My osX WORD can have a pagination problem. The 'page view' and final print can have different paginations. I have correct this problem using PDF.
This site is to serve as my note-book and to effectively communicate with my students and collaborators. Every now and then, a blog may be of interest to other researchers or teachers. Views in this blog are my own. All rights of research results and findings on this blog are reserved. See also http://youtube.com/c/hongqin @hongqin
Sunday, June 29, 2014
Saturday, June 28, 2014
HP Laser color jet M500
odd page first
even page, in reverse order (For odd number of total page, the last odd page has to be left out for even-page print).
Make 'collate' is check for multiple copies.
To make sure proper font size are use, choose 'actual size' and do not use 'shrink' or 'auto fit'.
even page, in reverse order (For odd number of total page, the last odd page has to be left out for even-page print).
Make 'collate' is check for multiple copies.
To make sure proper font size are use, choose 'actual size' and do not use 'shrink' or 'auto fit'.
Friday, June 27, 2014
Tuesday, June 24, 2014
q-value calculation based on fisher.test p-values
https://www.biostars.org/p/46187/
self regulated learning
slides handout
http://www.magnapubs.com/handouts/?cid=1185
Key terms/points:
self regulated learning
experiential learning, such as field work, simulation, role play,etc. (Case studies?)
meta-assignment
paraphrasing assignments
revise study game plans
self-reflective writing
Activity #2, awareness-raising one minute paper: How does the materials you've heard so far connect or conflict with your prior knowledge?
Activity #3
Qin: It seems the SRL basically to make sure students are self conscious about their learning behavior.
http://www.magnapubs.com/handouts/?cid=1185
Key terms/points:
self regulated learning
experiential learning, such as field work, simulation, role play,etc. (Case studies?)
meta-assignment
paraphrasing assignments
revise study game plans
self-reflective writing
Activity #2, awareness-raising one minute paper: How does the materials you've heard so far connect or conflict with your prior knowledge?
Activity #3
Qin: It seems the SRL basically to make sure students are self conscious about their learning behavior.
Sunday, June 22, 2014
research intro to 5th graders
Faculty Mentor: Hong Qin
Project Overview (a couple of sentences)
Why do some people tend to live a long life? My lab thinks that the wirings of our cells is part of the reasons. My lab thinks the interactions of genes in our cells behave like complex networks such as the internet. We use the mathematical models of these complex networks to study aging and to find out the network components that are important for longevity. With the ASPIRE support, a student is analyzing experimental data to verify our mathematical predictions.
Project Overview (a couple of sentences)
Why do some people tend to live a long life? My lab thinks that the wirings of our cells is part of the reasons. My lab thinks the interactions of genes in our cells behave like complex networks such as the internet. We use the mathematical models of these complex networks to study aging and to find out the network components that are important for longevity. With the ASPIRE support, a student is analyzing experimental data to verify our mathematical predictions.
Wednesday, June 18, 2014
Qvalue, how to choose lambda?
How to choose lambda for Qvalue calculation?
Sometimes, qvalue are smaller than uncorrected pvalues. Based on https://www.biostars.org/p/46187/
A very nice manual is available here:
http://genomics.princeton.edu/storeylab/qvalue/manual.pdf
Sometimes, qvalue are smaller than uncorrected pvalues. Based on https://www.biostars.org/p/46187/
First, I think you are correct with being concerned about the estimated q-values and the presence of the warning. In my understanding, p-values adjusted for multiple testing should always be greater-equal to the unadjusted p-values. The warning also indicates that something in the estimation process went wrong. It might have to do with your p-values not fully covering the whole interval [0,1]. If the method tries to find an estimate for the percentage of true null-hypotheses in the data, due to the lack of p-values close or equal to 1, it might not be able to do so. At least this is my interpretation of the warning message.
A very nice manual is available here:
http://genomics.princeton.edu/storeylab/qvalue/manual.pdf
One of the expert replied to my email:
We usually let the qvalue package select the optimal lambda (see the 2002 pnas paper), as the optimal value minimizes the variance of the computed q-values around the estimated mean.
Other than that, a lower lambda value would mean pi0 estimates would be higher. lambda 0 would result in the conservative BH adjusted p-values. Tuesday, June 17, 2014
print paper choices, index folders
http://www.walmart.com/ip/Avery-Ready-Index-Table-of-Contents-Dividers-11186-8-Tab-6-Sets/14660099
http://www.walmart.com/ip/Avery-Ready-Index-Table-of-Contents-Dividers-11186-8-Tab-6-Sets/14660099
http://www.staples.com/sbd/cre/products/perm/merch020622_paper_buying/
HammerMill® Heavyweight Laser Print Paper, 28 lb., 8 1/2" x 11", Ream
- Reviews forHammerMill® Heavyweight Laser Print Paper, 28 lb., 8 1/2" x 11", Ream
- 4.5stars
- (14 reviews)
- 28 lb.
- 98 US / 107+ Euro Bright
- Supersmooth sheet
Journal of computational and applied mathematics
http://www.journals.elsevier.com/journal-of-computational-and-applied-mathematics/
omics: journal of applied and computational mathematics
Papers may be submitted from any discipline related to Journals Classification which includes the following fields but are not limited to: | ||
Applied mathematical analysis
|
Applied Mathematics Modeling, Artificial Intelligence
| |
Computer Science & technology,
|
Stochastic methods, Data Structures and Algorithms
| |
Differential equations; applied probability
|
Theory of computation and complexity of algorithms
| |
Solving mathematical problems by computer simulation
|
Computer-assisted research in areas of mathematics
| |
Symbolic computation and computer algebra systems
|
Computational Theories, Electronics System
| |
Computational geometry, Information Technology
|
Computational topology, Machine Learning and Computational Learning Theory
| |
If possible, I would appreciate receiving your submission by June 30th, 2014 or let us know your possibility regarding submission date.
| ||
You may submit your paper to http://www.omicsgroup.org/editorialtracking/computational/SubmitManuscript.php | ||
or as e-mail attachment to the Editorial Office at editor.jacm@omicsonline.org OR at editor.jacm@omicsgroup.biz |
FDR, false discovery rate
http://en.wikipedia.org/wiki/False_discovery_rate
http://www.totallab.com/products/samespots/support/faq/pq-values.aspx
p.adjust BH fdr correction
http://stackoverflow.com/questions/10323817/r-unexpected-results-from-p-adjust-fdr
http://www.researchgate.net/post/How_do_I_adjust_the_p_value_of_haplotype_association_study_for_multiple_testing
p.adjust, example
#
require(graphics)
set.seed(123)
x <- rnorm(50, mean = c(rep(0, 25), rep(3, 25)))
p <- 2*pnorm(sort(-abs(x)))
round(p, 3)
round(p.adjust(p), 3)
round(p.adjust(p, "BH"), 3)
## or all of them at once (dropping the "fdr" alias):
p.adjust.M <- p.adjust.methods[p.adjust.methods != "fdr"]
p.adj <- sapply(p.adjust.M, function(meth) p.adjust(p, meth))
p.adj.60 <- sapply(p.adjust.M, function(meth) p.adjust(p, meth, n = 60))
stopifnot(identical(p.adj[,"none"], p), p.adj <= p.adj.60)
round(p.adj, 3)
## or a bit nicer:
noquote(apply(p.adj, 2, format.pval, digits = 3))
## and a graphic:
matplot(p, p.adj, ylab="p.adjust(p, meth)", type = "l", asp = 1, lty = 1:6,
main = "P-value adjustments")
legend(0.7, 0.6, p.adjust.M, col = 1:6, lty = 1:6)
## Can work with NA's:
pN <- p; iN <- c(46, 47); pN[iN] <- NA
pN.a <- sapply(p.adjust.M, function(meth) p.adjust(pN, meth))
## The smallest 20 P-values all affected by the NA's :
round((pN.a / p.adj)[1:20, ] , 4)
require(graphics)
set.seed(123)
x <- rnorm(50, mean = c(rep(0, 25), rep(3, 25)))
p <- 2*pnorm(sort(-abs(x)))
round(p, 3)
round(p.adjust(p), 3)
round(p.adjust(p, "BH"), 3)
## or all of them at once (dropping the "fdr" alias):
p.adjust.M <- p.adjust.methods[p.adjust.methods != "fdr"]
p.adj <- sapply(p.adjust.M, function(meth) p.adjust(p, meth))
p.adj.60 <- sapply(p.adjust.M, function(meth) p.adjust(p, meth, n = 60))
stopifnot(identical(p.adj[,"none"], p), p.adj <= p.adj.60)
round(p.adj, 3)
## or a bit nicer:
noquote(apply(p.adj, 2, format.pval, digits = 3))
## and a graphic:
matplot(p, p.adj, ylab="p.adjust(p, meth)", type = "l", asp = 1, lty = 1:6,
main = "P-value adjustments")
legend(0.7, 0.6, p.adjust.M, col = 1:6, lty = 1:6)
## Can work with NA's:
pN <- p; iN <- c(46, 47); pN[iN] <- NA
pN.a <- sapply(p.adjust.M, function(meth) p.adjust(pN, meth))
## The smallest 20 P-values all affected by the NA's :
round((pN.a / p.adj)[1:20, ] , 4)
Thursday, June 12, 2014
screencast softwares
Windows 7:
Screencast-o-matic
see http://teaching.software-carpentry.org/2014/05/30/motivational-screencast-for-data-structures-in-r/#comment-10949
Camtasia
OS X:
QuickTIme
screen-flow
https://www.telestream.net/screenflow/
OBS, open broadcaster software
OpenShot video editor
Screencast-o-matic
see http://teaching.software-carpentry.org/2014/05/30/motivational-screencast-for-data-structures-in-r/#comment-10949
Camtasia
OS X:
QuickTIme
screen-flow
https://www.telestream.net/screenflow/
OBS, open broadcaster software
OpenShot video editor
Wednesday, June 11, 2014
common discrete distributions
see wikipedia
Bernoulli, binomial, uniform, genometric, hyptergenomeric, negative binomial, poisson
Bernoulli, binomial, uniform, genometric, hyptergenomeric, negative binomial, poisson
git
To fix Windows git problems to download ~/novice/
git checkout -f remotes/orgin/gh-pages
git checkout -f gh-pages
git checkout -f remotes/orgin/gh-pages
git checkout -f gh-pages
Software carpentry bootcamp, day 2
Throughout the day, 29 participants showed up.
9:30am, 23 participants, including 8 Spelman faculty, 7 Spelman students.
10:15, 27 participants when more people trickled in.
2:20pm, 18 participants are still here.
After coffee break, 3pm, 13 participants.
On many Windows, notepad is in the $PATH and can be invoked directly.
One user has Avast that prevent git-bash from working properly.
To fix Windows git problems to download ~/novice/
git checkout -f remotes/orgin/gh-pages
git checkout -f gh-pages
import glob
print glob.glob("*.ipnb")
assert type(x) == int, "x is not an integer"
Indentation of Python need to be more explicit.
#for argument parsing
argparse
parser.add_argument()
9:30am, 23 participants, including 8 Spelman faculty, 7 Spelman students.
10:15, 27 participants when more people trickled in.
2:20pm, 18 participants are still here.
After coffee break, 3pm, 13 participants.
On many Windows, notepad is in the $PATH and can be invoked directly.
One user has Avast that prevent git-bash from working properly.
To fix Windows git problems to download ~/novice/
git checkout -f remotes/orgin/gh-pages
git checkout -f gh-pages
import glob
print glob.glob("*.ipnb")
assert type(x) == int, "x is not an integer"
Indentation of Python need to be more explicit.
#for argument parsing
argparse
parser.add_argument()
Tuesday, June 10, 2014
Install git 1.9.2 on osX and reset $PATH
Install git 1.9.2, and it is in /usr/local/git/bin
The older 1.8.x version are in /usr/bin and /usr/local/bin. The first is Apple default git. The second is installed by GitHub.
$nano -w .bash_profile
.....
# use 1.9.2 git in shell
export PATH="/usr/local/git/bin:$PATH"
byte:~ hqin$ source .bash_profile
byte:~ hqin$ which git
/usr/local/git/bin/git
byte:~ hqin$ git --version
git version 1.9.2
Xcode and make install
Xcode -> preference -> Download -> command line tools.
Reference
http://holgr.com/blog/2012/02/xcode-4-3-and-homebrew-where-did-my-command-line-tools-go/
Reference
http://holgr.com/blog/2012/02/xcode-4-3-and-homebrew-where-did-my-command-line-tools-go/
Software carpentry Bootcamp day1
====
Vendor require check payment for breakfast. We arranged PO and it satisfied the vendor.
Note: Morning traffic should be factored in during travel.
There were 65 online registration, and about 35 attended. (2 new people showed up on day 2, so total unique people is 37).
====
Use pink and green pos-tit. Pink indicates asking for help.
Use Mo-pad to give commands
https://etherpad.mozilla.org/2014-06-10-spelman
Morning on Unix shell and Git.
In windows, git-bash show some directory error when running "git clone ....". Major files of the direction are cloned, so we ignored the error.
10am: There are 32 participants + 2 instructors.
Later, a couple more people showed up.
The bootcamp ended at 4:30pm. Participants wrote their comments on the postIt. Some said too slow, some said too fast. Some ask for explicit key-board short-cut explanations.
Useful keyboard short cuts include:
shell: tab, arrows
ipython: shift-enter -> 'run'
Note:
->About half of the participants did not install before bootcamp. Most users use Windows.
->"git clone" ran into a compatability problem with Windows. Users were asked to download Github repot in zip file.
->Users with osX sometimes have older versions.
In one case, Xcode was installed without command-line tools, and this leads to "git clone" running errors.
Afternoon on ipython
shift-enter -> 'run'
Problems
A common problem is the windows firewall block ipython access to notebook. We can disable windows firewall.
Another common problem is to "ipython notebook" not in the same directory with the data file.
We had a break at 2pm. About 10 people left during the break.
After 3:30pm, many undergraduates started web surfacing. There are 23 participants + 2 instructor left.
Vendor require check payment for breakfast. We arranged PO and it satisfied the vendor.
Note: Morning traffic should be factored in during travel.
There were 65 online registration, and about 35 attended. (2 new people showed up on day 2, so total unique people is 37).
====
Use pink and green pos-tit. Pink indicates asking for help.
Use Mo-pad to give commands
https://etherpad.mozilla.org/2014-06-10-spelman
Morning on Unix shell and Git.
In windows, git-bash show some directory error when running "git clone ....". Major files of the direction are cloned, so we ignored the error.
10am: There are 32 participants + 2 instructors.
Later, a couple more people showed up.
The bootcamp ended at 4:30pm. Participants wrote their comments on the postIt. Some said too slow, some said too fast. Some ask for explicit key-board short-cut explanations.
Useful keyboard short cuts include:
shell: tab, arrows
ipython: shift-enter -> 'run'
Note:
->About half of the participants did not install before bootcamp. Most users use Windows.
->"git clone" ran into a compatability problem with Windows. Users were asked to download Github repot in zip file.
->Users with osX sometimes have older versions.
In one case, Xcode was installed without command-line tools, and this leads to "git clone" running errors.
Afternoon on ipython
shift-enter -> 'run'
Problems
A common problem is the windows firewall block ipython access to notebook. We can disable windows firewall.
Another common problem is to "ipython notebook" not in the same directory with the data file.
We had a break at 2pm. About 10 people left during the break.
After 3:30pm, many undergraduates started web surfacing. There are 23 participants + 2 instructor left.
Monday, June 9, 2014
Phylogeny in R and Python
http://www.r-bloggers.com/phylogenies-in-r-and-python/
Saturday, June 7, 2014
annaconda ipython
https://www.youtube.com/watch?v=NwyIuWK80gQ
Byte:anaconda hqin$ source bin/activate ~/anaconda/discarding /Users/hqin/anaconda/bin from PATH
prepending /Users/hqin/anaconda/bin to PATH
(/Users/hqin/anaconda)Byte:anaconda hqin$
(/Users/hqin/anaconda)Byte:anaconda hqin$ which ipython
/Users/hqin/anaconda/bin/ipython
$ ipython notebook
Byte:anaconda hqin$ source bin/activate ~/anaconda/discarding /Users/hqin/anaconda/bin from PATH
prepending /Users/hqin/anaconda/bin to PATH
(/Users/hqin/anaconda)Byte:anaconda hqin$
(/Users/hqin/anaconda)Byte:anaconda hqin$ which ipython
/Users/hqin/anaconda/bin/ipython
$ ipython notebook
Friday, June 6, 2014
student research, day 1, summer14
Introduction to network aging, using Google Hangout and watch my lecture video.
Qin Simple R vido
Students then ask to learn R. I give them 'simple.R' for exercise. I then challenge them to modify the code to generate a different plot.
Students then look through previous posters to pick their 'favorite' project to work on.
Students set up their GitHub project repository.
Qin Simple R vido
Students then ask to learn R. I give them 'simple.R' for exercise. I then challenge them to modify the code to generate a different plot.
Students then look through previous posters to pick their 'favorite' project to work on.
Students set up their GitHub project repository.
Thursday, June 5, 2014
Add collaborator in settings on Github repository
Go to settings.
https://help.github.com/articles/how-do-i-add-a-collaborator
I tested using qinlab2 on 'test' repo, by directly editing README. it worked.
Wednesday, June 4, 2014
Yeast2014 Seattle, July 29-August 3
Early registration June 26
Housing
Flight
Housing
Flight
Software carpentry bootcamp log
Tuesday, June 10, 2014 at 9:00 AM - Wednesday, June 11, 2014 at 4:30 PM (EDT)
440 Westview Dr. S.W.
Atlanta 30310
Course site:
http://wltrimbl.github.io/2014-06-10-spelman/
http://continuum.io/downloads
Pre-survey
https://docs.google.com/forms/d/117vOu7siYuixhLM6gkA1fAZgj1opiY4o-Gfy8DYvv6Y/viewform
Post-survey
https://docs.google.com/forms/d/1R21oyG_N2Ov5wnOsQ_VOQn0eIaHz4ijRbhxlG2IF_PI/viewform
Ethernet cables, loan request.
Coffee, tea, box lunches, paper cups
Table for the catering, request on lotus note.
Lectures
http://software-carpentry.org/lessons.html
Lessons learned:
-> Forgot to ask for affiliations during registration.
-> Catering ordered has not vegetarian option. One of the instructors is a vegetarian.
I called the catering vendor, and added 6 vegetarian sandwiches, with no additional cost. I replaced the coffee with orange juice.
Monday, June 2, 2014
Summer14 research: Install R and Rstudio
1. Install R (This is the main computing and programming engine).
1.1 Go to:
http://mirrors.nics.utk.edu/cran/
1.2 Pick the right R version for your computer platform. (Pick Mac OS in our case).
2. Install Rstudio (This is the user-friendly editor and environment to run R).
3. Create a Github account.
4. Install Github.
Todo: How to collaborate through GitHub?
2014 June 4: Collaborators can be added to a repo in its settings.
Subscribe to:
Posts (Atom)