The Performance Validation of Neural Network Based 13C NMR Prediction Using a Publicly Available Data Source.

The Performance Validation of Neural Network Based 13C NMR Prediction

Using a Publicly Available Data Source.

K.A. Blinov§, Y.D. Smurnyy§, M.E. Elyashberg§, T.S. Churanova§, M. Kvasha§,

C. Steinbeck#, B.A. Lefebvre† and A.J Williams‡

§
Advanced Chemistry Development, Moscow Department, 6 Akademik Bakulev
Street, Moscow 117513, Russian Federation
†
Advanced Chemistry Development, Inc., 110 Yonge Street, 14th floor, Toronto,
Ontario, Canada, M5C 1T4
# Steinbeck Molecular Informatics, Franz-John-Str. 10, 77855 Achern, Germany.
‡
ChemZoo Inc., 904 Tamaras Circle, Wake Forest, NC-27587

Abstract

The validation of the performance of a neural network based 13C NMR prediction

algorithm using a test set available from an open source publicly available database,

NMRShiftDB, is described. The validation was performed using a version of the database

containing ca. 214,000 chemical shifts as well as for two subsets of the database to

compare performance when overlap with the training set is taken into account. The first

subset contained ca. 93,000 chemical shifts that were absent from the ACDCNMR DB,

the ―excluded shift set‖ used for training of the neural network and the ACDCNMR

prediction algorithm, while the second contained ca. 121,000 shifts that were present in

the ACDCNMR DB training set, the ―included shift set‖. This work has shown that the

mean error between experimental and predicted shifts for the entire database is 1.59 ppm,

while the mean deviation for the subset with included shifts is 1.47 ppm and 1.74 ppm for

excluded shifts. Since similar work has been reported online for another algorithm we

1

compared the results with the errors determined using Robien’s CNMR Neural Network

Predictor using the entire NMRShiftDB for program validation.

1. Introduction

Since the 1950s NMR has been widely employed to elucidate molecular structures.

A combination of 1D and multinuclear NMR spectroscopy techniques make this form of

spectroscopy the definitive technique for based structure elucidation. As a rule both 1D

and 2D 1H and 13C spectra, are used in combination with mass spectrometry to elucidate
15
chemical structures. Other magnetically active nuclei, specifically N of late, are used

with increased voracity as a result of improvements in both hardware and improved pulse

sequences.
13
The analysis of C NMR spectral data is key to developing the framework of a

molecule under examination and these data can provide a large number of structural
13
constraints when compared with other nuclei. As a result C spectra have formed the

basis of many expert systems (see reviews1-2 developed for the purpose of Computer-

Assisted Structure Elucidation (CASE)). In these systems the program initially reveals
13
possible molecular substructure fragments from the C NMR data then all plausible

structures are generated and the most probable one selected on the basis of comparing the
13
predicted C NMR spectra of candidates with experimental spectrum. Since the output

file of an expert system may contain hundreds and thousands of structures, a program to

perform carbon chemical shift prediction must possess two properties. These are

generally contradictory in nature - soothe algorithm should be fast enough to deliver

predicted spectra for a large structural file in a reasonable time while maintaining high

2

enough accuracy to provide reliable identification of the most probable structure.

Spectrum prediction is also necessary to support the process of carbon chemical shift

assignment and verification of the structural hypotheses. The need to create software

capable of predicting 13C NMR spectra was realized very early on during the first steps of

computerized spectroscopy development.

The first algorithms developed3-6 were based on additive rules7. This approach

allowed a chemical shift of a given carbon atom to be calculated by the means of

increments characterizing different substituent patterns. Algorithms of this nature, and

the software programs derived from them, are very fast but their accuracy is

unsatisfactory for the correct selection of the preferred structure in all but the simplest of

cases.

Markedly higher accuracy is obtained using a structural database method. In this

approach the environment of each carbon atom within a molecule is described by a

Heirarchical Organization of Spherical Environments (HOSE) code as introduced by

Bremser8 and extended in other works9-14. The chemical shift is calculated by comparing

the HOSE codes of the analyzed molecules with the HOSE codes of reference molecules

present in the database. Our own experience with the development and implementation of

HOSE code based algorithms shows15-17 that this approach possesses an accuracy that, as

a rule, performs admirably in allowing the program to identify the most probable

structure within an answer file. Simultaneously a program equipped with appropriate

functionality can provide visual elements capable of explaining the details behind each

calculated chemical shift value. The investigator can utilize the program to show the

chemical structure and its HOSE codes whose chemical shift assignments were used

3

during the computation of the predicted shifts. One major shortcoming of the HOSE

approach is that the prediction is relatively slow, consuming some tens of seconds for

complex chemical structures even on modern computers. This prevents the application of

this approach to very large structural files.
13
C chemical shift prediction programs based on quantum-chemical calculations

have also been developed18-20. Experience has shown that they cannot be used for the

purpose of prediction for large structural files since they are very time consuming. Their

accuracy, in general, can also be insufficient for the selection of the preferred structure in

routine mode, though the accuracy can be refined when the program is adjusted to the

shift prediction of compounds belonging to a specific class21.

In an attempt to combine both high accuracy and speed of prediction the application

of artificial neural nets22 (ANN) to the 13
C spectrum prediction of different classes of

organic molecules was suggested in a series of publications23-25 . The ANN is efficient

when the dependence of a target value on a set of parameters is either unknown or the

dependence is very complex to calculate. ANNs can be taught to predict target values by

using a training set of reference data. Meiler et al13-14 reported a program based on ANN
13
algorithms allowing the prediction of C NMR spectra with average chemical shift

deviations of 1.6 ppm at a calculation speed about 1000 times faster than HOSE code

predictions. Therefore their work provided a good balance between accuracy and the

speed of the shift prediction.

Recently an attempt was made26-27 to improve on the chemical descriptor scheme
13
suggested by Meiler and to select an appropriate ANN architecture to provide C

chemical shift calculations using the commercial software program ACD/CNMR

4

Predictor. Since the size and quality of the training set are both very important parameters
13
the ACD/Labs’ database containing over 2,160,000 C chemical shifts was utilized. To

avoid overlaps with the training data 11,000 new compounds (over 150,000 chemical

shifts) described in the literature during the period 2005-2006 were chosen as the test

dataset. The detailed description of this investigation will be provided in a separate

article. Here we discuss only the important result regarding algorithmic validation: the

average chemical shift deviation calculated for the test dataset was less than 1.5 ppm.

The validation of the performance of NMR chemical shift prediction algorithms is a

challenging problem with the primary challenge being the availability of a quality data

set for validation of the prediction accuracy. If the validation data set contains a

significant number of structures that are well represented in the database used as the basis

of the prediction algorithms then the validation exercise will not truly represent the

challenges of prediction. The most valid test would be conducted on a validation set

containing chemical structures which are very different from these contained within the

training dataset. Ideally, an independent party without knowledge of the structures in the

training set should choose the validation set, so as to avoid any bias.

The quality of a validation database is important but difficult to prove in most cases.

The ideal validation set does not contain any errors in assignment and covers the whole

range of structural diversity available in present chemistry and in all future diversity

possibilities. While this is clearly impossible to attain, large diverse datasets do exist and,

while not ideal, can be used for the purpose of validation. Every large dataset contains

errors but for comparisons of prediction between different algorithms this is actually

irrelevant since any errors remain challenging for all algorithms.

5

In spite of the fact that the test dataset used for validation of the improved ANN

algorithm26-27 had no overlap with the training set, it was of interest to determine to what

degree the accuracy is dependent on the size, composition and diversity of the structural

file used as a testing set. A resource is available on the Internet that has met the above

criteria of size and quality to serve as a fair and reliable validation set. This resource is a

database called NMRShiftDB28-30 and has been created as a collaborative effort by

chemists and spectroscopists submitting data to the open access database. The current

work is devoted to an analysis of the performance of the ANN based ACD/CNMR

predictor using the NMRShiftDB database as the validation set. Due to the availability of

a comparison test issued by Wolfgang Robien31 we also had an opportunity to compare

performance with his neural network algorithm.

2. NMRShiftDB

The NMRShiftDB is an open source collection of chemical structures and their associated

NMR shift assignments. The database is generated as a result of contributions by the

public and has been described in detail elsewhere28-29. Currently, the database contains

19,958 structures with 214,136 assigned carbon chemical shifts. Datasets entered by

contributors are sent to registered reviewers for evaluation, who are presented the newly

entered spectrum together with a shift prediction and a color-coded table of deviations. A

significant part of NMRShiftDB, however, was initially assembled from in-house

databases from collaborating institutions and have been entered unchecked. This called

for external checks of the data based on independent databases and resources, which have

now been carried out as described in this paper. Based on a cursory examination of the

structural diversity within the database these data represent a statistically relevant set to

6

use in an evaluation of predictive accuracy and is the first large dataset available from an

independent source which we could use for this purpose.

Robien has already published an analysis of performance of his neural network

predictions31. This review provides an evaluation of the NMR prediction algorithms he

has developed over many years. These algorithms have been the basis of a number of

software products including a commercially available product, NMRPredict 31. Robien’s

analysis focused on the quality of the database in terms of the presence of a number of

outliers but gave no specific review of the quality of the dataset and focused only on the

problem assignments. A later comment suggested that about 0.3% of the data may be in

error, a low number for the purpose of the work reported here.

3. Performance Validation of ACD/Labs Neural Network CNMR Prediction.

As already discussed the NMRShiftDB website offers visitors the opportunity to

download a data file containing all of the structures and chemical shifts that compose the

database. This file was downloaded and the structures and shifts were imported into

ACD/Labs’ format.

As a first step, an analysis of the degree of overlap between the structures in the

training set within the ACD/CNMR Predictor and the validation set made up of

NMRShiftDB was undertaken. The presence or absence of a chemical shift in the

NMRShiftDB was determined in the following manner. For a specific carbon atom

existing in a structure contained within the NMRShiftDB, the HOSE code was

determined and then the atom with the same HOSE code was searched in the

ACDCNMR DB. If such an atom was identified then the corresponding chemical shift

7

was deemed to be present in both databases and therefore excluded. Otherwise, the shift

was included into the dataset for which the given chemical shift was absent from

NMRShiftDB.

It was determined that 57% of the carbon chemical shifts in the NMRShiftDB

were already contained within the ACD/Labs database. The NMRShiftDB database was

stripped of replicate chemical shifts used as the basis of the prediction algorithms in

ACD/CNMR Predictor.

The results of algorithm validation using the NMRShiftDB test dataset are shown in

Table 1.

Table 1. General Results of ACD/CNMR Neural Network Predictor validation.

Ave Std Max % % % % %
Calculation Shift Error Error Error <1 <2 <3 >3 >10
method: Count (ppm) (ppm) (ppm) ppm ppm ppm ppm ppm
1. Whole
dataset 214136 1.59 2.76 153.53 50 75 86 13 0.7
2. Absent
in data file 92927 1.74 3.22 133.19 49 72 84 16 1
3.Present
in data file 121209 1.47 2.35 153.53 51 76 88 12 0.4

It was revealed that from the total number of chemical shifts collected in the

NMRShiftDB (214,136) that 92,927 shifts were not contained within the ACD/CNMR

database and consequently their HOSE codes were new for the NN ACD/CNMR

Predictor. At the same time 121,209 chemical shifts made up the overlap of the two

databases. The average, standard and maximum errors are displayed for the whole

database and two subsets, as well as the percentages of chemical shifts predicted with

8

errors of d<1 ppm, d<2 ppm, d<3 ppm, d>3 ppm, and d>10 ppm for the entire database

and both subsets.

Table 1 shows that the mean error calculated for the entire dataset is 1.59 ppm

(rms=2.76 ppm) . This value can vary by +/- 9% depending on whether dataset 2 or 3 is

used for the purpose of algorithm validation. Since the NMRShiftDB library is composed

of compounds analyzed by chemists working in varied areas of organic chemistry we

believe that it forms a representative set for general chemistry. Assuming this to be true
13
then validation of our C chemical shift prediction method using a database of ca.

214,000 chemical shifts leads to an average deviation which is reliable within ±10 %.

The percentage of chemical shift deviations depending on the different ranges of the

values calculated for the three datasets presented in Table 1 are shown in Figure 1.

100

90 86 88
84

80 75 76
72
70

60
Absent
49 50 51
50 Whole
Present
40

30

20 16
13 12
10
1 0.7 0.4
0
<1 <2 <3 >3 >10

9

Figure 1. The percentage of chemical shift deviations depending on different ranges of
values as calculated for the three datasets presented in Table 1.

About 50% of chemical shifts were calculated with mean errors < 1 ppm in all three

cases. This observation allows us to conclude that independent of the presence or absence

of the predicted chemical shifts in the test database half of all of the predicted chemical

shifts are calculated with an error of <1 ppm. Errors <2 and <3 ppm encompass 72-76

and 84-88 % of all calculated shifts respectively. Chemical shifts predicted with

relatively low accuracy (d>3 ppm) make up only 12-16 % of entire shift number. This

number can correspond to errors in the database and some have already been identified

by Robien31 and in this work. However, this distribution also correlates with the

distribution of problems solved with the aid of the Structure Elucidator software and with

chemical shift deviations calculated for genuine structures17. Thus, the deviations

calculated by ACD/CNMR Predictor based on HOSE codes10 were >3 ppm for 18% of

all of the problems solved with Structure Elucidator and, in each case, a newly identified

natural product was elucidated. The percentage of shifts predicted with errors >10 ppm

varies from 0.4 % (―present‖) to 1 % (―absent‖) and are mainly associated with the

presence in NMRShiftDB of some outliers. These outliers can be from poor prediction

versus experimental or experimental data in error as a result of an incorrect structure

representation or mis-assignment. These errors are distributed as follows: d>10 ppm

(1,040; 0.5%), d>25 ppm (141; 0.07%) and d> 50 ppm (31; 0.01%). Examination of the

structure giving rise to the maximum error of ~150 ppm provides evidence that

NMRShiftDB either contains some erroneously drawn structures or poorly assigned

chemical shifts31. This is unavoidable in large database of this nature. Examples of

1
0

structures for which obviously erroneous chemical shift assignments were detected

(marked by red) as a result of the prediction accuracy validation are shown in Figure 2.

HC
3
C 3
H
2 .7
4 0 OH O 17 0
5 .9 6 .0
1 0

7 .8
3 0
2 .1
2 0 O 8 0
.3
3 .4
8 0
O
8 .1
5 0 O
18 0
3 .8
14 0
2 .7
18 0
4 .0
C 3
H N
2 .7
7 0
1 5 0 1 .5 O
3 .5 4 0
H 15 0
6 .8
3 .2
8 0
3 .1
4 0 9 .1
7 0
7 .0
7 0 C 2
H HN Br
14 0
2 .5
2 .7
9 0 15 0
2 .9 12 0
3 .0
2 .5
9 0
18 0
3 .8

C3
H
C 3
H 1 .1
4 0
1 .5
1 0

Figure 2. Examples of structures for which obviously erroneous chemical shift
assignments were detected (marked by red) as a result of the prediction accuracy
validation.

When the shifts with difference > 25 ppm were removed from the entire database

and the two subsets, the average errors decreased only slightly: from 1.59 to 1.56 ppm for

the entire DB, from 1.74 to 1.70 ppm for the ―absent‖ subset and from 1.47 to 1.46 ppm

for the ―present‖ subset. Consequently, the conclusion regarding the predictive ability of

the ACDCNMR NN Predictor remains.

The data presented in Table 1 and Figure 1 describe the average values
13
characterizing the results of the validation study. The accuracy of C NMR spectrum

prediction is known to depend on chemical classes to which a given carbon atom belongs,

on the number of representatives of a given class in the training sets, and on the influence

of stereochemical factors. We have therefore compared the average prediction accuracy

1
1

for quaternary carbons, methine, ethyl and methyl groups in aliphatic substructures as

well as the accuracy for alkenes, alkynes and aromatic compounds. In so doing we have

examined how the errors of chemical shift prediction are associated with the presence or

absence of a given shift in the validation set. The results of the calculations performed

with the whole database and both subsets are presented in Tables 2, 3, and 4. In these

Tables the mean and standard deviations are shown along with the numbers of shifts

predicted for each type of carbon atoms.

Table 2. Whole dataset. Deviations calculated for different atom types.
alkene alkene alkyne aroma aroma
Atom Types: C CH CH2 CH3 C CH C C CH
Number of
shifts 6108 17238 38296 28952 20192 11143 2693 38379 51135
Mean deviation 1.79 2.01 1.55 1.17 2.02 2.04 2.40 1.74 1.26
Standard
deviation 3.31 3.32 2.98 2.26 3.66 3.24 4.45 2.60 1.90

Table 3. Absent in data file. Atom types.
Number of
Shifts: 3116 9792 18205 12570 8628 4396 932 15289 19999
Mean deviations 1.93 2.16 1.71 1.30 2.23 2.27 2.51 1.96 1.30
Standard
deviations 3.69 3.80 3.66 2.44 4.15 3.89 4.50 3.00 2.09

Table 4. Present in data file. Atom types.
Number of
Shifts: 2992 7446 20091 16382 11564 6747 1761 23090 31136
Mean deviations 1.64 1.82 1.41 1.07 1.86 1.90 2.35 1.58 1.24
Standard
deviations 2.87 2.56 2.19 2.12 3.24 2.74 4.42 2.30 1.78

To assist in the analysis of the results they are graphically represented in Figure 3.

1
2

3

2.51
2.5 2.35
2.23 2.27
2.16
1.93 1.96
Average error, ppm

2 1.86 1.9
1.82
1.71
1.64 1.58 Absent
1.5 1.41 Whole
1.3 1.3 1.24
Present
1.07
1

0.5

0
C CH CH2 CH3 alken alken alkyn C aroma aroma
C CH C CH

Figure 3. The comparison of chemical shift prediction accuracy for different types of
atoms depending on their assignment to one of the three testing sets.

A striking observation is that the highest and almost equal accuracy is achieved for

the methyl group (d=1.30-1.07 ppm) and the aromatic protonated carbon atoms (d=1.30–

1.24 ppm) and the errors associated with the aromatic carbons is almost the same for the

entire database and both of its subsets. The next in the series is the -CH2- group for

which the error varies between 1.41 and 1.71 ppm. At first glance one can expect that the

accuracy of chemical shift prediction for >CH- groups should be higher than for

quaternary carbons since the latter have four non-hydrogen neighbors whose influence on

chemical shifts is complex and difficult to take into account. We however observe the

reverse: 1.64-1.93 ppm for quaternary carbons and 1.82-2.16 ppm for >CH- (see Figure

3). The accuracy of the chemical shift prediction for =CH and quaternary =C groups in

olefins is almost the same if it is considered separately within entire set and both subsets.

1
3

The error varies from 1.86 to 2.27 ppm when going from the ―present‖ subset to ―absent‖.

The relatively large errors are accounted for the difficulties associated with attempt to

allow for stereochemical factors playing an important role in the chemical shift prediction

of double bond carbons. The lowest accuracy of shift prediction (d=2.35-2.51 ppm) was

observed for alkynes, which can be explained by a very reduced dataset for such

compounds in the training set.

4. Comparison with Results of Previous Validation Work Performed using
NMRShiftDB.
As mentioned earlier the entire NMRShiftDB was recently used by Robien31 to validate
13
the performance of his C NMR shift prediction algorithms based on artificial neural

nets. The validation provided an average deviation of 2.22 ppm. Since these calculations

were performed only with the entire DB we cannot comment on the overlap between his

training set and the test set. We can only compare the results for the entire database (see

Table 5). It should be noted that the dataset tested by ourselves was a later dataset than

that examined by Robien and contained more data points.

Table 5. Validation of the ACD/CNMR NN Predictor and Robien’s Algorithms on the

Entire Dataset.

Average Standard Outliers (ppm Difference)
Shift
Program Deviation Deviation
Count >10 ppm >25 ppm >50 ppm
(ppm) (ppm)
ACD/CNMR 1,040 141 31
214,136 1.59 2.76
v10.05 (0.4%) (0.07%) (0.01%)
194 56
Robien 209,412 2.22 N/A N/A
(0.09%) (0.03%)

1
4

The comparison shows that the average deviation obtained by ACD/CNMR

Predictor (1.59 ppm) is 40% lower than that obtained by Robien, outperforming by a

significant margin.

It should be noted that only 203,284 unique carbon centers were represented in

the NMRShiftDB but some had multiple assignments. All redundancy was included in

case there was disagreement between the assignments. Therefore over 214,000

assignments were considered in our calculations. As commented earlier this is more than

the number used by Robien (209,412 chemical shifts). Only a small number of the errors

identified by Robien in his analysis had been corrected but majority remained unchanged.

The presence of outliers was almost the same in both investigations. The web posting of

Robien31 did not provide a measure of standard deviation or the number of chemical shift

predictions that were more than 10 ppm from their experimental value and this is the

reason for the absence of this parameter in the table. Robien quoted an average deviation

of 2.19 PPM after correction of some errors, but for comparison purposes, we have used

the 2.22 ppm value with no corrections since no corrections were made to dataset

examined with the ACD/CNMR Predictor.

5. Conclusion

The NMRShiftDB is an excellent resource for the purpose of evaluating chemical shift

prediction accuracy as evidenced by this work and the previous work of Robien. As

identified by Robien initially, and later in this work, there are certainly outliers in the

dataset requiring review and correction. Our previous work has shown that the literature

itself contains about 8% errors in the form of mis-assignments, transcription errors and

1
5

incorrect structures. The obvious errors in NMRShiftDB are certainly below this level

and this is a testament to the value of this resource. The NMRShiftDB dataset is large

and structurally diverse and continues to grow as scientists contribute. Both this study

and the one performed by Robien also demonstrate the virtues of open access to primary

research data, since they would not have been possible had NMRShiftDB been a closed

resource.

Despite a large overlap between the NMRShiftDB and the ACD/Labs carbon

NMR database, a statistically relevant validation set of ca. 93,000 chemicals shifts was

extracted from the NMRShiftDB and used to test the algorithms. The data presented here

shows that the ACD/Labs prediction algorithms have an average deviation of less than

1.8 ppm on the validation set (―absent‖ subset of entire NMRShiftDB) and significantly

outperforms the algorithms of Robien presented in his review. The algorithm defining the

ACD/ CNMR neural network predictor will be discussed in detail in a future publication.

REFERENCES

1. Munk, M.E. Computer-Based Structure Determination: Then and Now. J. Chem.

Inf. Comput. Sci. 1998, 38, 997-1009.

2. Elyashberg, M.E.; Williams, A.J.; Martin G.E. Computer-Assisted Structure

Verification and Elucidation Tools in NMR-Based Structure Elucidation. Prog.

NMR Spectrosc., 2007, doi:10.1016/j.pnmrs.2007.04.003.

3. Grant, D.M.; Paul, E.G. Carbon-13 Magnetic Resonance. II. Chemical Shift Data

For The Alkanes. J. Am. Chem. Soc. 1964, 86, 2984-2990.

1
6

4. Clerc, J.T.; Sommerauer, H.A. A Minicomputer Program Based On Additivity

Rules For The Estimation Of 13C NMR Chemical Shifts. Anal. Chim. Acta. 1977,

95, 33-40.

5. Fürst, A.; Pretsch, E.A Computer Program for the Prediction of 13C NMR Chemical

Shifts of Organic Compounds. Anal. Chim. Acta. 1990, 229, 17-25.

6. Chen, L.; Robien, W. OPSI: A Universal Method For Prediction Of Carbon-13

NMR Spectra Based On Optimized Additivity Models. Anal. Chem. 1993, 65, 2282-

2287.

7. Pretsch, E.; Clerc, T.; Seibl, J.; Simon, W. Tables of Spectral Data for Structure

Determination of Organic Compounds, Springer-Verlag, Berlin, 1989.

8. Bremser, W. HOSE—A Novel Substructure Code. Anal. Chim. Acta. 1978, 103,

355-365.

9. Chen, L.; Robien, W. The CSEARCH-NMR Data Base Approach To Solve

Frequent Questions Concerning Substituent Effects On 13C NMR Chemical Shifts.

Chemom. Intell. Lab. Syst. 1993, 19, 217-223.

10. ACD/CNMR Predictor, version 10.0;. Advanced Chemistry Development: Toronto,

Canada, 2007

11. Specinfo, Chemical Concepts GmbH, D-69442 Weinheim, Germany

12. Bremser,W. Expectation Ranges Of 13C NMR Chemical Shifts. Magn. Reson.

Chem. 1985, 23, 271-275

13. Meiler, J.; Meusinger, R.; Will, M. Fast Determination of 13C-NMR Chemical Shifts

Using Artificial Neural Networks. J. Chem. Inf. Comput. Sci. 2000, 40, 1169-1176.

1
7

14. Meiler, J.; Maier, W.; Will, M.; Meusinger, R. Using Neural Networks for 13C NMR

Chemical Shift Prediction–Comparison with Traditional Methods. J. Magn. Reson.

2002, 157, 242-252.

15. Blinov, K.A.; Carlson, D.; Elyashberg, M.E.; Martin G E.; Martirosian, E. R.;

Molodtsov, S. G.; Williams, A. J. Computer Assisted Structure Elucidation of

Natural Products with Limited Data: Application of the StrucEluc System. Magn

Reson. Chem. 41, 359-3724 (2003).

16. Elyashberg, M. E.; Blinov, K.A.; Molodtsov, S.G.; Williams, A.J.; Martin, G.E.

Structure Elucidator: A Versatile Expert System for Molecular Structure

Elucidation from 1D and 2D NMR Data and Molecular Fragments. J. Chem. Inf.

Comput. Sci. 2004, 44, 771-792

17. Elyashberg, M.E.; Blinov, K.A; Williams, A.J.; Molodtsov, S.G.; Martin,

G. Are Deterministic Expert Systems For Computer Assisted Structure

Elucidation Obsolete? J. Chem. Inf. Model. 2006, 46, 1643-1656.

18. Gaussian 03, Revision C.02; Gaussian Inc.: Wallingford, CT, 2003

19. COSMOS (Computer Simulation of Molecular Structures), version 5; COSMOS

Software GbR: Jena, Germany, 2007.

20. Bagno, A.; Saielli G. Computational NMR Spectroscopy: Reversing the information

Flow. Theor. Chem. Acc. 2007, 117, 603–619.

21. Rychnovsky, S.D. Predicting NMR Spectra by Computational Methods: Structure

Revision of Hexacyclinol. Org. Lett. 2006, 8, 2895-2898.

22. Zupan, J.; Gasteiger, J. Neural Networks for Chemists. VCH, Weinheim, 1993

1
8

23. Kvasnicka, V.; Sklenak, S.; Pospichal, J. Application Of Recurrent Neural Network

In Chemistry: Prediction And Classification Of 13C NMR Chemical Shifts In A

Series Of Monosubstituted Benzenes. J. Chem. Inf. Comput. Sci. 1992, 32, 742-747

24. Mitchell, B.E.; Jurs, P.C. Computer Assisted Simulation of 13C Nuclear Magnetic

Spectra of Monosaccharides. J. Chem. Inf. Comput. Sci. 1996, 36, 58-64.

25. Ivanciuc, O.; Rabine, J.-P.; Cabrol-Bass, D.; Panaye, A.; Doucet, J.P. 13C NMR

Chemical Shift Prediction of the sp3 Carbon Atoms in the -Position Relative to the

Double Bond in Acyclic Alkenes. J. Chem. Inf. Comput. Sci. 1997, 37, 587-598.

26. Smurnyy, Y.D.; Blinov, K.A.; Elyashberg, M.E.; Lefebvre, B.A.; Williams, A.J.

NMR Chemical Shift Prediction by Atomic Increment Based Algorithms. In

Experimental Nuclear Magnetic Resonance Conference, 48th ENC Conference

Proceedings, Daytona Beach, USA, April 22-28 2007, 2007, PH-150.

27. Smurnyy, Y.D.; Blinov, K.A.; Churanova, T.S.; Elyashberg, M.E.; Williams, A. J.

Towards More Reliable 13C and 1H Chemical Shift Prediction: A Systematic

Comparison of Neural Network and Least Squares Regression Based Approaches. J.

Chem. Inf. Model., ASAP Article 10.1021/ci700256n, Published on the Web

12/05/2007

28. Steinbeck, C.; Krause, S.; Kuhn, S. NMRShiftDB– Constructing A Chemical

Information System With Open Source Components. J. Chem. Inf. Comput. Sci.

2003, 43, 1733-1739.

29. Steinbeck, C.; Kuhn, S. NMRShiftDB – Compound Identification And Structure

Elucidation Support Through a Free Community-Built Web Database.

Phytochemistry. 2004, 65, 2711–2717.

1
9

30. The NMRShift Database, http://www.nmrshiftdb.org (accessed September 23 2007).

31. A Quality Check of the NMRShiftDB using the CSEARCH Algorithms

http://nmrpredict.orc.univie.ac.at/csearchlite/enjoy_its_free.html (accessed June 6 2007).

2
0

The Performance Validation of Neural Network Based 13C NMR Prediction Using a Publicly Available Data Source.

More Related Content

Viewers also liked (14)

Similar to The Performance Validation of Neural Network Based 13C NMR Prediction Using a Publicly Available Data Source. (20)

Recently uploaded (20)

The Performance Validation of Neural Network Based 13C NMR Prediction Using a Publicly Available Data Source.