[BioC] Deciding on a cut off after QC

Ankit Pal pal_ankit2000 at yahoo.com
Tue May 17 06:58:16 CEST 2005


Dear Dr Smyth,
I would prefer using the p-value with a threshold
value of 0.05.
In the case of an experiment(I sent you the code) I
did, the reult file contains p-values (after fdr) in
range of 0.96 - 0.97.
How did I get such values and where do I place a cut
off in this case?
Am I doing something wrong?
In the user guide it says
"If none of the raw p-value are less than 1/G,
where G is the number of genes included in the fit,
then all of the adjusted p-values will the
equal to 1.Since 1/G is about the expected size of the
smallest p-values given purely random variation and
uniform p-values, this means that there
is no overall evidence of differential expression."

I am not too sure I understand what it means.
Should there be atleast one p-value < 1/G?

I am attaching a sample data output file to this mail.
What should be done in my case?
Thank you,
sincerely,
-Ankit




--- Gordon Smyth <smyth at wehi.edu.au> wrote:
> At 01:48 PM 17/05/2005, Ankit Pal wrote:
> >Dear Adai,
> >Thank you for the detailed response.
> >Correct me if I'm wrong.
> >What you are saying is that after applying the
> "fdr"
> >I give a cut off of 0.05 for the p-value and write
> all
> >those spots into an object (positives).
> >That means, I do  not consider the B values.
> 
> This is one way to proceed. Have you read the
> section in the User's Guide 
> on "Statistics for differential expression" which
> discusses which statistic 
> to use?
> 
> >In essence, it is just a one sample t test afetr
> >adjusting the p-value and taking into consideration
> >all those spots that have a p-value < 0.05?
> >
> > From my code in a previous mail to Gordon Smyth, I
> >have done a quality control (QC) using parameters
> and
> >threshold values prescribed by genepix.
> >I know from experience, a large number of spots do
> not
> >get through the filter.
> >As I understand from LIMMA, a weight of "0" is
> given
> >to any spot that does not get through the QC
> filter.
> >How do I exclude these spots from the final result
> >summary file?
> 
> These spots are already excluded. You seem to be
> confused by the fact that 
> excluding a spot does not exclude the corresponding
> probe, since there are 
> four spots for each probe. You will get a valid
> t-statistic and p-value for 
> a probe if any one of the spots for that probe get a
> positive weight. (Note 
> you can get a Bayesian t-statistic even for a probe
> with no residual df.)
> 
> >I need to get a set of significantly differentially
> >expressed genes that have got through the QC
> filter.
> >How do I do it using LIMMA?
> 
> This is what you have been getting all along.
> 
> Gordon
> 
> >Thank you,
> >-Ankit
> 
> 


		
__________________________________ 


-------------- next part --------------
      Block Row Column        ID                                         Name       M      A      t P.Value      B
15254    19  26     17 NM_033613                              scl0001747.1_14  1.4052  5.986  5.654  0.9627 -4.360
29822    37  26     23  AB117944                              scl0003290.1_30  1.5988  5.571  5.557  0.9627 -4.362
18221    23  16     18 NM_033578                              scl093703.1_214  1.3846  7.291  5.498  0.9627 -4.363
33734    42  21     25 NM_175677                            scl00319236.1_170  1.2535  7.807  5.123  0.9627 -4.370
30787    39   2     18         -                             scl11230.1.1_125  1.5640 10.169  4.974  0.9627 -4.374
21676    27  24     21 NM_175657                              scl00319161.1_8  1.3489  6.576  4.839  0.9627 -4.377
10983    14  18      7 NM_007999                               scl014156.1_86  1.2005  4.078  4.821  0.9627 -4.377
26138    33  10      7 NM_028209                              scl24036.11_204  1.4833 10.811  4.772  0.9627 -4.378
25635    32  21     16 NM_207298                             scl0099151.1_201  1.2067  7.145  4.751  0.9627 -4.379
33449    42  11     10         -                               scl42410.1.3_0 -1.1950  6.997 -4.685  0.9627 -4.381
11683    15  14      6         -                              scl35668.26.1_1  1.3209  2.752  4.499  0.9627 -4.385
13694    17  28     21         -                        scl000055.1_1_REVCOMP  1.1755  6.008  4.496  0.9627 -4.386
14944    19  15      4         -                           scl27546.1.1069_39 -1.0644  6.182 -4.489  0.9627 -4.386
29762    37  24     17 NM_025284                             scl0019240.2_329  1.2948  9.347  4.479  0.9627 -4.386
11789    15  18      4 XM_148353                              scl067609.1_307  1.6845  3.191  4.433  0.9627 -4.387
2764      4  13     13 NM_178934                              scl39088.5.1_30  1.1694  6.481  4.367  0.9627 -4.389
29678    37  21     14 NM_146075                            scl00224640.2_275  1.2598  6.786  4.359  0.9627 -4.389
33435    42  10     23         -                             scl11006.1.1_298 -1.5154  4.933 -4.258  0.9627 -4.393
12481    16  13     22 NM_173731                              scl36691.12_254  1.3582  2.918  4.248  0.9627 -4.393
19597    25   7     19 NM_147027                           scl46618.1.187_149  2.2705  9.797  4.190  0.9627 -4.395
32290    40  28     10 NM_153798                               scl0000113.1_1  1.0130  4.491  4.157  0.9627 -4.396
11762    15  17      4         -                               scl073362.2_30  1.4282  2.531  4.128  0.9627 -4.397
15866    20  19      9         -                               scl077449.2_20  1.3121  2.870  4.127  0.9627 -4.397
14762    19   8     11 NM_025536                               scl47782.2_279  1.0271  5.729  4.109  0.9627 -4.397
27464    34  29     11 NC_001819 9629514_329 | Rauscher murine leukemia virus  1.2519  9.932  4.048  0.9627 -4.399
32482    41   5     14 NM_016875                              scl41354.10.1_7  1.3216 10.076  4.030  0.9627 -4.400
9365     12  18      7         -                               scl069350.1_47  1.2922  4.009  4.003  0.9627 -4.401
15841    20  18     11 NM_027268                               scl069938.2_27  1.7431  2.031  4.000  0.9627 -4.401
7426     10   6     10         -                               scl28349.3_240  1.1551  7.934  3.981  0.9627 -4.402
33257    42   4      7 NM_028243                              scl32376.11_593  0.9688  6.692  3.977  0.9627 -4.402
15479    20   4     27 NM_146551                              scl5601.1.1_211  0.9451  4.314  3.962  0.9627 -4.402
5896      8   9     17 NM_028108                                scl49079.8_50 -1.2436  6.015 -3.962  0.9627 -4.402
21375    27  13     17 NM_007830                                scl16375.7_22  0.9112  6.972  3.909  0.9627 -4.404
21793    27  29      3    K00604   IGHV1S16|K00604|Ig_heavy_variable_1S16_234  0.9863  6.598  3.904  0.9627 -4.404
29994    38   3      7 NM_018827                               scl33727.4.1_6  1.0797  7.621  3.891  0.9627 -4.405
13393    17  17     17 NM_019737                                scl056386.2_4  1.2250  3.139  3.871  0.9627 -4.406
15345    19  29     27         -                            AFFX-BioB-M-at_62  0.9412  6.040  3.864  0.9627 -4.406
29758    37  24     13 NM_013655                             scl0020315.1_134  0.9538  5.124  3.861  0.9627 -4.406
15716    20  13     21 NM_175528                              scl29095.10_195  1.3016  2.642  3.847  0.9627 -4.406
10670    14   6     18 XM_134476                             scl34486.9.1_200  1.7255  9.395  3.839  0.9627 -4.407


More information about the Bioconductor mailing list