hexane) contained in screw-capped glass
vial. The enzyme amount was added to the mixture was
sealed and shaken at 150 rpm in a horizontal water bath
shaker.
The learning process
The enzymatic reaction was terminated by adding 5 ml of
ethanol–acetone (50 : 50, v/v). The catalyst was then separated
by ltration, and the residual free acid into the nal mixture
sample was measured by standard NaOH (0.1 N) titration. The
value of reacted acid was calculated from the amounts obtained
for the test (with enzyme) and control (without enzyme)
samples. The amount of ester formation was expressed as
equivalent to the acid conversion.17,18 The conversion
percentage was calculated from consumption of NaOH for test
and control. The conversion was calculated using (eqn (1)).19
The ester formation was conrmed by thin-layer chromatog-
raphy (TLC) using chloroform : dichloromethane (95 : 5 v/v)
solvent system. Further identication for ester formation was
carried out by gas chromatography/mass spectroscopy GC-MS
on a Shimadzu (model GC 17A; model MS QP5050A, Japan)
and FTIR (Perkin Elmer, model 1650, UK) instruments.
For purication of the product, aer termination of the
reaction, the enzyme was ltered and the solvent removed by
evaporator under reduced pressure. Product in the remaining
mixture were separated via silica gel (Kieselgel 60, Merck,
particle size 0.063–0.200 mm) column chromatography (15 cm
ꢁ 20 mm) using a chloroform/dichloromethane (95/5, v/v)
mixture as eluent. A sample made up of 1 : 1 (w/w) ratio of
silica gel and the free solvent reaction mixture was deposited at
the top of the column previously equilibrated with chloroform/
dichloromethane (95/5, v/v) mixture. Five millilitre fractions
were collected and tested using thin layer chromatography to
identify the product-rich portions. Such fractions were pooled
and the solvent evaporated by a rotary evaporator. The purity of
product was then checked with TLC and GC before FTIR
analysis.
In the learning process, the weights are calculated by the
weighted summation (eqn (2)) of received data from the
former layer and transfer to next layer.24 The number of
hidden nodes is obtained by trial and error training calcu-
lation which is examined from one to n nodes. In the process,
the output of the hidden nodes in turn, acts as input to nal
(output) layer's nodes which undergoes similar or different
transformation.
nh
X
S ¼
ðb ꢂWiIiÞ
(2)
i¼1
where S is summation, b is bias, Ii is the ith input to hidden
neuron and Wi is the weight associated with Ii. The bias shis
the space of the nonlinearity properties.
The universal learning algorithms are IBP, BBP, QP, GA and
LM while the multilayer is the nodes' connection type.25 The
usual transfer function is the logarithmic sigmoid for both
hidden and output layers that is bounded from (0–1).26 The
sigmoid bounded area is used to normalize the input and
output data that is provided by the soware scalling. The scaled
data are passed into the rst layer, propagated to hidden layer
and nally meet the output layer of the network. Each node in
hidden layer or in output layer rstly acts as a summing junc-
tion which modies the inputs from the previous layer using the
following equation:
i
X
yi ¼
xiwij þ bj
(3)
j¼1
where yi is the input of the network to j node in hidden layer, i is
number of nodes, xi are the output of previous layer while wij are
the weights of connection between the ith node and jth node.
The bias associates with node j that is presented by bj. The main
aim of the process is to nd the weights for minimizing the
Vcontrol ꢂVtest
Conversion% ¼
ꢁ 100
(1)
Vcontrol
94910 | RSC Adv., 2015, 5, 94909–94918
This journal is © The Royal Society of Chemistry 2015

View Article Online
Paper
RSC Advances
error of RMSE which is obtained from difference between incremental backpropagation is based on weights updating
network prediction and actual responses.
aer the utilization of each pattern of the learning set.
1
2
!
n
X
ꢀ
ꢁ
1
2
Enzyme reusability study
RMSE ¼
ypi ꢂ yai
(4)
n
i¼1
The reusability study of Novozym 435 was carried out in term of
percentage conversion for the synthesis of dilauryl azelate ester.
The esterication experiments were conducted for 8 cycles of 6
h that more than 45 h working reaction time under the optimal
conditions, as follows: enzyme amount (0.14 g), reaction time
(360 min), reaction temperature (46 ꢀC), and molar ratio
(1 : 4.1). At the end of each reaction, the enzyme was separated
from the product by ltration and rinsed with n-hexane for
removing the organic phase that surrounded enzyme particles.
where n is number of the points, ypi is the predicted values and
yai is the actual values.27 Therefore, the learning process with an
algorithm is continued until nding the minimum RMSE which
is called topology. To avoid random correlation due to the
random initialization of the weights, learning of a topology is
repeated several times. As a result, the topology with the lowest
RMSE is selected to compare with other nodes' topologies.
Therefore, the topologies for the n numbers of hidden layer for
the considered algorithms are obtained in same way. Finally the
topologies of the algorithms are compared to select the provi-
sional model by maximum R2 (eqn (5)), minimum RMSE and
absolute average deviation (AAD) (eqn (6)).
Results and discussion
Modeling process
n
The topologies of the algorithms. In this research, the
examined neural network includes four inputs, including
enzyme amount, reaction time, reaction temperature, and
molar ratio of substrates, while the conversion (%) of dilauryl
azelate ester was only the node in output layer. It should be
noted that the experimental data of central composite design
were divided into two set, 20 of the data sets were used as the
training set and the remaining 5 data set were used as the test
set (Table 1). The structure of the hidden layer was determined
by examining a series of topologies with varied node number
from 1 to 15 for each algorithm. The model learning was per-
formed for testing data set to determine minimum value of
RMSE as error function. The performance was 10 times
X
ꢀ
ꢁ
2
ypi ꢂ yai
i¼1
R 2 ¼ 1 ꢂ
(5)
n
X
2
ðyai ꢂ ymÞ
i¼1
!
ꢂ
ꢂ
ꢂ
n
ꢂ
X
ypi ꢂ yai
yai
1
AAD ¼
ꢁ 100
(6)
n
i¼1
where n is the number of points, ypi is the predicted value, yai is
the actual value, and ym is the average of actual values.28
Incremental back propagation algorithm
Gradient descent backpropagation algorithm: this algorithm is repeated for each node to avoid random correlation due to the
one of the most popular training algorithms in the domain of random initialization of the weight.34
neural networks. It works by measuring the output error,
The training was identically carried out for IBP, BBP, QP, GA
calculating the gradient of this error, and adjusting the ANN and LM algorithms to discover the optimized topology for each
weights (and biases) in the descending gradient direction. algorithm. Among the 10 time learning repetition data for each
Hence, this method is a gradient descent local search proce- node, the minimum value of RMSE was selected and plotted
dure.29 This algorithm includes different versions such as: (a) versus the nodes of the algorithms' hidden layer (Fig. 1). As
standard or incremental backpropagation (IBP): the network shown, one node of 15 topologies for each algorithm has pre-
weights are updated aer presenting each pattern from the sented the lowest RMSE which was selected as the best topology
learning data set, rather than once per iteration30 (b) batch for comparison. The selected topologies were 4-14-1, 4-5-1, 4-13-
backpropagation (BBP): the network weights update takes place 1, 4-13-1, and 4-10-1 for IBP, BBP, QP, GA and LM algorithms,
once per iteration, while all learning data pattern are processed respectively. As Fig. 1 shown, the topology of IBP-4-14-1 pre-
through the network31 (c) quick propagation (QP): QP is sented the lowest RMSE among the other topologies was
a heuristic modication of the backpropagation algorithm. It is selected as provisional model for producing dilauryl azelate
proved much faster than IBP for many problems. QP is also ester.
dened as: mixed learning heuristics without momentum,
learning rate optimized during training.32
The model selection. To select the nal model for dilauryl
azelate ester optimum conditions, the values of RMSE, R2 and
The back propagation algorithm of learning a multilayer AAD were relatively studied for the topologies of IBP-4-14-1,
perceptron neural network (MLP – MultiLayers Perceptron) was BBP-4-5-1, QP-4-13-1, GA-4-13-1 and LM-4-10-1. To calculate
described for the rst time in 1969 by Arthur E. Bryson.33 With the R2, the topologies prediction and actual values of the
the version created in 1986 by David E. Rumelhart, Geoffrey E. dilauryl azelate ester conversion% were plotted for testing data
Hinton and Ronald J. Williams, the back propagation algorithm set (Fig. 2) as well as the R2 calculation of training set was
has gained popularity and interest to neural network eld. carried out in similar way (Fig. 3). As the scatter plots showed,
Batch backpropagation is an optimization technique where the IBP-4-14-1 has presented the highest R2 for testing (0.965) and
updating of the weights is based on the cyclic use of the entire training (1.0) data sets. Moreover, the AAD of testing and
learning set. Unlike the batch back propagation, the training sets for the topologies was calculated by Table 2.
This journal is © The Royal Society of Chemistry 2015
RSC Adv., 2015, 5, 94909–94918 | 94911

View Article Online
RSC Advances
Paper
Table 1 The experimental design that consists of training and testing data sets, each row indicates an experiment while the columns present the
composition of the synthesis of dilauryl azelate ester
Conversion (%)
Enzyme amount
(w/w %)
Reaction time
(hour)
Reaction temperature
(ꢀC)
Molar ratio of substrates,
AzA : LA (mol)
Run No.
Actual value
Predicted value
Training set
1
2
3
4
5
6
7
8
0.25
0.25
0.25
0.25
0.05
0.45
0.25
0.25
0.25
0.15
0.15
0.35
0.35
0.35
0.35
0.35
0.15
0.35
0.35
0.15
450
90
52
52
40
64
52
52
52
52
52
58
58
46
46
46
58
58
46
46
58
58
6
6
6
6
6
6
3
9
96.74
80.80
85.71
92.52
93.20
93.17
85.24
79.70
86.61
87.83
93.51
95.40
90.83
80.62
95.22
89.78
84.14
78.76
90.70
84.98
96.73
80.81
85.72
92.52
93.20
93.17
85.24
79.70
86.61
87.83
93.51
95.40
90.84
80.62
95.22
89.78
84.14
78.75
90.70
84.98
270
270
270
270
270
270
270
180
360
360
360
180
360
180
180
180
360
180
9
6
10
11
12
13
14
15
16
17
18
19
20
4.5
4.5
4.5
7.5
4.5
4.5
4.5
4.5
7.5
7.5
7.5
Test set
1
2
3
4
5
0.20
0.15
0.30
0.15
0.15
180
360
300
360
360
50
58
52
46
46
6
7.5
5
4.5
7.5
84.23
86.73
91.19
95.38
90.13
82.53
87.27
90.22
95.05
90.22
input, hidden and output layers.35,36 The input layer with 4
nodes (enzyme amount, reaction time, reaction temperature
and molar ratio of substrates) is the distributor for the hidden
layer with 14 nodes which were determined by learning process.
The input data of hidden nodes are calculated by weighted
summation (eqn (2)).37 Then the output data of hidden layer are
transferred to output layer (conversion%) by using log-sigmoid
function (eqn (7)).38
1
f ðxÞ ¼
(7)
1 þ expðꢂxÞ
where f(x) is the hidden output neuron. As a result, IBP-4-14-1
was used to determine the optimum values of the input vari-
ables of the dilauryl azelate ester synthesis.
Fig. 1 The selected RMSE vs. node number of the dilauryl azelate ester
network's hidden layer for IBP, BBP, QP, GA and LM. The lowest RMSE
belong to node 14 (IBP), 5 (BBP), 13 (QP), 15 (GA), 10 (LM).
Description of the dilauryl azelate ester synthesis. In the
modeling process, the optimized topologies for different
learning algorithms were determined by training and testing
data set. The comparison were carried out to dene the best
relative topology with optimum R2, RMSE and AAD which
selected as provisional model for more evaluation. The
adequacy of the selected model (IBP-4-14-1) was evaluated by
testing and validation data sets. Table 3 shows four new trials
combinations of experimental factors which do not participate
in the training data set. The comparison between experimental
observed and predicted data shows excellent agreement for the
As observed, the lowest value of the AAD has also belonged to
IBP-4-14-1. As a result, IBP-4-14-1 was pioneer in minimum
RMSE and AAD as well as at maximum R2 among the topologies
for testing and training data sets.
The network of IBP-4-14-1. Fig. 4 shows the network of IBP-4-
14-1 as nal model for dilauryl azelate ester which consists of
94912 | RSC Adv., 2015, 5, 94909–94918
This journal is © The Royal Society of Chemistry 2015

View Article Online
Paper
RSC Advances
Fig. 2 Scatter plot of predicted conversion (%) value versus actual conversion (%) value by using five algorithms for testing set.
response (conversion%). As a result of the process, the network quite close to the predicted value (95.05%), implying that the
of IBP-4-14-1 was selected to navigate the dilauryl azelate ester empirical model derived from central composite rotatable
synthesis. The navigation has contained optimization of the design can be used to adequately describe the relationship
effective variables as well as the importance of them. Table 4 between the independent variables and the response.
shows the predicted optimum values of were enzyme amount,
Graphical optimization of the variables. The validated model
reaction time, reaction temperature, and molar ratio of (IBP-4-14-1) simulated the interaction of the effective variables
substrates, which experimentally performed to obtain actual (enzyme amount (g), reaction time (min), reaction temperature
conversion (95.38%). The ANN result conrmed the validity of (ꢀC) and molar ratio of substrates (mol/mol)) on the
the model, and the experimental value was determined to be conversion% of dilauryl azelate ester without further
This journal is © The Royal Society of Chemistry 2015
RSC Adv., 2015, 5, 94909–94918 | 94913

View Article Online
RSC Advances
Paper
Fig. 3 Scatter plot of predicted conversion (%) value versus actual conversion (%) value by using five algorithms for training data set.
Table 2 The performance results of the optimized topologies, IBP-4-14-1, BBP-4-5-1, QP-4-13-1, GA-4-15-1, LM-4-10-1 of the dilauryl azelate
ester synthesis
Training data
RMSE
Testing data
RMSE
Learning algorithm
Architecture
R2
AAD
R2
AAD
GA
BBP
QP
LM
IBP
4-15-1
4-5-1
4-13-1
4-10-1
4-14-1
0.01715
0.00297
0.00123
0.00055
0.00220
1.000
1.000
1.000
1.000
1.000
0.01294
0.00247
0.00033
0.00093
0.00163
1.10181
0.92118
0.85146
0.85462
0.68859
0.920
0.950
0.937
0.936
0.965
1.29923
1.20485
1.10360
1.10333
0.83528
94914 | RSC Adv., 2015, 5, 94909–94918
This journal is © The Royal Society of Chemistry 2015

View Article Online
Paper
RSC Advances
min), and their mutual interaction on dilauryl azelate synthesis
at enzyme amount of 0.14 g and reaction temperature of 46 ꢀC.
It was shown that the maximum conversion of dilauryl azelate
ester (95.38%) was obtained when the amount of substrates
molar ratio was reached to the ratio of 1 : 4.1 mol (AzA : LA) and
by increasing the reaction time higher than 360 min. Addi-
tionally, it was observed that at the ratios higher than 1 : 5 mol
(AzA : LA), the conversion percentage of dilauryl azelate ester
decreased. This may due to out of the critical molar ratio,
competing alcohol binding reduce formation of the acyl–
enzyme complex and thereby results in decrease of
alcoholysis.39
As shown in Fig. 5c, the effect of reaction temperature and
reaction time were interpreted in range of 40–64 ꢀC and 90–450
min, respectively with the enzyme amount xed at 0.14 g and
molar ratio substrates at 1 : 4.1 mol (AzA : LA). Fig. 5c shows
that the higher percentage conversion of dilauryl azelate ester
(95.38%) was obtained at optimal reaction temperature range
between 46–50 ꢀC and reaction time higher than 360 min. These
results were similar in those most reviewed papers, which is
Novozym 435 was optimally used at temperature of 40 ꢀC and 60
ꢀC. Higher reaction temperatures tended to induce enzyme
inactivation due to denaturation processes.39
Importance of effective variables. According to Fig. 6, all
selected operating parameters are strongly inuential on the
conversion (%) of dilauryl azelate ester. Thus, any of the vari-
ables studied in this work cannot be neglected for process
analysis. The results indicate that molar ratio of substrates with
a relative importance of 27.93% is the most inuential param-
eter on the synthesis of dilauryl azelate ester. The order of
relative importance of the input variables on the synthesis of
dilauryl azelate ester was as follows: molar ratio of substrates >
enzyme amount > reaction temperature > reaction time.
Enzyme reusability and operational stability. A catalyst by
denition should be recovered and reused. The efficiency of
Fig. 4 Schematic representation of a multilayer perceptron feedfor-
word network of ANN based on IBP consisting of four inputs, one
hidden layer with 14 nodes and one output.
requirement of function and equation knowledge. The simula-
tions are the effect of nonlinear relationship of two variables on
the conversion% of dilauryl azelate ester which graphically
presents in three dimensional plots (3D plots).
Fig. 5a shows the effect of enzyme amount and reaction time
on the percentage conversion of dilauryl azelate ester. Response
surface plot was generated with a reaction temperature xed at
46 ꢀC and molar ratio of substrate 1 : 4.1 mol (AzA : LA) for
obtaining the interaction of varying enzyme amount (0.05–0.45
g) and the reaction time (90–450 min). The result showed that
when increasing the reaction time from 90 to 450 min, the
conversion% of dilauryl azelate ester rapidly was increased from
82 to 96%. However, enzyme amount was not signicant affect
on the percentage of conversion at any given amounts from 0.05
to 0.45 g. High percentage conversion (95.38%) was achieved by
increasing the reaction time and reducing the amount of
enzyme, which is important from the economic viewpoint since
the cost of enzyme is expensive.
Fig. 5b represents the effect of varying molar ratio of
substrates (AzA : LA, 1 : 3–1 : 9 mol) and reaction time (90–450
Table 3 Validation set predicted by selected model IBP-4-14-1 for dilauryl azelate ester synthesis
Conversion (%)
Actual value
Enzyme amount
(w/w %)
Reaction time
(hour)
Reaction temperature
(ꢀC)
Molar ratio of substrates,
AzA : LA (mol)
Predicted
value
Run No.
1
2
3
4
0.15
0.35
0.20
0.16
180
180
360
250
46
58
52
55
7.5
7.5
6.5
5.5
83.91
87.9
90.99
87.17
81.67
86.61
91.55
88.13
Table 4 Optimum conditions derived by RSM and ANN for dilauryl azelate ester synthesis
Independent variables Conversion (%)
Enzyme amount Reaction time Reaction temperature Molar ratio of substrates, Actual Predicted value Predicted value RSE (%) RSE (%)
(g)
(min)
(ꢀC)
AzA : LA (mol)
value by ANN
by RSM
by ANN by RSM
0.14
360
46
1 : 4.1
95.38 95.05
96.23
0.35 0.88
This journal is © The Royal Society of Chemistry 2015
RSC Adv., 2015, 5, 94909–94918 | 94915

View Article Online
RSC Advances
Paper
Fig. 6 The relative importance of dilauryl azelate ester synthesis of
input variables consist of molar ratio of substrates, enzyme amount,
reaction temperature, and reaction time.
Fig. 7 Reusability of Novozym 435 within 48 h working reaction time.
All cycles were done in optimum conditions (enzyme amount: 0.14 g,
reaction time: 6 h, reaction temperature: 46 ꢀC, and substrates molar
ratio: 1 : 4.1 mol) scale.
a catalyst is determined by studying its reusability.40 The reus-
ability experiment of Novozym-435 was carried out in term of
percentage conversion for the synthesis of dilauryl azelate ester.
Fig. 7 shows that Novozym 435 retains high activity even aer 8
cycles of 6 h under optimal conditions, so that, during more
than 45 h of working reaction time, the result had a 4.75% drop
in percentage conversion. This may be due to the shear effect on
the immobilized enzyme particle cause by agitator in a reaction
system. Shear effect may destroy the immobilization system of
Novozym 435 because of increasing in the collision of enzyme
particle with the wall of the screw-capped glass vial and cause
the enzyme activity to decrease from one cycle to another in the
Fig. 5 (a) Response surface plot shows the effect of the enzyme
amount, reaction temperature and their interaction on the synthesis
of dilauryl azelate ester. Other variables are constant; reaction
temperature 46 ꢀC and molar ratio of substrate 1 : 4.1 mol (AzA : LA).
(b) Response surface plot shows the effect of the molar ratio of
substrate, reaction time and their interaction on the synthesis of
dilauryl azelate ester. Other variables are constant; enzyme amount
0.14 g and reaction temperature of 46 ꢀC. (c) Response surface plot
shows the effect of the reaction temperature, reaction time and their
interaction on the synthesis of dilauryl azelate ester. Other variables
are constant; enzyme amount 0.14 g and molar ratio substrates at
1 : 4.1 mol (AzA : LA).
94916 | RSC Adv., 2015, 5, 94909–94918
This journal is © The Royal Society of Chemistry 2015

View Article Online
Paper
RSC Advances
reusability study. Meanwhile, the mass loss of the enzyme in the 11 P. J. Lisboa and A. F. Taktak, Neural Network, 2006, 19, 408–
recycling process may also lead to decrease in reaction
percentage conversion of dilauryl azelate ester.41
415.
12 M. Egmont-Petersen, D. de Ridder and H. Handels, Pattern
Recogn., 2002, 35, 2279–2301.
¨
13 J. J. Lahnajarvi, M. I. Lehtokangas and J. P. Saarinen,
Conclusions
Neurocomputing, 2004, 56, 345–363.
14 M. W. Craven and J. W. Shavlik, Future Generat. Comput.
Syst., 1997, 13, 211–229.
The ANN-based design of experiment was used for the synthesis
of dilauryl azelate ester. The optimization of process parameters
was carried out based on the investigations relating to the
inuence of enzyme amount, reaction time, reaction tempera-
ture, and molar ratio of substrates by using articial neural
networks. To obtain the qualied network, different algorithms
such as IBP, BBP, QP, GA and LM were learned by using
training, and testing data sets. The results of the learning
program were obtained by ve best topologies; IBP-4-14-1, BBP-
4-5-1, QP-4-13-1, GA-4-13-1 and LM-4-10-1. The performance of
the topologies was optimized by RMSE, AAD and R2. The
topology (IBP-4-14-1) with the lowest RMSE, AAD and the
highest R2 was selected as provisional network of the synthesis
of dilauryl azelate ester for validation test. The results of the
validation conrmed high predictability of the model. The
validated model determined the optimum values and relative
importance of the effective variables. The importance of the
variables which include molar ratio of substrates, 27.93%,
enzyme amount, 26.33%, reaction temperature, 25.65% and
reaction time, 20.09% showed none of the variables were
neglectable in this work. In conclusion, ANN is an efficient
quantitative tool which is able to model the effective input
variables to predict the conversion% of dilauryl azelate ester
enzymatic reaction.42
¨
15 D. Bingol, M. Hercan, S. Elevli and E. Kılıç, Bioresour.
Technol., 2012, 112, 111–115.
16 F. Despagne and D. L. Massart, Analyst, 1998, 123, 157R–
178R.
17 N. Chaibakhsh, M. Abdul Rahman, S. Abd-Aziz, M. Basri,
A. Salleh and R. Rahman, J. Ind. Microbiol. Biotechnol.,
2009, 36, 1149–1155.
18 H. R. Fard Masoumi, M. Basri, A. Kassim, D. Kuang
Abdullah, Y. Abdollahi, S. S. Abd Gani and M. Rezaee, Sci.
World J., 2013, 2013, 1–9.
19 S. C. Lau, H. N. Lim, M. Basri, H. R. F. Masoumi,
A. A. Tajudin, N. M. Huang, A. Pandikumar, C. H. Chia
and Y. Andou, PLoS One, 2014, 9, 1–10.
20 A. Ghaffari, H. Abdollahi, M. Khoshayand, I. S. Bozchalooi,
A. Dadgar and M. Raee-Tehrani, Int. J. Pharm., 2006, 327,
126–138.
21 M. G. Moghaddam, F. B. H. Ahmad, M. Basri and
M. B. A. Rahman, Electron. J. Biotechnol., 2010, 13, 3–4.
22 S. Aber, A. Amani-Ghadim and V. Mirzajani, J. Hazard.
Mater., 2009, 171, 484–490.
23 G. D. Garson, AI Expet, 1991, 6, 46–51.
24 M. Khare and S. S. Nagendra, Articial neural networks in
vehicular pollution modelling, Springer, 2007.
25 D. Salari, N. Daneshvar, F. Aghazadeh and A. Khataee, J.
Hazard. Mater., 2005, 125, 205–210.
26 Y. Abdollahi, A. Zakaria, A. H. Abdullah, H. R. F. Masoumi,
H. Jahangirian, K. Shameli, M. Rezayi, S. Banerjee and
T. Abdollahi, Chem. Cent. J., 2012, 6, 88.
27 H. R. F. Masoumi, M. Basri, A. Kassim, D. K. Abdullah,
Y. Abdollahi and S. S. A. Gani, J. Surfactants Deterg., 2014,
17, 287–294.
28 Y. Abdollahi, N. A. Sairi, M. K. Aroua, H. R. F. Masoumi,
H. Jahangirian and Y. Alias, J. Ind. Eng. Chem., 2014, 25,
168–175.
Acknowledgements
The nancial assistance provided by Universiti Putra Malaysia
under the Research University Grant Scheme (RUGS), is grate-
fully acknowledged.
References
1 A. Fitton and K. L. Goa, Drugs, 1991, 41, 780–798.
2 G. Webster, J. Am. Acad. Dermatol., 2000, 43, S47–S50.
´
3 J.-F. Hermanns, L. Petit, C. Pierard-Franchimont, P. Paquet 29 D. Rumelhart, G. Hinton and R. Williams, Nature, 1986, 323,
´
and G. Pierard, Dermatology, 2002, 204, 281–286.
533–536.
4 M. Nazzaro-Porro, Dermatology in Five Continents, Springer, 30 A. P. Plumb, R. C. Rowe, P. York and M. Brown, Eur. J. Pharm.
Verlag Berlin Heidelberg, 1988.
Sci., 2005, 25, 395–405.
5 D. Tamarkin, US Pat., 20,040,191,196, 2004.
6 C. Charnock, B. Brudeli and J. Klaveness, Eur. J. Pharm. Sci.,
2004, 21, 589–596.
7 P.-W. Hsieh, S. A. Al-Suwayeh, C.-L. Fang, C.-F. Lin,
C.-C. Chen and J.-Y. Fang, Eur. J. Pharm. Biopharm., 2012,
81, 369–378.
8 S. Haykin, Neural Networks: A Comprehensive Foundation,
Mac millian, New York, 1994.
9 M. Lam, Decis. Support Syst., 2004, 37, 567–581.
31 M. T. Hagan, H. B. Demuth and M. H. Beale, Neural network
design, Pws Boston, 1996.
32 A. Ghaffari, H. Abdollahi, M. R. Khoshayand, I. Soltani
Bozchalooi, A. Dadgara and M. Raee-Tehrani, Int. J.
Pharm., 2006, 327, 126–138.
33 A. E. Bryson, Y.-C. Ho and G. M. Siouris, IEEE Transactions on
Systems, Man, and Cybernetics, 1979, 9, 366–367.
34 M. Kasiri, H. Aleboyeh and A. Aleboyeh, Environ. Sci.
Technol., 2008, 42, 7970–7975.
10 R. Ghazali, A. Jaafar Hussain, N. Mohd Nawi and 35 W.-H. Ho, K.-T. Lee, H.-Y. Chen, T.-W. Ho and H.-C. Chiu,
B. Mohamad, Neurocomputing, 2009, 72, 2359–2367.
PLoS One, 2012, 7, 1–9.
This journal is © The Royal Society of Chemistry 2015
RSC Adv., 2015, 5, 94909–94918 | 94917

View Article Online
RSC Advances
Paper
36 H.-Y. Shi, K.-T. Lee, H.-H. Lee, W.-H. Ho, D.-P. Sun, 40 S. Karmee, Energy Sources, Part A, 2015, 37, 536–542.
J.-J. Wang and C.-C. Chiu, PLoS One, 2012, 7, 1–6.
37 J. Zhang, A. Morris, E. Martin and C. Kiparissides, Chem.
Eng. J., 1998, 69, 135–143.
41 H. R. F. Masoumi, M. Basri, A. Kassim, D. K. Abdullah,
Y. Abdollahi, S. S. A. Gani and M. Rezaee, J. Ind. Eng.
Chem., 2014, 20, 1973–1976.
38 L. Aijun, L. Hejun, L. Kezhi and G. Zhengbing, Acta Mater., 42 Y. Abdollahi, A. Zakaria and N. A. Sairi, Clean: Soil, Air,
2004, 52, 299–305.
Water, 2014, 42, 1292–1297.
39 M. B. A. Rahman, N. Chaibakhsh, M. Basri,
R. N. Z. R. A. Rahman, A. B. Salleh and S. M. Radzi, J.
Chem. Technol. Biotechnol., 2008, 83, 1534–1540.
94918 | RSC Adv., 2015, 5, 94909–94918
This journal is © The Royal Society of Chemistry 2015