iRSpot-PseDNC: identify recombination spots with
pseudo dinucleotide composition
Wei Chen1,2,*, Peng-Mian Feng3, Hao Lin4,* and Kuo-Chen Chou2,*
1Department of Physics, School of Sciences, Center for Genomics and Computational Biology, Hebei United
University, Tangshan, China,2Bioinformatics and Computer-Aided Drug Discovery, Gordon Life Science
Institute, San Diego, CA, USA,3School of Public Health, Hebei United University, Tangshan 063000, China and
4Key Laboratory for Neuro-Information of Ministry of Education, Center of Bioinformatics, School of Life
Science and Technology, University of Electronic Science and Technology of China, Chengdu, China
Received October 9, 2012; Revised November 27, 2012; Accepted December 12, 2012
Meiotic recombination is an important biological
process. As a main driving force of evolution, re-
combination provides natural new combinations of
genetic variations. Rather than randomly occurring
across a genome, meiotic recombination takes
place in some genomic regions (the so-called
‘hotspots’) with higher frequencies, and in the
other regions (the so-called ‘coldspots’) with lower
insights for in-depth studying of the mechanism of
recombination and the genome evolution process
as well. So far, the recombination regions have
been mainly determined by experiments, which are
both expensive and time-consuming. With the ava-
lanche of genome sequences generated in the post-
genomic age, it is highly desired to develop
automated methods for rapidly and effectively iden-
tifying the recombination regions. In this study, a
predictor, called ‘iRSpot-PseDNC’, was developed
for identifying the recombination hotspots and
coldspots. In the new predictor, the samples of
DNA sequences are formulated by a novel feature
vector, the so-called ‘pseudo dinucleotide compos-
ition’ (PseDNC), into which six local DNA structural
properties, i.e. three angular parameters (twist, tilt
and roll) and three translational parameters (shift,
slide and rise), are incorporated. It was observed
by the rigorous jackknife test that the overall
success rate achieved by iRSpot-PseDNC was
>82% in identifyingrecombination
Saccharomyces cerevisiae, indicating the new pre-
dictor is promising or at least may become a com-
plementary tool to the existing methods in this area.
Although the benchmark data set used to train and
test the current method was from S. cerevisiae, the
basic approaches can also be extended to deal with
all the other genomes. Particularly, it has not
escaped our notice that the PseDNC approach can
be also used to study many other DNA-related
problems. As a user-friendly web-server, iRSpot-
PseDNC is freely accessible at http://lin.uestc.edu.
Genetic recombination describes the generation of new
combinations of alleles that occurs at each generation in
diploid organisms. It is an important biological process
and results from a physical exchange of chromosomal
material (1). As a main driving force of evolution, recom-
bination provides new combinations of genetic variations
and accelerates the evolution of sexual reproductive or-
ganisms. A schematic illustration to show the meiotic re-
combination pathways is given in Figure 1.
As recombination is crucial to genome evolution, iden-
tification and characterization of recombination spots are
substantially important. In the past decades, several global
mapping studies have been performed to map double-
strand breaks sites on chromosomes in yeast to determine
the distribution pattern of recombination regions across
genome (3–5). They found that meiotic recombination
events generally concentrate in 1 ? 2:5 kilobase regions
and does not occur randomly across the genome.
Regions that exhibit elevated rates of recombination
*To whom correspondence should be addressed. Tel: +86 315 3725715; Fax: +86 315 3725715; Email: firstname.lastname@example.org;
Correspondence may also be addressed to Hao Lin. Tel: +86 28 8320 8232; Fax: +86 28 8320 8238; Email: email@example.com
Correspondence may also be addressed to Kuo-Chen Chou. Tel: +1 858 380 4623; Fax: +1 858 380 4623; Email: firstname.lastname@example.org
The authors wish it to be known that, in their opinion, the first two authors should be regarded as joint First Authors.
Published online 8 January 2013 Nucleic Acids Research, 2013, Vol. 41, No. 6e68
? The Author(s) 2013. Published by Oxford University Press.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/
by-nc/3.0/), which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
relative to a neutral expectation are called recombination
hotspots, whereas those with low rates of recombination
are recombination coldspots. Additionally, they also
found that recombination regions do not share a consen-
sus sequence. With the rapid increasing number of
sequenced genomes, it is highly desired to develop
reliable automated methods for timely identifying the re-
Although considerable progress has been made in this
regard, the computational predictive accuracy of recom-
bination spots still needs further improvements. The
spots prediction was based on the nucleotide sequence
contents (6), in which little sequence-order effect was
taken into account. To improve the prediction quality, it
is necessary to take into account this kind of effect.
However, the number of possible patterns for DNA se-
quences is extremely large, and their lengths vary widely,
making it difficult to incorporate the sequence-order in-
formation into a statistical predictor. Facing such a diffi-
culty, how can we take into account the sequence-order
effect to improve the prediction quality? If it is not feasible
to count all the sequence-order information, can we find
an approximate way to partially take into account it?
Similar problems were also encountered in computational
proteomics. To cope with this kind of problems, the
concept of pseudo amino acid composition (PseAAC)
was proposed by Chou (7). Since then, the concept of
PseAAC has penetrated into almost all the fields of com-
putational proteomics, such
submitochondrial localization (8), predicting protein
structural class (9), predicting DNA-binding proteins
(10), identifying bacterial virulent proteins (11), predicting
metalloproteinase family (12), predicting protein folding
rate (13), predicting GABA(A) receptor proteins (14), pre-
dicting protein supersecondary structure (15), predicting
cyclin proteins (16), classifying amino acids (17), predict-
ing enzyme family class (18), identifying risk type of
proteins (20), identifying G protein-coupled receptors
and their types (21) and discriminating outer membrane
proteins (22), among many others [see a long list of refer-
ences cited in a review (23)]. Because of its wide and
increasing usage, in 2012, a powerful software called
PseAAC-Builder (http://www.pseb.sf.net) (24) was estab-
lished for generating various special modes of PseAAC, in
addition to the earlier web-server PseAAC (http://www.
csbio.sjtu.edu.cn/bioinf/PseAAC) (25) built in 2008.
Encouraged by the successes of introducing the
PseAAC approach (7,26) into computational proteomics,
the present study was initiated in an attempt to propose a
novel feature vector, called ‘pseudo dinucleotide compos-
ition’ (PseDNC), to represent DNA sequence samples by
incorporating more sequence-order effects so as to
improve the quality of predicting the recombination spots.
As summarized in a review (23) and demonstrated by a
series of recent publications [see, e.g. (27–29)], to establish
a really useful statistical predictor for a biological system,
we need to consider the following procedures: (i) construct
or select a valid benchmark data set to train and test the
Figure 1. A schematic drawing to show the meiotic recombination pathways in a DNA system. Recombination is initiated by a double-strand break
(DSB) catalysed by the Spo11 protein (green ball), a relative of archaeal topoisomerase VI. After DSBs are formed, Spo11 is removed from the DNA
molecule (blue helix) and the single-stranded 30ends are formed. These tails undergo strand invasion of intact homologous duplexes (red helix),
ultimately yielding mature recombinant products. The repair of meiotic DSB can result in either reciprocal exchange of the chromosome arms
flanking the break (a crossover) as shown in the left lower panel, or no exchange of flanking arms (a non-crossover or parental configuration) as
shown in the right lower panel. Adapted from (2).
e68Nucleic Acids Research, 2013,Vol. 41,No. 6PAGE 2 OF 9
predictor; (ii) formulate the biological samples with an
effective mathematical expression that can truly reflect
their intrinsic correlation with the target to be predicted;
(iii) introduce or develop a powerful algorithm (or engine)
to operate the prediction; (iv) properly perform cross-
validation tests to objectively evaluate the anticipated
accuracy of the predictor; and (v) establish a user-friendly
web-server for the predictor that is accessible to the public.
Below, let us elaborate how to deal with these procedures
one by one.
MATERIALS AND METHODS
Benchmark data set
The benchmark data set S for the recombination hotspots
and coldspots was taken from Liu et al. (6). It contains
490 recombination hotspots and 591 recombination
coldspots, as can be formulated by
S ¼ S+[ S?
where [ represents the symbol for ‘union’ in the set
theory; the subset
hotspots only, whereas S?
only. For the convenience of readers, the 490 sequences
in S+and 591 sequences in S?
Supplementary Information S1.
are given in the
Suppose a DNA sequence D with L nucleic acid residues;
D ¼ R1R2R3R4R5R6R7...RL
where R1 represents the nucleic acid residue at the
sequence position 1, R2 the nucleic acid residue at
position 2 and so forth. If the feature vector of the
DNA sequence is formulated by its nucleic acid compos-
ition (NAC), we have
where fðAÞ, fðCÞ, fðGÞ, and fðTÞ are the normalized occur-
rence frequencies of adenine (A), cytosine (C), guanine (G)
and thymine (T), respectively, in the DNA sequence; the
symbol T is the transpose operator. As we can see from
Equation 3, all the sequence-order information is missed if
using NAC to represent a DNA sequence. If using the
DNC to represent the DNA sequence, instead of the
four components as shown in Equation 3, the correspond-
ing feature vector will contain 4 ? 4 ¼ 16 components, as
where f1¼ fðAAÞ is the normalized occurrence frequency
of AA in the DNA sequence; f2¼ fðACÞ, that of AC;
f3¼ fðAGÞ, that of AG and so forth. Although the most
contiguous local sequence-order information is included in
D ¼ fðAÞ
D ¼ fðAAÞ
Equation 4, none of the global sequence-order informa-
tion is reflected by the formulation. DNC is the most
simple pseudo NAC, or PseNAC, according to the termin-
ology similar to that used in (7).
To incorporate the global sequence-order information
into the feature vector for the DNA sequence, let us
consider the following approach. As shown in Equation
2, the first dinucleotide in the DNA sequence is R1R2, the
second dinucleotide is R2R3and so forth; the last one is
RL-1RL. Thus, by following the similar procedures as
described in (7) to reflect the global sequence-order infor-
order-correlated factors, for the DNA sequence of
Equation 2, we also have the corresponding factors as
where ?1 is called the first-tier correlation factor that
reflects the sequence-order correlation between all the
most contiguous dinucleotide along a DNA sequence
between all the second most contiguous dinucleotide
(Figure 2b); ?3, the third-tier correlation factor between
all the third most contiguous dinucleotide (Figure 2c) and
In Equation 5, the parameter ? is an integer, represent-
ing the highest counted rank (or tier) of the correlation
along a DNA sequence, and the correlation function is
ð? < LÞð5Þ
ðÞ ? PuRjRj+1
where ? is the number of local DNA structural properties
considered that is equal to 6 in the current study as will be
explained later in the text; PuðRiRi+1Þ, the numerical value
of the u-th ðu ¼ 1,2,???,?Þ DNA local property for the
dinucleotide RiRi+1 at position i and PuðRjRj+1Þ, the
corresponding value for the dinucleotide RjRj+1 at
DNA local structural properties
Multiple lines of evidences have indicated that some local
DNA structural properties, i.e. angular parameters (twist,
tilt and roll) and translational parameters (shift, slide and
rise), have important roles in biological processes, such as
protein–DNA interactions, formation of chromosomes
and higher-order organization of the genetic material
(30–32). Accordingly, these six structural properties
PAGE 3 OF 9Nucleic AcidsResearch, 2013, Vol.41,No. 6e68
might have impact on DNA binding of regulatory
proteins, either directly by hampering or favoring
complex formation or indirectly through the modulation
of the chromatin structures and hence the DNA
accessibility (33). Listed in Table 1 are their original
numerical values derived from (32) for twist P1ðRiRi+1Þ,
tilt P2ðRiRi+1Þ, roll P3ðRiRi+1Þ, shift P4ðRiRi+1Þ, slide
P5ðRiRi+1Þ, and rise P6ðRiRi+1Þ, respectively, where
RiRi+1represents the 16 possible dinucleotides AA, AC,
AG, AT,..., TT. It was these six DNA local physical
structural properties that were to be used as correlation
functions to derive the PseDNC for the current study.
Meanwhile, it is also self-evident why ? ¼ 6 in Equation
6 for the current case.
Before substituting into Equation 6, the original values
as listed in Table 1 for PuðRiRi+1Þ ðu ¼ 1,2,???,6Þ, they
were all subjected to a standard conversion (26), as
described by the following equation
PuðRiRi+1Þ ¼PuðRiRi+1Þ? < Pu>
where the symbol < > means taking the average of the
quantity therein for 16 different dinucleotides (cf.
Equation 4), and SD means the corresponding standard
deviation. The converted values obtained by Equation 7
will have a zero mean value for the 16 different
through the same conversion procedure again. Listed in
Table 2 are the values of PuðRiRi+1Þ ðu ¼ 1,2,???,6Þ
obtained via the standard conversion of Equation 7
from those of Table 1.
Now we can see from Figure 2 that the sequence-order
effect of a DNA sequence can be, to some extent, reflected
through a set of sequence-correlation factors ?1?2, ?3, ???,
??, as clearly defined by Equations 5 and 6. Similar to the
procedure as described in (7) for converting the amino
acid composition to the PseACC, let us augment the
DNC of Equation 4 to the PseDNC as given later in the
where fk ðk ¼ 1,2,???,16Þ are the same as those in
Equation 4, ?jðj ¼ 1,2,???,?Þ are given by Equation 5, ?
is the number of the total counted ranks (or tiers) of the
correlations along a DNA sequence and w is the weight
factor. The concrete values for ? and w will be discussed
further. Thus, instead of a 16-D (dimensional) vector (cf.
Equation 4), the DNA sequence is now formulated by a
ð16+?Þ?D vector as shown in Equation 8. It is through the
additional ? correlation factors (Figure 2) that not only
incorporated but the DNA sequences with extreme
difference in length can also be converted into a set of
feature vectors with a same dimension. The latter is an
important pre-requisite for formulating the statistical
samples because many powerful classification engines,
such as Covariant Discriminant (34,35), Support Vector
Machine (SVM) (36) and K-Nearest Neighbor (37–39)
algorithms, require the input to be a set of digital
vectors with a fixed number of components.
D ¼ d1
ð1 ? k ? 16Þ
ð17 ? k ? 16+?Þ
SVM is an effective method for supervised pattern
recognition and has been widely used in the realm of
bioinformatics [see, e.g. (14,40–45)]. The basic idea of
SVM is to transform the data into a high dimensional
feature space and then determine the optimal separating
hyperplane. A brief introduction about the formulation of
SVM was given in (46). In this study, the SVM
package LIBSVM 2.84 written by Chang and Lin (47).
Because of its effectiveness and speed in training
process, the radial basis kernel function was used to
Figure 2. A schematic illustration to show the correlations of dinucleo-
tides along a DNA sequence. (a) The first-tier correlation reflects the
sequence-order mode between all the most contiguous dinucleotide.
(b) The second-tier correlation reflects the sequence-order mode
between all the second-most contiguous dinucleotide. (c) The third-tier
correlation reflects the sequence-order mode between all the third-most
e68Nucleic Acids Research, 2013,Vol. 41,No. 6PAGE 4 OF 9
procedure using a grid search approach, and their actual
values thus obtained for the current study were C ¼ 32
and ? ¼ 0:5.
iRSpot-PseDNC and its parameters
were determined via an optimization
C and the kernel width
The predictor obtained via the aforementioned procedures
is called iRSpot-PseDNC. The PseDNC as formulated in
Equations 8 and 9 contains two uncertain parameters ?
and w. The former represents the total number of
correlation ranks counted (cf. Equation 5 and Figure 2),
which is an integer and should be smaller than the length
of any of the DNA sequences involved in this study,
whereas the latter is the weight factor ranged from 0 to
1 (26). Generally speaking, the greater the value of ?, the
However, if the value of ? is too large, it might cause
disaster’ (49). Preliminary tests indicated that in using
the iRSpot-PseDNC predictor on the benchmark data
set S (Supplementary Information S1), a peak was
observed for the overall accuracy ? (cf. Equation 11) or
Acc (cf. Equation 12) when ? ¼ 3 and w ¼ 0:05.
respectively used for the two uncertain parameters in
sequence-order effectswill be incorporated.
(48) or‘high dimension
RESULTS AND DISCUSSIONS
One of the important procedures in developing a useful
statistical predictor (23) is to objectively evaluate its
Table 1. The original numerical values for the six DNA dinucleotide physical structures
Dinucleotide Physical structuresa
aIn this table, the following symbols were used to represent the six physical structures of dinucleotide (32): P1for ‘twist, P2for ‘tilt’, P3for ‘roll’, P4
for ‘shift’, P5 for ‘slide’ and P6 for ‘rise’.
Table 2. The normalized values for the six DNA dinucleotide physical structures
aSee footnote a of Table 1 for further explanation.
PAGE 5 OF 9Nucleic AcidsResearch, 2013, Vol.41,No. 6e68
performance or anticipated success rate. Now let us
address this problem.
Criteria for performance evaluation
To provide a more intuitive and easier-to-understand
method to measure the prediction quality, the criteria
proposed in (50) was adopted here. According to that
criteria, therates ofcorrect
recombination coldspots in data set S?are respectively
defined by (cf. Equation 1)
where N+is the total number of the recombination
hotspots investigated, whereas N+
the coldspots; N?the total number of the recombination
coldspots investigated, whereas N?
the recombination coldspots incorrectly predicted as the
hotspots. The overall success prediction rate is given by
N+ , for the recombination hotspots
, for the recombination coldspots
?the number of the
the number of
¼ 1 ?N+
It is obvious from Equations 10 and 11 that, if and only
noneof the recombination
success rate ? ¼ 1. Otherwise, the overall success rate
would be <1.
On the other hand, it is instructive to point out
that thefollowing equation
literatures for examining the performance quality of a
where TP represents the true positive; TN, the true
negative; FP, the false positive; FN, the false negative;
Sn, the sensitivity; Sp, the specificity; Acc, the accuracy;
MCC, the Mathew’s correlation coefficient.
The relations between the symbols in Equation 11 and
those in Equation 12 are given by
Substituting Equation 13 into Equation 12 and also
noting Equation 11, we obtain
+¼ 0 and ?+¼ ??¼ 1, we have the overall
set is oftenused in
TP ¼ N+? N+
TN ¼ N?? N?
FP ¼ N?
FN ¼ N+
Sn ¼ 1 ?N+
Sp ¼ 1 ?N?
Acc ¼ ?¼1 ?N+
coldspots, we have the sensitivity Sn ¼ 1, whereas
were mispredicted to be the coldspots, we have the
sensitivity Sn ¼ 0. Likewise, when N?
none of the recombination coldspots was mispredicted,
wehavethe specificitySp ¼ 1,
meaning all the recombination coldspots were incorrectly
predicted as recombination hotspots, we have the
specificity Sp ¼ 0. When N+
none of the recombination hotspots in the data set S+
and none of the recombination coldspots in S?was
incorrectly predicted, we have the overall accuracy
Acc ¼ ? ¼ 1, whereas N+
that all the recombination hotspots in the data set S+and
all the recombination coldspots in S?were mispredicted,
we have the overall accuracy Acc ¼ ? ¼ 0. The MCC
correlation coefficient is usually used for measuring the
+¼ 0, meaning that none of the recombination
hotspots in the data set S+and none of the recombination
coldspots in S?was mispredicted, we have Mcc ¼ 1; when
no better than random prediction; when N+
ment between prediction and observation. As we can see
from the aforementioned discussion, it is much more
intuitive and easier to understand when using Equation
14 to examine a predictor for its sensitivity, specificity,
overall accuracy and Mathew’s correlation coefficient.
none of the
?¼ N+, meaning that all the recombination hotspots
+¼ 0 , meaning
+¼ 0, meaning that
?¼ N+and N?
+¼ N?, meaning
?¼ N+=2 and N?
+¼ N?=2, we have Mcc ¼ 0, meaning
+¼ N?we have MCC ¼ ?1, meaning total disagree-
methods are often used to evaluate the quality of a
predictor: independent data set test, subsampling (K-fold
cross-validation) test and jackknife test. However, as
elaborated by an analysis in (52) and demonstrated by
Equations 28–32 of (23), among the three cross-validation
methods, the jackknife test is deemed the least arbitrary
and most objective because it can always yield a unique
result for a given benchmark data set, and hence has been
widely recognized and increasingly used by investigators
to examine the quality of various predictors [see, e.g.
(11,16,21,22,29,53–57)]. Accordingly, the jackknife test
was also adopted in this study to examine the anticipated
success rates of the current predictor. In the jackknife test,
all the samples in the benchmark data set S will be singled
out one by one and tested by the predictor trained by the
remaining samples. During the jackknifing process, both
literatures, thefollowingthree cross-validation
e68 Nucleic Acids Research, 2013,Vol. 41,No. 6PAGE 6 OF 9
the training data set and testing data set are actually open,
and each sample will be in turn moved between the two.
The results obtained with iRSpot-PseDNC on the
benchmark data set S of Supplementary Information S1
by the jackknife test are given in Table 3, where for
facilitating comparison, the corresponding results by the
IDQD predictor (6) on the same benchmark data set are
also given. As indicated in Table 3, the results reported by
Liu et al. (6) were derived by the 5-fold cross-validation
test. As elucidated in (23), this would make their test
without a unique result as demonstrated later in the text.
For the current case, the benchmark data set S consists of
S+and S?, where S+contains 490 recombination
hotspots, and S?contains 591 recombination coldspots.
Substituting these data into Equations 28 and 29 of (23)
with M ¼ 2 (number of groups for classification) and
? ¼ 5 (number of folds for cross-validation), we obtain
490 ? Int 490=5
591 ? Int 591=5
ð591 ? 118Þ!118!> 1:17 ? 10232
ð490 ? 98Þ!98!?
where the symbol Int is the integer-truncating operator
meaning to take the integer part for the number in the
bracket right after it. The result of Equation 15 indicates
that the number of possible combinations of taking one-
fifth samples from each of the two subsets, S+and S?, for
conducting the 5-fold cross-validation will be >10232,
which is an astronomical figure, too large to be practical.
Therefore, in their study (6), Liu et al. only randomly
picked one of ?1:17 ? 10232possible combinations (cf.
Equation 15) to perform the 5-fold cross-validation. To
make the comparison between iRspot-PseNDC and
IDQD (6) with the same test method, we also randomly
picked one of the possible combinations from the same
benchmark data set to perform the 5-fold cross-validation
test with iRspot-PseNDC, and the corresponding results
thus obtained are given in Table 3 as well.
As we can see from the table, not only the overall
accuracy (Acc) achieved by iRSpot-PseDNC using the
than that by the IDQD (6) but the overall accuracy
achieved by iRSpot-PseDNC using the rigorous jackknife
test is also higher than that by the IDQD. Besides the
overall accuracy, the MCC rates achieved by the
iRSpot-PseDNC predictor derived from both 5-fold
cross-validation and jackknife tests are also higher than
those by the IDQD predictor.
To further demonstrate its performance, we used iRSpot-
PseDNC to identify the 452 experimentally annotated
recombination hotspots by Pan et al. (58) for the
S. cerevisiae chromosome IV. The results are given in the
Supplementary Information S2, from which we can see that
347 outcomes by the predictor were consistent with the
experimental observations. The overall success rate was
76.77%, indicating that the method as proposed in this
article is promising in identifying recombination hot/cold
spots, or can at the very least play a complementary role to
the existing method in this area.
For the convenience of the vast majority of experimental
scientists, let us give a step-by-step guide on how to use the
iRSpot-PseDNC web-server to get their desired results
without the need to follow the complicated mathematic
equations that were presented just for the integrity in
developing the predictor. The detailed steps are as follows.
Open the web server at http://lin.uestc.edu.cn/server/
iRSpot-PseDNC and you will see the top page of
iRSpot-PseDNC on your computer screen, as shown in
Figure 3. Click on the Read Me button to see a brief
introduction about the predictor and the caveat when
Figure 3. A semi-screenshot to show the top page of the iRSpot-
PseDNC web-server. Its website address is at http://lin.uestc.edu.cn/
Table 3. A comparison of between iRSpot-PseDNC with the existing method
Predictor Test method Sn (%)Sp (%) Acc (%)MCC
5-fold cross 79.40 81.0080.300.603
aThe parameters used: ? ¼ 3 and w ¼ 0:05 for Equation 9; C ¼ 32 and ? ¼ 0:5 for the LIBSVM operation engine (47).
bFrom Liu et al. (6).
PAGE 7 OF 9 Nucleic AcidsResearch, 2013, Vol.41,No. 6e68
Either type or copy/paste the query DNA sequence into
the input box at the center of Figure 3. The input sequence
should be in the FASTA format. A sequence in FASTA
format consists of a single initial line beginning with a
greater-than symbol (‘>’) in the first column, followed
by lines of sequence data. The words right after the ‘>’
symbol in the single initial line are optional and only used
for the purpose of identification and description. All lines
should not be longer than 120 characters and usually do
not exceed 80 characters. The sequence ends if another line
starting with a ‘>’ appears; this indicates the start of
another sequence. Example sequences in FASTA format
can be seen by clicking on the Example button right above
the input box.
Click on the Submit button to see the predicted result. For
example, if you use the query DNA sequences in the
Example window as the input, after clicking the Submit
button, you will see the following shown on the screen of
your computer: the outcome for the first query sample is
‘recombination hotspot’; the outcome for the second
query sample is ‘recombination coldspot’. All these
resultsare fully consistent
aforementioned computation before the predicted result
appears on your computer screen; the more number of
query sequences and longer of each sequence, the more
time it is usually needed.
Click on the Citation button to find the relevant papers
that document the detailed development and algorithm of
Click on the Data button to download the benchmark
data sets used to train and test the iRSpot-PseDNC
Supplementary Data are available at NAR Online:
Supplementary Data sets 1 and 2.
The authors wish to thank the two anonymous reviewers
for their constructive comments, which were indeed
very helpful for strengthening the presentation of this
Funding for open access charge: The National Nature
Scientific Foundation of China [61100092, 61202256].
Conflict of interest statement. None declared.
1. Lewin,B. (2008) Genes IX, Chap.18. Jones & Bartlett,
Massachusetts, pp. 428–456.
2. Keeney,S. (2008) Spo11 and the Formation of DNA Double-
Strand Breaks in Meiosis. Genome Dyn. Stab., 2, 81–123.
3. Baudat,F. and Nicolas,A. (1997) Clustering of meiotic double-
strand breaks on yeast chromosome III. Proc. Natl Acad. Sci.
USA, 94, 5213–5218.
4. Klein,S., Zenvirth,D., Dror,V., Barton,A.B., Kaback,D.B. and
Simchen,G. (1996) Patterns of meiotic double-strand breakage on
native and artificial yeast chromosomes. Chromosoma, 105,
5. Zenvirth,D., Arbel,T., Sherman,A., Goldway,M., Klein,S. and
Simchen,G. (1992) Multiple sites for double-strand breaks in
whole meiotic chromosomes of Saccharomyces cerevisiae. EMBO
J., 11, 3441–3447.
6. Liu,G., Liu,J., Cui,X. and Cai,L. (2012) Sequence-dependent
prediction of recombination hotspots in Saccharomyces cerevisiae.
J. Theor. Biol., 293, 49–54.
7. Chou,K.C. (2001) Prediction of protein cellular attributes using
pseudo amino acid composition. Proteins, 43, 246–255.
8. Nanni,L. and Lumini,A. (2008) Genetic programming for creating
Chou’s pseudo amino acid based features for submitochondria
localization. Amino Acids, 34, 653–660.
9. Sahu,S.S. and Panda,G. (2010) A novel feature representation
method based on Chou’s pseudo amino acid composition for
protein structural class prediction. Comput. Biol. Chem., 34,
10. Fang,Y., Guo,Y., Feng,Y. and Li,M. (2008) Predicting DNA-
binding proteins: approached from Chou’s pseudo amino acid
composition and other specific sequence features. Amino Acids,
11. Nanni,L., Lumini,A., Gupta,D. and Garg,A. (2012) Identifying
bacterial virulent proteins by fusing a set of classifiers based on
variants of Chou’s pseudo amino acid composition and on
evolutionary information. IEEE/ACM Trans. Comput. Biol.
Bioinform., 9, 467–475.
12. Mohammad Beigi,M., Behjati,M. and Mohabatkar,H. (2011)
Prediction of metalloproteinase family based on the concept of
Chou’s pseudo amino acid composition using a machine learning
approach. J. Struct. Funct. Genom., 12, 191–197.
13. Guo,J., Rao,N., Liu,G., Yang,Y. and Wang,G. (2011)
Predicting protein folding rates using the concept of Chou’s
pseudo amino acid composition. J. Comput. Chem., 32,
14. Mohabatkar,H., Mohammad Beigi,M. and Esmaeili,A. (2011)
Prediction of GABA(A) receptor proteins using the concept of
Chou’s pseudo-amino acid composition and support vector
machine. J. Theor. Biol., 281, 18–23.
15. Zou,D., He,Z., He,J. and Xia,Y. (2011) Supersecondary structure
prediction using Chou’s pseudo amino acid composition.
J. Comput. Chem., 32, 271–278.
16. Mohabatkar,H. (2010) Prediction of cyclin proteins using Chou’s
pseudo amino acid composition. Protein Pept. Lett., 17,
17. Georgiou,D.N., Karakasidis,T.E., Nieto,J.J. and Torres,A. (2009)
Use of fuzzy clustering technique and matrices to classify amino
acids and its impact to Chou’s pseudo amino acid composition.
J. Theor. Biol., 257, 17–26.
18. Zhou,X.B., Chen,C., Li,Z.C. and Zou,X.Y. (2007) Using Chou’s
amphiphilic pseudo-amino acid composition and support vector
machine for prediction of enzyme subfamily classes. J. Theor.
Biol., 248, 546–551.
19. Esmaeili,M., Mohabatkar,H. and Mohsenzadeh,S. (2010) Using
the concept of Chou’s pseudo amino acid composition for risk
type prediction of human papillomaviruses. J. Theor. Biol., 263,
20. Mohabatkar,H., Beigi,M.M., Abdolahi,K. and Mohsenzadeh,S.
(2012) Prediction of allergenic proteins by means of the concept
of Chou’s pseudo amino acid composition and a machine
learning approach. Med. Chem.
21. Zia Ur,R. and Khan,A. (2012) Identifying GPCRs and their types
with Chou’s Pseudo amino acid composition: an approach from
e68Nucleic Acids Research, 2013,Vol. 41,No. 6PAGE 8 OF 9
multi-scale energy representation and position specific scoring Download full-text
matrix. Protein Pept. Lett., 19, 890–903.
22. Hayat,M. and Khan,A. (2012) Discriminating outer membrane
proteins with fuzzy K-Nearest neighbor algorithms based on
the general form of Chou’s PseAAC. Protein Pept. Lett., 19,
23. Chou,K.C. (2011) Some remarks on protein attribute prediction
and pseudo amino acid composition (50th Anniversary Year
Review). J. Theor. Biol., 273, 236–247.
24. Du,P., Wang,X., Xu,C. and Gao,Y. (2012) PseAAC-Builder: a
cross-platform stand-alone program for generating various special
Chou’s pseudo-amino acid compositions. Anal. Biochem., 425,
25. Shen,H.B. and Chou,K.C. (2008) PseAAC: a flexible web-server
for generating various kinds of protein pseudo amino acid
composition. Anal. Biochem., 373, 386–388.
26. Chou,K.C. (2005) Using amphiphilic pseudo amino acid
composition to predict enzyme subfamily classes. Bioinformatics,
27. Lin,W.Z., Fang,J.A., Xiao,X. and Chou,K.C. (2011) iDNA-Prot:
identification of DNA binding proteins using random forest with
grey model. PLoS One, 6, e24756.
28. Xiao,X., Wu,Z.C. and Chou,K.C. (2011) iLoc-Virus: a multi-label
learning classifier for identifying the subcellular localization of
virus proteins with both single and multiple sites. J. Theor. Biol.,
29. Chou,K.C., Wu,Z.C. and Xiao,X. (2012) iLoc-Hum: using
accumulation-label scale to predict subcellular locations of human
proteins with both single and multiple sites. Molecular Biosystems,
30. Abeel,T., Saeys,Y., Bonnet,E., Rouze,P. and Van de Peer,Y.
(2008) Generic eukaryotic core promoter prediction using
structural features of DNA. Genome. Res., 18, 310–323.
31. Goni,J.R., Fenollosa,C., Perez,A., Torrents,D. and Orozco,M.
(2008) DNAlive: a tool for the physical analysis of DNA at the
genomic scale. Bioinformatics, 24, 1731–1732.
32. Goni,J.R., Perez,A., Torrents,D. and Orozco,M. (2007)
Determining promoter location based on DNA structure first-
principles calculations. Genome Biol., 8, R263.
33. Miele,V., Vaillant,C., d’Aubenton-Carafa,Y., Thermes,C. and
Grange,T. (2008) DNA physical properties determine nucleosome
occupancy from yeast to fly. Nucleic Acids Res., 36, 3746–3756.
34. Chou,K.C., Liu,W., Maggiora,G.M. and Zhang,C.T. (1998)
Prediction and classification of domain structural classes. Proteins,
35. Chou,K.C. and Cai,Y.D. (2005) Prediction of membrane protein
types by incorporating amphipathic effects. J. Chem. Inf. Model.,
36. Vapnik,V.N. (1995) The Nature of Statistical Learning Theory.
Springer Verlag, New York.
37. Denoeux,T. (1995) A k-nearest neighbor classification rule based
on Dempster-Shafer theory. IEEE Trans. Syst. Man Cybern., 25,
38. Shen,H.B. and Chou,K.C. (2007) Virus-PLoc: A fusion classifier
for predicting the subcellular localization of viral proteins within
host and virus-infected cells. Biopolymers, 85, 233–240.
39. Chou,K.C. and Shen,H.B. (2007) Review: recent progresses in
protein subcellular location prediction. Anal. Biochem., 370, 1–16.
40. Chen,W. and Lin,H. (2010) Prediction of midbody, centrosome
and kinetochore proteins based on gene ontology information.
Biochem. Biophys. Res. Commun., 401, 382–384.
41. Cai,Y.D., Zhou,G.P. and Chou,K.C. (2003) Support vector
machines for predicting membrane protein types by using
functional domain composition. Biophys. J., 84, 3257–3263.
42. Lin,H. and Ding,H. (2011) Predicting ion channels and their
types by the dipeptide mode of pseudo amino acid composition.
J. Theor. Biol., 269, 64–69.
43. Zhu,L., Yang,J. and Shen,H.B. (2009) Multi label learning for
prediction of human protein subcellular localizations. Protein J.,
44. Chen,W., Feng,P. and Lin,H. (2012) Prediction of replication
origins by calculating DNA structural properties. FEBS Lett.,
45. Chen,C., Shen,Z.B. and Zou,X.Y. (2012) Dual-Layer wavelet
SVM for predicting protein structural class via the general form
of Chou’s pseudo amino acid composition. Protein Pept. Lett.,
46. Chou,K.C. and Cai,Y.D. (2002) Using functional domain
composition and support vector machines for prediction of
protein subcellular location. J. Biol. Chem., 277, 45765–45769.
47. Chang,C.C. and Lin,C.J. (2001) LIBSVM: a library for support
vector machines, Software. http://www.csie.ntu.edu.tw/_cjlin/
48. Chou,K.C. (1999) A key driving force in determination of protein
structural classes. Biochem. Biophys. Res. Commun., 264, 216–224.
49. Wang,T., Yang,J., Shen,H.B. and Chou,K.C. (2008) Predicting
membrane protein types by the LLDA algorithm. Protein Pept.
Lett., 15, 915–921.
50. Chou,K.C. (2001) Using subsite coupling to predict signal
peptides. Protein Eng., 14, 75–79.
51. Chou,K.C. (2001) Prediction of signal peptides using scaled
window. Peptides, 22, 1973–1979.
52. Chou,K.C. and Shen,H.B. (2010) Cell-PLoc 2.0: an improved
package of web-servers for predicting subcellular localization of
proteins in various organisms. Natural Science, 2, 1090–1103.
53. Hayat,M. and Khan,A. (2012) MemHyb: Predicting membrane
protein types by hybridizing SAAC and PSSM. J. Theor. Biol.,
54. Sun,X.Y., Shi,S.P., Qiu,J.D., Suo,S.B., Huang,S.Y. and
Liang,R.P. (2012) Identifying protein quaternary structural
attributes by incorporating physicochemical properties into the
general form of Chou’s PseAAC via discrete wavelet transform.
Mol. Biosyst., 8, 3178–3184.
55. Hayat,M. and Khan,A. (2011) Predicting membrane protein types
by fusing composite protein sequence features into pseudo amino
acid composition. J. Theor. Biol., 271, 10–17.
56. Mei,S. (2012) Predicting plant protein subcellular multi-
localization by Chou’s PseAAC formulation based multi-label
homolog knowledge transfer learning. J. Theor. Biol., 310, 80–87.
57. Chou,K.C., Wu,Z.C. and Xiao,X. (2011) iLoc-Euk: a multi-label
classifier for predicting the subcellular localization of singleplex
and multiplex eukaryotic proteins. PLoS One, 6, e18258.
58. Pan,J., Sasaki,M., Kniewel,R., Murakami,H., Blitzblau,H.G.,
Tischfield,S.E., Zhu,X., Neale,M.J., Jasin,M., Socci,N.D. et al.
(2011) A hierarchical combination of factors shapes the genome-
wide topography of yeast meiotic recombination initiation. Cell,
PAGE 9 OF 9Nucleic AcidsResearch, 2013, Vol.41,No. 6e68