PREDICTION OF ANTICANCER / NON-ANTICANCER DRUGS BASED ON COMPARATIVE MOLECULAR MOMENT DESCRIPTORS USING ARTIFICIAL
NEURAL NETWORK AND SUPPORT VECTOR MACHINE
PRADEEP KUMAR NAIK*, AMIYA PATELa
Department of Bioinformatics and Biotechnology, Jaypee University of Information Technology, Waknaghat, Distt.-Solan, Himachal Pradesh, India (Pin-173215).
aSchool of Life Sciences, Sambalpur University, Jyoti Vihar, Burla, Sambalpur-768019, Orissa, India
The structure-activity relationship (QSAR) model developed discriminate anticancer / non-anticancer drugs using machine learning techniques: artificial neural network (ANN) and support vector machine (SVM). The ANN used here is a feed-forward neural network with a standard back-propagation training algorithm. The performance was compared using 13 shape and electrostatic (Molecular Moments) descriptors. For the complete set of 13 molecular moment descriptors, ANN reveal a superior model (accuracy = 86.7%, Qpred
= 76.7%, sensitivity = 0.958, specificity = 0.805 Matthews correlation coefficient (MCC)
= 0.74) in comparison to the SVM model (accuracy = 84.28%, Qpred = 74.28%, sensitivity
= 0.9285, specificity = 0.7857, MCC = 0.6998). These methods were trained and tested on a non redundant data set of 180 drugs (90 anticancer and 90 non-anticancer). The proposed model can be used for the prediction of the anti-cancer activity of novel classes of compounds enabling a virtual screening of large databases.
(Receieved January 11, 2009; accepted January 20, 2009)
Keywords: Artificial neural network, comparative molecular moment descriptors, support vector machine, drug design, structure activity relationship.
1. Introduction
A number of natural and synthetic products have been found to exhibit anticancer activity against tumor cell lines [1-5]. Eventually, the number of anticancer drugs is increasing exponentially day by day. Hence, discrimination between anticancer and non-anticancer drugs is a major challenge in current cancer research. The worldwide pharmaceutical industry is investing in technologies for high-throughput screening (HTS) of such compounds. Therefore, development of in silico techniques for anticancer drug screening is the demand of today’s anticancer drug discovery. The use of computational tools for discrimination of anticancer drugs from lead molecules prior to their chemical synthesis will accelerate the drug discovery processes in the pharmaceutical industry [6-8].
Early-phase virtual screening and compound library design often employs filtering routines which are based on binary classifiers and are meant to eliminate potentially unwanted molecules from a compound library [9,10]. Currently two classifier systems are most often used in these applications: PLS based classifiers [11,12] and various types of artificial neural networks (ANN) [13]. Typically, these systems yield an average overall accuracy of 80% correct predictions for binary decision tasks following the “likeness concept” in virtual screening [10]. Xue et al. [14]
*Corresponding author: [email protected]
have successfully used the probabilistic neural networks for the classification of 102 active compounds from diverse medicinal plants with anticancer activity using molecular descriptors.
The support vector machine (SVM) approach was first introduced by Vapnik as a potential alternative to conventional artificial neural networks [15,16]. Its popularity has grown ever since in various areas of research and first applications in molecular informatics and pharmaceutical research have been described [17]. Although SVM can be applied to multiclass separation problems, its original implementation solves binary class/nonclass separation problems. Here we described application of ANN and SVM to the anticancer/non-anticancer drugs classification problem which employs a class/nonclass implementation of ANN and SVM. Both SVM and ANN algorithms can be formulated in terms of learning machines. The standard scenario for classifier development consists of two stages: training and testing. During first stage the learning machine is presented with labeled samples which are basically n-dimensional vectors with a class membership label attached. The learning machine generates a classifier for prediction of the class label of the input coordinates. During the second stage, the generalization ability of the model is tested.
Currently various sets of molecular descriptors are available [18-20]. For application to class/nonclass classification of compounds, the molecules are typically represented by n- dimensional vectors. In this work, we focused on CoMMA i.e. Comparative Molecular Moment Analysis [21] for calculating the molecular descriptors. It utilizes information from moment expansions of molecular mass and charge, up through and inclusive of second order to perform molecular comparison. It also allows deriving shape and electrostatic descriptors. CoMMA uses the lower order moments of the molecular mass and charge distributions in addition to one higher- order multipole moment of the charge density distribution, namely, the quadrupole moment as well as a description of the relationship between the two distributions by projections of the electrostatic moments upon the principal component inertial axes. This, together with the ability to perform similarity assignments between different molecules without the requirement of molecular superposition makes the CoMMA descriptors a powerful three-dimensional representation of molecular structure.
In the present paper an attempt has been made to develop a structure-activity relationship model that could help to predict novel classes of compounds having anticancer activity. We have used two machine-learning techniques: a support vector machine (SVM) and an Artificial Neural Network (ANN) as binary classifiers.
2. Materials and methods Data Set
To discriminate between the anticancer and non-anticancer drugs, a data set of 180 drug molecules consisted of 90 non redundant anticancer and the same number of non redundant non- anticancer drugs were used for training, validation and testing. The 3D structure of all the drug molecules in Mol2 format is obtained from the DRUG BANK database [22]. The complete list of the drug molecules used along with their properties is given in the supplementary material.
Prediction of molecular moment’s descriptors
A set of 13 molecular moment descriptors were computed for each chemical structure following Comparative Molecular Moment Analysis (CoMMA) that uniquely encode all the 180 structures, some of which are shown in Table 1. It includes two electrostatic descriptors p and q.
The descriptor ‘p’ calculates the multiple moment descriptors; depending upon the definition of center-of-mass of molecule. Whereas, the descriptor ‘q’ define the quadrupole moment which depends upon the definition of the center-of-dipole. Besides, p and q it includes 3 moments of inertia, Ix, Iy and Iz with respect to three axes X, Y and Z. Eight additional descriptors that relate the charge to the distribution of mass, dx, dy, dz, the magnitudes of projections of the dipole upon the principal inertial axes, Px, Py, Pz, and two components of the quadruple tensor written in the
frame of the principal inertial axes, qxx and qyy are also included [23]. The moment descriptors provide a succinct representation of the three-dimensional distribution of molecular mass, shape and charge.
Table 1. A set of 13 shape and electrostatistic descriptors predicted using CoMMA.
1 2 3 4
S T R U C T U R E
CC C16H14O6
Hesperetin
C5H11Cl2N
Mechlorethamine
C20H28O2
Tretinoin
C12H19N3O Procarbazine
D E S C R I P T O R S
Ix = 387.815 Iy = 2115.55 Iz = 2503.37 Px = 0.331978 Py = 0.428902 Pz = 0
P = 0.542371 Q = 3.70709 qxx = 2.31823 qyy = 1.38886 dx = 2.45122 dy = 3.39761 dz = 0
Ix = 37.8164 Iy = 585.882 Iz = 623.698 Px = 0.000451848 Py = 0.153977 Pz = 0
P = 0.153978 Q = 1.04965 qxx = -1.04965 qyy = -9.03893e- 06
dx = 0.122569 dy = 2.38712 dz = 0
Ix = 243.311 Iy = 3596.59 Iz = 3839.9 Px = 0.162838 Py = 0.0761897 Pz = 0
P = 0.179781 Q = 1.30762 qxx = 0.234843 qyy = 1.07277 dx = 1.21492 dy = 1.08092 dz = 0
Ix = 115.937 Iy = 1550.96 Iz = 1666.9 Px = 0.106196 Py = 0.352981 Pz = 0
P = 0.368609 Q = 2.24136 qxx = 2.05533 qyy = 0.186034 dx = 1.47717 dy = 0.462454 dz = 0
Implementation of the Neural Network Predictor
Neural network predictor was implemented using the Stuttgart neural network simulator (SNNS) (http://www-ra.informatik.uni-tuebingen.de/SNNS/) in Microsoft Windows environment with cygwin. A feed-forward neural network with back-propagation algorithm was used to discriminate between anticancer and non-anticancer drugs. The neural network consisting of 13 input nodes, 4 hidden nodes and 1 output node. For each drug molecule in the training and testing sets, we have transformed 13 network input parameters into the normalized values varying from 0 to 1. Similarly, the output parameters from the ANN were in the range of [0:1]. During the learning phase, a value of 1 was assigned for the anticancer drugs and 0 for non-anticancer drugs.
100 independent training runs were performed to evaluate the average predictive power of the network. The corresponding counts of the false/true positive and negative predictions were estimated using 0.1 and 0.9 cut-off values for non-anticancer and anticancer drugs respectively.
Thus, an anticancer drug from the testing set was considered correctly predicted by the ANN only when its output value ranged from 0.9 to 1.0. For each non-anticancer drug of the testing set the correct prediction was assumed if the corresponding ANN output lies between 0 and 0.1. Thus, all network output values ranging from 0.2 to 0.9 have been ultimately considered as incorrect predictions (rather than undetermined or non-defined).
Implementation of the SVM
SVM learning was implemented using SVMlight [24] available at http://svmlight.joachims.org. In this study the regression mode of SVM was used to model the discrimination between anticancer and non-anticancer drugs. Window size of 13 nodes was used as input to SVM, where each node corresponds to a molecular moment descriptor. The SVM model was also trained and tested on the data set of 90 anticancer and 90 non-anticancer drugs.
Assuming that we have number of drugs xi Є Rd (i = 1, 2…..N) with corresponding target values yiЄ
‹target value›, the xi corresponds to the molecular moment descriptors representing a drug molecule presented to SVM for learning. Here, the target value is either +1, representing an anticancer drug or -1, representing a non-anticancer drug. The kernel chosen was Radial Basis Function (RBF) with regression mode. The QSAR model develops in this study using ANN and SVM is depicted in Figure 1.
Fig. 1. Pictorial representation of the prediction methods of anticancer and non- anticancer drugs using ANN and SVM.
Fourfold cross-validation
The prediction accuracy of both the trained ANN and SVM model was tested using a fourfold cross validation technique. The models were trained and tested on a datasets of 90 anticancer and 90 non-anticancer drugs. Both the data sets were divided into a total of 3 subsets:
training set, validation set and a testing set, each of which consisted of 60 drug molecules (30 anticancer and 30 non anticancer molecules). These three sets were randomly reordered and selected, i.e. the procedure of division of 180 molecules into 3 subsets was done four times. The reason for this division is to avoid over-fitting of the neural network model since it has the capability to learn even the experimental noise of the data. The ANN model was trained only on the training set since the validation set was used to monitor the external prediction error and thus to avoid overtraining. The performance measures given have been averaged over the four testing datasets.
Performance measures
The prediction results from both SVM and ANN were evaluated for test dataset using the following statistical measures.
1. Accuracy of the methods: The accuracy of prediction for neural network and SVM model were calculated as follows:
T N
Q
ACC= P +
, T = (P+N+O+U)Where P and N refer to correctly predicted anticancer and non-anticancer drugs, O and U refer to incorrectly predicted anticancer and non-anticancer drugs, respectively.
2. The Matthews correlation coefficient (MCC) is defined as:
( ) ( )
( P U ) ( P O ) ( N U ) ( N O )
U O N MCC P
+
× +
× +
× +
×
−
= ×
3. Sensitivity (Qsens) and specificity (Qspec) of the prediction methods are defined as:
U P Q
sensP
= + O N Q
specN
= +
4. QPred (Probability of correct prediction) is defined as:
× 100
= + O P Q
predP
3. Results and discussion
Prediction of anticancer / non-anticancer drugs from the comparative molecular moment descriptors has not been undertaken so far. However, the works on the classification of drugs and non-drugs were reported by applying the methods of support vector machines [25], probability- based classification [26], the ANN [27-29] and the Bayesian Neural Networks [13]. Here, we have explored the learning potentials of machine learning techniques, namely, ANN and SVM for the differentiation of anticancer drugs from the non-anticancer drugs. The present work is practically more important as it uses only a limited number of structural descriptors which are easy for statistical analysis due to their limited number. This QSAR model can be useful for virtual screening, combinatorial library design and data mining of anticancer drugs. The average values of the 13 CoMMA descriptors independently calculated for anticancer and non-anticancer drugs are shown in Table 2. It revealed that the two classes of compounds were clearly separated, hence, these descriptors appeared appropriate for building QSAR model of ‘anticancer-likeness’. Table 3 contains the resulting values of specificity, sensitivity, accuracy and other performance measures
of separation of anticancer and non-anticancer drugs in the testing sets using ANN and SVM. The ANN model revealed a superior model (accuracy = 86.7%, Qpred = 76.7%, sensitivity = 0.958, specificity = 0.805 and MCC = 0.74) in comparison to the SVM model (accuracy = 84.28%, Qpred
= 74.28%, sensitivity = 0.9285, specificity = 0.7857 and MCC = 0.6998). Figure 2a & b represents the average predicted range of the output values for the four testing sets consisting of equal number of anticancer and non-anticancer drugs using ANN and SVM. As it can readily be seen from the graph, the vast majority of the predictions has been contained within (0.0 – 0.1) for non- anticancer and (0.9 – 1.0) for anticancer drugs which also illustrates that 0.1 and 0.9 cut-offs values provide very adequate separation of two bioactive classes using.
Table 2. The average values of 13 descriptors independently calculated for anticancer and non- anticancer drugs using CoMMA.
Ix Iy Iz Px Py Pz P Q qxx qyy dx dy dz
Anti- cancer
927.5 4269.3 5123.1 0.393 0.449 0.040 0.688 2.762 0.133 0.325 291.58 221.3 0.157
Non- anti- cancer
1468.7 5873.5 6907.2 0.262 0.277 0.192 0.526 7.019 2.656 -1.045 2.843 3.27 e+14 1.36 e+14
Table 3. Performance Measures of SNNS and SVM_Light classifiers using 13 CoMMA descriptors.
Method Accuracy
(%) QPred (%) Mathew correlation
co-efficient (MCC) Sensitivity
(Sn) Specificity (Sp) Artificial Neural
Network (ANN) 86.67 76.67 0.74 0.95 0.80
Support Vector
Machine (SVM) 84.28 74.28 0.67 0.93 0.79
(a) Predicted output using ANN
0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8
0.0-0.1 0.11-0.2 0.21-0.3 0.31-0.4 0.41-0.5 0.51-0.6 0.61-0.7 0.71-0.8 0.81-0.9 0.91-1.0 Output Range
Proportion of predicted anticancer/non- anticance drugs
Non-anticancer drugs Anticancer drugs
0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9
0.00-0.1 0.11-0.2 0.21-0.3 0.31-0.4 0.41-0.5 0.51-0.6 0.61-0.7 0.71-0.8 0.81-0.9 0.91-1.0 Output Range
Proportion of predicted anticancer/non- anticancer drugs
Anticancer drugs Non Anticancer drugs
Fig. 2. Distribution of the output values of anticancer and non-anticancer drugs of test dataset from the (a) ANN and (b) SVM prediction model.
The results on discrimination of anticancer compounds by the ANN and SVM based QSAR solutions built upon the ‘CoMMA’ descriptors clearly demonstrate an adequacy and good predictive power of the developed model. Thus, there is strong evidence, that the ‘CoMMA’
descriptors do adequately reflect the structural properties of organic chemicals which are relevant for their anticancer activity (though the mechanisms of action of different classes of anticancer drugs are completely different). These observations could be explained by the fact that the parameters calculated by CoMMA cover a broad range of properties of bound atoms and molecules related to their shape, electrostatics, molecular mass, quadruple moment, moment of inertia, etc.
(b) Predicted output using SVM
4. Conclusions
The results have shown that ANN and SVM can be used to predict the activity of drugs from calculated information derived from structure and available physicochemical descriptors.
These results are particularly interesting from a clinical perspective. This is the first time, an instance of ANN and SVM has been applied with success from the limited set of molecular moment descriptors of a drug molecule as input. Intelligent systems such as this could markedly reduce costs of experimental approaches of prediction of anticancer drugs.
Acknowledgements
The calculation of all molecular descriptors with the program CoMMA obtained from IBM Thomas J. Watson Research Center is gratefully acknowledged.
References
[1] M.E. Bracke, R.M.L. Van Cauwenberge, M.M. Mareel, Clin. Metastasis 2, 161 (1984).
[2] R. Giavazzi, A. Garofalo, G. Damia, S. Garattini, M. D’Incalci, British J. of Cancer 57(3), 277 (1988).
[3] S. Mukherjee, V. Kumar, A.K. Prasad, H.G. Raj, M.E. Bracke, C.E. Olsen, S.C. Jain, V.S.
Parmar, Bioorganic Med. Chem. 9(2), 337 (2001).
[4] B.W. Vanhoecke, H.T. Depypere, A. De Beyter, S.K. Sharma, V.S. Parmar, D. De Keukeleire, M.E. Bracke, Pure App. Chem. 71(1), 65 (2005).
[5] L. Sartor, E. Pezzato, I. Dell’Aica, R. Caniato, S. Biggin, S. Garbisa, Biochem. Pharm. 64(2), 229 (2002).
[6] P. Buchwald, N. Bodor, N. Drugs Future 27, 577 (2002).
[7] E.A. Lunney, Med. Chem. Research 8, 352 (1998).
[8] W.L. Jorgensen, Science 303, 1813 (2004).
[9] D.E. Clark, S.D. Pickett, Drug Disco. Today 5, 49 (2000).
[10] G. Schneider, H.J. Bohm, Drug Discov. Today 7, 64 (2002).
[11] S. Wold, Chemometrics Intel. Lab. Sys. 23, 149 (1994).
[12] M. Forina, M.C. Casolino, C. de la Pezuela Martinez, J. Pharma. Biomed. Analysis 18, 21 (1998).
[13] A. Ajay, W.P. Walters, M.A. Murcko, J. Med. Chem. 41(18), 3314 (1998).
[14] C.X. Xue, X.Y. Zhang, M.C. Liu, Z.D. Hu, B.T. Fan, J. Pharm. Biomed. Anal. 38(3), 497 (2005).
[15] V.N. Vapnik, Statistical Learning Theory (New York, Wiley) (1998).
[16] J. Weston, F. Perez-Cruz, O. Bousquet, O. Chapelle, A. Elisseeff, B. Schoelkopf, Bioinformatics 19(6), 764 (2003).
[17] R. Burbidge, M. Trotter, B. Buxton, S. Holden, Comp. Chem. 26, 5 (2001).
[18] D.E. Clark, Combi. Chem. High Throughput Screen. 4(6), 477 (2001).
[19] F. Atkinson, S. Cole, C. Green, H. van de Waterbeemd, Curr. Med. Chem. 2(3), 229 ( 2002).
[20] D.E. Clark, Drug Discov. Today 8, 927 (2003).
[21] B.D. Silverman, D.E. Platt, M. Pitman, I. Rigoutsos, Perspectives in Drug Discov. and Design 399(11), 183 (1998).
[22] D.S. Wishart, C. Knox, A.C. Guo, S. Shrivastava, M. Hassanali, P. Stothard, Z. Chang, J.
Woolsey, Nucl. Acids Res. 34(1), D668 (2006).
[23] B.D. Silverman, Rev. in Med. Chem. 1(1), 1 (2001).
[24] T. Joachims, Proceedings of the ACM Conference on Knowledge Discovery and Data Mining (KDD) ACM (2002).
[25] E. Byvatov, G. Schneider, App. Bioinf. 2(2), 67 (2003).
[26] Y. Takaoka, Y. Endo, S. Yamanobe, H. Kakinuma, T. Okubo, Y. Shimazaki, T. Ota, S.
Sumiya, K. Yoshikawa, J. Chem. Inf. and Comp. Sc. 43(4), 1269 (2003).
[27] J. Zupan, J. Gasteiger, Neural Networks in Chemistry and Drug Design: An Introduction, (Germany, John Wiley) (1999).
[28] C.Y. Zhao, R.S. Zhang, H.X. Liu, C.X. Xue, S.G. Zhao, X.F. Zhou, M.C. Liu, T. Fan, J. Chem. Inf. and Sc. 44(6), 2040 (2004).
[29] J. Galvez, J.V. de Julian-Ortiz, R. Garcia-Demenech, J. Mol. Graphics and Model.
20(1), 84 (2001).
Dataset used for training, validation and testing of the model.
Anticancer dataset (90 molecules):
Serial
Number Accession I.D. of
DrugBank Name of the molecule Molecular Formula
Description / Property / Usage (Taken from DrugBank)
1. APRD00007 Ifosfamide C7H15Cl2N2O2P
For third line chemotherapy of germ cell testicular cancer. It should ordinarily be used in combination with a prophylactic agent for hemorrhagic cystitis, such as mesna.
2. APRD00016 Anastrozole C17H19N5 For treatment of breast cancer in post-menopausal women.
3. APRD00021 Amifostine C5H15N2O3PS
For reduction in the cumulative renal toxicity in patients with ovarian cancer (using cisplatin) and moderate to severe
xerostomia in patients undergoing post-operative radiation treatment for head and neck cancer.
4. APRD00028 Tramadol C16H25NO2
Indicated in the treatment of moderate to severe pain.
Tramadol is used to treat postoperative, dental, cancer, and acute musculosketetal pain and as an adjuvant to NSAID therapy in patients with osteoarthritis.
5. APRD00042 Bicalutamide C18H14F4N2O4S
For treatment (together with surgery or LHRH analogue) of advanced prostatic cancer.
6. APRD00064 Amsacrine C21H19N3O3S For treatment of acute myeloid leukaemia.
7. APRD00078 Porfimer C68H74N8O11 Indicated in the treatment of esophageal cancer.
8. APRD00090 Dexrazoxane C11H16N4O4
For reducing the incidence and severity of cardiomyopathy associated with doxorubicin administration in women with metastatic breast cancer.
9. APRD00100 Aprepitant C23H21F7N4O3
For the prevention of nausea and vomiting associated with highly emetogenic cancer chemotherapy, including high- dose cisplatin (in combination with other antiemetic agents).
Animal and human Positron Emission Tomography (PET) studies with Aprepitant have shown that it crosses the blood brain barrier and occupies brain NK1 receptors. Animal and human studies show that Aprepitant augments the
antiemetic activity of the 5- HT3-receptor antagonist ondansetron and the corticosteroid ethasone and inhibits both the acute and delayed phases of cisplatin induced emesis.
10. APRD00101 Vinorelbine C45H54N4O8 For the treatment of non-small- cell lung carcinoma
11. APRD00115 Chlorambucil C14H19Cl2NO2
For treatment of chronic lymphatic (lymphocytic) leukemia, malignant lymphomas including
lymphosarcoma, giant follicular lymphoma, and Hodgkin's disease. Chlorambucil is an antineoplastic in the class of alkylating agents and is used to treat various forms of cancer.
12. APRD00117 Hesperetin C16H14O6
For lowering cholesterol and, possibly, otherwise favorably affecting lipids. In vitro research also suggests the possibility that hesperetin might have some anticancer effects and that it might have some anti-aromatase activity, as well as activity again.
13. APRD00118 Melphalan C13H18Cl2N2O2
For the palliative treatment of multiple myeloma and for the palliation of non-resectable epithelial carcinoma of the ovary.
14. APRD00123 Tamoxifen C26H29NO For the treatment of breast cancer.
15. APRD00124 Dactinomycin C62H86N12O16
For the treatment of Wilms' tumor, childhood
rhabdomyosarcoma, Ewing's sarcoma and metastatic, nonseminomatous testicular cancer as part of a combination chemotherapy and/or multi- modality treatment regimen
16. APRD00125 Venlafaxine C17H27NO2
For the treatment of severe depression. It is used to treat melancholia, generalized anxiety disorder (GAD), panic disorder, post-traumatic stress disorder, and hot flashes in breast cancer survivors.
17. APRD00144 Exemestane C20H24O2
For the treatment of advanced breast cancer in
postmenopausal women whose disease has progressed following tamoxifen therapy.
18. APRD00150 Nilutamide C12H10F3N3O4
For use in combination with surgical castration for the treatment of metastatic prostate cancer (Stage D2)
19. APRD00174 Clonidine C9H9Cl2N3 Clonidine is an antihypertensive
agent and an epidural agent for refractory cancer pain.
20. APRD00201 Gemcitabine C9H11F2N3O4
For the first-line treatment of patients with metastatic breast cancer, locally advanced (Stage IIIA or IIIB), or metastatic (Stage IV) non-small cell lung cancer and as first-line treatment for patients with adenocarcinoma of the pancreas.
21. APRD00202 Pentostatin C11H16N4O4
For the treatment of hairy cell leukaemia refractory to alpha interferon.
22. APRD00203 Capecitabine C15H22FN3O6
For the treatment of patients with metastatic breast cancer resistant to both paclitaxel and an anthracycline-containing chemotherapy regimen.
23. APRD00209 Streptozocin C8H15N3O7
For the treatment of malignant neoplasms of pancreas (metastatic islet cell carcinoma).
24. APRD00239 Etoposide C29H32O13
For use in combination with other chemotherapeutic agents in the treatment of refractory testicular tumors and as first line treatment in patients with small cell lung cancer. Also used to treat other malignancies such as lymphoma, non- lymphocytic leukemia, and glioblastoma multiforme.
25. APRD00246 Calcitriol C27H44O3
Calcitriol has been found to induce differentiation and/or inhibit cell proliferation in a number of malignant cell lines including human prostate cancer cells.
26. APRD00249 Mechlorethamine C5H11Cl2N
For the palliative treatment of Hodgkin's disease (Stages III and IV), lymphosarcoma, chronic myelocytic or chronic lymphocytic leukemia, polycythemia vera, mycosis fungoides, and bronchogenic carcinoma. Also for the palliative treatment of
metastatic carcinoma resulting in effusion.
27. APRD00255 Orlistat C29H53NO5
In the March 15, 2004 issue of Cancer Research, [1] Steven J.
Kridel et al. state that orlistat may also inhibit growth of prostate cancer, and in theory may be useful in treating other cancers, by interfering with the metabolism of fats.
28. APRD00259 Paclitaxel C47H51NO14 Used in the treatment of Kaposi's sarcoma and cancer of
the lung, ovarian, and breast.
29. APRD00260 Cladribine C10H12ClN5O3
For the treatment of active hairy cell leukemia (leukemic
reticuloendotheliosis) as defined by clinically significant anemia, neutropenia, thrombocytopenia, or disease-related symptoms.
30. APRD00268 Trimetrexate C19H23N5O3
For use, with concurrent leucovorin administration (leucovorin protection), as an alternative therapy for the treatment of moderate-to-severe Pneumocystis carinii
pneumonia (PCP) in
immunocompromised patients, including patients with the acquired immunodeficiency syndrome (AIDS). Also used to treat several types of cancer including colon cancer.
31. APRD00292 Lomustine C9H16ClN3O2
Indicated primarily for the treatment of brain tumours.
Also for the treatment of breast cancer, Hodgkin's disease, lung cancer, malignant melanoma, multiple myeloma, Non- Hodgkin's lymphomas, ovarian cancer, pancreatic cancer, and renal cell cancer.
32. APRD00347 Fentanyl C22H28N2O
For the treatment of cancer patients with severe pain that breaks through their regular narcotic therapy.
33. APRD00351 Palonosetron C19H24N2O For the treatment of nausea and vomiting associated with cancer chemotherapy.
34. APRD00359 Cisplatin Cl2H4N2Pt
For the treatment of metastatic testicular tumors, metastatic ovarian tumors and advanced bladder cancer.
35. APRD00361 Epirubicin C27H29NO11
For use as a component of adjuvant therapy in patients with evidence of axillary node tumor involvement following resection of primary breast cancer
36. APRD00362 Tretinoin C20H28O2
For the induction of remission in patients with acute
promyelocytic leukemia (APL), French-American-British (FAB) classification M3 (including the M3 variant); For the topical treatment of acne vulgaris, flat warts and other skin conditions (psoriasis, ichthyosis congenita, icthyosis vulgaris, lamellar icthyosis, keratosis palmaris et
plantaris, epidermolytic hyperkeratosis, senile comedones, senile keratosis, keratosis follicularis (Darier's disease), and basal cell carcinomas.); For palliative therapy to improve fine wrinkling, mottled
hyperpigmentation, roughness associated with photodamage.
37. APRD00364 Paroxetine C19H20FNO3
It is used to treat depression resistant to other
antidepressants, depression complicated by anxiety, panic disorder, social and general anxiety disorder, obsessive- compulsive disorder (OCD), premenstrual dysphoric disorder, premature ejaculation, and hot flashes of menopause in women with breast cancer.
38. APRD00391 Toremifene C26H28ClNO
For the treatment of metastatic breast cancer in
postmenopausal women with estrogen receptor-positive or receptor-unknown tumors 39. APRD00392 Vindesine C43H55N5O7
For the treatment of acute leukaemia, malignant
lymphoma, Hodgkin's disease, acute erythraemia and acute panmyelosis
40. APRD00396 Conjugated Estrogens C18H21NaO5S
For the treatment of moderate to severe vasomotor symptoms associated with the menopause, atrophic vaginitis, osteoporosis, hypoestrogenism due to hypogonadism, castration, primary ovarian failure, breast cancer (for palliation only), and Advanced androgen-dependent carcinoma of the prostate (for palliation only)
41. APRD00400 Raloxifene C28H27NO4S
Raloxifene is used in the prevention of postmenopausal osteoporosis and breast cancer.
42. APRD00408 Cyclophosphamide C7H15Cl2N2O2P
For management of malignant lymphomas, multiple
myeloma,leukemias, mycosis fungoides (advanced disease), neuroblastoma (disseminated disease), adenocarcinoma of the ovary, retinoblastoma and carcinoma of the breast.
43. APRD00430 Raltitrexed C21H22N4O6S For the treatment of malignant neoplasm of colon and rectum 44. APRD00433 Testosterone C19H28O2
Testosterone is an
antineoplastic hormonal agent primarily used in the treatment of prostate cancer.
45. APRD00466 Carboplatin C6H12N2O4Pt2 For the initial treatment of
advanced ovarian carcinoma in established combination with other approved
chemotherapeutic agents. One established combination regimen consists of PARAPLATIN and cyclophosphamide.
46. APRD00481 Ondansetron C18H19N3O
Ondansetron is an antinauseant and antiemetic agent indicated for the prevention of nausea and vomiting associated with moderately-emetogenic cancer chemotherapy and for the prevention of postoperative nausea and vomiting.
47. APRD00495 Vincristine C46H56N4O10
For treatment of acute leukaemia, malignant
lymphoma, Hodgkin's disease, acute erythraemia, acute panmyelosis
48. APRD00516 Fluorouracil C4H3FN2O2
For the topical treatment of multiple actinic or solar keratoses. In the 5% strength it is also useful in the treatment of superficial basal cell
carcinomas when conventional methods are impractical, such as with multiple lesions or difficult treatment sites.
Fluorouracil injection is indicated in the palliative management of some types of cancer, including colon, rectum, breast, stomach and pancrease.
49. APRD00518 Dolasetron C19H20N2O3
For the prevention of nausea and vomiting associated with moderately-emetogenic cancer chemotherapy, including initial and repeat courses and
prevention of postoperative nausea and vomiting 50. APRD00559 Marimastat C15H29N3O5 For the treatment of various
cancers
51. APRD00571 Marinol C21H30O2
For the treatment of anorexia associated with weight loss in patients with AIDS, and nausea and vomiting associated with cancer chemotherapy in patients who have failed to respond adequately to conventional antiemetic treatments
52. APRD00573 Pemetrexed C20H21N5O6
For the treatment of malignant pleural mesothelioma and locally advanced or metastatic non-small cell lung cancer (NSCLC) after prior chemotherapy
53. APRD00579 Irinotecan C33H38N4O6 For the treatment of metastatic
colorectal cancer (first-line therapy when administered with 5-fluorouracil and leucovorin).
54. APRD00594 Fludarabine C10H13FN5O7P
For the treatment of adult patients with B-cell chronic lymphocytic leukemia (CLL) who have not responded to or whose disease has progressed during treatment with at least one standard alkylating-agent containing regimen
55. APRD00627 Medroxyprogesterone C22H32O3
Used as a contraceptive and to treat amenorrhea, abnormal uterine bleeding, endometriosis, endometrial and renal cell carcinomas, and pulmonary disorders such as chronic obstructive pulmonary disease (COPD), Pickwickian syndrome, and other hypercapnic pulmonary conditions.
56. APRD00640 Testolactone C19H24O3
For palliative treatment of advanced breast cancer in postmenopausal women.
57. APRD00652 Altretamine C9H18N6
For use as a single agent in the palliative treatment of patients with persistent or recurrent ovarian cancer following first- line therapy with a cisplatin and/or alkylating agent-based combination.
58. APRD00654 Fulvestrant C32H47F5O3S
For the treatment of hormone receptor positive metastatic breast cancer in
postmenopausal women with disease progression following antiestrogen therapy.
59. APRD00662 Valrubicin C34H36F3NO13 Bladder cancer
60. APRD00664 Busulfan C6H14O6S2
For use in combination with cyclophosphamide as a conditioning regimen prior to allogeneic hematopoietic progenitor cell transplantation for chronic myelogenous leukemia.
61. APRD00687 Topotecan C23H23N3O5
For the treatment of metastatic carcinoma of the ovary and small cell lung cancer following the failure of first-line
chemotherapy.
62. APRD00691 Ethinyl Estradiol C20H24O2
For treatment of moderate to severe vasomotor symptoms associated with the menopause, female hypogonadism, prostatic carcinoma-palliative therapy of advanced disease, breast cancer, as an oral contraceptive, and as emergency
contraceptive.
63. APRD00695 Procarbazine C12H19N3O
For use with other anticancer drugs for the treatment of stage III and stage IV Hodgkin's disease.
64. APRD00698 Leucovorin C20H23N7O7
For the treatment of
osteosarcoma (after high dose methotrexate therapy). Used to diminish the toxicity and counteract the effects of impaired methotrexate elimination and of inadvertent overdosages of folic acid antagonists, and to treat megaloblastic anemias due to folic acid deficiency. Also used in combination with 5-
fluorouracil to prolong survival in the palliative treatment of patients with advanced colorectal cancer.
65. APRD00703 Cerulenin C12H17NO3
Inhibition of FAS by cerulenin leads to cytotoxicity and apoptosis in human cancer cell lines, an effect believed to be mediated by the accumulation of malonyl-coenzyme A in cells with an upregulated FAS pathway.
66. APRD00708 Vinblastine C46H58N4O9
For treatment of breast cancer, testicular cancer, lymphomas, neuroblastoma, Hodgkin's and non-Hodgkin's lymphomas, mycosis fungoides, histiocytosis, and Kaposi's sarcoma.
67. APRD00715 Chlorotrianisene C23H21ClO3
Used to treat symptoms of menopause, deficiencies in ovary function (including underdevelopment of female sexual characteristics and some types of infertility), and in rare cases, prostate cancer.
68. APRD00809 Azacitidine C8H12N4O5
The cytotoxic effects of azacitidine cause the death of rapidly dividing cells, including cancer cells that are no longer responsive to normal growth control mechanisms. Non- proliferating cells are relatively insensitive to azacitidine.
69. APRD00828 Bortezomib C19H25BN4O4
For treatment of multiple myeloma in patients who have not been successfully treated with at least two previous therapies.
70. APRD00878 Clofarabine C10H11ClFN5O3
For the treatment of pediatric patients 1 to 21 years old with relapsed or refractory acute lymphoblastic leukemia after at least two prior regimens.
71. APRD00920 Diethylstilbestrol C18H20O2
Used in the treatment of prostate cancer. Previously used in the prevention of miscarriage or premature delivery in pregnant women prone to miscarriage or premature delivery.
72. APRD00932 Docetaxel C43H53NO14
For the treatment of patients with locally advanced or metastatic breast cancer after failure of prior chemotherapy.
73. APRD00938 Dromostanolone C23H36O3
For use in females, for palliation of
androgenresponsive recurrent mammary cancer in women who are more than one year but less than five years
postmenopausal.
74. APRD00951 Erlotinib C22H23N3O4
For the treatment of patients with locally advanced or metastatic non-small cell lung cancer after failure of at least one prior chemotherapy regimen.
75. APRD00981 Fluoxymesterone C20H29FO3
In males, used as replacement therapy in conditions associated with symptoms of deficiency or absence of endogenous
testosterone. In females, for palliation of
androgenresponsive recurrent mammary cancer in women who are more than one year but less than five years
postmenopausal.
76. APRD00984 Flutamide C11H11F3N2O3
For the management of locally confined Stage B2-C and Stage D2 metastatic carcinoma of the prostate
77. APRD00997 Gefitinib C22H24ClFN4O3
For the continued treatment of patients with locally advanced or metastatic non-small cell lung cancer after failure of either platinum-based or docetaxel chemotherapies.
78. APRD01002 Granisetron C18H24N4O
For the prevention of: nausea and vomiting associated with initial and repeat courses of emetogenic cancer therapy, including high-dose cisplatin.
79. APRD01021 Hydromorphone C17H19NO3
For the relief of moderate to severe pain such as that due to surgery, cancer, trauma/injury, burns, myocardial infarction and colic.
80. APRD01030 Imiquimod C14H16N4
Imiquimod can be used to treat certain types of skin cancer called superficial basal cell carcinoma.
81. APRD01066 Letrozole C17H11N5 For the extended adjuvant
treatment of early breast cancer in postmenopausal women who have received 5 years of adjuvant tamoxifen therapy.
Also for first-line treatment of postmenopausal women with hormone receptor positive or hormone receptor unknown locally advanced or metastatic breast cancer. Also indicated for the treatment of advanced breast cancer in
postmenopausal women with disease progression following antiestrogen therapy.
82. APRD01067 Levamisole C11H12N2S
For adjuvant treatment in combination with fluorouracil after surgical resection in patients with Dukes' stage C colon cancer. Also used to treat malignant melanoma and head/neck cancer.
83. APRD01084 Masoprocol C18H22O4
Used for the treatment of actinic keratoses (precancerous skin growths that can become malignant if left untreated).
84. APRD01092 Megestrol C22H30O3
For the treatment of anorexia, cachexia, or an unexplained, significant weight loss in patients with a diagnosis of acquired immunodeficiency syndrome (AIDS). Also used to treat breast cancer, endometrial cancer, and prostate cancer in Canada and some other countries.
85. APRD01127 Nabilone C24H36O3
Used for the control of nausea and vomiting, caused by chemotherapeutic agents used in the treatment of cancer, in patients who have failed to respond adequately to conventional antiemetic treatments.
86. APRD01161 Pamidronate C3H11NO7P2
For the treatment of moderate or severe hypercalcemia associated with malignancy.
87. APRD01246 Tazarotene C21H21NO2S
Tazarotene is associated with a significant reduction in atypical melanocytes and keratocytes - cells considered to be
precursors of skin cancer.
88. APRD01294 Zoledronate C5H10N2O7P2
For the treatment of
hypercalcemia of malignancy.
Also for the treatment of patients with multiple myeloma and patients with documented bone metastases from solid tumors, in conjunction with standard antineoplastic therapy.
89. APRD01304 Sorafenib C21H16ClF3N4O3
Anticancer Agent. For the treatment of patients with advanced renal cell carcinoma.
90. EXPT00120 1,6-Fructose Diphosphate
(Linear Form) C6H14O12P2 The drug target of this drug is Lung cancer antigen NY-LU-1.
Non Anticancer dataset (90 molecules):
Serial Number
Accession I.D. of
DrugBank Name of the molecule Molecular Formula
Description / Property / Usage (Taken from DrugBank)
1. EXPT00370 Adenosine‐3'‐5'‐Diphosphate C10H15N5O10P2
Mediates the metabolic activation of
carcinogenic N- hydroxyarylamines to DNA binding products and could so participate as modulating factor of cancer risk
2. APRD00880 Clomifene C26H28ClNO
Clomifene can lead to multiple ovulation, and hence increasing the risk of twins. In comparison to purified FSH, the rate of ovarian
hyperstimulation syndrome is low. There may be an increased risk of ovarian cancer, and weight gain.
3. APRD00263 Ganciclovir C9H13N5O4 Suspected cancer agent.
4. APRD00438 Sulfanilamide C6H8N2O2S
Side effects include itching, burning, skin rash, redness, swelling, or other sign of irritation not present before use of this medicine and long- term use of sulfonamides may cause cancer of the thyroid gland.
5. EXPT01291 1, 4‐Dithiothreitol C4H10O2S2
Its target induces apoptosis in cancer cells.
6. APRD00924 Dimenhydrinate C24H28ClN5O3
Dimenhydrinate is an antiemetics drug combination that contains
diphenhydramine and theophylline. It is not effective in the
treatment of nausea associated with cancer chemotherapy.
7. APRD00738 Ethanol C2H6O
For therapeutic neurolysis of nerves or ganglia for the relief of intractable chronic pain in such conditions as inoperable cancer and trigeminal neuralgia (tic douloureux), in patients for whom neurosurgical procedures are contraindicated.
8. EXPT01171 Diisopropylphosphono Group C6H14O3P1 Complement Factor B inhibitor
9. EXPT01172 5‐Deoxyflavanone C15H12O4 Chalcone--Flavonone Isomerase 1 inhibitor 10. EXPT01174 2‐Deoxy‐Glucitol‐6‐Phosphate C6H15O8P1
Myo-Inositol-1- Phosphate Synthase inhibitor
11. EXPT01175 D‐Glucuronic Acid C6H8O Chondroitinase Ac & B inhibitor
12. EXPT01176 Digalactosyl Diacyl Glycerol (Dgdg)
C51H96O15
Chlorophyll A-B Binding Protein, Chloroplast inhibitor
13. EXPT01177
1‐[Glycerolylphosphonyl]‐2‐[8‐
(2‐Hexyl‐Cyclopropyl)‐Octanal‐
1‐Yl]‐
3‐[Hexadecanal‐1‐Yl]‐Glycerol
C39H75O10P1 Flavohemoprotein inhibitor
14. EXPT01178 (2r)‐Amino(4‐
Hydroxyphenyl)Acetic Acid
C8H9N1O3 Feglymycin inhibitor
15. EXPT01179 2'‐Deoxyguanosine‐5'‐
Diphosphate
C10H15N5O10P2
Nucleoside
Diphosphate Kinase II inhibitor
16. EXPT01180 D‐Glutamic Acid C5H9N1O4 Thermolysin inhibitor 17. EXPT01181 D‐Glutamine C5H10N2O3 Glutamate Racemase
inhibitor 18. EXPT01182 2'‐Deoxyguanosine‐5'‐
Monophosphate
C10H14N5O7P1 Rc-Rnase6
Ribonuclease inhibitor 19. EXPT01183 3,6‐Anhydro‐D‐Galactose‐2‐
Sulfate
C6H10O8S1 Iota-Carrageenase inhibitor
20. EXPT01184 2'‐Deoxyguanosine‐5'‐
Triphosphate
C10H16N5O13P3
Nucleoside
Diphosphate Kinase II inhibitor
21. EXPT01185 (2s,3s)‐Trans‐Dihydroquercetin C15H12O7 Leucoanthocyanidin Dioxygenase inhibitor
22. EXPT01186 2,3‐Didehydroalanine C3H5N1O2 Lantibiotic Mersacidin inhibitor
23. EXPT01187 3,4‐Dihydroxybenzoic Acid C7H6O4 Lipoxygenase-3 inhibitor
24. EXPT01188 3,4‐Dihydroxycinnamic Acid C9H8O4 Photoactive Yellow Protein inhibitor 25. EXPT01189 Heme D C34H32N4O10Fe1 Nitrite Reductase
inhibitor 26. EXPT01190 Dihydrofolic Acid C19H21N7O6 Dihydrofolate
Reductase inhibitor 27. EXPT01191 3‐Dehydroshikimate C7H10O5 3-Dehydroquinate
Dehydratase inhibitor 28. EXPT01192 2,6‐Dimethyl‐7‐Octen‐2‐Ol C10H20O1 Odorant-Binding
Protein inhibitor 29. EXPT01193 5‐Hydroxy Norvaline C5H11N1O3
Sst1-Selective Somatosatin Analog inhibitor
30. EXPT01194 Deoxycholic Acid C24H40O4 Major Pollen Allergen Bet V 1-L inhibitor 31. EXPT01195 3‐Decyl‐2,5‐Dioxo‐4‐Hydroxy‐3‐
Pyrroline
C14H23N1O3 Glycolate Oxidase inhibitor
32. EXPT01196 3,4‐Dihydro‐5‐Methyl‐
Isoquinolinone
C10H11N1O1 Poly inhibitor
33. EXPT01197 (2s)‐Hydroxy(4‐
Hydroxyphenyl)Ethanenitrile
C8H7N1O2 Beta-Glucosidase inhibitor
34. EXPT01198 3‐Amino‐4,5‐Dihydroxy‐
Cyclohex‐1‐Enecarboxylate
C7H10N1O41
3-Dehydroquinate Dehydratase Arod inhibitor
35. EXPT01199 Dihydrotestosterone C19H30O2 Sex Hormone-Binding Globulin inhibitor 36. EXPT01200 2‐(3,4‐Dihydroxyphenyl)Acetic
Acid
C8H8O4
Homoprotocatechuate 2,3-Dioxygenase inhibitor
37. EXPT01201 Octamethylenediamine C8H20N2 Polyamine Oxidase inhibitor
38. EXPT01202 3,4‐Dichloroisocoumarin C9H4O2Cl2 Factor D inhibitor
39. EXPT01203 4,4'[1,6‐Hexanediylbis(Oxy)]
Bisbenzenecarboximidamide
C20H26N4O2
Transcriptional Regulator Qacr inhibitor 40. EXPT01205 2,5‐Dideoxy‐2,5‐Imino‐D‐
Glucitol
C6H13N1O4 D-Xylose Isomerase inhibitor
41. EXPT01206
4'‐Deaza‐1'‐Aza‐2'‐Deoxy‐1'‐(9‐
Methylene)‐Immucillin‐H, (3r,4r)‐N‐[9‐Deazahypoxanthin‐
9‐Yl)Methyl]‐4‐Hydroxymethyl‐
C12H19N4O31+ Purine Nucleoside Phosphorylase inhibitor
Pyrrolidin‐3‐Ol
42. EXPT01207 Methylphosphonic Acid Diisopropyl Ester
C7H17O3P1 Parathion Hydrolase inhibitor
43. EXPT01208 1,4‐Diethylene Dioxide C4H8O2 Epsin inhibitor 44. EXPT01209 Dinor‐N(Omega)‐Hydroxy‐L‐
Arginine
C4H10N4O3 Arginase 1 inhibitor 45. EXPT01210 Disordered Solvent H2O1 Alpha-1-Purothionin
inhibitor
46. EXPT01211 D‐Isovaline C5H11N1O2 Antiamoebin I inhibitor 47. EXPT01212 Dcka, 5,7‐Dichlorokynurenic
Acid
C10H5N1O3Cl2
N-Methyl-D-Aspartate Receptor Subunit 1 inhibitor
48. EXPT01213 Decanoic Acid C10H20O2 Daptomycin inhibitor
49. EXPT01214
4‐[2‐(3‐
Benzyloxycarbonylamino‐4‐
Cyclohexyl‐1‐Hydroxy‐2‐Oxo‐
Butylamino)‐5‐Guanidino‐
Pentanoylamino]‐4‐(1‐Carboxy‐
2‐Cyclohexyl‐Ethylcarbamoyl)‐
Butyric Acid
C38H57N7O10 Tricorn Protease inhibitor
50. EXPT01215 D‐Lactic Acid C3H6O3 2-Haloacid
Dehalogenase inhibitor 51. EXPT01216 D‐Leucine C6H13N1O2 Gramicidin A inhibitor 52. EXPT01217 2‐Hexyloxy‐6‐Hydroxymethyl‐
Tetrahydro‐Pyran‐3,5‐Diol
C12H24O5
Histo-Blood Group Abo System
Transferase inhibitor 53. EXPT01218 Di‐Linoleoyl‐3‐Sn‐
Phosphatidylcholine
C44H80N1O8P1
Phosphatidylcholine Transfer Protein inhibitor 54. EXPT01219 D‐Lysine C6H14N2O2
Catabolic Alanine Racemase Dadx inhibitor
55. EXPT01221 Dimethylallyl Diphosphate C5H12O7P2 Farnesyl Diphosphate Synthase inhibitor 56. EXPT01222 5,6‐Dimethylbenzimidazole C9H10N2
Nicotinate
Mononucleotide:5,6- Dimethylbenzi inhibitor
57. EXPT01224 Dimethylformamide C3H7N1O1 Elastase inhibitor 58. EXPT01225 Dimethylglycine C4H9N1O2 Sarcosine Oxidase
inhibitor 59. EXPT01226 2,3‐Dimethylimidazolium Ion C5H9N21+ Cytochrome C
Peroxidase inhibitor 60. EXPT01227 1‐Deoxymannojirimycin C6H13N1O4
Mannosyl-
Oligosaccharide Alpha- 1,2-Mannosida
inhibitor
61. EXPT01228 Terminal Dimethyl C2H6 Lysozyme inhibitor 62. EXPT01229 Alpha‐Difluoromethylornithine C6H12N2O2F2
Ornithine Decarboxylase inhibitor 63. EXPT01230 Dmp450(Inhibitor of Dupont
Merck)
C33H38N4O3 Hiv-1 Protease inhibitor
64. EXPT01231 Dimethyl Sulfoxide C2H6O1S1 Four-Helix Bundle Model inhibitor 65. EXPT01232 2,3‐Dihydroxy‐Valerianic Acid C6H12O4
Acetohydroxy-Acid Isomeroreductase inhibitor
66. EXPT01233 3,5‐Dinitrocatechol C6H4N2O6
Catechol O- Methyltransferase inhibitor
67. EXPT01234 Deamido‐Nad+ C21H27N6O15P21+ Nh inhibitor 68. EXPT01235 2,4‐Dinitrophenol C6H4N2O5
Pentaerythritol Tetranitrate Reductase inhibitor
69. EXPT01236 1‐Deoxy‐Nojirimycin C6H13N1O4 D-Xylose Isomerase inhibitor
70. EXPT01237 7,8‐Diamino‐Nonanoic Acid C9H20N2O2 Dethiobiotin Synthetase inhibitor 71. EXPT01238 3‐Amino‐Alanine C3H9N2O21+ Edap : Ace-Ile-Trp-
Glu-Ser-Gly-Lys-Leu- Il inhibitor
72. EXPT01239 Dnqx C8H2N4O6 Glutamate Receptor 2 inhibitor
73. EXPT01240 2‐Amino‐6‐Oxo‐Hexanoic Acid C6H11N1O3 Glutaminase-
Asparaginase inhibitor 74. EXPT01241 2,4‐Dihydroxybenzoic Acid C7H6O4 P-Hydroxybenzoate
Hydroxylase inhibitor 75. EXPT01242 2',3'‐Dideoxycytidine‐5'‐
Monophosphate
C9H14N3O6P1 Cytidylate Kinase inhibitor
76. EXPT01244
4‐(3,12,14‐Trihydroxy‐10,13‐
Dimethyl‐Hexadecahydro‐
Cyclopenta[a]Phenanthren‐17‐
Yl)‐5h‐Furan‐2‐One
C23H34O5 Diga16 inhibitor
77. EXPT01245 Beta‐Hydroxy Aspartic Acid C4H7N1O5 Coagulation Factor X inhibitor
78. EXPT01246 Dalfopristin C34H50N4O9S1
Streptogramin A Acetyltransferase inhibitor
79. EXPT01247 2'‐Deoxymaltose C12H22O10 Beta-Amylase inhibitor 80. EXPT01248 Domoic Acid C15H21N1O6
Glutamate Receptor, Ionotropic Kainate 2 inhibitor
81. EXPT01249 Dihydroorotic Acid C5H6N2O4 Dihydroorotase inhibitor 82. EXPT01250 Delta‐Bis(2,2'‐
Bipyridine)Imidazole Osmium (Ii)
C23H20N6Os12+ Azurin inhibitor
83. EXPT01252 L‐N(Omega)‐Nitroarginine‐2,4‐
L‐Diaminobutyric Amide
C10H22N8O4 Nitric-Oxide Synthase, Endothelial inhibitor
84. EXPT01253 N‐{(4s)‐4‐Amino‐5‐[(2‐
Aminoethyl)Amino]Pentyl}‐N'‐
Nitroguanidine
C8H21N7O2 Nitric-Oxide Synthase, Endothelial inhibitor
85. EXPT01254 L‐N(Omega)‐Nitroarginine‐(4r)‐
Amino‐L‐Proline Amide
C11H22N8O4 Nitric-Oxide Synthase, Endothelial inhibitor 86. EXPT01255 Dpb‐T C17H19N2O8P1 5 inhibitor 87. EXPT01256 Dipyrromethane Cofactor C20H24N2O8 Porphobilinogen
Deaminase inhibitor
88. EXPT01257 D‐Phenylalanine C9H11N1O2 Sandostatin inhibitor
89. EXPT01258 Diphosphate O7P24- Nh inhibitor
90. EXPT01259 D‐Proline C5H9N1O2
Tetrameric Beta-Beta- Alpha Mini-Protein inhibitor