-
Notifications
You must be signed in to change notification settings - Fork 4
/
paper.bib
executable file
·1423 lines (1306 loc) · 72 KB
/
paper.bib
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
%% This BibTeX bibliography file was created using BibDesk.
%% http://bibdesk.sourceforge.net/
%% Created for Rajarshi Guha at 2011-11-13 13:07:25 -0500
%% Saved with string encoding Unicode (UTF-8)
@article{Breiman:2001fk,
Abstract = {There are two cultures in the use of statistical modeling to reach conclusions from data. One assumes that the data are generated by a given stochastic data model. The other uses algorithmic models and treats the data mechanism as unknown. The statistical community has been committed to the almost exclusive use of data models. This commitment has led to irrelevant theory, questionable conclusions, and has kept statisticians from working on a large range of interesting current problems. Algorithmic modeling, both in theory and practice, has developed rapidly in fields outside statistics. It can be used both on large complex data sets and as a more accurate and informative alternative to data modeling on smaller data sets. If our goal as a field is to use data to solve problems, then we need to move away from exclusive dependence on data models and adopt a more diverse set of tools.},
Address = {PO BOX 22718, BEACHWOOD, OH 44122 USA},
Author = {Breiman, L.},
Date-Added = {2011-11-13 13:02:03 -0500},
Date-Modified = {2011-11-13 13:02:15 -0500},
Isi = {000172846900001},
Isi-Recid = {122894188},
Isi-Ref-Recids = {102145400 122894189 122894190 56736490 109253157 121151946 122894191 96837512 99456757 53594983 117012006 19083140 107900004 48805179 115824930 112797231 122894192 63657561 98926502 122894194 78680696 103022545 122894195 116875000 74359540 106547635 51858425 103227721 25149426 89931393 34950196 68883566 25791531 110445963 100643948 74459143 115084391},
Journal = {Stat.~Sci.},
Month = aug,
Number = {3},
Pages = {199--215},
Publisher = {INST MATHEMATICAL STATISTICS},
Times-Cited = {247},
Title = {Statistical modeling: {T}he two cultures},
Volume = {16},
Year = {2001},
Bdsk-Url-1 = {http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS&DestLinkType=FullRecord;KeyUT=000172846900001}}
@article{Kind:2010zr,
Abstract = {The structural elucidation of small molecules using mass spectrometry plays an important role in modern life sciences and bioanalytical approaches. This review covers different soft and hard ionization techniques and figures of merit for modern mass spectrometers, such as mass resolving power, mass accuracy, isotopic abundance accuracy, accurate mass multiple-stage MS(n) capability, as well as hybrid mass spectrometric and orthogonal chromatographic approaches. The latter part discusses mass spectral data handling strategies, which includes background and noise subtraction, adduct formation and detection, charge state determination, accurate mass measurements, elemental composition determinations, and complex data-dependent setups with ion maps and ion trees. The importance of mass spectral library search algorithms for tandem mass spectra and multiple-stage MS(n) mass spectra as well as mass spectral tree libraries that combine multiple-stage mass spectra are outlined. The successive chapter discusses mass spectral fragmentation pathways, biotransformation reactions and drug metabolism studies, the mass spectral simulation and generation of in silico mass spectra, expert systems for mass spectral interpretation, and the use of computational chemistry to explain gas-phase phenomena. A single chapter discusses data handling for hyphenated approaches including mass spectral deconvolution for clean mass spectra, cheminformatics approaches and structure retention relationships, and retention index predictions for gas and liquid chromatography. The last section reviews the current state of electronic data sharing of mass spectra and discusses the importance of software development for the advancement of structure elucidation of small molecules. ELECTRONIC SUPPLEMENTARY MATERIAL: The online version of this article (doi:10.1007/s12566-010-0015-9) contains supplementary material, which is available to authorized users.},
Author = {Kind, Tobias and Fiehn, Oliver},
Date-Added = {2011-11-13 11:17:54 -0500},
Date-Modified = {2011-11-13 11:18:03 -0500},
Doi = {10.1007/s12566-010-0015-9},
Journal = {Bioanal.~Rev.},
Journal-Full = {Bioanalytical reviews},
Month = {Dec},
Number = {1-4},
Pages = {23-60},
Pmc = {PMC3015162},
Pmid = {21289855},
Pst = {ppublish},
Title = {Advances in structure elucidation of small molecules using mass spectrometry},
Volume = {2},
Year = {2010},
Bdsk-Url-1 = {http://dx.doi.org/10.1007/s12566-010-0015-9}}
@article{glaxo-malaria,
Abstract = {Malaria is a devastating infection caused by protozoa of the genus Plasmodium. Drug resistance is widespread, no new chemical class of antimalarials has been introduced into clinical practice since 1996 and there is a recent rise of parasite strains with reduced sensitivity to the newest drugs. We screened nearly 2 million compounds in GlaxoSmithKline's chemical library for inhibitors of P. falciparum, of which 13,533 were confirmed to inhibit parasite growth by at least 80\% at 2 microM concentration. More than 8,000 also showed potent activity against the multidrug resistant strain Dd2. Most (82\%) compounds originate from internal company projects and are new to the malaria community. Analyses using historic assay data suggest several novel mechanisms of antimalarial action, such as inhibition of protein kinases and host-pathogen interaction related targets. Chemical structures and associated data are hereby made public to encourage additional drug lead identification efforts and further research into this disease.},
Author = {Gamo, Francisco-Javier and Sanz, Laura M. and Vidal, Jaume and de Cozar, Cristina and Alvarez, Emilio and Lavandera, Jose-Luis and Vanderwall, Dana E. and Green, Darren V.S. and Kumar, Vinod and Hasan, Samiul and Brown, James R. and Peishoff, Catherine E. and Cardon, Lon R. and Garcia-Bustos, Jose F.},
Date-Added = {2011-11-13 11:13:22 -0500},
Date-Modified = {2011-11-13 11:13:58 -0500},
Doi = {10.1038/nature09107},
Journal = {Nature},
Journal-Full = {Nature},
Mesh = {Animals; Antimalarials; Cell Line, Tumor; Drug Discovery; Drug Resistance, Multiple; Humans; Malaria, Falciparum; Models, Biological; Phylogeny; Plasmodium falciparum; Small Molecule Libraries},
Month = {May},
Number = {7296},
Pages = {305--310},
Pmid = {20485427},
Pst = {ppublish},
Title = {Thousands of chemical starting points for antimalarial lead identification},
Volume = {465},
Year = {2010},
Bdsk-Url-1 = {http://dx.doi.org/10.1038/nature09107}}
@article{Barnard:1991vn,
Abstract = {The history of the development of computer systems for storage and retrieval of Markush structures is reviewed briefly. The systems currently being developed by Chemical Abstracts Service, Derwent Publications/Questel/INPI, and International Documentation Company for Chemistry (IDC) are introduced, and the similarities and differences between the approaches they use for input representation and search are examined, especially in relation to the handling of generic nomenclature, the prospects for future development of such systems is discussed in light of recent and continuing research work, as is the potential for exchange of Markush structure databases between the different search systems.},
Author = {Barnard, J.M.},
Date-Added = {2011-11-13 11:07:52 -0500},
Date-Modified = {2011-11-13 11:08:06 -0500},
Journal = {J.~Chem.~Inf.~Comput.~Sci.},
Journal-Full = {Journal of chemical information and computer sciences},
Mesh = {Computer Systems; Databases, Bibliographic; Drug Design; Molecular Structure; Patents as Topic},
Month = {Feb},
Number = {1},
Pages = {64--68},
Pmid = {2026663},
Pst = {ppublish},
Title = {A comparison of different approaches to Markush structure handling},
Volume = {31},
Year = {1991}}
@article{Masek:2008kx,
Abstract = {Studies to assess the risks of revealing chemical structures by sharing various chemical descriptor data are presented. Descriptors examined include "Lipinski-like" properties, 2D-BCUT descriptors, and a high-dimensional "fingerprint-like" descriptor (MACCs-vector). We demonstrate that unless sufficient precautions are taken, de novo design software such as EA-Inventor is able to derive a unique chemical structure or a set of closely related analogs from some commonly used descriptors. Based on the results of our studies, a set of guidelines or recommendations for safely sharing chemical information without revealing chemical structure is presented. A procedure for assessing the risk of revealing chemical structure when exchanging chemical descriptor information was also developed. The procedure is generic and can be applied to any chemical descriptor or combination of descriptors and to any set of structures to enable a decision about whether the exchange of information can be done without revealing the chemical structures.},
Author = {Masek, Brian B. and Shen, Lingling and Smith, Karl M. and Pearlman, Robert S.},
Date-Added = {2011-11-13 10:59:27 -0500},
Date-Modified = {2011-11-13 12:16:16 -0500},
Doi = {10.1021/ci600383v},
Journal = {J.~Chem.~Inf.~Model.},
Journal-Full = {Journal of chemical information and modeling},
Mesh = {Chemistry; Computer Security; Databases, Factual; Information Management; Information Storage and Retrieval; Molecular Structure; Software},
Month = {Feb},
Number = {2},
Pages = {256--261},
Pmid = {18254609},
Pst = {ppublish},
Title = {Sharing Chemical Information without Sharing Chemical tructure},
Volume = {48},
Year = {2008},
Bdsk-Url-1 = {http://dx.doi.org/10.1021/ci600383v}}
@article{Schneider:2005uq,
Abstract = {Ever since the first automated de novo design techniques were conceived only 15 years ago, the computer-based design of hit and lead structure candidates has emerged as a complementary approach to high-throughput screening. Although many challenges remain, de novo design supports drug discovery projects by generating novel pharmaceutically active agents with desired properties in a cost- and time-efficient manner. In this review, we outline the various design concepts and highlight current developments in computer-based de novo design.},
Author = {Schneider, Gisbert and Fechner, Uli},
Date-Added = {2011-11-13 10:52:38 -0500},
Date-Modified = {2011-11-13 10:52:54 -0500},
Doi = {10.1038/nrd1799},
Journal = {Nat.~Rev.~Drug Discov.},
Journal-Full = {Nature reviews. Drug discovery},
Mesh = {Computer-Aided Design; Drug Design; Models, Molecular; Technology, Pharmaceutical},
Month = {Aug},
Number = {8},
Pages = {649--663},
Pmid = {16056391},
Pst = {ppublish},
Title = {Computer-based de novo design of drug-like molecules},
Volume = {4},
Year = {2005},
Bdsk-Url-1 = {http://dx.doi.org/10.1038/nrd1799}}
@article{Brown:2006fk,
Abstract = {A workflow for the inverse quantitative structure-property relationship (QSPR) problem is reported in this paper for the de novo design of novel chemical entities (NCE) in silico through the application of existing QSPR models to calculate multiple objectives, including prediction confidence measures, to be optimized during the de novo design process. Two physical property datasets are applied as case studies of the inverse QSPR workflow (IQW): mean molecular polarizability and aqueous solubility. The case studies demonstrate the optimization of molecular structures to within a property range of interest; the optimized structures are then validated against QSPR models that are generated from sets of alternative descriptors to those used in the IQW. The paper concludes with a discussion of the results from the case studies.},
Author = {Brown, Nathan and McKay, Ben and Gasteiger, Johann},
Date-Added = {2011-11-13 10:50:22 -0500},
Date-Modified = {2011-11-13 10:50:48 -0500},
Doi = {10.1007/s10822-006-9063-1},
Journal = {J.~Comp.~Aid.~Molec.~Des.},
Journal-Full = {Journal of computer-aided molecular design},
Mesh = {Least-Squares Analysis; Models, Chemical; Quantitative Structure-Activity Relationship; Solubility},
Month = {May},
Number = {5},
Pages = {333--341},
Pmid = {17031542},
Pst = {ppublish},
Title = {A novel workflow for the inverse {QSPR} problem using multiobjective optimization},
Volume = {20},
Year = {2006},
Bdsk-Url-1 = {http://dx.doi.org/10.1007/s10822-006-9063-1}}
@article{Sayle:2009uq,
Abstract = {Chemical compound names remain the primary method for conveying molecular structures between chemists and researchers. In research articles, patents, chemical catalogues, government legislation, and textbooks, the use of IUPAC and traditional compound names is universal, despite efforts to introduce more machine-friendly representations such as identifiers and line notations. Fortunately, advances in computing power now allow chemical names to be parsed and generated (read and written) with almost the same ease as conventional connection tables. A significant complication, however, is that although the vast majority of chemistry uses English nomenclature, a significant fraction is in other languages. This complicates the task of filing and analyzing chemical patents, purchasing from compound vendors, and text mining research articles or Web pages. We describe some issues with manipulating chemical names in various languages, including British, American, German, Japanese, Chinese, Spanish, Swedish, Polish, and Hungarian, and describe the current state-of-the-art in software tools to simplify the process.},
Author = {Sayle, Roger},
Date-Added = {2011-11-12 19:52:14 -0500},
Date-Modified = {2011-11-12 19:52:42 -0500},
Doi = {10.1021/ci800243w},
Journal = {J.~Chem.~Inf.~Model.},
Journal-Full = {Journal of chemical information and modeling},
Month = {Mar},
Number = {3},
Pages = {519--530},
Pmc = {PMC2659868},
Pmid = {19239237},
Pst = {ppublish},
Title = {Foreign language translation of chemical nomenclature by computer},
Volume = {49},
Year = {2009},
Bdsk-Url-1 = {http://dx.doi.org/10.1021/ci800243w}}
@article{Jessop:2011fk,
Abstract = {ABSTRACT: The Open-Source Chemistry Analysis Routines (OSCAR) software, a toolkit for the recognition of named entities and data in chemistry publications, has been developed since 2002. Recent work has resulted in the separation of the core OSCAR functionality and its release as the OSCAR4 library. This library features a modular API (based on reduction of surface coupling) that permits client programmers to easily incorporate it into external applications. OSCAR4 offers a domain-independent architecture upon which chemistry specific text-mining tools can be built, and its development and usage are discussed.},
Author = {Jessop, David M. and Adams, Sam E. and Willighagen, Egon L. and Hawizy, Lezan and Murray-Rust, Peter},
Date-Added = {2011-11-12 19:50:16 -0500},
Date-Modified = {2011-11-12 19:50:48 -0500},
Doi = {10.1186/1758-2946-3-41},
Journal = {J.~Cheminf.},
Journal-Full = {Journal of cheminformatics},
Number = {1},
Pages = {41},
Pmc = {PMC3205045},
Pmid = {21999457},
Pst = {epublish},
Title = {{OSCAR4}: {A} flexible architecture for chemical text-mining},
Volume = {3},
Year = {2011},
Bdsk-Url-1 = {http://dx.doi.org/10.1186/1758-2946-3-41}}
@article{Oprea:2007fk,
Abstract = {The increasing availability of data related to genes, proteins and their modulation by small molecules has provided a vast amount of biological information leading to the emergence of systems biology and the broad use of simulation tools for data analysis. However, there is a critical need to develop cheminformatics tools that can integrate chemical knowledge with these biological databases and simulation approaches, with the goal of creating systems chemical biology.},
Author = {Oprea, Tudor I. and Tropsha, Alexander and Faulon, Jean-Loup and Rintoul, Mark D.},
Date-Added = {2011-11-11 23:11:36 -0500},
Date-Modified = {2011-11-11 23:11:56 -0500},
Doi = {10.1038/nchembio0807-447},
Journal = {Nat.~Chem.~Biol.},
Journal-Full = {Nature chemical biology},
Mesh = {Animals; Biological Assay; Cell Physiological Phenomena; Computational Biology; Databases, Factual; Drug Design; Genomics; Humans; Models, Chemical; Models, Molecular; Molecular Biology; Peptide Library; Proteomics; Research; Systems Biology},
Month = {Aug},
Number = {8},
Pages = {447--450},
Pmc = {PMC2734506},
Pmid = {17637771},
Pst = {ppublish},
Title = {Systems Chemical Biology},
Volume = {3},
Year = {2007},
Bdsk-Url-1 = {http://dx.doi.org/10.1038/nchembio0807-447}}
@article{Swamidass:2007ve,
Abstract = {Chemical fingerprints are used to represent chemical molecules by recording the presence or absence, or by counting the number of occurrences, of particular features or substructures, such as labeled paths in the 2D graph of bonds, of the corresponding molecule. These fingerprint vectors are used to search large databases of small molecules, currently containing millions of entries, using various similarity measures, such as the Tanimoto or Tversky's measures and their variants. Here, we derive simple bounds on these similarity measures and show how these bounds can be used to considerably reduce the subset of molecules that need to be searched. We consider both the case of single-molecule and multiple-molecule queries, as well as queries based on fixed similarity thresholds or aimed at retrieving the top K hits. We study the speedup as a function of query size and distribution, fingerprint length, similarity threshold, and database size |D| and derive analytical formulas that are in excellent agreement with empirical values. The theoretical considerations and experiments show that this approach can provide linear speedups of one or more orders of magnitude in the case of searches with a fixed threshold, and achieve sublinear speedups in the range of O(|D|0.6) for the top K hits in current large databases. This pruning approach yields subsecond search times across the 5 million compounds in the ChemDB database, without any loss of accuracy.},
Author = {Swamidass, S. Joshua and Baldi, Pierre},
Date = {2007 Mar-Apr},
Date-Added = {2011-11-10 11:53:37 -0500},
Date-Modified = {2011-11-10 11:53:49 -0500},
Doi = {10.1021/ci600358f},
Journal = {J.~Chem.~Inf.~Model.},
Journal-Full = {Journal of chemical information and modeling},
Mesh = {Algorithms; Computational Biology; Models, Chemical; Molecular Structure; Nonlinear Dynamics; Protein Binding; Receptors, Estrogen; Time Factors},
Number = {2},
Pages = {302--317},
Pmc = {PMC2527184},
Pmid = {17326616},
Pst = {ppublish},
Title = {Bounds and algorithms for fast exact searches of chemical fingerprints in linear and sublinear time},
Volume = {47},
Year = {2007},
Bdsk-Url-1 = {http://dx.doi.org/10.1021/ci600358f}}
@misc{Weininger:2011ly,
Author = {Weininger, D.},
Date-Added = {2011-11-10 11:24:44 -0500},
Date-Modified = {2011-11-10 11:26:28 -0500},
Howpublished = {\url{http://www.daylight.com/dayhtml/doc/theory/theory.finger.html}},
Month = {last accessed November},
Title = {Fingerprints - Screening and Similarity},
Year = {2011}}
@article{Balaban:2005zr,
Author = {Balaban, A.T.},
Date-Added = {2011-11-10 10:32:45 -0500},
Date-Modified = {2011-11-10 10:33:18 -0500},
Journal = {Foundations of Chemistry},
Number = {3},
Pages = {289--306},
Title = {Reflections About Mathematical Chemistry},
Volume = {7},
Year = {2005}}
@book{Helm:1897ys,
Address = {New York, NY},
Author = {Helm, G.},
Date-Added = {2011-11-10 10:31:24 -0500},
Date-Modified = {2011-11-10 10:32:00 -0500},
Publisher = {John Wiley \& Sons},
Title = {The Principles of Mathematical Chemistry},
Year = {1897}}
@article{DENDRAL,
Abstract = {The DENDRAL Project was one of the first large-scale programs to embody the strategy of using detailed, task-specific knowledge about a problem domain as a source of heuristics, and to seek generality through automating the acquisition of such knowledge. This paper summarizes the major conceptual contributions and accomplishments of that project. It is an attempt to distill from this research the lessons that are of importance to artificial intelligence research and to provide a record of the final status of two decades of work.},
Address = {PO BOX 211, 1000 AE AMSTERDAM, NETHERLANDS},
Author = {Lindsay, R.K. and Buchanan, B.G. and Feigenbaum, E.A. and Lederberg, J.},
Date-Added = {2011-11-10 09:58:45 -0500},
Date-Modified = {2011-11-10 09:59:55 -0500},
Isi = {A1993LD95000002},
Isi-Recid = {83615985},
Isi-Ref-Recids = {73472965 25938655 25938656 35264539 21185858 33700940 23150731 33613325 52843213 18693349 8197400 27875520 29677968 83615986 17190189 23795377 83615987 48425146 34260727 51432262 48635229 83615988 83615989 74915269 8293419 70046933 83615990 43181781 13877469 13877470 13877471 75148217 65525733 29096806 43231217 66826636 77491594 83615991 27086205 28969928 13714356 73779544 31453817 36535434 43881017 83615992 10204763 59971666 16244507 21584223 23624699 28403583 23795375 30195188 82472090 83615993 37178359},
Journal = {Artificial Intelligence},
Month = jun,
Number = {2},
Pages = {209--261},
Publisher = {ELSEVIER SCIENCE BV},
Times-Cited = {25},
Title = {{DENDRAL} - {A} case study of the first expert system for scientific hypothesis formation},
Volume = {61},
Year = {1993},
Bdsk-Url-1 = {http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS&DestLinkType=FullRecord;KeyUT=A1993LD95000002}}
@article{GDB,
Abstract = {GDB-13 enumerates small organic molecules containing up to 13 atoms of C, N, O, S, and Cl following simple chemical stability and synthetic feasibility rules. With 977,468,314 structures, GDB-13 is the largest publicly available small organic molecule database to date.},
Author = {Blum, Lorenz C. and Reymond, Jean-Louis},
Date-Added = {2011-11-10 09:52:24 -0500},
Date-Modified = {2011-11-13 12:15:56 -0500},
Doi = {10.1021/ja902302h},
Journal = {J.~Am.~Chem.~Soc.},
Journal-Full = {Journal of the American Chemical Society},
Mesh = {Algorithms; Databases, Factual; Drug Design; Molecular Structure; Pharmaceutical Preparations; Small Molecule Libraries},
Month = {Jul},
Number = {25},
Pages = {8732-8733},
Pmid = {19505099},
Pst = {ppublish},
Title = {970 million druglike small molecules for virtual screening in the chemical universe database {GDB-13}},
Volume = {131},
Year = {2009},
Bdsk-Url-1 = {http://dx.doi.org/10.1021/ja902302h}}
@article{openbabel2011,
Abstract = {ABSTRACT:},
Author = {O'Boyle, Noel M. and Banck, Michael and James, Craig A. and Morley, Chris and Vandermeersch, Tim and Hutchison, Geoffrey R.},
Date-Added = {2011-11-10 09:51:10 -0500},
Date-Modified = {2011-11-10 09:51:38 -0500},
Doi = {10.1186/1758-2946-3-33},
Journal = {J.~Cheminf.},
Journal-Full = {Journal of cheminformatics},
Pages = {33},
Pmc = {PMC3198950},
Pmid = {21982300},
Pst = {epublish},
Title = {{Open Babel}: {A}n open chemical toolbox},
Volume = {3},
Year = {2011},
Bdsk-Url-1 = {http://dx.doi.org/10.1186/1758-2946-3-33}}
@article{BlueObelisk2011,
Abstract = {ABSTRACT:},
Author = {O'Boyle, Noel M. and Guha, Rajarshi and Willighagen, Egon L. and Adams, Samuel E. and Alvarsson, Jonathan and Bradley, Jean-Claude and Filippov, Igor V. and Hanson, Robert M. and Hanwell, Marcus D and Hutchison, Geoffrey R. and James, Craig A. and Jeliazkova, Nina and Lang, Andrew {SID} and Langner, Karol M. and Lonie, David C. and Lowe, Daniel M. and Pansanel, J{\'e}r{\^o}me and Pavlov, Dmitry and Spjuth, Ola and Steinbeck, Christoph and Tenderholt, Adam L. and Theisen, Kevin J. and Murray-Rust, Peter},
Date-Added = {2011-11-10 09:49:46 -0500},
Date-Modified = {2011-11-10 09:50:51 -0500},
Doi = {10.1186/1758-2946-3-37},
Journal = {J.~Cheminf.},
Journal-Full = {Journal of cheminformatics},
Number = {1},
Pages = {37},
Pmc = {PMC3205042},
Pmid = {21999342},
Pst = {epublish},
Title = {Open Data, Open Source and Open Standards in chemistry: The Blue Obelisk five years on},
Volume = {3},
Year = {2011},
Bdsk-Url-1 = {http://dx.doi.org/10.1186/1758-2946-3-37}}
@article{Albuquerque:1998ys,
Abstract = {A series of 39 (a training set of 29 and a test set of 10) interphenylene 7-oxabicyclo [2.2.1]heptane oxazole thromboxane A2 (TXA2) receptor antagonists were studied using four-dimensional quantitative structure-activity relationship (4D-QSAR) analysis. Two thousand conformations of each analogue were sampled to generate a conformational energy profile (CEP) from a molecular dynamic simulation (MDS) of 100,000 trajectory states. Each conformation was placed in a grid cell lattice for each of six trial alignments. Cubic grid cell sizes of 1 and 2 A were considered. The frequency of occupation of each grid cell was computed for each of seven types of pharmacophoric group classes of atoms of each compound. These grid cell occupancy descriptors (GCODs) were then used as independent variables in constructing three-dimensional (3D)-QSAR models after data reduction. The types of data reduction included doing no reducing, reduction based on individual GCOD correlation with activity, and reduction from minimum variance constraints over the GCOD population. The 3D-QSAR models were generated and evaluated by a scheme that combines a genetic algorithm (GA) optimization with partial least squares (PLS) regression. The 3D-QSAR models were evaluated by cross-validation using the leave-one-out technique. The cross-validated correlation coefficient, Q2, ranged from 0.27 to 0.86. The models are not from chance correlation because a scrambled data set was generated and evaluated (Q2 = 0.25-0.37). A composite 3D-QSAR model was constructed using the best models derived from GCODs of both 1 and 2 A grid cell size lattices. The 3D-QSAR models provide detailed 3D pharmacophore requirements in terms of atom types and corresponding locations needed for high TXA2 inhibition activity. Specific sites in space that should not be occupied by an active inhibitor are also specified. The GCOD measures for the compounds in the training set permit reference points regarding which pharmacophore sites can provide the largest boosts in inhibition activity relative to the existing analogues.},
Author = {Albuquerque, M.G. and Hopfinger, A.J. and Barreiro, E.J. and de Alencastro, R.B.},
Date = {1998 Sep-Oct},
Date-Added = {2011-11-09 11:41:42 -0500},
Date-Modified = {2011-11-09 11:42:09 -0500},
Journal = {J.~Chem.~Inf.~Comput.~Sci.},
Journal-Full = {Journal of chemical information and computer sciences},
Mesh = {Drug Design; Models, Chemical; Oxazoles; Protein Conformation; Receptors, Thromboxane; Structure-Activity Relationship},
Number = {5},
Pages = {925--938},
Pmid = {9770304},
Pst = {ppublish},
Title = {Four-dimensional quantitative structure-activity relationship analysis of a series of interphenylene 7-oxabicycloheptane oxazole thromboxane A2 receptor antagonists},
Volume = {38},
Year = {1998}}
@article{Warr:2011vn,
Author = {Warr, W.},
Date-Added = {2011-11-09 09:02:13 -0500},
Date-Modified = {2011-11-09 09:02:57 -0500},
Journal = {Interdisciplinary Rev.~Comp.~Mol.~Sci.},
Number = {4},
Pages = {557--579},
Title = {Representation of Chemical Structures},
Volume = {1},
Year = {2011}}
@article{Weininger:1988kx,
Author = {Weininger, D},
Date-Added = {2011-11-09 08:56:34 -0500},
Date-Modified = {2011-11-09 08:57:10 -0500},
Journal = {J.~Chem.~Inf.~Comput.~Sci.},
Number = {1},
Pages = {31--36},
Title = {SMILES, A Chemical Language and Information System. 1. {I}ntroduction to methodology and enoding rules},
Volume = {28},
Year = {1988}}
@article{Chen:2010zr,
Abstract = {Predictive models are widely used in computer-aided drug discovery, particularly for identifying potentially biologically active molecules based on training sets of compounds with known activity or inactivity. The use of these models (amongst others) has enabled "virtual screens" to be used to identify compounds in large data sets that are predicted to be active, and which would thus be good candidates for experimental testing. The PubChem BioAssay database contains an increasing amount of experimental data from biological screens that has the potential to be used to train predictive models for a wide range of assays and targets, yet there has been little work carried out on using this data to build models. In this paper, we take an initial look at this by investigating the quality of naive Bayesian predictive models built using BioAssay data, and find that overall the predictive quality of such models is good, indicating that they could have utility in virtual screening.},
Author = {Chen, Bin and Wild, David J.},
Date-Added = {2011-11-09 11:43:49 -0500},
Date-Modified = {2011-11-09 11:44:12 -0500},
Doi = {10.1016/j.jmgm.2009.10.001},
Journal = {J.~Mol.~Graph.~Model.},
Journal-Full = {Journal of molecular graphics \& modelling},
Mesh = {Algorithms; Bayes Theorem; Biological Assay; Databases, Factual},
Month = {Jan},
Number = {5},
Pages = {420--426},
Pmid = {19897391},
Pst = {ppublish},
Title = {{PubChem BioAssays} as a data source for predictive models},
Volume = {28},
Year = {2010},
Bdsk-Url-1 = {http://dx.doi.org/10.1016/j.jmgm.2009.10.001}}
@book{Johnson:1990qf,
Address = {New York, NY},
Author = {Johnson, M.A. and Maggiora, G.M.},
Date-Added = {2011-11-09 21:18:42 -0500},
Date-Modified = {2011-11-09 21:19:27 -0500},
Publisher = {John Wiley \& Sons},
Title = {Concepts and Applications of Molecular Similarity},
Year = {1990}}
@article{Bohacek:1996ve,
Author = {Bohacek, R.S. and McMartin, C. and Guida, W.C.},
Date-Added = {2011-11-09 20:55:14 -0500},
Date-Modified = {2011-11-09 20:57:08 -0500},
Journal = {Med.~Res.~Rev.},
Number = {1},
Pages = {3--50},
Title = {The Art and Practice of Structure Based Drug Design: {A} Molecular Modeling Perspective},
Volume = {16},
Year = {1996}}
@article{Swamidass:2011uq,
Abstract = {Repurposing and repositioning drugs--discovering new uses for existing and experimental medicines-is an attractive strategy for rescuing stalled pharmaceutical projects, finding treatments for neglected diseases, and reducing the time, cost and risk of drug development. As this strategy emerged, academic researchers began performing high-throughput screens (HTS) of small molecules--the type of experiments once exclusively conducted in industry--and making the data from these screens available to all. Several methods can mine this data to inform repurposing and repositioning efforts. Despite these methods' limitations, it is hopeful that they will accelerate the discovery of new uses for known drugs, but this hope has not yet been realized.},
Author = {Swamidass, S Joshua},
Date-Added = {2011-11-09 08:08:36 -0500},
Date-Modified = {2011-11-09 08:08:46 -0500},
Doi = {10.1093/bib/bbr028},
Journal = {Brief.~Bioinform.},
Journal-Full = {Briefings in bioinformatics},
Month = {Jul},
Number = {4},
Pages = {327--335},
Pmid = {21715466},
Pst = {ppublish},
Title = {Mining small-molecule screens to repurpose drugs},
Volume = {12},
Year = {2011},
Bdsk-Url-1 = {http://dx.doi.org/10.1093/bib/bbr028}}
@article{Dudley:2011fk,
Abstract = {Finding new uses for existing drugs, or drug repositioning, has been used as a strategy for decades to get drugs to more patients. As the ability to measure molecules in high-throughput ways has improved over the past decade, it is logical that such data might be useful for enabling drug repositioning through computational methods. Many computational predictions for new indications have been borne out in cellular model systems, though extensive animal model and clinical trial-based validation are still pending. In this review, we show that computational methods for drug repositioning can be classified in two axes: drug based, where discovery initiates from the chemical perspective, or disease based, where discovery initiates from the clinical perspective of disease or its pathology. Newer algorithms for computational drug repositioning will likely span these two axes, will take advantage of newer types of molecular measurements, and will certainly play a role in reducing the global burden of disease.},
Author = {Dudley, Joel T and Deshpande, Tarangini and Butte, Atul J},
Date-Added = {2011-11-09 08:08:08 -0500},
Date-Modified = {2011-11-09 08:08:23 -0500},
Doi = {10.1093/bib/bbr013},
Journal = {Brief.~Bioinform.},
Journal-Full = {Briefings in bioinformatics},
Month = {Jul},
Number = {4},
Pages = {303--311},
Pmc = {PMC3137933},
Pmid = {21690101},
Pst = {ppublish},
Title = {Exploiting drug-disease relationships for computational drug repositioning},
Volume = {12},
Year = {2011},
Bdsk-Url-1 = {http://dx.doi.org/10.1093/bib/bbr013}}
@article{Klebe:1994ly,
Abstract = {An alternative approach is reported to compute property fields based on similarity indices of drug molecules that have been brought into a common alignment. The fields of different physicochemical properties use a Gaussian-type distance dependence, and no singularities occur at the atomic positions. Accordingly, no arbitrary definitions of cutoff limits and deficiencies due to different slopes of the fields are encountered. The fields are evaluated by a PLS analysis similar to the CoMFA formalism. Two data sets of steroids binding to the corticosteroid-binding-globulin and thermolysin inhibitors were analyzed in terms of the conventional CoMFA method (Lennard-Jones and Coulomb potential fields) and the new comparative molecular similarity indices analysis (CoMSIA). Models of comparative statistical significance were obtained. Field contribution maps were produced for the different models. Due to cutoff settings in the CoMFA fields and the steepness of the potentials close to the molecular surface, the CoMFA maps are often rather fragmentary and not contiguously connected. This makes their interpretation difficult. The maps obtained by the new CoMSIA approach are superior and easier to interpret. Whereas the CoMFA maps denote regions apart from the molecules where interactions with a putative environment are to be expected, the CoMSIA maps highlight those regions within the area occupied by the ligand skeletons that require a particular physicochemical property important for activity. This is a more significant guide to trace the features that really matter especially with respect to the design of novel compounds.},
Author = {Klebe, G. and Abraham, U. and Mietzner, T.},
Date-Added = {2011-11-08 22:20:40 -0500},
Date-Modified = {2011-11-08 22:21:11 -0500},
Journal = {J.~Med.~Chem.},
Journal-Full = {Journal of medicinal chemistry},
Mesh = {Models, Molecular; Molecular Conformation; Steroids; Structure-Activity Relationship; Thermolysin},
Month = {Nov},
Number = {24},
Pages = {4130--4146},
Pmid = {7990113},
Title = {Molecular similarity indices in a comparative analysis ({CoMSIA}) of drug molecules to correlate and predict their biological activity},
Volume = {37},
Year = {1994}}
@article{Cramer:1988zr,
Author = {Cramer, R.D. and Patterson, D.E. and Bunce, J.D.},
Date-Added = {2011-11-08 22:19:10 -0500},
Date-Modified = {2011-11-08 22:19:56 -0500},
Journal = {J.~Am.~Chem.~Soc.},
Pages = {5959--5967},
Title = {Comparative Molecular Field Analysis (CoMFA). I. Effect of Shape on Binding of Steroids to Carrier Protiens},
Volume = {110},
Year = {1988}}
@article{Free:1964ys,
Author = {Free, S.M. and Wilson, J.W.},
Date-Added = {2011-11-08 22:13:58 -0500},
Date-Modified = {2011-11-08 22:14:59 -0500},
Journal = {J.~Med.~Chem.},
Pages = {395--399},
Title = {A Mathematical Contribution to Structure Activity Studies},
Volume = {7},
Year = {1964}}
@article{Hansch:1962vn,
Author = {Hansch, C. and Maloney, P.P. and Fujita, T. and Muir, R.M.},
Date-Added = {2011-11-08 22:09:43 -0500},
Date-Modified = {2011-11-13 12:17:55 -0500},
Journal = {Nature},
Pages = {178--180},
Title = {Correlation of biological activity of phnoxyacetic acids with {Hammett} substituent constants and partitiion coefficients.},
Volume = {194},
Year = {1962}}
@article{Vleduts:1963kx,
Author = {Vleduts, G.E.},
Date-Added = {2011-11-08 21:37:08 -0500},
Date-Modified = {2011-11-08 21:37:52 -0500},
Journal = {Inf.~Stor.~Ret.},
Pages = {117--146},
Title = {Concerning one system of classification and codification of organic reactions},
Volume = {1},
Year = {1963}}
@article{Feldman:1975uq,
Author = {Feldman, A. and Hodes, L.},
Date-Added = {2011-11-08 21:24:57 -0500},
Date-Modified = {2011-11-08 21:25:44 -0500},
Journal = {J.~Chem.~Inf.~Comput.~Sci.},
Pages = {147--152},
Title = {An efficient design for chemical structure searching. {I}. {T}he screens},
Volume = {15},
Year = {1975}}
@article{Adamson:1973fk,
Author = {Adamson, G.W. and Cowell, J. and Lynch M.F. and McLure A.H.W. and Tow, W.G. and Yapp, A.M.},
Date-Added = {2011-11-08 21:23:07 -0500},
Date-Modified = {2011-11-08 21:23:56 -0500},
Journal = {J.~Chem.~Doc.},
Pages = {153--157},
Title = {Strategic considerations in the design of screening systems for substructure searches of chemical structure files},
Volume = {13},
Year = {1973}}
@article{Agrafiotis2007,
__Markedentry = {[joergkurtwegner:]},
Abstract = {Chemoinformatics is a large scientific discipline that deals with
the storage, organization, management, retrieval, analysis, dissemination,
visualization, and use of chemical information. Chemoinformatics
techniques are used extensively in drug discovery and development.
Although many consider it a mature field, the advent of high-throughput
experimental techniques and the need to analyze very large data sets
have brought new life and challenges to it. Here, we review a selection
of papers published in 2006 that caught our attention with regard
to the novelty of the methodology that was presented. The field is
seeing significant growth, which will be further catalyzed by the
widespread availability of public databases to support the development
and validation of new approaches.},
Author = {Agrafiotis, Dimitris K. and Bandyopadhyay, Deepak and Wegner, J{\"{o}}rg K. and Vlijmen, Herman van},
Doi = {10.1021/ci700059g},
Institution = {Johnson Pharmaceutical Research and Development, L.L.C., Exton, Pennsylvania 19341, USA. [email protected]},
Journal = {J Chem Inf Model},
Keywords = {Combinatorial Chemistry Techniques; Drug Industry; Genomics; Informatics; Quantitative Structure-Activity Relationship},
Language = {eng},
Medline-Pst = {ppublish},
Number = {4},
Owner = {joergkurtwegner},
Pages = {1279--1293},
Pmid = {17511441},
Timestamp = {2011.11.05},
Title = {Recent advances in chemoinformatics.},
Url = {http://dx.doi.org/10.1021/ci700059g},
Volume = {47},
Year = {2007},
Bdsk-Url-1 = {http://dx.doi.org/10.1021/ci700059g}}
@book{baaderdl2007,
Author = {Baader, F. and Calvanese, D. and McGuiness, D.L. and Nardi, D. and Patel-Schneider, P.F.},
Publisher = {Cambridge University Press},
Title = {The Description Logic Handbook: Theory, Implementation, and Applications},
Year = {2007}}
@article{bender2004,
Author = {A. Bender and R.C. Glen},
Journal = {Org.~Biomol.~Chem.},
Pages = {3204--3218},
Title = {Molecular similarity: A key technique in molecular informatics},
Volume = {2},
Year = {2004}}
@article{Berger2004,
Author = {Berger, Franziska and Flamm, Christoph and Gleiss, Petra M and Leydold, Josef and Stadler, Peter F},
Journal = {J.~Chem.~Inf.~Comput.~Sci.},
Month = {Mar-Apr},
Number = {2},
Pages = {323--331},
Title = {Counterexamples in chemical ring perception.},
Volume = {44},
Year = {2004}}
@inbook{brown1998,
Author = {Frank K. Brown},
Chapter = {Chapter 35. Chemoinformatics: What is it and How does it Impact Drug Discovery.},
Date-Modified = {2011-11-08 16:38:10 -0500},
Owner = {joergkurtwegner},
Pages = {375-384},
Publisher = {Elsevier},
Timestamp = {2011.11.05},
Title = {Annual Reports in Medicinal Chemistry},
Year = {1998}}
@article{brown2009,
Author = {N. Brown},
Date-Modified = {2011-11-13 12:16:31 -0500},
Journal = {{ACM} Comput.~Surv.},
Pages = {1--38},
Title = {Chemoinformatics -- {A}n Introduction for Computer Scientists},
Volume = {41},
Year = {2009}}
@article{cokfl06,
Abstract = {SMILES strings and other classic 2D structural formats offer a convenient
way to represent molecules as a simplistic connection table, with
the inherent advantages of ease of handling and storage. In the context
of virtual screening, chemical databases to be screened are often
initially represented by canonicalised SMILES strings that can be
filtered and pre-processed in a number of ways, resulting in molecules
that occupy similar regions of chemical space to active compounds
of a therapeutic target. A wide variety of software exists to convert
molecules into SMILES format, namely, Mol2smi (Daylight Inc.), MOE
(Chemical Computing Group) and Babel (Openeye Scientific Software).
Depending on the algorithm employed, the atoms of a SMILES string
defining a molecule can be ordered differently. Upon conversion to
3D coordinates they result in the production of ostensibly the same
molecule.In this work we show how different permutations of a SMILES
string can affect conformer generation, affecting reliability and
repeatability of the results. Furthermore, we propose a novel procedure
for the generation of conformers, taking advantage of the permutation
of the input strings--both SMILES and other 2D formats, leading to
more effective sampling of conformation space in output, and also
implementing fingerprint and principal component analyses step to
post process and visualise the results.},
Author = {G. Carta and V. Onnis and A. J. S. Knox and D. Fayne and D. G. Lloyd},
Doi = {10.1007/s10822-006-9044-4},
File = {cokfl06.pdf:cokfl06.pdf:PDF},
Institution = {Molecular Design Group, School of Biochemistry and Immunology, Trinity College Dublin, Dublin 2, Ireland, [email protected].},
Journal = {J Comput Aided Mol Des},
Keywords = {Algorithms; Databases as Topic; Drug Design; Drug Evaluation, Preclinical; Molecular Conformation; Software},
Month = {Mar},
Number = {3},
Owner = {[email protected]},
Pages = {179--190},
Pmid = {16841235},
Timestamp = {2008.02.21},
Title = {{P}ermuting input for more effective sampling of {3D} conformer space},
Volume = {20},
Year = {2006},
Bdsk-Url-1 = {http://dx.doi.org/10.1007/s10822-006-9044-4}}
@article{Chen2006,
Abstract = {The history of chemoinformatics is reviewed in a decade-by-decade
manner from the 1940s to the present. The focus is placed on four
traditional research areas: chemical database systems, computer-assisted
structure elucidation systems, computer-assisted synthesis design
systems, and 3D structure builders. Considering the fact that computer
technology has been one of the major driving forces of the development
of chemoinformatics, each section will start from a brief description
of the new advances in computer technology of each decade. The summary
and future prospects are given in the last section.},
Author = {W. L. Chen},
Doi = {10.1021/ci060016u},
Institution = {Elsevier MDL, 2440 Camino Ramon, Suite 300, San Ramon, California 94583, USA. [email protected]},
Journal = {J Chem Inf Model},
Keywords = {Algorithms; Chemistry, Pharmaceutical, history/methods/trends; Combinatorial Chemistry Techniques, methods; Databases, Factual; History, 20th Century; Informatics, methods},
Language = {eng},
Medline-Pst = {ppublish},
Number = {6},
Owner = {joergkurtwegner},
Pages = {2230--2255},
Pmid = {17125167},
Timestamp = {2011.11.05},
Title = {Chemoinformatics: past, present, and future.},
Url = {http://dx.doi.org/10.1021/ci060016u},
Volume = {46},
Year = {2006},
Bdsk-Url-1 = {http://dx.doi.org/10.1021/ci060016u}}
@inproceedings{clark:pct,
Author = {Malcolm Clark},
Booktitle = {TeX90 Conference Proceedings},
Month = {March},
Organization = {TeX Users Group},
Pages = {84-89},
Title = {Post Congress Tristesse},
Year = {1991}}
@inproceedings{cordella2001,
Author = {Cordella, L.P. and Foggia, P. and Sansone, C. and Vento, M.},
Booktitle = {In: 3rd {IAPR-TC15} Workshop on Graph-based Representations in Pattern Recognition},
Pages = {149--159},
Title = {An improved algorithm for matching large graphs},
Year = {2001}}
@article{CoreyWipke1969,
Author = {Corey, E. J. and Wipke, W. T},
Journal = {Science},
Owner = {joergkurtwegner},
Pages = {178-192},
Timestamp = {2011.11.06},
Title = {Computer-Assisted Design of Complex Organic Syntheses},
Volume = {166},
Year = {1969}}
@book{faulon2010,
Address = {Boca Raton, Florida},
Author = {J.-L. Faulon and A. Bender},
Publisher = {{CRC} Press},
Title = {Handbook of Cheminformatics Algorithms},
Year = {2010}}
@article{faulon2003,
Author = {J.-L. Faulon and D. Visco and C.J. Churchwell},
Journal = {J.~Chem.~Inf.~Model.},
Number = {3},
Pages = {721--734},
Title = {The Signature Molecular Descriptor. 2. Enumerating Molecules from their Extended Valence Sequences},
Volume = {43},
Year = {2003}}
@article{couto2010,
Author = {Ferreira, J.D. and Couto, F.M.},
Journal = {{PLoS} Comput.~Biol.},
Pages = {e1000937},
Title = {Semantic Similarity for Automatic Classification of Chemical Compounds},
Volume = {6},
Year = {2010}}
@article{fujiwara2008,
Author = {H. Fujiwara and J.W.L. Zhao and H. Nagamochi and T. Akutsu},
Journal = {J.~Chem.~Inf.~Model.},
Number = {7},
Pages = {1345--1357},
Title = {Enumerating Treelike Chemical Graphs with Given Path Frequency},
Volume = {48},
Year = {2008}}
@article{gm78,
Author = {J. Gasteiger and M. Marsili},
Groupsearch = {0},
Journal = {Tetrahedron Lett.},
Owner = {joergkurtwegner},
Pages = {3181--3184},
Timestamp = {2011.11.06},
Title = {{A} {N}ew {M}odel for {C}alculating {A}tomic {C}harges in {M}olecules},
Volume = {34},
Year = {1978}}
@article{goldberg1999,
Author = {Goldberg, L.A. and Jerrum, M.},
Date-Modified = {2011-11-13 12:18:22 -0500},
Journal = {{SIAM} J.~Comput.},
Number = {3},
Pages = {834--853},
Title = {Randomly Sampling Molecules},
Volume = {29},
Year = {1999}}
@book{Gray1986,
Author = {N.A.B. Gray},
Owner = {joergkurtwegner},
Publisher = {John Wiley \& Sons},
Timestamp = {2011.11.06},
Title = {Computer-assisted Structure Elucidation},
Year = {1986}}
@inproceedings{hastingsowled2010,
Author = {Hastings, J. and Dumontier, M. and Hull, D. and Horridge, M. and Steinbeck, C. and Sattler, U. and Stevens, R. and H\"{o}rne, T. and Britz, K.},
Booktitle = {In: Proc. of {OWL}: Experiences and Directions (OWLED 2010)},
Title = {Representing chemicals using {OWL}, description graphs and rules},
Year = {2010}}
@article{hsn07,
Abstract = {Ligand docking is a widely used approach in virtual screening. In
recent years a large number of publications have appeared in which
docking tools are compared and evaluated for their effectiveness
in virtual screening against a wide variety of protein targets. These
studies have shown that the effectiveness of docking in virtual screening
is highly variable due to a large number of possible confounding
factors. Another class of method that has shown promise in virtual
screening is the shape-based, ligand-centric approach. Several direct
comparisons of docking with the shape-based tool ROCS have been conducted
using data sets from some of these recent docking publications. The
results show that a shape-based, ligand-centric approach is more
consistent than, and often superior to, the protein-centric approach
taken by docking.},
Author = {P. C. D. Hawkins and A. G. Skillman and A. Nicholls},
Doi = {10.1021/jm0603365},
File = {hsn07.pdf:hsn07.pdf:PDF},
Journal = {J Med Chem},
Keywords = {Binding Sites; Crystallography, X-Ray; Ligands; Molecular Conformation; Molecular Structure; Protein Binding; Proteins; Quantitative Structure-Activity Relationship; ROC Curve},
Number = {1},
Owner = {[email protected]},
Pages = {74--82},
Pmid = {17201411},
Timestamp = {2007.10.18},
Title = {{C}omparison of shape--matching and docking as virtual screening tools},
Volume = {50},
Year = {2007},
Bdsk-Url-1 = {http://dx.doi.org/10.1021/jm0603365}}
@article{herlihy:methodology,
Author = {Maurice Herlihy},
Journal = {ACM Trans. Program. Lang. Syst.},
Month = {November},
Number = {5},
Pages = {745-770},
Title = {A Methodology for Implementing Highly Concurrent Data Objects},
Volume = {15},
Year = {1993}}
@article{horst2009,
Author = {E. van der Horst and Y. Okuno and A. Bender and A.P. Ijzerman},
Journal = {J.~Chem.~Inf.~Model.},
Pages = {348--360},
Title = {Substructure Mining of {GPCR} Ligands Reveals Activity-Class Specific Functional Groups in an Unbiased Manner},
Volume = {49},
Year = {2009}}
@inproceedings{kti03,
Address = {Washington, DC, USA},
Author = {H. Kashima and K. Tsuda and A. Inokuchi},
Booktitle = {{T}he 20th {I}nternational {C}onference on {M}achine {L}earning ({ICML}2003)},
File = {kti03.pdf:kti03.pdf:PDF},
Owner = {[email protected]},
Timestamp = {2011.11.06},
Title = {{M}arginalized {K}ernels {B}etween {L}abeled {G}raphs},
Url = {http://www.informatik.uni-freiburg.de/cgnm/lehre/pm-05s/bib/structured-input/graphs/Gaertner2003-marginalized-kernels-for-labeled-graphs.pdf},
Year = {2003},
Bdsk-Url-1 = {http://www.informatik.uni-freiburg.de/cgnm/lehre/pm-05s/bib/structured-input/graphs/Gaertner2003-marginalized-kernels-for-labeled-graphs.pdf}}
@article{kct1946,
Author = {King, G. W. ands Cross, P. C. and Thomas, G. B.},
Journal = {J. Chem. Phys.},
Owner = {joergkurtwegner},
Pages = {35-42},
Timestamp = {2011.11.06},
Title = {The Asymmetric Rotor. III. Punched-Card Methods of Constructing Band Spectra},
Volume = {14},
Year = {1946}}
@article{kireev1995,
Author = {D. B. Kireev},
Journal = {J. Chem. Inf. Comput. Sci.},
Owner = {joergkurtwegner},
Pages = {175-180},
Timestamp = {2011.11.06},
Title = {ChemNet: A Novel Neural Network Based Method for Graph/Property Mapping},
Volume = {35},
Year = {1995}}
@article{kuhn2010,
Author = {Kuhn, Michael and Campillos, Monica and Letunic, Ivica and Jensen, Lars Juhl J. and Bork, Peer},
Citeulike-Article-Id = {6567205},
Citeulike-Linkout-0 = {http://dx.doi.org/10.1038/msb.2009.98},
Citeulike-Linkout-1 = {http://dx.doi.org/10.1038/msb200998},
Citeulike-Linkout-2 = {http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2824526/},
Citeulike-Linkout-3 = {http://view.ncbi.nlm.nih.gov/pubmed/20087340},
Citeulike-Linkout-4 = {http://www.hubmed.org/display.cgi?uids=20087340},
Day = {19},
Doi = {10.1038/msb.2009.98},
Issn = {1744-4292},
Journal = {Molecular systems biology},
Keywords = {drugs, medicine, side\_effect},
Month = jan,
Pmcid = {PMC2824526},
Pmid = {20087340},
Posted-At = {2011-05-16 06:30:16},
Priority = {2},
Publisher = {Nature Publishing Group},
Title = {A side effect resource to capture phenotypic effects of drugs.},
Url = {http://dx.doi.org/10.1038/msb.2009.98},
Volume = {6},
Year = {2010},
Bdsk-Url-1 = {http://dx.doi.org/10.1038/msb.2009.98}}
@article{lapinsh2001,
Author = {Lapinsh, M.},
Citeulike-Article-Id = {9540237},
Citeulike-Linkout-0 = {http://dx.doi.org/10.1016/S0304-4165(00)00187-2},
Citeulike-Linkout-1 = {http://linkinghub.elsevier.com/retrieve/pii/S0304-4165(00)00187-2},
Day = {16},
Doi = {10.1016/S0304-4165(00)00187-2},
Issn = {03044165},
Journal = {Biochimica et Biophysica Acta (BBA) - General Subjects},
Keywords = {proteochemometrics},
Month = feb,
Number = {1-2},
Pages = {180--190},
Posted-At = {2011-07-13 06:48:33},
Priority = {2},
Title = {Development of proteo-chemometrics: a novel technology for the analysis of drug-receptor interactions},
Volume = {1525},
Year = {2001},
Bdsk-Url-1 = {http://dx.doi.org/10.1016/S0304-4165(00)00187-2}}
@book{Leach2001,
Author = {A. L. Leach},
Edition = {second edition},
Isbn = {0--582--38210--6},
Owner = {[email protected]},
Publisher = {Prentice Hall},
Timestamp = {2011.11.06},
Title = {{M}olecular {M}odelling -- {P}rinciples and {A}pplications},
Year = {2001}}
@book{leachgillet2007,
Author = {A. R. Leach and V.J. Gillet},
Owner = {joergkurtwegner},
Publisher = {Springer},
Timestamp = {2011.11.06},
Title = {An Introduction to Chemoinformatics},
Year = {2007}}
@book{Malinowski2002,
Author = {E.R. Malinowski},
Owner = {joergkurtwegner},
Publisher = {Wiley},
Timestamp = {2011.11.05},
Title = {Factor Analysis in Chemistry},
Year = {2002}}
@article{Morgan1965,
Author = {H. L. Morgan},
File = {mor65.pdf:mor65.pdf:PDF},
Groupsearch = {0},
Journal = {J. Chem. Doc.},
Owner = {joergkurtwegner},
Pages = {107--113},
Timestamp = {2011.11.06},
Title = {{T}he {G}eneration of a {U}nique {M}achine {D}escription for {C}hemical {S}tructures -- {A} {T}echnique {D}eveloped at {C}hemical {A}bstracts {S}ervice.},
Volume = {5},
Year = {1965}}
@inbook{okada2006,
Author = {Takashi Okada},
Chapter = {Mining from Chemical Graphs},
Editor = {Diane J. Cook and Lawrence B. Holder},
Owner = {joergkurtwegner},
Pages = {347-380},
Publisher = {Wiley},
Timestamp = {2011.11.05},
Title = {Mining Graph Data},
Year = {2006}}
@inbook{polanski2009,
Author = {J. Polanski},
Chapter = {14},
Editor = {S.D. Brown},
Owner = {joergkurtwegner},
Publisher = {Elsevier},
Series = {Comprehensive Chemometrics},
Timestamp = {2011.11.05},
Title = {Chemoinformatics},
Volume = {4},
Year = {2009}}
@article{RayKirsch1957,
Author = {Ray, L. C. and Kirsch, R. A.},
Journal = {Science},
Owner = {joergkurtwegner},
Pages = {814-819},
Timestamp = {2011.11.06},
Title = {Finding Chemical Records by Digital Computers},
Volume = {126},
Year = {1957}}
@article{rijnbeek2009,
Author = {Rijnbeek, M. and Steinbeck, C.},
Date-Modified = {2011-11-13 12:17:06 -0500},
Journal = {J.~Cheminf.},
Pages = {17},
Title = {An Open Source Chemistry Search Engine for {O}racle},
Volume = {1},
Year = {2009}}
@phdthesis{Schwab2001,
Author = {C. Schwab},
File = {sch01.pdf:sch01.pdf:PDF},
Groupsearch = {0},
Owner = {joergkurtwegner},
School = {Erlangen},
Timestamp = {2011.11.06},
Title = {{K}onformative {F}lexibilit{\"a}t von {L}iganden im {W}irkstoffdesign},
Year = {2001}}
@article{Bioclipse2,
Author = {Spjuth, Ola and Alvarsson, Jonathan and Berg, Arvid and Eklund, Martin and Kuhn, Stefan and Masak, Carl and Torrance, Gilleain and Wagener, Johannes and Willighagen, Egon L and Steinbeck, Christoph and Wikberg, Jarl E S},
Journal = {{BMC} Bioinformatics},
Pages = {397},
Title = {Bioclipse 2: A scriptable integration platform for the life sciences.},
Volume = {10},
Year = {2009}}
@inproceedings{inchi,
Author = {Stein, S.E. and Heller, S.R. and Tchekhovskoi, D.},
Booktitle = {In: Proc.~2003 International Chemical Information Conference},
Organization = {Infonortics},
Pages = {131--143},
Title = {An Open Standard for Chemical Structure Representation: {T}he {IUPAC} Chemical Identifier,},
Year = {2003}}
@article{steinbeck2003,
Address = {Max-Planck-Institute of Chemical Ecology, Jena, Germany. [email protected]},
Author = {Steinbeck, C. and Han, Y. and Kuhn, S. and Horlacher, O. and Luttmann, E. and Willighagen, E.},
Citeulike-Article-Id = {423382},
Citeulike-Linkout-0 = {http://dx.doi.org/10.1021/ci025584y},
Citeulike-Linkout-1 = {http://pubs.acs.org/doi/abs/10.1021/ci025584y},
Citeulike-Linkout-2 = {http://view.ncbi.nlm.nih.gov/pubmed/12653513},
Citeulike-Linkout-3 = {http://www.hubmed.org/display.cgi?uids=12653513},
Date-Modified = {2011-11-13 11:33:34 -0500},
Day = {1},
Doi = {10.1021/ci025584y},
Issn = {0095-2338},
Journal = {J.~Chem.~Inf.~Comput.~Sci.},
Keywords = {cheminformatics, cito--cites--1375511, cito--definesmethodusedby--8972090, java, opensource, papers},
Month = mar,
Number = {2},
Pages = {493--500},
Pmid = {12653513},
Posted-At = {2007-06-09 09:31:09},