-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy paththesis.bib
12969 lines (10952 loc) · 652 KB
/
thesis.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 file was created with JabRef 2.10.
% Encoding: MacRoman
@String { p-gcb = {Proc. of the German Conference on Bioinformatics} }
@String { j-acmcs = {ACM Comput. Surv.} }
@String { j-ajmedgen = {Am. J. Med. Genet.} }
@String { j-alg = {Algorithmica} }
@String { j-anbiochem = {Anal. Biochem.} }
@String { j-bioinf = {Bioinformatics} }
@String { j-bmcbio = {BMC Bioinf.} }
@String { j-cacm = {Commun. ACM} }
@String { j-cell = {Cell} }
@String { j-dam = {Discrete Appl. Math.} }
@String { j-dmkd = {Data Min. Knowl. Discov.} }
@String { j-fund = {Fund. Inform.} }
@String { j-gb = {Genome Biol.} }
@String { j-genomics = {Genomics} }
@String { j-gi = {Genome Inform.} }
@String { j-gr = {Genome Res.} }
@String { j-ieeetc = {IEEE T. Comput.} }
@String { j-ja = {J. Algorithms} }
@String { j-jacm = {J. ACM} }
@String { j-jbcb = {J. Bioinform. Comput. Biol.} }
@String { j-jcb = {J. Comput. Biol.} }
@String { j-jmb = {J. Mol. Biol.} }
@String { j-joda = {J. Discrete Algorithms} }
@String { j-mamgen = {Mamm. Genome} }
@String { j-mathprog = {Math. Program.} }
@String { j-nar = {Nucleic Acids Res.} }
@String { j-nat = {Nature} }
@String { j-natbt = {Nat. Biotechnol.} }
@String { j-natgen = {Nat. Genet.} }
@String { j-natmeth = {Nat. Methods} }
@String { j-natneuro = {Nat. Neurosci.} }
@String { j-natpr = {Nat. Protoc.} }
@String { j-plantmolbio = {Plant Mol. Biol.} }
@String { j-ploscb = {PLoS Comput. Biol.} }
@String { j-plosone = {PLoS ONE} }
@String { j-pnas = {PNAS} }
@String { j-recomb = {RECOMB} }
@String { j-science = {Science} }
@String { j-spe = {Software Pract. Exper.} }
@String { j-tcbb = {IEEE/ACM Trans. Comput. Biol. Bioinf.} }
@String { j-tcs = {Theoret. Comput. Sci.} }
@String { pub-acm = {ACM Press} }
@String { pub-acm:adr = {New York, NY, USA} }
@String { pub-cambridge = {Cambridge University Press} }
@String { pub-crc = {CRC Press} }
@String { pub-ieee = {IEEE Computer Society} }
@String { pub-nat = {Nature Publishing Group} }
@String { pub-oxford = {Oxford University Press} }
@String { pub-oxford:adr = {Oxford, UK} }
@String { pub-plos = {Public Library of Science} }
@String { pub-springer = {Springer} }
@String { pub-springer:adr = {New York, NY, USA} }
@String { ser-lnai = {LNAI} }
@String { ser-lnbi = {Lecture Notes in Bioinformatics} }
@String { ser-lncs = {LNCS} }
@InProceedings{Chan2003,
Title = {Mining Emerging Substrings},
Author = {Sarah Chan and Ben Kao and Chi Lap Yip and Michael Tang},
Booktitle = {Proc. of the 8th International Conference on Database Systems for Advanced Applications},
Year = {2003},
Pages = {119--126},
Series = {DASFAA~'03},
Bibsource = {DBLP, http://dblp.uni-trier.de},
Crossref = {DBLP:conf/dasfaa/2003},
Ee = {http://doi.ieeecomputersociety.org/10.1109/DASFAA.2003.1192375},
Owner = {esiragusa},
Timestamp = {2014.08.07}
}
@InProceedings{Dementiev2005,
Title = {Better External Memory Suffix Array Construction},
Author = {Roman Dementiev and Juha K{\"a}rkk{\"a}inen and Jens Mehnert and Peter Sanders},
Booktitle = {ALENEX/ANALCO},
Year = {2005},
Pages = {86-97},
Bibsource = {DBLP, http://dblp.uni-trier.de},
Crossref = {DBLP:conf/alenex/2005},
Ee = {http://www.siam.org/meetings/alenex05/papers/08rdementiev.pdf},
Owner = {esiragusa},
Timestamp = {2014.08.07}
}
@InProceedings{Gog2011,
Title = {Fast and Lightweight LCP-Array Construction Algorithms},
Author = {Simon Gog and Enno Ohlebusch},
Booktitle = {Proc. of the Workshop on Algorithm Engineering and Experiments},
Year = {2011},
Pages = {25--34},
Series = {ALENEX~'11},
Bibsource = {DBLP, http://dblp.uni-trier.de},
Crossref = {DBLP:conf/alenex/2011},
Ee = {http://www.siam.org/proceedings/alenex/2011/alx11_03_gogs.pdf},
Owner = {esiragusa},
Timestamp = {2014.08.07}
}
@Article{1998,
Title = {Comparative Sequence Analysis of a Gene-Rich Cluster at Human Chromosme 12p13 and its Syntenic Region in Mouse Chromosome 6},
Author = {M. Ali Ansari-lari and J. C. Oeltjen and Z. Zhang and D. M. Muzny and J. Liu and J. H. Gorrell and A. C. Chinault and J. W. Belmont and W. Miller and R. A. Gibbs},
Journal = j-GR,
Year = {1998},
Pages = {29-40},
Volume = {8},
Owner = {weese},
Timestamp = {2010.09.20}
}
@Article{Abouelhoda2004,
Title = {Replacing suffix trees with enhanced suffix arrays},
Author = {Abouelhoda, M.I. and Kurtz, S. and Ohlebusch, E.},
Journal = {Journal of Discrete Algorithms},
Year = {2004},
Number = {1},
Pages = {53--86},
Volume = {2},
Owner = {esiragusa},
Publisher = {Elsevier},
Timestamp = {2014.08.07}
}
@InProceedings{Abouelhoda2003,
Title = {Chaining methods revisited},
Author = {Abouelhoda, M. and Ohlebusch, E.},
Booktitle = {Proc. of the 14th Annual Symposium on Combinatorial Pattern Matching},
Year = {2003},
Pages = {1-16},
Series = {CPM~'03},
Owner = {weese},
Timestamp = {2010.09.20}
}
@InProceedings{Abouelhoda2002,
Title = {The Enhanced Suffix Array and its Applications to Genome Analysis},
Author = {Abouelhoda, M. I. and Kurtz, S. and Ohlebusch, E.},
Booktitle = {Proc. of the 2nd Workshop on Algorithms in Bioinformatics},
Year = {2002},
Pages = {449-463},
Publisher = pub-SPRINGER,
Series = ser-LNCS,
Volume = {2452},
Bdsk-url-1 = {http://www.zbh.uni-hamburg.de/staff/kurtz/papers/AboKurOhl2002.pdf},
Owner = {weese},
Timestamp = {2010.09.20},
Url = {http://www.zbh.uni-hamburg.de/staff/kurtz/papers/AboKurOhl2002.pdf}
}
@InProceedings{Abouelhoda2002a,
Title = {Optimal Exact String Matching Based on Suffix Arrays},
Author = {Abouelhoda, M. I. and Ohlebusch, E. and Kurtz, S.},
Booktitle = {Proc. of the 9th International Symposium on String Processing and Information Retrieval},
Year = {2002},
Pages = {31-43},
Publisher = pub-SPRINGER,
Series = ser-LNCS,
Volume = {2476},
Bdsk-url-1 = {http://www.zbh.uni-hamburg.de/staff/kurtz/papers/AboOhlKur2002.pdf},
Owner = {weese},
Timestamp = {2010.09.20},
Url = {http://www.zbh.uni-hamburg.de/staff/kurtz/papers/AboOhlKur2002.pdf}
}
@Article{Adamidi2011,
Title = {{De novo assembly and validation of planaria transcriptome by massive parallel sequencing and shotgun proteomics}},
Author = {Adamidi, C and Wang, Y and Gruen, D and Mastrobuoni, G and You, X and Tolle, D and Dodt, M and Mackowiak, S D and Gogol-D{\"o}ring, A and Oenal, P and Rybak, A and Ross, E and Alvarado, A S and Kempa, S and Dieterich, C and Rajewsky, N and Chen, W},
Journal = j-GR,
Year = {2011},
Month = jul,
Number = {7},
Pages = {1193--1200},
Volume = {21},
Owner = {esiragusa},
Timestamp = {2014.08.07}
}
@Article{Adams2000,
Title = {The genome sequence of Drosophila melanogaster},
Author = {Adams, Mark D and Celniker, Susan E and Holt, Robert A and Evans, Cheryl A and Gocayne, Jeannine D and Amanatides, Peter G and Scherer, Steven E and Li, Peter W and Hoskins, Roger A and Galle, Richard F and others},
Journal = {Science},
Year = {2000},
Number = {5461},
Pages = {2185--2195},
Volume = {287},
Publisher = {American Association for the Advancement of Science}
}
@InProceedings{Agarwal1998,
Title = {Detecting non-adjoining correlations within signals in {DNA}},
Author = {P. Agarwal and V. Bafna},
Booktitle = j-RECOMB,
Year = {1998},
Pages = {1-7},
Publisher = {ACM press},
Owner = {weese},
Timestamp = {2010.09.20}
}
@Article{Agarwala1996,
Title = {On the approximability of numerical taxonomy: fitting distances by tree metrics},
Author = {R. Agarwala and V. Bafna and M. Farach and B. Narayanan and M. Paterson and M. Thorup},
Journal = {Proc. of the 7th Annual ACM-SIAM Symposium on Discrete Algorithms},
Year = {1996},
Pages = {365-372},
Owner = {weese},
Timestamp = {2010.09.20}
}
@InProceedings{Aggarwal1988,
Title = {The Input/Output Complexity of Sorting and Related Problems},
Author = {Aggarwal, A. and Vitter, J.S.},
Booktitle = j-CACM,
Year = {1988},
Number = {31(9):1116{1127}},
Owner = {weese},
Timestamp = {2010.09.20}
}
@InProceedings{Agrawal1993,
Title = {Mining Association Rules between Sets of Items in Large Databases},
Author = {Rakesh Agrawal and Tomasz Imielinski and Arun N. Swami},
Booktitle = {Proc. of the 1993 ACM SIGMOD International Conference on Management of Data},
Year = {1993},
Editor = {Peter Buneman and Sushil Jajodia},
Pages = {207-216},
Publisher = pub-ACM,
Owner = {esiragusa},
Timestamp = {2014.08.07}
}
@InProceedings{Agrawal1994,
Title = {Fast Algorithms for Mining Association Rules},
Author = {Rakesh Agrawal and Ramakrishnan Srikant},
Booktitle = {Proc. 20th Int. Conf. Very Large Data Bases, {VLDB}},
Year = {1994},
Editor = {Jorge B. Bocca and Matthias Jarke and Carlo Zaniolo},
Month = {12--15~},
Pages = {487--499},
Publisher = {Morgan Kaufmann},
Owner = {esiragusa},
Timestamp = {2014.08.07}
}
@Article{Ahmadi2012,
Title = {Hobbes: optimized gram-based methods for efficient read alignment},
Author = {Ahmadi, Athena and Behm, Alexander and Honnalli, Nagesh and Li, Chen and Weng, Lingjie and Xie, Xiaohui},
Journal = j-NAR,
Year = {2012},
Number = {6},
Pages = {e41},
Volume = {40},
Bdsk-url-1 = {http://nar.oxfordjournals.org/content/40/6/e41.abstract},
Bdsk-url-2 = {http://dx.doi.org/10.1093/nar/gkr1246},
Doi = {10.1093/nar/gkr1246},
Eprint = {http://nar.oxfordjournals.org/content/40/6/e41.full.pdf+html},
Owner = {esiragusa},
Timestamp = {2014.08.07},
Url = {http://nar.oxfordjournals.org/content/40/6/e41.abstract}
}
@Book{Aho1974,
Title = {The Design and Analysis of Computer Algorithms},
Author = {Aho, A.V. and Hopcroft, J.E. and Ullman, J.D.},
Publisher = {Addison-Wesley},
Year = {1974},
ISBN = {0-20100029 -6},
Owner = {weese},
Timestamp = {2010.09.20}
}
@Article{Aho1975,
Title = {Efficient string matching: an aid to bibliographic search},
Author = {Aho, Alfred V. and Corasick, Margaret J.},
Journal = j-CACM,
Year = {1975},
Month = {June},
Pages = {333--340},
Volume = {18},
Acmid = {360855},
Address = {New York, NY, USA},
Bdsk-url-1 = {http://doi.acm.org/10.1145/360825.360855},
Doi = {http://doi.acm.org/10.1145/360825.360855},
ISSN = {0001-0782},
Issue = {6},
Keywords = {bibliographic search, computational complexity, finite state machines, information retrieval, keywords and phrases, string pattern matching, text-editing},
Numpages = {8},
Owner = {esiragusa},
Publisher = pub-ACM,
Timestamp = {2014.08.07},
Url = {http://doi.acm.org/10.1145/360825.360855}
}
@Article{Akutsu2001,
Title = {Dynamic programming algorithms for {RNA} secondary structure prediction with pseudoknots},
Author = {Akutsu, T.},
Journal = j-DAM,
Year = {2001},
Pages = {45-62},
Volume = {104},
Owner = {esiragusa},
Timestamp = {2014.08.07}
}
@Article{Alkan2009,
Title = {Personalized copy number and segmental duplication maps using next-generation sequencing},
Author = {Can Alkan and Jeffrey M Kidd and Tomas Marques-Bonet and Gozde Aksay and Francesca Antonacci and Fereydoun Hormozdiari and Jacob O Kitzman and Carl Baker and Maika Malig and Onur Mutlu and S. Cenk Sahinalp and Richard A Gibbs and Evan E Eichler},
Journal = {Nat. Genet.},
Year = {2009},
Number = {10},
Pages = {1061--1067},
Volume = {41},
Abstract = {Despite their importance in gene innovation and phenotypic variation, duplicated regions have remained largely intractable owing to difficulties in accurately resolving their structure, copy number and sequence content. We present an algorithm (mrFAST) to comprehensively map next-generation sequence reads, which allows for the prediction of absolute copy-number variation of duplicated segments and genes. We examine three human genomes and experimentally validate genome-wide copy number differences. We estimate that, on average, 73-87 genes vary in copy number between any two individuals and find that these genic differences overwhelmingly correspond to segmental duplications (odds ratio = 135; P < 2.2 x 10(-16)). Our method can distinguish between different copies of highly identical genes, providing a more accurate assessment of gene content and insight into functional constraint without the limitations of array-based technology.},
Bdsk-url-1 = {http://dx.doi.org/10.1038/ng.437},
Doi = {10.1038/ng.437},
Institution = {Department of Genome Sciences, University of Washington School of Medicine, Seattle, Washington, USA.},
Keywords = {Algorithms; Chromosome Mapping, methods; DNA, analysis/genetics; Gene Dosage; Gene Duplication; Genome, Human; Genomic Library; Humans; Polymorphism, Genetic; Sequence Analysis, DNA, methods},
Language = {eng},
Medline-pst = {ppublish},
Owner = {holtgrew},
Pii = {ng.437},
Pmid = {19718026},
Timestamp = {2012.01.24},
Url = {http://dx.doi.org/10.1038/ng.437}
}
@Article{Alt1991,
Title = {Computing a Maximum Cardinality Matching of a Bipartite Graph in Time ${O}(n^{1.5} \sqrt{m/\log n})$},
Author = {Helmut Alt and Norbert Blum and Kurt Mehlhorn and Markus Paul},
Journal = {Inform. Process. Lett.},
Year = {1991},
Pages = {237--240},
Volume = {37},
Owner = {weese},
Timestamp = {2010.09.20}
}
@InBook{Althaus2008,
Title = {Bioinformatics research and development},
Author = {E. Althaus and S. Canzar},
Chapter = {{LASA}: {A} tool for non-heuristic alignment of multiple sequences},
Pages = {489--498},
Publisher = pub-SPRINGER,
Year = {2008},
Owner = {weese},
Timestamp = {2010.09.20}
}
@InProceedings{Althaus2007,
Title = {{A Lagrangian relaxation approach for the multiple sequence alignment problem}},
Author = {E. Althaus and S. Canzar},
Booktitle = {{Proc.\ COCOA'07}},
Year = {2007},
Pages = {267-278},
Series = ser-LNCS,
Volume = {4616},
Owner = {esiragusa},
Timestamp = {2014.08.07}
}
@Article{Althaus2002,
Title = {Multiple sequence alignment with arbitrary gap costs: {C}omputing an optimal solution using polyhedral combinatorics},
Author = {Althaus, E. and Caprara, A. and Lenhof, H. P. and Reinert, K.},
Journal = j-BIOINF,
Year = {2002},
Pages = {S4-S16},
Volume = {18 Suppl 2},
Owner = {weese},
Timestamp = {2010.09.20}
}
@Article{Althaus2006,
Title = {A branch-and-cut algorithm for multiple sequence alignment},
Author = {E.~Althaus and A.~Caprara and H.-P.~Lenhof and K.~Reinert},
Journal = j-MATHPROG,
Year = {2006},
Number = {2-3},
Pages = {387-425},
Volume = {105},
Owner = {esiragusa},
Timestamp = {2014.08.07}
}
@InProceedings{Althaus2000,
Title = {A combinatorial approach to protein docking with flexible side-chains},
Author = {E. Althaus and O. Kohlbacher and H.-P. Lenhof and P. M{\"u}ller},
Booktitle = {Proc.\ RECOMB'00},
Year = {2000},
Pages = {15-24},
Owner = {esiragusa},
Timestamp = {2014.08.07}
}
@Article{Altschul1986,
Title = {Locally optimal subalignments using nonlinear similarity functions},
Author = {Altschul, S. F. and Erickson, B. W.},
Journal = {Bull. Math. Biol.},
Year = {1986},
Pages = {633-660},
Volume = {48},
Owner = {weese},
Timestamp = {2010.09.20}
}
@Article{Altschul1990,
Title = {Basic local alignment search tool.},
Author = {S. F. Altschul and W. Gish and W. Miller and E. W. Myers and D. J. Lipman},
Journal = j-JMB,
Year = {1990},
Month = oct,
Number = {3},
Pages = {403--410},
Volume = {215},
Abstract = {A new approach to rapid sequence comparison, basic local alignment search tool (BLAST), directly approximates alignments that optimize a measure of local similarity, the maximal segment pair (MSP) score. Recent mathematical results on the stochastic properties of MSP scores allow an analysis of the performance of this method as well as the statistical significance of alignments it generates. The basic algorithm is simple and robust; it can be implemented in a number of ways and applied in a variety of contexts including straightforward DNA and protein sequence database searches, motif searches, gene identification searches, and in the analysis of multiple regions of similarity in long DNA sequences. In addition to its flexibility and tractability to mathematical analysis, BLAST is an order of magnitude faster than existing sequence comparison tools of comparable sensitivity.},
Bdsk-url-1 = {http://dx.doi.org/10.1006/jmbi.1990.9999},
Doi = {10.1006/jmbi.1990.9999},
Institution = {National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, MD 20894.},
Keywords = {Algorithms; Amino Acid Sequence; Base Sequence; Databases, Factual; Mutation; Sensitivity and Specificity; Sequence Homology, Nucleic Acid; Software},
Language = {eng},
Medline-pst = {ppublish},
Owner = {bkehr},
Pii = {S0022283680799990},
Pmid = {2231712},
Timestamp = {2010.07.28}
}
@Article{Altschul1997,
Title = {Gapped {BLAST} and {PSI}-{BLAST}: a new generation of protein database search programs.},
Author = {S. F. Altschul and T. L. Madden and A. A. Sch\"affer and J. Zhang and Z. Zhang and W. Miller and D. J. Lipman},
Journal = j-NAR,
Year = {1997},
Number = {17},
Pages = {3389--3402},
Volume = {25},
Abstract = {The BLAST programs are widely used tools for searching protein and DNA databases for sequence similarities. For protein comparisons, a variety of definitional, algorithmic and statistical refinements described here permits the execution time of the BLAST programs to be decreased substantially while enhancing their sensitivity to weak similarities. A new criterion for triggering the extension of word hits, combined with a new heuristic for generating gapped alignments, yields a gapped BLAST program that runs at approximately three times the speed of the original. In addition, a method is introduced for automatically combining statistically significant alignments produced by BLAST into a position-specific score matrix, and searching the database using this matrix. The resulting Position-Specific Iterated BLAST (PSI-BLAST) program runs at approximately the same speed per iteration as gapped BLAST, but in many cases is much more sensitive to weak but biologically relevant sequence similarities. PSI-BLAST is used to uncover several new and interesting members of the BRCT superfamily.},
Institution = {National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, MD 20894, USA. [email protected]},
Keywords = {Algorithms; Amino Acid Sequence; Animals; DNA, chemistry; Databases, Factual; Humans; Molecular Sequence Data; Proteins, chemistry; Sequence Alignment; Software},
Language = {eng},
Medline-pst = {ppublish},
Owner = {bkehr},
Pii = {gka562},
Pmid = {9254694},
Timestamp = {2010.08.19}
}
@Article{Ambainis1997,
Title = {Nearly tight bounds on the learnability of evolution},
Author = {R. Ambainis and R. Desper and M. Farach and S. Kannan},
Journal = {Proc. of the 38th Annual IEEE Symposium on the Foundations of Computer Science},
Year = {1997},
Pages = {524-533},
Owner = {weese},
Timestamp = {2010.09.20}
}
@Article{Anson1997,
Title = {{ReAligner}: {A} Program for Refining {DNA} Sequence Multi-Alignments},
Author = {E. L. Anson and E. W. Myers},
Year = {1997},
Pages = {9--16},
Address = {Santa Fe, NM},
Bdsk-url-1 = {citeseer.ist.psu.edu/anson97realigner.html},
Booktitle = {Proc. of the1st Annual International Conference on Computational Molecular Biology (RECOMB)},
Owner = {weese},
Publisher = pub-ACM,
Timestamp = {2010.09.20},
Url = {citeseer.ist.psu.edu/anson97realigner.html}
}
@InProceedings{Anson1997a,
Title = {Re{A}ligner: {A} program for refining {DNA} sequence multi-alignments},
Author = {Anson,, Eric L. and Myers,, Eugene W.},
Booktitle = {Proc. 1st Annual International Conference on Computational Molecular Biology},
Year = {1997},
Address = {New York, NY, USA},
Pages = {9--16},
Publisher = pub-ACM,
Owner = {weese},
Timestamp = {2010.09.20}
}
@InCollection{Apostolico1985,
Title = {The myriad virtues of subword trees},
Author = {Apostolico, Alberto},
Booktitle = {Combinatorial algorithms on words},
Publisher = {Springer},
Year = {1985},
Pages = {85--96}
}
@Article{Apostolico2000,
Title = {{O}ptimal amnesic probabilistic automata or how to learn and classify proteins in linear time and space.},
Author = {Alberto Apostolico and Gill Bejerano},
Journal = j-JCB,
Year = {2000},
Number = {3-4},
Pages = {381--393},
Volume = {7},
Abstract = {Statistical modeling of sequences is a central paradigm of machine learning that finds multiple uses in computational molecular biology and many other domains. The probabilistic automata typically built in these contexts are subtended by uniform, fixed-memory Markov models. In practice, such automata tend to be unnecessarily bulky and computationally imposing both during their synthesis and use. Recently, D. Ron, Y. Singer, and N. Tishby built much more compact, tree-shaped variants of probabilistic automata under the assumption of an underlying Markov process of variable memory length. These variants, called Probabilistic Suffix Trees (PSTs) were subsequently adapted by G. Bejerano and G. Yona and applied successfully to learning and prediction of protein families. The process of learning the automaton from a given training set S of sequences requires theta(Ln2) worst-case time, where n is the total length of the sequences in S and L is the length of a longest substring of S to be considered for a candidate state in the automaton. Once the automaton is built, predicting the likelihood of a query sequence of m characters may cost time theta(m2) in the worst case. The main contribution of this paper is to introduce automata equivalent to PSTs but having the following properties: Learning the automaton, for any L, takes O (n) time. Prediction of a string of m symbols by the automaton takes O (m) time. Along the way, the paper presents an evolving learning scheme and addresses notions of empirical probability and related efficient computation, which is a by-product possibly of more general interest.},
Bdsk-url-1 = {http://dx.doi.org/10.1089/106652700750050844},
Doi = {10.1089/106652700750050844},
Keywords = {Algorithms, Computational Biology, Linear Models, Markov Chains, Models, Proteins, Statistical, 11108469},
Owner = {Marcello},
Pmid = {11108469},
Timestamp = {2007.03.15},
Url = {http://dx.doi.org/10.1089/106652700750050844}
}
@Article{Apweiler2004,
Title = {UniProt: the Universal Protein knowledgebase.},
Author = {Apweiler, R. and Bairoch, A. and Wu, C. H. and Barker, W. C. and Boeckmann, B. and Ferro, S. and Gasteiger, E. and Huang, H. and Lopez, R. and Magrane, M. and Martin, M. J. and Natale, D. A. and O'Donovan, C. and Redaschi, N. and Yeh, L. S.},
Journal = j-NAR,
Year = {2004},
Month = {January},
Number = {Database issue},
Volume = {32},
Abstract = {To provide the scientific community with a single, centralized, authoritative resource for protein sequences and functional information, the Swiss-Prot, TrEMBL and PIR protein database activities have united to form the Universal Protein Knowledgebase (UniProt) consortium. Our mission is to provide a comprehensive, fully classified, richly and accurately annotated protein sequence knowledgebase, with extensive cross-references and query interfaces. The central database will have two sections, corresponding to the familiar Swiss-Prot (fully manually curated entries) and TrEMBL (enriched with automated classification, annotation and extensive cross-references). For convenient sequence searches, UniProt also provides several non-redundant sequence databases. The UniProt NREF (UniRef) databases provide representative subsets of the knowledgebase suitable for efficient searching. The comprehensive UniProt Archive (UniParc) is updated daily from many public source databases. The UniProt databases can be accessed online (http://www.uniprot.org) or downloaded in several formats (ftp://ftp.uniprot.org/pub). The scientific community is encouraged to submit data for inclusion in UniProt.},
Address = {The EMBL Outstation--European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SD, UK. [email protected]},
Bdsk-url-1 = {http://view.ncbi.nlm.nih.gov/pubmed/14681372},
Citeulike-article-id = {921623},
ISSN = {1362-4962},
Keywords = {uniprot},
Owner = {weese},
Priority = {0},
Timestamp = {2008.01.14},
Url = {http://view.ncbi.nlm.nih.gov/pubmed/14681372}
}
@Article{Arlazarov1970,
Title = {On economical construction of the transitive closure of a directed graph},
Author = {Arlazarov, V. and Dinic, E. and Kronrod, M. and Faradzev, I.},
Journal = {Dokl. Akad. Nauk.},
Year = {1970},
Pages = {194},
Volume = {11},
Owner = {esiragusa},
Timestamp = {2014.08.07}
}
@Article{Armougom2006,
Title = {{{E}xpresso: {A}utomatic incorporation of structural information in multiple sequence alignments using 3{D}-{C}offee}},
Author = {Armougom, F. and Moretti, S. and Poirot, O. and Audic, S. and Dumas, P. and Schaeli, B. and Keduas, V. and Notredame, C.},
Journal = j-NAR,
Year = {2006},
Month = {Jul},
Pages = {W604--608},
Volume = {34},
Owner = {weese},
Timestamp = {2010.09.20}
}
@Misc{Asuncion2007,
Title = {{UCI} Machine Learning Repository},
Author = {A. Asuncion and D.J. Newman},
HowPublished = {\url{http://www.ics.uci.edu/~mlearn/MLRepository.html}},
Year = {2007},
Bdsk-url-1 = {http://archive.ics.uci.edu/ml/},
Institution = {University of California, Irvine, School of Information and Computer Sciences},
Owner = {weese},
Timestamp = {2008.04.02},
Url = {http://archive.ics.uci.edu/ml/}
}
@InCollection{Atteson1997,
Title = {The performance of neighbor-joining algorithms of phylogeny reconstruction},
Author = {K. Atteson},
Publisher = pub-SPRINGER,
Year = {1997},
Editor = {Tao Jiang and D. T. Lee},
Note = {Cocoon '97},
Pages = {101-110},
Series = ser-LNCS,
Volume = {1276},
Owner = {weese},
Timestamp = {2010.09.20}
}
@Book{Austern1998,
Title = {Generic Programming and the STL},
Author = {M. H. Austern},
Publisher = {Addison-Wesley},
Year = {1998},
Owner = {weese},
Timestamp = {2010.09.20}
}
@Book{Austern1998a,
Title = {Generic programming and the {STL}: {U}sing and extending the {C++} {Standard Template Library}},
Author = {M. H. Austern},
Publisher = {Addison-Wesley},
Year = {1998},
Series = {Addison-Wesley professional computing series},
Owner = {weese},
Timestamp = {2010.09.20}
}
@Article{Buehlmann1999,
Title = {Variable length Markov Chains},
Author = {Peter B\"{u}hlmann and Abraham J. Wyner},
Journal = {Ann. Statist.},
Year = {1999},
Number = {2},
Pages = {480-513},
Volume = {27},
Owner = {schulz_m},
Timestamp = {2010.09.20}
}
@Article{Backofen2004,
Title = {Local sequence-structure motifs in {RNA}},
Author = {R.~Backofen and S.~Will},
Journal = j-JBCB,
Year = {2004},
Month = {Dec},
Number = {4},
Pages = {681--698},
Volume = {2},
Abstract = {Ribonuclic acid (RNA) enjoys increasing interest in molecular biology; despite this interest fundamental algorithms are lacking, e.g. for identifying local motifs. As proteins, RNA molecules have a distinctive structure. Therefore, in addition to sequence information, structure plays an important part in assessing the similarity of RNAs. Furthermore, common sequence-structure features in two or several RNA molecules are often only spatially local, where possibly large parts of the molecules are dissimilar. Consequently, we address the problem of comparing RNA molecules by computing an optimal local alignment with respect to sequence and structure information. While local alignment is superior to global alignment for identifying local similarities, no general local sequence-structure alignment algorithms are currently known. We suggest a new general definition of locality for sequence-structure alignments that is biologically motivated and efficiently tractable. To show the former, we discuss locality of RNA and prove that the defined locality means connectivity by atomic and non-atomic bonds. To show the latter, we present an efficient algorithm for the newly defined pairwise local sequence-structure alignment (lssa) problem for RNA. For molecules of lengthes n and m, the algorithm has worst-case time complexity of O(n2 x m2 x max(n,m)) and a space complexity of only O(n x m). An implementation of our algorithm is available at http://www.bio.inf.uni-jena.de. Its runtime is competitive with global sequence-structure alignment.},
Keywords = {Algorithms; Base Sequence; Models, Chemical; Models, Molecular; Molecular Sequence Data; Nucleic Acid Conformation; RNA; Sequence Alignment; Sequence Analysis, RNA},
Owner = {markus},
Pii = {S0219720004000818},
Pmid = {15617161},
Timestamp = {2008.03.12}
}
@InProceedings{Baeza1999,
Title = {A fast algorithm on average for all-against-all sequence matching},
Author = {Ricardo A. Baeza-Yates and Gaston H. Gonnet},
Booktitle = {SPIRE/CRIWG},
Year = {1999},
Organization = {IEEE},
Pages = {16--23},
Ee = {http://computer.org/proceedings/spire/0268/02680016abs.htm},
Owner = {esiragusa},
Timestamp = {2014.08.07}
}
@Article{Baeza1999b,
Title = {Faster approximate string matching},
Author = {Ricardo A. Baeza-Yates and Gonzalo Navarro},
Journal = {Algorithmica},
Year = {1999},
Number = {2},
Pages = {127-158},
Volume = {23},
Bibsource = {DBLP, http://dblp.uni-trier.de},
Ee = {http://dx.doi.org/10.1007/PL00009253},
Owner = {esiragusa},
Timestamp = {2014.08.07}
}
@InProceedings{Baeza1992,
Title = {Fast and practical approximate string matching},
Author = {Baeza-Yates, Ricardo A and Perleberg, Chris H},
Booktitle = {Combinatorial Pattern Matching},
Year = {1992},
Organization = {Springer},
Pages = {185--192},
Owner = {esiragusa},
Timestamp = {2014.08.10}
}
@Book{Baeza1999c,
Title = {Modern Information Retrieval},
Author = {Baeza-Yates, Ricardo A. and Ribeiro-Neto, Berthier},
Publisher = {Addison-Wesley},
Year = {1999},
ISBN = {020139829X},
Owner = {esiragusa},
Timestamp = {2014.08.07}
}
@Book{Baeza2011,
Title = {Modern Information Retrieval -- the concepts and technology behind search, Second edition},
Author = {Ricardo A. Baeza-Yates and Berthier A. Ribeiro-Neto},
Publisher = {Pearson Education Ltd., Harlow, England},
Year = {2011},
Bibsource = {DBLP, http://dblp.uni-trier.de},
Ee = {http://www.mir2ed.org/},
ISBN = {978-0-321-41691-9},
Owner = {esiragusa},
Timestamp = {2014.08.07}
}
@InProceedings{Bafna2000,
Title = {The Conserved Exon Method for Gene Finding},
Author = {V. Bafna and D.~H. Huson},
Year = {2000},
Address = {Menlo Park, California},
Editor = {R. Altman and T.~L. Bailey and P. Bourne and M. Gribskov and T. Lengauer and I.~N. Shindyalov and L.~F. Ten Eyck and H. Weissig},
Pages = {3-12},
Publisher = {AAAI Press},
Owner = {weese},
Timestamp = {2010.09.20}
}
@InProceedings{Bafna1995,
Title = {Computing similarity between {RNA} strings},
Author = {V. Bafna and S. Muthukrishnan and R. Ravi},
Year = {1995},
Number = {937},
Pages = {1--16},
Publisher = pub-SPRINGER,
Series = {CPM~'95},
Optaddress = {Espoo, Finland},
Opteditor = {Z. Galil and E. Ukkonen},
Opturl = {citeseer.nj.nec.com/bafna95computing.html},
Owner = {esiragusa},
Timestamp = {2014.08.07}
}
@Article{Bailey2002,
Title = {Recent Segmental \marginstar Duplications in the Human Genome},
Author = {Bailey, J.~A. and Gu, Z. and Clark, R.~A. and Reinert, K. and Samonte, R.~V. and Schwartz, S.~S. and Adams, M.~D. and Myers, E.~W. and Li, P. and Eichler, E.~E.},
Journal = j-Science,
Year = {2002},
Pages = {1003-1007},
Volume = {297},
Owner = {weese},
Timestamp = {2010.09.20}
}
@Article{Bailey2002a,
Title = {Recent Segmental Duplications in the Human Genome},
Author = {Bailey, J.~A. and Gu, Z. and Clark, R.~A. and Reinert, K. and Samonte, R.~V. and Schwartz, S.~S. and Adams, M.~D. and Myers, E.~W. and Li, P. and Eichler, E.~E.},
Journal = j-Science,
Year = {2002},
Pages = {1003-1007},
Volume = {297},
Owner = {weese},
Timestamp = {2010.09.20}
}
@Article{Bailey2001,
Title = {Segmental duplications: organization and impact within the current human genome project assembly},
Author = {Bailey, Jeffrey A and Yavor, Amy M and Massa, Hillary F and Trask, Barbara J and Eichler, Evan E},
Journal = {Genome research},
Year = {2001},
Number = {6},
Pages = {1005--1017},
Volume = {11},
Owner = {esiragusa},
Publisher = {Cold Spring Harbor Lab},
Timestamp = {2014.08.08}
}
@Article{Bailey2006,
Title = {{MEME}: {D}iscovering and analyzing {DNA} and protein sequence motifs},
Author = {Bailey, T. L. and Williams, N. and Misleh, C. and Li, W. W.},
Journal = j-NAR,
Year = {2006},
Number = {suppl 2},
Pages = {W369-373},
Volume = {34},
Owner = {weese},
Timestamp = {2010.09.20}
}
@Article{Baldauf1993,
Title = {Animals and fungi are each other's closest relatives: congruent evidence from multiple proteins},
Author = {S. L. Baldauf and J. D. Palmer},
Journal = {Proc. Natn. Acad. Sci. USA},
Year = {1993},
Pages = {11558-11562},
Owner = {weese},
Timestamp = {2010.09.20},
Voulme = {90}
}
@Article{Bandelt1992,
Title = {A canonical decomposition theory for metrics on a finite set},
Author = {H.-J. Bandelt and A. W. M. Dress},
Journal = {Advances in Mathematics},
Year = {1992},
Pages = {47-105},
Volume = {92},
Owner = {weese},
Timestamp = {2010.09.20}
}
@Article{Baron2005,
Title = {Antisequential Suffix Sorting for {BWT}-Based Data Compression},
Author = {Dror Baron and Yoram Bresler},
Journal = j-IEEETC,
Year = {2005},
Number = {4},
Pages = {385--397},
Volume = {54},
Address = {Los Alamitos, CA, USA},
Bdsk-url-1 = {http://doi.ieeecomputersociety.org/10.1109/TC.2005.56},
Doi = {http://doi.ieeecomputersociety.org/10.1109/TC.2005.56},
ISSN = {0018-9340},
Owner = {esiragusa},
Publisher = pub-IEEE,
Timestamp = {2014.08.07}
}
@Article{Barski2007,
Title = {High-Resolution Profiling of Histone Methylations in the Human Genome},
Author = {A. Barski and S. Cuddapah and K. Cui and T. Roh and D. Schones and Z. Wang and G. Wei and I. Chepelev and K. Zhao},
Journal = {Cell},
Year = {2007},
Pages = {823-837},
Volume = {129},
Owner = {weese},
Timestamp = {2010.09.20}
}
@Book{Barthelemy1991,
Title = {Trees and Proximity Representations},
Author = {Jean-Pierre Barth\'elemy},
Publisher = {Wiley},
Year = {1991},
Owner = {weese},
Pubaddress = {Chichester},
Timestamp = {2010.09.20}
}
@InProceedings{Barve1999,
Title = {A Simple and Efficient Parallel Disk Mergesort},
Author = {Barve, R.D. and Vitter, J.S.},
Booktitle = {{ACM} Symposium on Parallel Algorithms and Architectures},
Year = {1999},
Pages = {232--241},
Owner = {weese},
Timestamp = {2010.09.20}
}
@PhdThesis{Batten2010,
Title = {Simplified vector-thread architectures for flexible and efficient data-parallel accelerators},
Author = {Batten, Christopher Francis},
School = {Massachusetts Institute of Technology},
Year = {2010},
Owner = {esiragusa},
Timestamp = {2014.08.07}
}
@Article{Batzoglou2000,
Title = {Human and Mouse Gene Structure: Comparative Analysis and Application to Exon Prediction},
Author = {S. Batzoglou and L. Pachter and J.P. Mesirov and B. Berger and E.S. Lander},
Journal = j-GR,
Year = {2000},
Pages = {950--958},
Volume = {10},
Owner = {weese},
Timestamp = {2010.09.20}
}
@InProceedings{Bauer2004,
Title = {Structural Alignment \marginstar of Two \mbox{RNA} Sequences with Lagrangian Relaxation},
Author = {M. Bauer and G. Klau},
Booktitle = {Proc. of the 15th International Symposium, ISAAC 2004, Hong Kong},
Year = {2004},
Pages = {113-125},
Publisher = pub-SPRINGER,
Series = ser-LNCS,
Volume = {3341},
Owner = {weese},
Timestamp = {2010.09.20}
}
@Article{Bauer2008,
Title = {{An exact mathematical programming approach to multiple {RNA} sequence-structure alignment}},
Author = {Bauer, M. and Klau, G.W. and Reinert, K.},
Journal = {Algorithmic Operations Research},
Year = {2008},
Note = {to appear},
Owner = {mbauer},
Timestamp = {2007.12.17}
}
@InProceedings{Bauer2005,
Title = {Fast \marginstar and Accurate Structural \mbox{RNA} Alignment by Progressive Lagrangian Relaxation},
Author = {Bauer, M. and Klau, G.W. and Reinert, K.},
Booktitle = {Proc. of the 1st International Symposium on Computational Life Science (CompLife-05)},
Year = {2005},
Pages = {217-228},
Owner = {weese},
Timestamp = {2010.09.20}
}
@InProceedings{Bauer2005a,
Title = {Multiple \marginstar Structural \mbox{RNA} Alignment with Lagrangian Relaxation},
Author = {Bauer, M. and Klau, G.W. and Reinert, K.},
Booktitle = {Proc. of the 5th Workshop on Algorithms Bioinformatics (WABI-05)},
Year = {2005},
Pages = {303-314},
Owner = {weese},
Timestamp = {2010.09.20}
}
@InProceedings{Bauer2004a,
Title = {{Structural alignment of two {RNA} sequences with Lagrangian relaxation}},
Author = {Bauer, M. and Klau, G.~W.},
Booktitle = {{Proc.\ ISAAC'04}},
Year = {2004},
Number = {3341},
Pages = {113-123},
Publisher = pub-SPRINGER,
Series = ser-LNCS,
Bdsk-url-1 = {http://dx.doi.org/10.1007/b104582},
Doi = {10.1007/b104582},
Location = {Hongkong, China},
Owner = {esiragusa},
Timestamp = {2014.08.07}
}
@Article{Bauer2007,
Title = {{Accurate multiple sequence-structure alignment of {RNA} sequences using combinatorial optimization}},
Author = {M. Bauer and G.~W.~Klau and K. Reinert},
Journal = j-BMCBIO,
Year = {2007},
Month = {Jul},
Pages = {271},
Volume = {8},
Owner = {esiragusa},
Timestamp = {2014.08.07}
}
@InProceedings{Bauer2005b,