From yurii.aulchenko at gmail.com Mon Jan 6 20:00:17 2014 From: yurii.aulchenko at gmail.com (Yury Aulchenko) Date: Mon, 6 Jan 2014 20:00:17 +0100 Subject: [GenABEL-dev] CRAN package MetABEL In-Reply-To: <21194.64514.866424.347543@fangorn.hornik.net> References: <21172.48479.385656.257533@fangorn.hornik.net> <21193.23467.229635.663015@fangorn.hornik.net> <21194.64060.636290.847143@fangorn.hornik.net> <6373BB2F-55FB-45DD-B536-418ACBC63757@gmail.com> <21194.64514.866424.347543@fangorn.hornik.net> Message-ID: <34B26CD8-BF07-495D-9784-05FAECB89CFD@gmail.com> Thank you! - will try to fix asap. Yurii On Jan 6, 2014, at 19:54, Kurt Hornik wrote: >>>>>> Yury Aulchenko writes: > >> Thank you very much for reminder; apparently this escaped our radar... >> Yurii > > Thanks for the reply ... pls get this fixed asap. > > Also, any chance to fix the clang errors for VariABEL, see > ? > > Best > -k > >> On Jan 6, 2014, at 19:47, Kurt Hornik wrote: > >>>>>>>> Kurt Hornik writes: >>> >>> Ping? >>> >>> -k >>> >>>>>>>> Kurt Hornik writes: >>>> Ping? >>> >>>> -k >>> >>>>> This has >>>>> m.struchalin at erasmusmc.nl >>> >>>>> as maintainer address, which no longer works. >>> >>>>> Can we pls asap have an update with a working maintainer email address? >>> >>>>> Best >>>>> -k > From Kurt.Hornik at wu.ac.at Mon Jan 6 20:58:37 2014 From: Kurt.Hornik at wu.ac.at (Kurt Hornik) Date: Mon, 6 Jan 2014 20:58:37 +0100 Subject: [GenABEL-dev] CRAN package MetABEL In-Reply-To: <34B26CD8-BF07-495D-9784-05FAECB89CFD@gmail.com> References: <21172.48479.385656.257533@fangorn.hornik.net> <21193.23467.229635.663015@fangorn.hornik.net> <21194.64060.636290.847143@fangorn.hornik.net> <6373BB2F-55FB-45DD-B536-418ACBC63757@gmail.com> <21194.64514.866424.347543@fangorn.hornik.net> <34B26CD8-BF07-495D-9784-05FAECB89CFD@gmail.com> Message-ID: <21195.2797.878793.871874@fangorn.hornik.net> >>>>> Yury Aulchenko writes: > Thank you! - will try to fix asap. > Yurii Great, thanks! Best -k > On Jan 6, 2014, at 19:54, Kurt Hornik wrote: >>>>>>> Yury Aulchenko writes: >> >>> Thank you very much for reminder; apparently this escaped our radar... >>> Yurii >> >> Thanks for the reply ... pls get this fixed asap. >> >> Also, any chance to fix the clang errors for VariABEL, see >> ? >> >> Best >> -k >> >>> On Jan 6, 2014, at 19:47, Kurt Hornik wrote: >> >>>>>>>>> Kurt Hornik writes: >>>> >>>> Ping? >>>> >>>> -k >>>> >>>>>>>>> Kurt Hornik writes: >>>>> Ping? >>>> >>>>> -k >>>> >>>>> This has >>>>> m.struchalin at erasmusmc.nl >>>> >>>>> as maintainer address, which no longer works. >>>> >>>>> Can we pls asap have an update with a working maintainer email address? >>>> >>>>> Best >>>>> -k >> From kooyman at gmail.com Mon Jan 6 23:21:55 2014 From: kooyman at gmail.com (Maarten Kooyman) Date: Mon, 06 Jan 2014 23:21:55 +0100 Subject: [GenABEL-dev] Roadmap ProbABEL Message-ID: <52CB2C83.5030701@gmail.com> Dear List, Lennart and I did discus a roadmap for ProbABEL. We made this roadmap after comparing ProbABEL with other GWAS applications (more on this later). We are welcome for comments, ideas or patches. You will find here a small summary of our discussion. -ProbABEL 0.4.3: bugfix release - Fix regression in converting numbers from filevector/DatABEL files. Lennart already started on this :http://lists.r-forge.r-project.org/pipermail/genabel-commits/2014-January/000922.html -ProbABEL 0.5.0: P-values and Faster - Add P-values to output. (Most likely with help of BOOST library) - Log likelihood is disabled by default since wald test is better. - masking data in matrix before regression in a more effective way. Now this operation is done twice. - Vectorize code for palinear with EIGEN library - Optimize compiler flags: executables are unnecessary large in size and matrix calculations can go faster. - Other fixes/opportunities. - ProbABEL 0.5.1: palogist optimisations and bugfixes. - Vectorize code for palogist - bug fixes With kind regards, Maarten From yurii.aulchenko at gmail.com Tue Jan 7 09:09:22 2014 From: yurii.aulchenko at gmail.com (Yury Aulchenko) Date: Tue, 7 Jan 2014 09:09:22 +0100 Subject: [GenABEL-dev] Roadmap ProbABEL In-Reply-To: <52CB2C83.5030701@gmail.com> References: <52CB2C83.5030701@gmail.com> Message-ID: <59970A89-F80A-4F18-8419-423ACD1BBBBE@gmail.com> On Jan 6, 2014, at 23:21, Maarten Kooyman wrote: > Dear List, > > Lennart and I did discus a roadmap for ProbABEL. We made this roadmap after comparing ProbABEL with other GWAS applications (more on this later). We are welcome for comments, ideas or patches. You will find here a small summary of our discussion. > > > -ProbABEL 0.4.3: bugfix release > - Fix regression in converting numbers from filevector/DatABEL files. Lennart already started on this :http://lists.r-forge.r-project.org/pipermail/genabel-commits/2014-January/000922.html > > -ProbABEL 0.5.0: P-values and Faster > - Add P-values to output. (Most likely with help of BOOST library) > - Log likelihood is disabled by default since wald test is better. In what sense it is better? In principle, it can be argued that the likelihood ratio test is the "better" because of its statistical properties (after all, Wald is an approximation to the LRT); score is "better" because it is faster... I can imagine that Wald is "better" because of technical reasons (which is totally fine) - but please comment. best, Yurii > - masking data in matrix before regression in a more effective way. Now this operation is done twice. > - Vectorize code for palinear with EIGEN library > - Optimize compiler flags: executables are unnecessary large in size and matrix calculations can go faster. > - Other fixes/opportunities. > > - ProbABEL 0.5.1: palogist optimisations and bugfixes. > - Vectorize code for palogist > - bug fixes > > > With kind regards, > > Maarten > > > > > _______________________________________________ > genabel-devel mailing list > genabel-devel at lists.r-forge.r-project.org > https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/genabel-devel From lennart at karssen.org Wed Jan 8 13:23:02 2014 From: lennart at karssen.org (L.C. Karssen) Date: Wed, 08 Jan 2014 13:23:02 +0100 Subject: [GenABEL-dev] Roadmap ProbABEL In-Reply-To: <59970A89-F80A-4F18-8419-423ACD1BBBBE@gmail.com> References: <52CB2C83.5030701@gmail.com> <59970A89-F80A-4F18-8419-423ACD1BBBBE@gmail.com> Message-ID: <52CD4326.8050506@karssen.org> Hi Yurii, On 07-01-14 09:09, Yury Aulchenko wrote: > > On Jan 6, 2014, at 23:21, Maarten Kooyman wrote: > >> Dear List, >> >> Lennart and I did discus a roadmap for ProbABEL. We made this roadmap after comparing ProbABEL with other GWAS applications (more on this later). We are welcome for comments, ideas or patches. You will find here a small summary of our discussion. >> >> >> -ProbABEL 0.4.3: bugfix release >> - Fix regression in converting numbers from filevector/DatABEL files. Lennart already started on this :http://lists.r-forge.r-project.org/pipermail/genabel-commits/2014-January/000922.html >> >> -ProbABEL 0.5.0: P-values and Faster >> - Add P-values to output. (Most likely with help of BOOST library) >> - Log likelihood is disabled by default since wald test is better. > > In what sense it is better? In principle, it can be argued that the likelihood ratio test is the "better" because of its statistical properties (after all, Wald is an approximation to the LRT); score is "better" because it is faster... > > I can imagine that Wald is "better" because of technical reasons (which is totally fine) - but please comment. > After I had re-implemented the LRT-based chi^2 in ProbABEL I had a discussion with a colleague who knows more about statistics and she said that Wald was more accurate than LRT and reminded me of an example we had in a statistical genetics course. Yesterday I looked up the example (see below) and it turns out she was wrong. As you can see the LRT-based p-value is closer to the exact one. So you are right. We can scratch this from the roadmap. The example: Say we want to do hypothesis testing on a binomial problem: tossing a coin 20 times, we observe 4 heads. Question: is the coin fair? H_0: p = 0.5 H_1: p != 0.5 The exact (binomial) solution can be calculated in that case, as well as the normal approximation, the Wald test, the chi^2 test and the LRT. I quickly coded this in R (see attachment) and got the following results: pval.binom pval.norm pval.chi2 pval.wald pval.lrt 0.01181793 0.0139063 0.0139063 0.002107897 0.005492213 So, although the p-values of Wald and LRT are quite far off, the LRT-based p-value is closer to the binomial one. Thanks for pointing this out! Lennart. > best, > Yurii > >> - masking data in matrix before regression in a more effective way. Now this operation is done twice. >> - Vectorize code for palinear with EIGEN library >> - Optimize compiler flags: executables are unnecessary large in size and matrix calculations can go faster. >> - Other fixes/opportunities. >> >> - ProbABEL 0.5.1: palogist optimisations and bugfixes. >> - Vectorize code for palogist >> - bug fixes >> >> >> With kind regards, >> >> Maarten >> >> >> >> >> _______________________________________________ >> genabel-devel mailing list >> genabel-devel at lists.r-forge.r-project.org >> https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/genabel-devel > > _______________________________________________ > genabel-devel mailing list > genabel-devel at lists.r-forge.r-project.org > https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/genabel-devel > -- *-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-* L.C. Karssen Utrecht The Netherlands lennart at karssen.org http://blog.karssen.org GPG key ID: A88F554A -*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*- -------------- next part -------------- ## Hypothesis testing and various approximations ## ## Time-stamp: <2014-01-08 10:53:52 (L.C. Karssen)> ## ## Problem: ## we want to do hypothesis testing on a binomial problem: ## toss a coin 20 times, observe 4 heads. Question is the coin fair? p <- 0.5 # prob for heads if coin is fair q <- 1 - p n <- 20 # nr of tries X <- 4 # observed nr of heads bot <- 0:X top <- (n - X):n ## Binomial (exaxt): pval.binom <- sum(dbinom(bot, n, p), dbinom(top, n, p)) ## Normal approximation (score test): mean <- n * p stddev <- sqrt(n * p * q) z.norm <- (X + 0.5 - mean) / stddev # 0.5 is continuity correction pval.norm <- 2 * pnorm(z.norm) ## Wald test: p.obs <- X / n q.obs <- 1 - p.obs stddev <- sqrt(n * p.obs * q.obs) z.wald <- (X + 0.5 - mean)/stddev pval.wald <- 2 * pnorm(z.wald) ## Chi^2 test ## class 1: 4 heads observed, 10 expected ## class 2: 16 tails observed, 10 expected chi2 <- (X - mean + 0.5)^2 / mean + ((n - X) - mean - 0.5)^2 / mean pval.chi2 <- pchisq(chi2, df=1, lower.tail=FALSE) ## Likelihood-ratio test ## H_0: p = 0.5 ## H_1: p.obs = X/n = 4/20 p.0 <- dbinom(X, n, p) p.1 <- dbinom(X, n, p.obs) lrt <- -2 * log(p.0 / p.1) pval.lrt <- pchisq(lrt, df=1, lower.tail=FALSE) results <- data.frame(pval.binom, pval.norm, pval.chi2, pval.wald, pval.lrt) -------------- next part -------------- A non-text attachment was scrubbed... Name: signature.asc Type: application/pgp-signature Size: 230 bytes Desc: OpenPGP digital signature URL: From mgmaria at yandex.ru Fri Jan 17 12:40:58 2014 From: mgmaria at yandex.ru (Maria G) Date: Fri, 17 Jan 2014 15:40:58 +0400 Subject: [GenABEL-dev] Roadmap ProbABEL In-Reply-To: <52CD4326.8050506@karssen.org> References: <52CB2C83.5030701@gmail.com> <59970A89-F80A-4F18-8419-423ACD1BBBBE@gmail.com> <52CD4326.8050506@karssen.org> Message-ID: <184671389958858@web27g.yandex.ru> Dear all, thanks for open discussion! For me personally is was alway an important question, what do developers mean by choosing a specific test for a default mode. The same with therm "better" - I also have noticed, that in many scripts applicable for huge data-sets, "better" would mean "faster" rather then "more accurate". Which is fine, but good to know in advance ;) best regards Maria 08.01.2014, 16:23, "L.C. Karssen" : > Hi Yurii, > > On 07-01-14 09:09, Yury Aulchenko wrote: > >> ?On Jan 6, 2014, at 23:21, Maarten Kooyman wrote: >>> ?Dear List, >>> >>> ?Lennart and I did discus a roadmap for ProbABEL. We made this roadmap after comparing ProbABEL with other GWAS applications (more on this later). We are welcome for comments, ideas or patches. You will find here a small summary of our discussion. >>> >>> ?-ProbABEL 0.4.3: bugfix release >>> ?- Fix regression in converting numbers from filevector/DatABEL files. Lennart already started on this :http://lists.r-forge.r-project.org/pipermail/genabel-commits/2014-January/000922.html >>> >>> ?-ProbABEL 0.5.0: P-values and Faster >>> ?- Add P-values to output. (Most likely with help of BOOST library) >>> ?- Log likelihood is disabled by default since wald test is better. >> ?In what sense it is better? In principle, it can be argued that the likelihood ratio test is the "better" because of its statistical properties (after all, Wald is an approximation to the LRT); score is "better" because it is faster... >> >> ?I can imagine that Wald is "better" because of technical reasons (which is totally fine) - but please comment. > > After I had re-implemented the LRT-based chi^2 in ProbABEL I had a > discussion with a colleague who knows more about statistics and she said > that Wald was more accurate than LRT and reminded me of an example we > had in a statistical genetics course. > > Yesterday I looked up the example (see below) and it turns out she was > wrong. As you can see the LRT-based p-value is closer to the exact one. > > So you are right. We can scratch this from the roadmap. > > The example: > > Say we want to do hypothesis testing on a binomial problem: > tossing a coin 20 times, we observe 4 heads. Question: is the coin fair? > > H_0: p = 0.5 > H_1: p != 0.5 > > The exact (binomial) solution can be calculated in that case, as well as > the normal approximation, the Wald test, the chi^2 test and the LRT. I > quickly coded this in R (see attachment) and got > the following results: > > ?????pval.binom pval.norm pval.chi2 pval.wald ??pval.lrt > ?????0.01181793 0.0139063 0.0139063 0.002107897 0.005492213 > > So, although the p-values of Wald and LRT are quite far off, the > LRT-based p-value is closer to the binomial one. > > Thanks for pointing this out! > > Lennart. > >> ?best, >> ?Yurii >>> ?- masking data in matrix before regression in a more effective way. Now this operation is done twice. >>> ?- Vectorize code for palinear with EIGEN library >>> ?- Optimize compiler flags: executables are unnecessary large in size and matrix calculations can go faster. >>> ?- Other fixes/opportunities. >>> >>> ?- ProbABEL 0.5.1: palogist optimisations and bugfixes. >>> ?- Vectorize code for palogist >>> ?- bug fixes >>> >>> ?With kind regards, >>> >>> ?Maarten >>> >>> ?_______________________________________________ >>> ?genabel-devel mailing list >>> ?genabel-devel at lists.r-forge.r-project.org >>> ?https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/genabel-devel >> ?_______________________________________________ >> ?genabel-devel mailing list >> ?genabel-devel at lists.r-forge.r-project.org >> ?https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/genabel-devel > > -- > *-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-* > L.C. Karssen > Utrecht > The Netherlands > > lennart at karssen.org > http://blog.karssen.org > GPG key ID: A88F554A > -*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*- > > , > _______________________________________________ > genabel-devel mailing list > genabel-devel at lists.r-forge.r-project.org > https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/genabel-devel From Kurt.Hornik at wu.ac.at Sat Jan 18 09:42:23 2014 From: Kurt.Hornik at wu.ac.at (Kurt Hornik) Date: Sat, 18 Jan 2014 09:42:23 +0100 Subject: [GenABEL-dev] CRAN package MetABEL In-Reply-To: <34B26CD8-BF07-495D-9784-05FAECB89CFD@gmail.com> References: <21172.48479.385656.257533@fangorn.hornik.net> <21193.23467.229635.663015@fangorn.hornik.net> <21194.64060.636290.847143@fangorn.hornik.net> <6373BB2F-55FB-45DD-B536-418ACBC63757@gmail.com> <21194.64514.866424.347543@fangorn.hornik.net> <34B26CD8-BF07-495D-9784-05FAECB89CFD@gmail.com> Message-ID: <21210.15983.158548.600355@fangorn.hornik.net> >>>>> Yury Aulchenko writes: Two weeks later: we really need the updates asap ... -k > Thank you! - will try to fix asap. > Yurii > On Jan 6, 2014, at 19:54, Kurt Hornik wrote: >>>>>>> Yury Aulchenko writes: >> >>> Thank you very much for reminder; apparently this escaped our radar... >>> Yurii >> >> Thanks for the reply ... pls get this fixed asap. >> >> Also, any chance to fix the clang errors for VariABEL, see >> ? >> >> Best >> -k >> >>> On Jan 6, 2014, at 19:47, Kurt Hornik wrote: >> >>>>>>>>> Kurt Hornik writes: >>>> >>>> Ping? >>>> >>>> -k >>>> >>>>>>>>> Kurt Hornik writes: >>>>> Ping? >>>> >>>>> -k >>>> >>>>> This has >>>>> m.struchalin at erasmusmc.nl >>>> >>>>> as maintainer address, which no longer works. >>>> >>>>> Can we pls asap have an update with a working maintainer email address? >>>> >>>>> Best >>>>> -k >> From lennart at karssen.org Mon Jan 20 09:09:21 2014 From: lennart at karssen.org (L.C. Karssen) Date: Mon, 20 Jan 2014 09:09:21 +0100 Subject: [GenABEL-dev] CRAN package MetABEL In-Reply-To: <21210.15983.158548.600355@fangorn.hornik.net> References: <21172.48479.385656.257533@fangorn.hornik.net> <21193.23467.229635.663015@fangorn.hornik.net> <21194.64060.636290.847143@fangorn.hornik.net> <6373BB2F-55FB-45DD-B536-418ACBC63757@gmail.com> <21194.64514.866424.347543@fangorn.hornik.net> <34B26CD8-BF07-495D-9784-05FAECB89CFD@gmail.com> <21210.15983.158548.600355@fangorn.hornik.net> Message-ID: <52DCD9B1.6090107@karssen.org> Dear Kurt, Thanks for the reminder. I will put it on my todo list for this week. Lennart Karssen. On 18-01-14 09:42, Kurt Hornik wrote: >>>>>> Yury Aulchenko writes: > > Two weeks later: we really need the updates asap ... > > -k > > >> Thank you! - will try to fix asap. >> Yurii > >> On Jan 6, 2014, at 19:54, Kurt Hornik wrote: > >>>>>>>> Yury Aulchenko writes: >>> >>>> Thank you very much for reminder; apparently this escaped our radar... >>>> Yurii >>> >>> Thanks for the reply ... pls get this fixed asap. >>> >>> Also, any chance to fix the clang errors for VariABEL, see >>> ? >>> >>> Best >>> -k >>> >>>> On Jan 6, 2014, at 19:47, Kurt Hornik wrote: >>> >>>>>>>>>> Kurt Hornik writes: >>>>> >>>>> Ping? >>>>> >>>>> -k >>>>> >>>>>>>>>> Kurt Hornik writes: >>>>>> Ping? >>>>> >>>>>> -k >>>>> >>>>>> This has >>>>>> m.struchalin at erasmusmc.nl >>>>> >>>>>> as maintainer address, which no longer works. >>>>> >>>>>> Can we pls asap have an update with a working maintainer email address? >>>>> >>>>>> Best >>>>>> -k >>> > > _______________________________________________ > genabel-devel mailing list > genabel-devel at lists.r-forge.r-project.org > https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/genabel-devel > -- *-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-* L.C. Karssen Utrecht The Netherlands lennart at karssen.org http://blog.karssen.org GPG key ID: A88F554A -*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*- -------------- next part -------------- A non-text attachment was scrubbed... Name: signature.asc Type: application/pgp-signature Size: 230 bytes Desc: OpenPGP digital signature URL: From Kurt.Hornik at wu.ac.at Mon Jan 20 09:11:45 2014 From: Kurt.Hornik at wu.ac.at (Kurt Hornik) Date: Mon, 20 Jan 2014 09:11:45 +0100 Subject: [GenABEL-dev] CRAN package MetABEL In-Reply-To: <52DCD9B1.6090107@karssen.org> References: <21172.48479.385656.257533@fangorn.hornik.net> <21193.23467.229635.663015@fangorn.hornik.net> <21194.64060.636290.847143@fangorn.hornik.net> <6373BB2F-55FB-45DD-B536-418ACBC63757@gmail.com> <21194.64514.866424.347543@fangorn.hornik.net> <34B26CD8-BF07-495D-9784-05FAECB89CFD@gmail.com> <21210.15983.158548.600355@fangorn.hornik.net> <52DCD9B1.6090107@karssen.org> Message-ID: <21212.55873.487319.389308@fangorn.hornik.net> >>>>> L C Karssen writes: > Dear Kurt, > Thanks for the reminder. I will put it on my todo list for this week. Thanks. -k > Lennart Karssen. > On 18-01-14 09:42, Kurt Hornik wrote: >>>>>>> Yury Aulchenko writes: >> >> Two weeks later: we really need the updates asap ... >> >> -k >> >> >>> Thank you! - will try to fix asap. >>> Yurii >> >>> On Jan 6, 2014, at 19:54, Kurt Hornik wrote: >> >>>>>>>>> Yury Aulchenko writes: >>>> >>>>> Thank you very much for reminder; apparently this escaped our radar... >>>>> Yurii >>>> >>>> Thanks for the reply ... pls get this fixed asap. >>>> >>>> Also, any chance to fix the clang errors for VariABEL, see >>>> ? >>>> >>>> Best >>>> -k >>>> >>>>> On Jan 6, 2014, at 19:47, Kurt Hornik wrote: >>>> >>>>>>>>>>> Kurt Hornik writes: >>>>>> >>>>> Ping? >>>>>> >>>>> -k >>>>>> >>>>>>>>>>> Kurt Hornik writes: >>>>>>> Ping? >>>>>> >>>>>>> -k >>>>>> >>>>>>> This has >>>>>>> m.struchalin at erasmusmc.nl >>>>>> >>>>>>> as maintainer address, which no longer works. >>>>>> >>>>>>> Can we pls asap have an update with a working maintainer email address? >>>>>> >>>>>>> Best >>>>>>> -k >>>> >> >> _______________________________________________ >> genabel-devel mailing list >> genabel-devel at lists.r-forge.r-project.org >> https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/genabel-devel >> > -- > *-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-* > L.C. Karssen > Utrecht > The Netherlands > lennart at karssen.org > http://blog.karssen.org > GPG key ID: A88F554A > -*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*- > xapplication/pgp-signature [Click mouse-2 to save to a file] From lennart at karssen.org Tue Jan 21 09:11:11 2014 From: lennart at karssen.org (L.C. Karssen) Date: Tue, 21 Jan 2014 09:11:11 +0100 Subject: [GenABEL-dev] Roadmap ProbABEL In-Reply-To: <184671389958858@web27g.yandex.ru> References: <52CB2C83.5030701@gmail.com> <59970A89-F80A-4F18-8419-423ACD1BBBBE@gmail.com> <52CD4326.8050506@karssen.org> <184671389958858@web27g.yandex.ru> Message-ID: <52DE2B9F.1070404@karssen.org> Dear Maria, You are right. As developers we should be more explicit in what we mean with 'better'. At the moment we would like to have the most accurate test in ProbABEL, which too my knowledge is the LRT (except when mmscore is used, then the Wald test is used). Some users have asked for the Wald test in all cases. We may add that as an option. By the way, for the 2DF model in combination with mmscore we still have not implemented a chi^2 statistic. This would require the implementation of the 2df Wald test as outlined in the ProbABEL paper, but when I tried to implement it last year I didn't get the expected results. I guess I should invest some more time in that, maybe I just missed something simple (help is very welcome!). Best, Lennart. On 17-01-14 12:40, Maria G wrote: > Dear all, > > thanks for open discussion! > > For me personally is was alway an important question, what do developers mean by choosing a specific test for a default mode. The same with therm "better" - I also have noticed, that in many scripts applicable for huge data-sets, "better" would mean "faster" rather then "more accurate". Which is fine, but good to know in advance ;) > > best regards > > Maria > > 08.01.2014, 16:23, "L.C. Karssen" : >> Hi Yurii, >> >> On 07-01-14 09:09, Yury Aulchenko wrote: >> >>> On Jan 6, 2014, at 23:21, Maarten Kooyman wrote: >>>> Dear List, >>>> >>>> Lennart and I did discus a roadmap for ProbABEL. We made this roadmap after comparing ProbABEL with other GWAS applications (more on this later). We are welcome for comments, ideas or patches. You will find here a small summary of our discussion. >>>> >>>> -ProbABEL 0.4.3: bugfix release >>>> - Fix regression in converting numbers from filevector/DatABEL files. Lennart already started on this :http://lists.r-forge.r-project.org/pipermail/genabel-commits/2014-January/000922.html >>>> >>>> -ProbABEL 0.5.0: P-values and Faster >>>> - Add P-values to output. (Most likely with help of BOOST library) >>>> - Log likelihood is disabled by default since wald test is better. >>> In what sense it is better? In principle, it can be argued that the likelihood ratio test is the "better" because of its statistical properties (after all, Wald is an approximation to the LRT); score is "better" because it is faster... >>> >>> I can imagine that Wald is "better" because of technical reasons (which is totally fine) - but please comment. >> >> After I had re-implemented the LRT-based chi^2 in ProbABEL I had a >> discussion with a colleague who knows more about statistics and she said >> that Wald was more accurate than LRT and reminded me of an example we >> had in a statistical genetics course. >> >> Yesterday I looked up the example (see below) and it turns out she was >> wrong. As you can see the LRT-based p-value is closer to the exact one. >> >> So you are right. We can scratch this from the roadmap. >> >> The example: >> >> Say we want to do hypothesis testing on a binomial problem: >> tossing a coin 20 times, we observe 4 heads. Question: is the coin fair? >> >> H_0: p = 0.5 >> H_1: p != 0.5 >> >> The exact (binomial) solution can be calculated in that case, as well as >> the normal approximation, the Wald test, the chi^2 test and the LRT. I >> quickly coded this in R (see attachment) and got >> the following results: >> >> pval.binom pval.norm pval.chi2 pval.wald pval.lrt >> 0.01181793 0.0139063 0.0139063 0.002107897 0.005492213 >> >> So, although the p-values of Wald and LRT are quite far off, the >> LRT-based p-value is closer to the binomial one. >> >> Thanks for pointing this out! >> >> Lennart. >> >>> best, >>> Yurii >>>> - masking data in matrix before regression in a more effective way. Now this operation is done twice. >>>> - Vectorize code for palinear with EIGEN library >>>> - Optimize compiler flags: executables are unnecessary large in size and matrix calculations can go faster. >>>> - Other fixes/opportunities. >>>> >>>> - ProbABEL 0.5.1: palogist optimisations and bugfixes. >>>> - Vectorize code for palogist >>>> - bug fixes >>>> >>>> With kind regards, >>>> >>>> Maarten >>>> >>>> _______________________________________________ >>>> genabel-devel mailing list >>>> genabel-devel at lists.r-forge.r-project.org >>>> https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/genabel-devel >>> _______________________________________________ >>> genabel-devel mailing list >>> genabel-devel at lists.r-forge.r-project.org >>> https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/genabel-devel >> >> -- >> *-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-* >> L.C. Karssen >> Utrecht >> The Netherlands >> >> lennart at karssen.org >> http://blog.karssen.org >> GPG key ID: A88F554A >> -*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*- >> >> , >> _______________________________________________ >> genabel-devel mailing list >> genabel-devel at lists.r-forge.r-project.org >> https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/genabel-devel -- *-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-* L.C. Karssen Utrecht The Netherlands lennart at karssen.org http://blog.karssen.org GPG key ID: A88F554A -*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*- -------------- next part -------------- A non-text attachment was scrubbed... Name: signature.asc Type: application/pgp-signature Size: 230 bytes Desc: OpenPGP digital signature URL: From yurii.aulchenko at gmail.com Tue Jan 21 11:47:07 2014 From: yurii.aulchenko at gmail.com (Yurii Aulchenko) Date: Tue, 21 Jan 2014 17:47:07 +0700 Subject: [GenABEL-dev] Roadmap ProbABEL In-Reply-To: <52DE2B9F.1070404@karssen.org> References: <52CB2C83.5030701@gmail.com> <59970A89-F80A-4F18-8419-423ACD1BBBBE@gmail.com> <52CD4326.8050506@karssen.org> <184671389958858@web27g.yandex.ru> <52DE2B9F.1070404@karssen.org> Message-ID: <-7202474220622918880@unknownmsgid> Re: Wald 2df I have figured it out a couple if times, so if we ever have an hour to spend I should be able to reproduce that in R... ---------------------- Yurii Aulchenko (sent from mobile device) > On Jan 21, 2014, at 3:11 PM, "L.C. Karssen" wrote: > > Dear Maria, > > You are right. As developers we should be more explicit in what we mean > with 'better'. At the moment we would like to have the most accurate > test in ProbABEL, which too my knowledge is the LRT (except when mmscore > is used, then the Wald test is used). Some users have asked for the Wald > test in all cases. We may add that as an option. > > By the way, for the 2DF model in combination with mmscore we still have > not implemented a chi^2 statistic. This would require the implementation > of the 2df Wald test as outlined in the ProbABEL paper, but when I tried > to implement it last year I didn't get the expected results. I guess I > should invest some more time in that, maybe I just missed something > simple (help is very welcome!). > > > Best, > > Lennart. > >> On 17-01-14 12:40, Maria G wrote: >> Dear all, >> >> thanks for open discussion! >> >> For me personally is was alway an important question, what do developers mean by choosing a specific test for a default mode. The same with therm "better" - I also have noticed, that in many scripts applicable for huge data-sets, "better" would mean "faster" rather then "more accurate". Which is fine, but good to know in advance ;) >> >> best regards >> >> Maria >> >> 08.01.2014, 16:23, "L.C. Karssen" : >>> Hi Yurii, >>> >>>> On 07-01-14 09:09, Yury Aulchenko wrote: >>>> >>>>> On Jan 6, 2014, at 23:21, Maarten Kooyman wrote: >>>>> Dear List, >>>>> >>>>> Lennart and I did discus a roadmap for ProbABEL. We made this roadmap after comparing ProbABEL with other GWAS applications (more on this later). We are welcome for comments, ideas or patches. You will find here a small summary of our discussion. >>>>> >>>>> -ProbABEL 0.4.3: bugfix release >>>>> - Fix regression in converting numbers from filevector/DatABEL files. Lennart already started on this :http://lists.r-forge.r-project.org/pipermail/genabel-commits/2014-January/000922.html >>>>> >>>>> -ProbABEL 0.5.0: P-values and Faster >>>>> - Add P-values to output. (Most likely with help of BOOST library) >>>>> - Log likelihood is disabled by default since wald test is better. >>>> In what sense it is better? In principle, it can be argued that the likelihood ratio test is the "better" because of its statistical properties (after all, Wald is an approximation to the LRT); score is "better" because it is faster... >>>> >>>> I can imagine that Wald is "better" because of technical reasons (which is totally fine) - but please comment. >>> >>> After I had re-implemented the LRT-based chi^2 in ProbABEL I had a >>> discussion with a colleague who knows more about statistics and she said >>> that Wald was more accurate than LRT and reminded me of an example we >>> had in a statistical genetics course. >>> >>> Yesterday I looked up the example (see below) and it turns out she was >>> wrong. As you can see the LRT-based p-value is closer to the exact one. >>> >>> So you are right. We can scratch this from the roadmap. >>> >>> The example: >>> >>> Say we want to do hypothesis testing on a binomial problem: >>> tossing a coin 20 times, we observe 4 heads. Question: is the coin fair? >>> >>> H_0: p = 0.5 >>> H_1: p != 0.5 >>> >>> The exact (binomial) solution can be calculated in that case, as well as >>> the normal approximation, the Wald test, the chi^2 test and the LRT. I >>> quickly coded this in R (see attachment) and got >>> the following results: >>> >>> pval.binom pval.norm pval.chi2 pval.wald pval.lrt >>> 0.01181793 0.0139063 0.0139063 0.002107897 0.005492213 >>> >>> So, although the p-values of Wald and LRT are quite far off, the >>> LRT-based p-value is closer to the binomial one. >>> >>> Thanks for pointing this out! >>> >>> Lennart. >>> >>>> best, >>>> Yurii >>>>> - masking data in matrix before regression in a more effective way. Now this operation is done twice. >>>>> - Vectorize code for palinear with EIGEN library >>>>> - Optimize compiler flags: executables are unnecessary large in size and matrix calculations can go faster. >>>>> - Other fixes/opportunities. >>>>> >>>>> - ProbABEL 0.5.1: palogist optimisations and bugfixes. >>>>> - Vectorize code for palogist >>>>> - bug fixes >>>>> >>>>> With kind regards, >>>>> >>>>> Maarten >>>>> >>>>> _______________________________________________ >>>>> genabel-devel mailing list >>>>> genabel-devel at lists.r-forge.r-project.org >>>>> https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/genabel-devel >>>> _______________________________________________ >>>> genabel-devel mailing list >>>> genabel-devel at lists.r-forge.r-project.org >>>> https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/genabel-devel >>> >>> -- >>> *-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-* >>> L.C. Karssen >>> Utrecht >>> The Netherlands >>> >>> lennart at karssen.org >>> http://blog.karssen.org >>> GPG key ID: A88F554A >>> -*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*- >>> >>> , >>> _______________________________________________ >>> genabel-devel mailing list >>> genabel-devel at lists.r-forge.r-project.org >>> https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/genabel-devel > > -- > *-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-* > L.C. Karssen > Utrecht > The Netherlands > > lennart at karssen.org > http://blog.karssen.org > GPG key ID: A88F554A > -*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*- > > _______________________________________________ > genabel-devel mailing list > genabel-devel at lists.r-forge.r-project.org > https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/genabel-devel From lennart at karssen.org Mon Jan 27 00:11:50 2014 From: lennart at karssen.org (L.C. Karssen) Date: Mon, 27 Jan 2014 00:11:50 +0100 Subject: [GenABEL-dev] CRAN package MetABEL In-Reply-To: <52DCD9B1.6090107@karssen.org> References: <21172.48479.385656.257533@fangorn.hornik.net> <21193.23467.229635.663015@fangorn.hornik.net> <21194.64060.636290.847143@fangorn.hornik.net> <6373BB2F-55FB-45DD-B536-418ACBC63757@gmail.com> <21194.64514.866424.347543@fangorn.hornik.net> <34B26CD8-BF07-495D-9784-05FAECB89CFD@gmail.com> <21210.15983.158548.600355@fangorn.hornik.net> <52DCD9B1.6090107@karssen.org> Message-ID: <52E59636.6040402@karssen.org> Dear list, I just submitted MetABEL 0.1-0 to CRAN. Except for the fixes required by the CRAN checks (some functions keywords were not written in full and some lines in the documentation were too loing), as well as changing the maintainer from Maksim to me, nothing changed. Best, Lennart. On 20-01-14 09:09, L.C. Karssen wrote: > Dear Kurt, > > Thanks for the reminder. I will put it on my todo list for this week. > > > Lennart Karssen. > > On 18-01-14 09:42, Kurt Hornik wrote: >>>>>>> Yury Aulchenko writes: >> >> Two weeks later: we really need the updates asap ... >> >> -k >> >> >>> Thank you! - will try to fix asap. >>> Yurii >> >>> On Jan 6, 2014, at 19:54, Kurt Hornik wrote: >> >>>>>>>>> Yury Aulchenko writes: >>>> >>>>> Thank you very much for reminder; apparently this escaped our radar... >>>>> Yurii >>>> >>>> Thanks for the reply ... pls get this fixed asap. >>>> >>>> Also, any chance to fix the clang errors for VariABEL, see >>>> ? >>>> >>>> Best >>>> -k >>>> >>>>> On Jan 6, 2014, at 19:47, Kurt Hornik wrote: >>>> >>>>>>>>>>> Kurt Hornik writes: >>>>>> >>>>>> Ping? >>>>>> >>>>>> -k >>>>>> >>>>>>>>>>> Kurt Hornik writes: >>>>>>> Ping? >>>>>> >>>>>>> -k >>>>>> >>>>>>> This has >>>>>>> m.struchalin at erasmusmc.nl >>>>>> >>>>>>> as maintainer address, which no longer works. >>>>>> >>>>>>> Can we pls asap have an update with a working maintainer email address? >>>>>> >>>>>>> Best >>>>>>> -k >>>> >> >> _______________________________________________ >> genabel-devel mailing list >> genabel-devel at lists.r-forge.r-project.org >> https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/genabel-devel >> > > > > _______________________________________________ > genabel-devel mailing list > genabel-devel at lists.r-forge.r-project.org > https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/genabel-devel > -- *-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-* L.C. Karssen Utrecht The Netherlands lennart at karssen.org http://blog.karssen.org GPG key ID: A88F554A -*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*- -------------- next part -------------- A non-text attachment was scrubbed... Name: signature.asc Type: application/pgp-signature Size: 230 bytes Desc: OpenPGP digital signature URL: From yurii.aulchenko at gmail.com Mon Jan 27 00:16:44 2014 From: yurii.aulchenko at gmail.com (Yury Aulchenko) Date: Mon, 27 Jan 2014 06:16:44 +0700 Subject: [GenABEL-dev] CRAN package MetABEL In-Reply-To: <52E59636.6040402@karssen.org> References: <21172.48479.385656.257533@fangorn.hornik.net> <21193.23467.229635.663015@fangorn.hornik.net> <21194.64060.636290.847143@fangorn.hornik.net> <6373BB2F-55FB-45DD-B536-418ACBC63757@gmail.com> <21194.64514.866424.347543@fangorn.hornik.net> <34B26CD8-BF07-495D-9784-05FAECB89CFD@gmail.com> <21210.15983.158548.600355@fangorn.hornik.net> <52DCD9B1.6090107@karssen.org> <52E59636.6040402@karssen.org> Message-ID: Thank you very much, Lennart! Something which was long on our list. Will keep fingers crossed! Yurii ---------------- Sent from mobile device, please excuse possible typos > On 27 Jan 2014, at 06:11, "L.C. Karssen" wrote: > > Dear list, > > I just submitted MetABEL 0.1-0 to CRAN. Except for the fixes required by > the CRAN checks (some functions keywords were not written in full and > some lines in the documentation were too loing), as well as changing the > maintainer from Maksim to me, nothing changed. > > > Best, > > Lennart. > >> On 20-01-14 09:09, L.C. Karssen wrote: >> Dear Kurt, >> >> Thanks for the reminder. I will put it on my todo list for this week. >> >> >> Lennart Karssen. >> >> On 18-01-14 09:42, Kurt Hornik wrote: >>>>>>>> Yury Aulchenko writes: >>> >>> Two weeks later: we really need the updates asap ... >>> >>> -k >>> >>> >>>> Thank you! - will try to fix asap. >>>> Yurii >>> >>>> On Jan 6, 2014, at 19:54, Kurt Hornik wrote: >>> >>>>>>>>>> Yury Aulchenko writes: >>>>> >>>>>> Thank you very much for reminder; apparently this escaped our radar... >>>>>> Yurii >>>>> >>>>> Thanks for the reply ... pls get this fixed asap. >>>>> >>>>> Also, any chance to fix the clang errors for VariABEL, see >>>>> ? >>>>> >>>>> Best >>>>> -k >>>>> >>>>>> On Jan 6, 2014, at 19:47, Kurt Hornik wrote: >>>>> >>>>>>>>>>>> Kurt Hornik writes: >>>>>>> >>>>>>> Ping? >>>>>>> >>>>>>> -k >>>>>>> >>>>>>>>>>>> Kurt Hornik writes: >>>>>>>> Ping? >>>>>>> >>>>>>>> -k >>>>>>> >>>>>>>> This has >>>>>>>> m.struchalin at erasmusmc.nl >>>>>>> >>>>>>>> as maintainer address, which no longer works. >>>>>>> >>>>>>>> Can we pls asap have an update with a working maintainer email address? >>>>>>> >>>>>>>> Best >>>>>>>> -k >>>>> >>> >>> _______________________________________________ >>> genabel-devel mailing list >>> genabel-devel at lists.r-forge.r-project.org >>> https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/genabel-devel >>> >> >> >> >> _______________________________________________ >> genabel-devel mailing list >> genabel-devel at lists.r-forge.r-project.org >> https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/genabel-devel >> > > -- > *-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-* > L.C. Karssen > Utrecht > The Netherlands > > lennart at karssen.org > http://blog.karssen.org > GPG key ID: A88F554A > -*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*- > > _______________________________________________ > genabel-devel mailing list > genabel-devel at lists.r-forge.r-project.org > https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/genabel-devel From lennart at karssen.org Mon Jan 27 12:15:17 2014 From: lennart at karssen.org (L.C. Karssen) Date: Mon, 27 Jan 2014 12:15:17 +0100 Subject: [GenABEL-dev] Building VariABEL Message-ID: <52E63FC5.5010302@karssen.org> Dear Maksim, dear list, I have been trying to build the VariABEL package, but I can't seem to get it to work. Compilation of the VariABEL.so file by R CMD check works, but then when it tries to load the shared lib I get the following error. Any idea how to fix this? How did you get it to work for you last CRAN submission? ** testing if installed package can be loaded Error in dyn.load(file, DLLpath = DLLpath, ...) : unable to load shared object '/home/lennart/Projecten/GenABEL/VariABEL-build/VariABEL.Rcheck/VariABEL/libs/VariABEL.so': /home/lennart/Projecten/GenABEL/VariABEL-build/VariABEL.Rcheck/VariABEL/libs/VariABEL.so: undefined symbol: mych2inv_ Error: loading failed Execution halted ERROR: loading failed * removing ?/home/lennart/Projecten/GenABEL/VariABEL-build/VariABEL.Rcheck/VariABEL? If I build the .so file by hand (R CMD SHLIB VariABEL/src/*.cpp) I get the .so file, but when I try to load the lib in R manually I get the same error: > dyn.load(paste("/home/lennart/Projecten/GenABEL/VariABEL-build/VariABEL/src/VariABEL", .Platform$dynlib.ext, sep="")) Error in dyn.load(paste("/home/lennart/Projecten/GenABEL/VariABEL-build/VariABEL/src/VariABEL", : unable to load shared object '/home/lennart/Projecten/GenABEL/VariABEL-build/VariABEL/src/VariABEL.so': /home/lennart/Projecten/GenABEL/VariABEL-build/VariABEL/src/VariABEL.so: undefined symbol: mych2inv_ > Thanks, Lennart. -- *-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-* L.C. Karssen Utrecht The Netherlands lennart at karssen.org http://blog.karssen.org GPG key ID: A88F554A -*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*- -------------- next part -------------- A non-text attachment was scrubbed... Name: signature.asc Type: application/pgp-signature Size: 230 bytes Desc: OpenPGP digital signature URL: From m.v.struchalin at mail.ru Mon Jan 27 13:34:32 2014 From: m.v.struchalin at mail.ru (Maksim Struchalin) Date: Mon, 27 Jan 2014 19:34:32 +0700 Subject: [GenABEL-dev] Building VariABEL In-Reply-To: <52E63FC5.5010302@karssen.org> References: <52E63FC5.5010302@karssen.org> Message-ID: Hi Lennart, The function mych2inv is a fortran function with C 'name' (in a header file which I made myself). Find this fun and try to play with a name. May be there is some problems with dash. I'll take a look tomorrow if u do not succeed. Best, Maksim Sent from my iPhone > 27 ???. 2014 ?., ? 18:15, "L.C. Karssen" ???????(?): > > mych2inv From lennart at karssen.org Mon Jan 27 14:19:18 2014 From: lennart at karssen.org (L.C. Karssen) Date: Mon, 27 Jan 2014 14:19:18 +0100 Subject: [GenABEL-dev] CRAN package MetABEL In-Reply-To: References: <21172.48479.385656.257533@fangorn.hornik.net> <21193.23467.229635.663015@fangorn.hornik.net> <21194.64060.636290.847143@fangorn.hornik.net> <6373BB2F-55FB-45DD-B536-418ACBC63757@gmail.com> <21194.64514.866424.347543@fangorn.hornik.net> <34B26CD8-BF07-495D-9784-05FAECB89CFD@gmail.com> <21210.15983.158548.600355@fangorn.hornik.net> <52DCD9B1.6090107@karssen.org> <52E59636.6040402@karssen.org> Message-ID: <52E65CD6.5010402@karssen.org> It's on CRAN :-). Best, Lennart. On 27-01-14 00:16, Yury Aulchenko wrote: > Thank you very much, Lennart! > > Something which was long on our list. Will keep fingers crossed! > > Yurii > > ---------------- > Sent from mobile device, please excuse possible typos > >> On 27 Jan 2014, at 06:11, "L.C. Karssen" wrote: >> >> Dear list, >> >> I just submitted MetABEL 0.1-0 to CRAN. Except for the fixes required by >> the CRAN checks (some functions keywords were not written in full and >> some lines in the documentation were too loing), as well as changing the >> maintainer from Maksim to me, nothing changed. >> >> >> Best, >> >> Lennart. >> >>> On 20-01-14 09:09, L.C. Karssen wrote: >>> Dear Kurt, >>> >>> Thanks for the reminder. I will put it on my todo list for this week. >>> >>> >>> Lennart Karssen. >>> >>> On 18-01-14 09:42, Kurt Hornik wrote: >>>>>>>>> Yury Aulchenko writes: >>>> >>>> Two weeks later: we really need the updates asap ... >>>> >>>> -k >>>> >>>> >>>>> Thank you! - will try to fix asap. >>>>> Yurii >>>> >>>>> On Jan 6, 2014, at 19:54, Kurt Hornik wrote: >>>> >>>>>>>>>>> Yury Aulchenko writes: >>>>>> >>>>>>> Thank you very much for reminder; apparently this escaped our radar... >>>>>>> Yurii >>>>>> >>>>>> Thanks for the reply ... pls get this fixed asap. >>>>>> >>>>>> Also, any chance to fix the clang errors for VariABEL, see >>>>>> ? >>>>>> >>>>>> Best >>>>>> -k >>>>>> >>>>>>> On Jan 6, 2014, at 19:47, Kurt Hornik wrote: >>>>>> >>>>>>>>>>>>> Kurt Hornik writes: >>>>>>>> >>>>>>>> Ping? >>>>>>>> >>>>>>>> -k >>>>>>>> >>>>>>>>>>>>> Kurt Hornik writes: >>>>>>>>> Ping? >>>>>>>> >>>>>>>>> -k >>>>>>>> >>>>>>>>> This has >>>>>>>>> m.struchalin at erasmusmc.nl >>>>>>>> >>>>>>>>> as maintainer address, which no longer works. >>>>>>>> >>>>>>>>> Can we pls asap have an update with a working maintainer email address? >>>>>>>> >>>>>>>>> Best >>>>>>>>> -k >>>>>> >>>> >>>> _______________________________________________ >>>> genabel-devel mailing list >>>> genabel-devel at lists.r-forge.r-project.org >>>> https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/genabel-devel >>>> >>> >>> >>> >>> _______________________________________________ >>> genabel-devel mailing list >>> genabel-devel at lists.r-forge.r-project.org >>> https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/genabel-devel >>> >> >> -- >> *-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-* >> L.C. Karssen >> Utrecht >> The Netherlands >> >> lennart at karssen.org >> http://blog.karssen.org >> GPG key ID: A88F554A >> -*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*- >> >> _______________________________________________ >> genabel-devel mailing list >> genabel-devel at lists.r-forge.r-project.org >> https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/genabel-devel -- *-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-* L.C. Karssen Utrecht The Netherlands lennart at karssen.org http://blog.karssen.org GPG key ID: A88F554A -*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*- -------------- next part -------------- A non-text attachment was scrubbed... Name: signature.asc Type: application/pgp-signature Size: 230 bytes Desc: OpenPGP digital signature URL: From lennart at karssen.org Thu Jan 30 10:54:00 2014 From: lennart at karssen.org (L.C. Karssen) Date: Thu, 30 Jan 2014 10:54:00 +0100 Subject: [GenABEL-dev] [Genabel-commits] r1573 - branches/ProbABEL-0.50/src In-Reply-To: <20140129230042.6D3D5186D27@r-forge.r-project.org> References: <20140129230042.6D3D5186D27@r-forge.r-project.org> Message-ID: <52EA2138.80308@karssen.org> Hi Maarten, Interesting changes! More use of Eigen is good :-). I've got a few questions about this commit: 1) Is it still possible to compile ProbABEL/palinear without EIGEN? Or is it time to decide to really depend on it? 2) I see you're using a lot of MatrixXd variables. These are matrices of double type. Wouldn't it make more sense to use the Matrix construction? In case we ever decide to go with all computations in float (would be an easier search/replace of double with float)? Or is that a much slower implementation? I know it's a bit of a weird argument, but I was wondering if you gave it a thought. 3) Are you planning to do some computation time comparisons with and without these changes? I've got a few more questions and comments in your below. Thanks for all the good work! Lennart. On 30-01-14 00:00, noreply at r-forge.r-project.org wrote: > Author: maartenk > Date: 2014-01-30 00:00:40 +0100 (Thu, 30 Jan 2014) > New Revision: 1573 > > Modified: > branches/ProbABEL-0.50/src/reg1.cpp > branches/ProbABEL-0.50/src/reg1.h > Log: > changed linear_reg::estimate to use more eigen functions: cholesky.h is not nessary for palinear. > > Modified: branches/ProbABEL-0.50/src/reg1.cpp > =================================================================== > --- branches/ProbABEL-0.50/src/reg1.cpp 2014-01-29 17:25:58 UTC (rev 1572) > +++ branches/ProbABEL-0.50/src/reg1.cpp 2014-01-29 23:00:40 UTC (rev 1573) > @@ -285,17 +285,14 @@ > chi2_score = chi2[0]; > } > > + > void linear_reg::estimate(regdata& rdatain, int verbose, double tol_chol, > int model, int interaction, int ngpreds, masked_matrix& invvarmatrixin, > int robust, int nullmodel) { > // suda interaction parameter > // model should come here > regdata rdata = rdatain.get_unmasked_data(); > - if (invvarmatrixin.length_of_mask != 0) > - { > - invvarmatrixin.update_mask(rdatain.masked_data); > - // invvarmatrixin.masked_data->print(); > - } > + > if (verbose) > { > cout << rdata.is_interaction_excluded > @@ -334,8 +331,14 @@ > > double sigma2_internal; > mematrix tXX_i; > +#if EIGEN > + LDLT Ch ; > +#endif > if (invvarmatrixin.length_of_mask != 0) > { > + //retrieve masked data W > + invvarmatrixin.update_mask(rdatain.masked_data); > + > // This regression is Weighted Least Square: used for mmscore : > // FLOPS count are calculated for 3*1000 matrix as follow: > //C=AB (m X n matrix A and n x P matrix B) > @@ -343,6 +346,10 @@ > //Oct 26, 2009 > mematrix tXW = transpose(X) * invvarmatrixin.masked_data; // flops 5997000 > tXX_i = tXW * X; // 17991 flops > +#if EIGEN > + Ch=LDLT (tXX_i.data.selfadjointView()); > +#endif > + it seems that you do the work for EIGEN in an #if/#endif, but the cholesky2_mm is still used below. Shouldn't that be in the #else part? > // use cholesky to invert > cholesky2_mm(tXX_i, tol_chol); > chinv2_mm(tXX_i); > @@ -356,23 +363,41 @@ > sigma2 += val * val; // flops: 3000 > } > double N = X.nrow; > - sigma2_internal = sigma2 / (N - static_cast(length_beta)); > + //sigma2_internal = sigma2 / (N - static_cast(length_beta)); > + // Ugly fix to the fact that if we do mmscore, sigma2 is already > + // in the matrix... > + // YSA, 2009.07.20 > + sigma2_internal = 1.0; > sigma2 /= N; > - //NO mm-score regression : normal least square regression > + > } > - else > + else//NO mm-score regression : normal least square regression > { > +#if EIGEN > + int m = X.ncol; > + MatrixXd txx = MatrixXd(m, m).setZero().selfadjointView().rankUpdate(X.data.adjoint()); > + Ch=LDLT (txx.selfadjointView()); > + beta.data= Ch.solve(X.data.adjoint() * rdata.Y.data); > + > + tXX_i.data=Ch.solve(MatrixXd(m, m).Identity(m,m)); > + tXX_i.nrow=tXX_i.data.rows(); > + tXX_i.ncol=tXX_i.data.cols(); > + tXX_i.nelements=tXX_i.ncol*tXX_i.nrow; > + > +#else > mematrix tX = transpose(X); > // use cholesky to invert > - tXX_i = tX * X; > - cholesky2_mm(tXX_i, tol_chol); > - chinv2_mm(tXX_i); > - beta = tXX_i * (tX * (rdata.Y)); > + tXX_i = tX * X; > + cholesky2_mm(tXX_i, tol_chol); > + chinv2_mm(tXX_i); > + beta = tXX_i * (tX * (rdata.Y)); > +#endif > + > // now compute residual variance > sigma2 = 0.; > mematrix sigma2_matrix = rdata.Y - (X * beta); > #if EIGEN > - sigma2 = sigma2_matrix.data.array().square().sum(); > + sigma2 = sigma2_matrix.data.squaredNorm() ; > #else > for (int i = 0; i < sigma2_matrix.nrow; i++) > { > @@ -380,8 +405,9 @@ > sigma2 += val * val; > } > #endif > - double N = X.nrow; > - sigma2_internal = sigma2 / (N - static_cast(length_beta)); > + double N = static_cast(X.nrow); Code layout: remember we have a space around operators :-) > + double P=static_cast(length_beta); > + sigma2_internal = sigma2 / (N - P); > sigma2 /= N; > } > /* > @@ -407,8 +433,8 @@ > double intercept = beta.get(0, 0); > residuals.data= rdata.Y.data.array()-intercept; > //matrix. > - Eigen::ArrayXXd betacol = beta.data.block(1,0,beta.data.rows()-1,1).array().transpose(); > - Eigen::ArrayXXd resid_sub = (X.data.block(0,1,X.data.rows(),X.data.cols()-1)*betacol.matrix().asDiagonal()).rowwise().sum() ; And also space after comma's and lines shorter than 80 characters... Otherwise Jenkins will be pissed again ;-). > + ArrayXXd betacol = beta.data.block(1,0,beta.data.rows()-1,1).array().transpose(); > + ArrayXXd resid_sub = (X.data.block(0,1,X.data.rows(),X.data.cols()-1)*betacol.matrix().asDiagonal()).rowwise().sum() ; > //std::cout << resid_sub << std::endl; > residuals.data-=resid_sub.matrix(); > //residuals[i] -= resid_sub; > @@ -422,41 +448,77 @@ > double resid = rdata.Y[i] - beta.get(0, 0); // intercept > for (int j = 1; j < beta.nrow; j++){ > resid -= beta.get(j, 0) * X.get(i, j); > - > } > residuals[i] = resid; > loglik -= halfrecsig2 * resid * resid; > } > #endif > > - > - > loglik -= static_cast(rdata.nids) * log(sqrt(sigma2)); > - // cout << "estimate " << rdata.nids << "\n"; > - // > - // Ugly fix to the fact that if we do mmscore, sigma2 is already > - // in the matrix... > - // YSA, 2009.07.20 > - // > - //cout << "estimate 0\n"; > - if (invvarmatrixin.length_of_mask != 0) > - sigma2_internal = 1.0; > +#if EIGEN > + MatrixXd tXX_inv=Ch.solve(MatrixXd(length_beta, length_beta).Identity(length_beta,length_beta)); > +#endif > > mematrix robust_sigma2(X.ncol, X.ncol); > if (robust) > { > +#if EIGEN > + MatrixXd Xresiduals = X.data.array().colwise()*residuals.data.col(0).array(); > + MatrixXd XbyR = MatrixXd(X.ncol, X.ncol).setZero().selfadjointView().rankUpdate(Xresiduals.adjoint()); > + robust_sigma2.data= tXX_inv*XbyR *tXX_inv; > +#else > + > mematrix XbyR = X; > - for (int i = 0; i < X.nrow; i++) > + for (int i = 0; i < X.nrow; i++){ > for (int j = 0; j < X.ncol; j++) > { > double tmpval = XbyR.get(i, j) * residuals[i]; > XbyR.put(tmpval, i, j); > } > + } > XbyR = transpose(XbyR) * XbyR; > robust_sigma2 = tXX_i * XbyR; > robust_sigma2 = robust_sigma2 * tXX_i; > + > +#endif > + > + > } > //cout << "estimate 0\n"; > +#if EIGEN > + if (robust) > + { > + sebeta.data = robust_sigma2.data.diagonal().array().sqrt(); > + } > + else > + { > + sebeta.data = > + (sigma2_internal > + * tXX_inv.diagonal().array()).sqrt(); > + } > + int offset=X.ncol- 1; > + //if additive and interaction and 2 predictors and more then 2 betas > + > + if (model == 0 && interaction != 0 && ngpreds == 2 && length_beta > 2){ > + offset=X.ncol - 2; > + } > + > + if (robust) > + { > + covariance.data = robust_sigma2.data.bottomLeftCorner( > + offset, offset).diagonal(); > + > + } > + else > + { > + covariance.data = sigma2_internal > + * tXX_inv.bottomLeftCorner(offset, > + offset).diagonal().array(); > + } > + > +#else > + > + //cout << "estimate 0\n"; > for (int i = 0; i < (length_beta); i++) > { > if (robust) > @@ -510,12 +572,8 @@ > //Oct 26, 2009 > } > } > - //cout << "estimate E\n"; > - if (verbose) > - { > - std::cout << "sebeta (" << sebeta.nrow << "):\n"; > - sebeta.print(); > - } > +#endif > + > } > > void linear_reg::score(mematrix& resid, regdata& rdatain, int verbose, > > Modified: branches/ProbABEL-0.50/src/reg1.h > =================================================================== > --- branches/ProbABEL-0.50/src/reg1.h 2014-01-29 17:25:58 UTC (rev 1572) > +++ branches/ProbABEL-0.50/src/reg1.h 2014-01-29 23:00:40 UTC (rev 1573) > @@ -30,6 +30,7 @@ > #include "regdata.h" > #include "maskedmatrix.h" > > + > mematrix apply_model(mematrix& X, int model, int interaction, > int ngpreds, bool is_interaction_excluded, bool iscox = false, > int nullmodel = 0); > > _______________________________________________ > Genabel-commits mailing list > Genabel-commits at lists.r-forge.r-project.org > https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/genabel-commits > -- *-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-* L.C. Karssen Utrecht The Netherlands lennart at karssen.org http://blog.karssen.org GPG key ID: A88F554A -*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*- -------------- next part -------------- A non-text attachment was scrubbed... Name: signature.asc Type: application/pgp-signature Size: 230 bytes Desc: OpenPGP digital signature URL: From m.v.struchalin at mail.ru Thu Jan 30 11:27:27 2014 From: m.v.struchalin at mail.ru (Maksim Struchalin) Date: Thu, 30 Jan 2014 17:27:27 +0700 Subject: [GenABEL-dev] VariABEL is submited Message-ID: <52EA290F.1060500@mail.ru> Dear All-who-is-interested, I just have submited VariABEL to CRAN. Waiting for their response. best, Maksim From yurii.aulchenko at gmail.com Thu Jan 30 11:39:18 2014 From: yurii.aulchenko at gmail.com (Yury Aulchenko) Date: Thu, 30 Jan 2014 11:39:18 +0100 Subject: [GenABEL-dev] VariABEL is submited In-Reply-To: <52EA290F.1060500@mail.ru> References: <52EA290F.1060500@mail.ru> Message-ID: <27F002E7-FF97-490E-8C87-D38CA05A85E5@gmail.com> Great, Maksim! Will keep fingers crossed :) Y On Jan 30, 2014, at 11:27, Maksim Struchalin wrote: > Dear All-who-is-interested, > > I just have submited VariABEL to CRAN. Waiting for their response. > > best, > Maksim > _______________________________________________ > genabel-devel mailing list > genabel-devel at lists.r-forge.r-project.org > https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/genabel-devel From lennart at karssen.org Thu Jan 30 11:41:10 2014 From: lennart at karssen.org (L.C. Karssen) Date: Thu, 30 Jan 2014 11:41:10 +0100 Subject: [GenABEL-dev] VariABEL is submited In-Reply-To: <52EA290F.1060500@mail.ru> References: <52EA290F.1060500@mail.ru> Message-ID: <52EA2C46.3020006@karssen.org> Hi Maksim, Thanks for taking the time to adapt VariABEL to CRAN's checks. Let's hope that the package passes all of them. Best, Lennart. On 30-01-14 11:27, Maksim Struchalin wrote: > Dear All-who-is-interested, > > I just have submited VariABEL to CRAN. Waiting for their response. > > best, > Maksim > _______________________________________________ > genabel-devel mailing list > genabel-devel at lists.r-forge.r-project.org > https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/genabel-devel -- *-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-* L.C. Karssen Utrecht The Netherlands lennart at karssen.org http://blog.karssen.org GPG key ID: A88F554A -*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*- -------------- next part -------------- A non-text attachment was scrubbed... Name: signature.asc Type: application/pgp-signature Size: 230 bytes Desc: OpenPGP digital signature URL: From m.v.struchalin at mail.ru Thu Jan 30 15:01:59 2014 From: m.v.struchalin at mail.ru (Maksim Struchalin) Date: Thu, 30 Jan 2014 21:01:59 +0700 Subject: [GenABEL-dev] Fwd: Re: CRAN submission VariABEL 0.9-2 In-Reply-To: <21226.15110.701853.750429@fangorn.hornik.net> References: <21226.15110.701853.750429@fangorn.hornik.net> Message-ID: <52EA5B57.8020800@mail.ru> VariABEL is on CRAN. Maksim -------- Original Message -------- Subject: Re: CRAN submission VariABEL 0.9-2 Date: Thu, 30 Jan 2014 12:44:06 +0100 From: Kurt Hornik Reply-To: Kurt.Hornik at wu.ac.at To: Maksim Struchalin CC: CRAN >>>>> Maksim Struchalin writes: Thanks, on CRAN now. Best -k > [This was generated from CRAN.R-project.org/submit.html] > The following package was uploaded to CRAN: > =========================================== > Package Information: > Package: VariABEL > Version: 0.9-2 > Title: Testing of genotypic variance heterogeneity to detect potentially > interacting SNP. > Author(s): Maksim Struchalin > Maintainer: Maksim Struchalin > Depends: R (>= 2.13.0) > Suggests: GenABEL, DatABEL > Description: Presence of interaction between a SNP and another SNP (or > another factor) can result in heterogeneity of variance > between the genotypes of an interacting SNP. Detecting such > heterogeneity gives prior knowledge for constructing a > genetic model underlying complex trait. > License: GPL (>= 2) > The maintainer confirms that he or she > has read and agrees to the CRAN policies. > Submitter's comment: Dear Maintainer, > This version of VariABEL contains > 'clangs' warnings fixes as you requred, > best > regards, > Maksim -------------- next part -------------- An HTML attachment was scrubbed... URL: From yurii.aulchenko at gmail.com Thu Jan 30 15:44:53 2014 From: yurii.aulchenko at gmail.com (Yury Aulchenko) Date: Thu, 30 Jan 2014 15:44:53 +0100 Subject: [GenABEL-dev] CRAN submission VariABEL 0.9-2 In-Reply-To: <52EA5B57.8020800@mail.ru> References: <21226.15110.701853.750429@fangorn.hornik.net> <52EA5B57.8020800@mail.ru> Message-ID: <19372756-EB85-474F-AC20-F08860525F71@gmail.com> Congrats! Y On Jan 30, 2014, at 15:01, Maksim Struchalin wrote: > VariABEL is on CRAN. > Maksim > > > -------- Original Message -------- > Subject: Re: CRAN submission VariABEL 0.9-2 > Date: Thu, 30 Jan 2014 12:44:06 +0100 > From: Kurt Hornik > Reply-To: Kurt.Hornik at wu.ac.at > To: Maksim Struchalin > CC: CRAN > > >>>>> Maksim Struchalin writes: > > Thanks, on CRAN now. > > Best > -k > > > [This was generated from CRAN.R-project.org/submit.html] > > The following package was uploaded to CRAN: > > =========================================== > > > Package Information: > > Package: VariABEL > > Version: 0.9-2 > > Title: Testing of genotypic variance heterogeneity to detect potentially > > interacting SNP. > > Author(s): Maksim Struchalin > > Maintainer: Maksim Struchalin > > Depends: R (>= 2.13.0) > > Suggests: GenABEL, DatABEL > > Description: Presence of interaction between a SNP and another SNP (or > > another factor) can result in heterogeneity of variance > > between the genotypes of an interacting SNP. Detecting such > > heterogeneity gives prior knowledge for constructing a > > genetic model underlying complex trait. > > License: GPL (>= 2) > > > > The maintainer confirms that he or she > > has read and agrees to the CRAN policies. > > > Submitter's comment: Dear Maintainer, > > > This version of VariABEL contains > > 'clangs' warnings fixes as you requred, > > > best > > regards, > > Maksim > > > > _______________________________________________ > genabel-devel mailing list > genabel-devel at lists.r-forge.r-project.org > https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/genabel-devel -------------- next part -------------- An HTML attachment was scrubbed... URL: From lennart at karssen.org Thu Jan 30 20:28:17 2014 From: lennart at karssen.org (L.C. Karssen) Date: Thu, 30 Jan 2014 20:28:17 +0100 Subject: [GenABEL-dev] Abstract for the EMGM 2014 conference Message-ID: <52EAA7D1.5080106@karssen.org> Dear list, I'm planning to go to the EMGM (European Mathematical Genetics Meeting) in Cologne in April. I'd like to present a poster there and wrote the abstract below. Please let me know any comments or suggestions as soon possible as the deadline for abstract submission is tomorrow (Fri 31 Jan). Thank you very much, Lennart. --------------8<----------------8<------------------8<------------- Over the last year the GenABEL project has seen a considerable number of improvements. These improvements do not only consist of updates to the existing packages of the GenABEL suite, but are also manifest in the way the development process is being handled and the way the packages are made available to the users. On our poster we will demonstrate the newly implemented features in the various packages of the GenABEL suite. We also welcome a new member to the GenABEL family: OmicABEL, a package for rapid mixed-model based genome-wide association analysis of multiple traits (think metabolomics, glycomics, etc.). Recently we started using the open source Jenkins Continuous Integration server to help us release software of higher quality. Jenkins is a framework that automatically runs several tests (e.g. static code analysis, checks for memory leaks) for each of our packages. It builds and tests each project after a new commit in our version control system. This allows us to detect problems in the code at an early stage, before they bug the user. After the GenABEL package, ProbABEL is the second package that is available as a Debian package. This means that users of upcoming Debian releases will be able to install ProbABEL with a simple click of a button or a single command. Moreover, since many other Linux distributions like Ubuntu and Linux Mint are derived from Debian, users of these distributions automatically benefit as well. In the coming year more packages are expected to be added the GenABEL suite as well as continued efforts to improve the existing ones. Moreover, we plan to increase both the ease of installation as well as the visibility of the GenABEL suite by adding more packages into both the Debian and Red Hat Enterprise Linux repositories (as well as derivatives like CentOS and Scientific Linux). --------------8<----------------8<------------------8<------------- -- *-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-* L.C. Karssen Utrecht The Netherlands lennart at karssen.org http://blog.karssen.org GPG key ID: A88F554A -*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*- -------------- next part -------------- A non-text attachment was scrubbed... Name: signature.asc Type: application/pgp-signature Size: 230 bytes Desc: OpenPGP digital signature URL: From yurii.aulchenko at gmail.com Thu Jan 30 20:31:42 2014 From: yurii.aulchenko at gmail.com (Yury Aulchenko) Date: Thu, 30 Jan 2014 20:31:42 +0100 Subject: [GenABEL-dev] Abstract for the EMGM 2014 conference In-Reply-To: <52EAA7D1.5080106@karssen.org> References: <52EAA7D1.5080106@karssen.org> Message-ID: <1951EA55-5DB4-4A28-837A-AA947FBA2D2D@gmail.com> What is the title? ---------------- Sent from mobile device, please excuse possible typos > On 30 Jan 2014, at 20:28, "L.C. Karssen" wrote: > > Dear list, > > I'm planning to go to the EMGM (European Mathematical Genetics Meeting) > in Cologne in April. I'd like to present a poster there and wrote the > abstract below. > Please let me know any comments or suggestions as soon possible as the > deadline for abstract submission is tomorrow (Fri 31 Jan). > > Thank you very much, > > Lennart. > > > --------------8<----------------8<------------------8<------------- > Over the last year the GenABEL project has seen a considerable > number of improvements. These improvements do not only consist of > updates to the existing packages of the GenABEL suite, but are also > manifest in the way the development process is being handled and > the way the packages are made available to the users. > > On our poster we will demonstrate the newly implemented features in > the various packages of the GenABEL suite. We also welcome a new > member to the GenABEL family: OmicABEL, a package for rapid > mixed-model based genome-wide association analysis of multiple > traits (think metabolomics, glycomics, etc.). > > Recently we started using the open source Jenkins Continuous > Integration server to help us release software of higher > quality. Jenkins is a framework that automatically runs several > tests (e.g. static code analysis, checks for memory leaks) for each > of our packages. It builds and tests each project after a new commit > in our version control system. This allows us to detect problems in > the code at an early stage, before they bug the user. > > After the GenABEL package, ProbABEL is the second package that is > available as a Debian package. This means that users of upcoming > Debian releases will be able to install ProbABEL with a simple click > of a button or a single command. Moreover, since many other Linux > distributions like Ubuntu and Linux Mint are derived from Debian, > users of these distributions automatically benefit as well. > > In the coming year more packages are expected to be added the > GenABEL suite as well as continued efforts to improve the existing > ones. Moreover, we plan to increase both the ease of installation as > well as the visibility of the GenABEL suite by adding more packages > into both the Debian and Red Hat Enterprise Linux repositories (as > well as derivatives like CentOS and Scientific Linux). > --------------8<----------------8<------------------8<------------- > > > > > > > > > > > -- > *-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-* > L.C. Karssen > Utrecht > The Netherlands > > lennart at karssen.org > http://blog.karssen.org > GPG key ID: A88F554A > -*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*- > > _______________________________________________ > genabel-devel mailing list > genabel-devel at lists.r-forge.r-project.org > https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/genabel-devel From yurii.aulchenko at gmail.com Thu Jan 30 20:35:04 2014 From: yurii.aulchenko at gmail.com (Yury Aulchenko) Date: Thu, 30 Jan 2014 20:35:04 +0100 Subject: [GenABEL-dev] Abstract for the EMGM 2014 conference In-Reply-To: <52EAA7D1.5080106@karssen.org> References: <52EAA7D1.5080106@karssen.org> Message-ID: <191CE790-8962-4A60-AD79-D20C5E7ADC67@gmail.com> Very general comments: I suggest not say "poster" - you may get an oral. Why not? Any words about the community to add? Forum, etc - we have few numbers in the UseR! presentation (on our site). - but may be it will get too broad then... ---------------- Sent from mobile device, please excuse possible typos > On 30 Jan 2014, at 20:28, "L.C. Karssen" wrote: > > Dear list, > > I'm planning to go to the EMGM (European Mathematical Genetics Meeting) > in Cologne in April. I'd like to present a poster there and wrote the > abstract below. > Please let me know any comments or suggestions as soon possible as the > deadline for abstract submission is tomorrow (Fri 31 Jan). > > Thank you very much, > > Lennart. > > > --------------8<----------------8<------------------8<------------- > Over the last year the GenABEL project has seen a considerable > number of improvements. These improvements do not only consist of > updates to the existing packages of the GenABEL suite, but are also > manifest in the way the development process is being handled and > the way the packages are made available to the users. > > On our poster we will demonstrate the newly implemented features in > the various packages of the GenABEL suite. We also welcome a new > member to the GenABEL family: OmicABEL, a package for rapid > mixed-model based genome-wide association analysis of multiple > traits (think metabolomics, glycomics, etc.). > > Recently we started using the open source Jenkins Continuous > Integration server to help us release software of higher > quality. Jenkins is a framework that automatically runs several > tests (e.g. static code analysis, checks for memory leaks) for each > of our packages. It builds and tests each project after a new commit > in our version control system. This allows us to detect problems in > the code at an early stage, before they bug the user. > > After the GenABEL package, ProbABEL is the second package that is > available as a Debian package. This means that users of upcoming > Debian releases will be able to install ProbABEL with a simple click > of a button or a single command. Moreover, since many other Linux > distributions like Ubuntu and Linux Mint are derived from Debian, > users of these distributions automatically benefit as well. > > In the coming year more packages are expected to be added the > GenABEL suite as well as continued efforts to improve the existing > ones. Moreover, we plan to increase both the ease of installation as > well as the visibility of the GenABEL suite by adding more packages > into both the Debian and Red Hat Enterprise Linux repositories (as > well as derivatives like CentOS and Scientific Linux). > --------------8<----------------8<------------------8<------------- > > > > > > > > > > > -- > *-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-* > L.C. Karssen > Utrecht > The Netherlands > > lennart at karssen.org > http://blog.karssen.org > GPG key ID: A88F554A > -*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*- > > _______________________________________________ > genabel-devel mailing list > genabel-devel at lists.r-forge.r-project.org > https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/genabel-devel From lennart at karssen.org Thu Jan 30 20:39:20 2014 From: lennart at karssen.org (L.C. Karssen) Date: Thu, 30 Jan 2014 20:39:20 +0100 Subject: [GenABEL-dev] Abstract for the EMGM 2014 conference In-Reply-To: <1951EA55-5DB4-4A28-837A-AA947FBA2D2D@gmail.com> References: <52EAA7D1.5080106@karssen.org> <1951EA55-5DB4-4A28-837A-AA947FBA2D2D@gmail.com> Message-ID: <52EAAA68.5080600@karssen.org> Good point! :-) I've got several options: 1) The State of the GenABEL Project 2) The GenABEL project: improvements and additions 3) New software and developments in the GenABEL project 4) GenABEL: implementing statistical genetics in software Any other suggestions? I'm a bit concerned that it may be too software-developement oriented for a statistical genetics meeting. We'll see On 30-01-14 20:31, Yury Aulchenko wrote: > What is the title? > > ---------------- > Sent from mobile device, please excuse possible typos > >> On 30 Jan 2014, at 20:28, "L.C. Karssen" wrote: >> >> Dear list, >> >> I'm planning to go to the EMGM (European Mathematical Genetics Meeting) >> in Cologne in April. I'd like to present a poster there and wrote the >> abstract below. >> Please let me know any comments or suggestions as soon possible as the >> deadline for abstract submission is tomorrow (Fri 31 Jan). >> >> Thank you very much, >> >> Lennart. >> >> >> --------------8<----------------8<------------------8<------------- >> Over the last year the GenABEL project has seen a considerable >> number of improvements. These improvements do not only consist of >> updates to the existing packages of the GenABEL suite, but are also >> manifest in the way the development process is being handled and >> the way the packages are made available to the users. >> >> On our poster we will demonstrate the newly implemented features in >> the various packages of the GenABEL suite. We also welcome a new >> member to the GenABEL family: OmicABEL, a package for rapid >> mixed-model based genome-wide association analysis of multiple >> traits (think metabolomics, glycomics, etc.). >> >> Recently we started using the open source Jenkins Continuous >> Integration server to help us release software of higher >> quality. Jenkins is a framework that automatically runs several >> tests (e.g. static code analysis, checks for memory leaks) for each >> of our packages. It builds and tests each project after a new commit >> in our version control system. This allows us to detect problems in >> the code at an early stage, before they bug the user. >> >> After the GenABEL package, ProbABEL is the second package that is >> available as a Debian package. This means that users of upcoming >> Debian releases will be able to install ProbABEL with a simple click >> of a button or a single command. Moreover, since many other Linux >> distributions like Ubuntu and Linux Mint are derived from Debian, >> users of these distributions automatically benefit as well. >> >> In the coming year more packages are expected to be added the >> GenABEL suite as well as continued efforts to improve the existing >> ones. Moreover, we plan to increase both the ease of installation as >> well as the visibility of the GenABEL suite by adding more packages >> into both the Debian and Red Hat Enterprise Linux repositories (as >> well as derivatives like CentOS and Scientific Linux). >> --------------8<----------------8<------------------8<------------- >> >> >> >> >> >> >> >> >> >> >> -- >> *-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-* >> L.C. Karssen >> Utrecht >> The Netherlands >> >> lennart at karssen.org >> http://blog.karssen.org >> GPG key ID: A88F554A >> -*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*- >> >> _______________________________________________ >> genabel-devel mailing list >> genabel-devel at lists.r-forge.r-project.org >> https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/genabel-devel -- *-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-* L.C. Karssen Utrecht The Netherlands lennart at karssen.org http://blog.karssen.org GPG key ID: A88F554A -*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*- -------------- next part -------------- A non-text attachment was scrubbed... Name: signature.asc Type: application/pgp-signature Size: 230 bytes Desc: OpenPGP digital signature URL: From lennart at karssen.org Thu Jan 30 20:50:26 2014 From: lennart at karssen.org (L.C. Karssen) Date: Thu, 30 Jan 2014 20:50:26 +0100 Subject: [GenABEL-dev] Abstract for the EMGM 2014 conference In-Reply-To: <191CE790-8962-4A60-AD79-D20C5E7ADC67@gmail.com> References: <52EAA7D1.5080106@karssen.org> <191CE790-8962-4A60-AD79-D20C5E7ADC67@gmail.com> Message-ID: <52EAAD02.3090605@karssen.org> Hi Yurii, Thanks for the suggestions! On 30-01-14 20:35, Yury Aulchenko wrote: > Very general comments: I suggest not say "poster" - you may get an > oral. Why not? True. I've removed the word poster. ? Any words about the community to add? Forum, etc - we > have few numbers in the UseR! presentation (on our site). - but may be > it will get too broad then... That's what I'm a bit afraid of. Last year you already mentioned OmicABEL (although maybe not by that name, I don't remember exactly). So in terms of new statistical methods which should be really interesting for the meeting we haven't really much to offer. I hope that by that time OmicABEL is out of the beta stage. That would be great. As well as having OmicABELnoMM in beta stage (or beyond!). By then ProbABEL should be at 0.5.0 which includes numerous speed improvements and p-values in the output. Best, Lennart. > > ---------------- > Sent from mobile device, please excuse possible typos > >> On 30 Jan 2014, at 20:28, "L.C. Karssen" wrote: >> >> Dear list, >> >> I'm planning to go to the EMGM (European Mathematical Genetics Meeting) >> in Cologne in April. I'd like to present a poster there and wrote the >> abstract below. >> Please let me know any comments or suggestions as soon possible as the >> deadline for abstract submission is tomorrow (Fri 31 Jan). >> >> Thank you very much, >> >> Lennart. >> >> >> --------------8<----------------8<------------------8<------------- >> Over the last year the GenABEL project has seen a considerable >> number of improvements. These improvements do not only consist of >> updates to the existing packages of the GenABEL suite, but are also >> manifest in the way the development process is being handled and >> the way the packages are made available to the users. >> >> On our poster we will demonstrate the newly implemented features in >> the various packages of the GenABEL suite. We also welcome a new >> member to the GenABEL family: OmicABEL, a package for rapid >> mixed-model based genome-wide association analysis of multiple >> traits (think metabolomics, glycomics, etc.). >> >> Recently we started using the open source Jenkins Continuous >> Integration server to help us release software of higher >> quality. Jenkins is a framework that automatically runs several >> tests (e.g. static code analysis, checks for memory leaks) for each >> of our packages. It builds and tests each project after a new commit >> in our version control system. This allows us to detect problems in >> the code at an early stage, before they bug the user. >> >> After the GenABEL package, ProbABEL is the second package that is >> available as a Debian package. This means that users of upcoming >> Debian releases will be able to install ProbABEL with a simple click >> of a button or a single command. Moreover, since many other Linux >> distributions like Ubuntu and Linux Mint are derived from Debian, >> users of these distributions automatically benefit as well. >> >> In the coming year more packages are expected to be added the >> GenABEL suite as well as continued efforts to improve the existing >> ones. Moreover, we plan to increase both the ease of installation as >> well as the visibility of the GenABEL suite by adding more packages >> into both the Debian and Red Hat Enterprise Linux repositories (as >> well as derivatives like CentOS and Scientific Linux). >> --------------8<----------------8<------------------8<------------- >> >> >> >> >> >> >> >> >> >> >> -- >> *-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-* >> L.C. Karssen >> Utrecht >> The Netherlands >> >> lennart at karssen.org >> http://blog.karssen.org >> GPG key ID: A88F554A >> -*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*- >> >> _______________________________________________ >> genabel-devel mailing list >> genabel-devel at lists.r-forge.r-project.org >> https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/genabel-devel -- *-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-* L.C. Karssen Utrecht The Netherlands lennart at karssen.org http://blog.karssen.org GPG key ID: A88F554A -*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*- -------------- next part -------------- A non-text attachment was scrubbed... Name: signature.asc Type: application/pgp-signature Size: 230 bytes Desc: OpenPGP digital signature URL: From yurii.aulchenko at gmail.com Thu Jan 30 21:07:17 2014 From: yurii.aulchenko at gmail.com (Yury Aulchenko) Date: Thu, 30 Jan 2014 21:07:17 +0100 Subject: [GenABEL-dev] Abstract for the EMGM 2014 conference In-Reply-To: <52EAAA68.5080600@karssen.org> References: <52EAA7D1.5080106@karssen.org> <1951EA55-5DB4-4A28-837A-AA947FBA2D2D@gmail.com> <52EAAA68.5080600@karssen.org> Message-ID: <4F9A56C1-6AD6-487C-987E-C8A107F513E4@gmail.com> I like 3 and then 2 (given what you say in next email) ---------------- Sent from mobile device, please excuse possible typos > On 30 Jan 2014, at 20:39, "L.C. Karssen" wrote: > > Good point! :-) > I've got several options: > > 1) The State of the GenABEL Project > > 2) The GenABEL project: improvements and additions > > 3) New software and developments in the GenABEL project > > 4) GenABEL: implementing statistical genetics in software > > > Any other suggestions? > I'm a bit concerned that it may be too software-developement oriented > for a statistical genetics meeting. We'll see > > >> On 30-01-14 20:31, Yury Aulchenko wrote: >> What is the title? >> >> ---------------- >> Sent from mobile device, please excuse possible typos >> >>> On 30 Jan 2014, at 20:28, "L.C. Karssen" wrote: >>> >>> Dear list, >>> >>> I'm planning to go to the EMGM (European Mathematical Genetics Meeting) >>> in Cologne in April. I'd like to present a poster there and wrote the >>> abstract below. >>> Please let me know any comments or suggestions as soon possible as the >>> deadline for abstract submission is tomorrow (Fri 31 Jan). >>> >>> Thank you very much, >>> >>> Lennart. >>> >>> >>> --------------8<----------------8<------------------8<------------- >>> Over the last year the GenABEL project has seen a considerable >>> number of improvements. These improvements do not only consist of >>> updates to the existing packages of the GenABEL suite, but are also >>> manifest in the way the development process is being handled and >>> the way the packages are made available to the users. >>> >>> On our poster we will demonstrate the newly implemented features in >>> the various packages of the GenABEL suite. We also welcome a new >>> member to the GenABEL family: OmicABEL, a package for rapid >>> mixed-model based genome-wide association analysis of multiple >>> traits (think metabolomics, glycomics, etc.). >>> >>> Recently we started using the open source Jenkins Continuous >>> Integration server to help us release software of higher >>> quality. Jenkins is a framework that automatically runs several >>> tests (e.g. static code analysis, checks for memory leaks) for each >>> of our packages. It builds and tests each project after a new commit >>> in our version control system. This allows us to detect problems in >>> the code at an early stage, before they bug the user. >>> >>> After the GenABEL package, ProbABEL is the second package that is >>> available as a Debian package. This means that users of upcoming >>> Debian releases will be able to install ProbABEL with a simple click >>> of a button or a single command. Moreover, since many other Linux >>> distributions like Ubuntu and Linux Mint are derived from Debian, >>> users of these distributions automatically benefit as well. >>> >>> In the coming year more packages are expected to be added the >>> GenABEL suite as well as continued efforts to improve the existing >>> ones. Moreover, we plan to increase both the ease of installation as >>> well as the visibility of the GenABEL suite by adding more packages >>> into both the Debian and Red Hat Enterprise Linux repositories (as >>> well as derivatives like CentOS and Scientific Linux). >>> --------------8<----------------8<------------------8<------------- >>> >>> >>> >>> >>> >>> >>> >>> >>> >>> >>> -- >>> *-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-* >>> L.C. Karssen >>> Utrecht >>> The Netherlands >>> >>> lennart at karssen.org >>> http://blog.karssen.org >>> GPG key ID: A88F554A >>> -*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*- >>> >>> _______________________________________________ >>> genabel-devel mailing list >>> genabel-devel at lists.r-forge.r-project.org >>> https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/genabel-devel > > -- > *-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-* > L.C. Karssen > Utrecht > The Netherlands > > lennart at karssen.org > http://blog.karssen.org > GPG key ID: A88F554A > -*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*- > From lennart at karssen.org Fri Jan 31 18:49:28 2014 From: lennart at karssen.org (L.C. Karssen) Date: Fri, 31 Jan 2014 18:49:28 +0100 Subject: [GenABEL-dev] Abstract for the EMGM 2014 conference In-Reply-To: <52EAA7D1.5080106@karssen.org> References: <52EAA7D1.5080106@karssen.org> Message-ID: <52EBE228.70503@karssen.org> Dear GenABEL devs, Thank you for the various comments you sent. I have incorporated them, but also hd to shorten the abstract to 250 words. Please find below the abstract I submitted. Best regards, Lennart. Title: New software and developments in the GenABEL project Authors: L.C. Karssen, on behalf of the GenABEL team Abstract: In the last year the GenABEL project has seen a considerable number of improvements. These improvements do not only consist of updates to the packages in the GenABEL suite, but we also improved the development process and the way packages are made available to our users. We will demonstrate newly implemented features in the GenABEL suite packages, as well as introduce OmicABEL, a package for rapid mixed-model based genome-wide association analysis of multiple traits (for example, metabolomics, glycomics, etc.). Recently we started using the Jenkins Continuous Integration server to help us release software of higher quality. Jenkins is a framework that automatically runs several tests (e.g. static code analysis, checks for memory leaks) after a new commit to our version control system. This allows us to detect problems in the code at an early stage, before they bug the user. After GenABEL, ProbABEL is the second package that is available as a Debian package, allowing users of upcoming Debian releases to install and upgrade ProbABEL with a single command. This also benefits users of Linux distributions derived from Debian, like Ubuntu. In the coming year more packages are expected to be added the GenABEL suite as well as continued efforts to improve the existing ones. Moreover, we plan to increase both the ease of installation as well as the visibility of the GenABEL suite by adding more packages into both the Debian and Red Hat Linux repositories (as well as derivatives like CentOS and Scientific Linux). On 30-01-14 20:28, L.C. Karssen wrote: > Dear list, > > I'm planning to go to the EMGM (European Mathematical Genetics Meeting) > in Cologne in April. I'd like to present a poster there and wrote the > abstract below. > Please let me know any comments or suggestions as soon possible as the > deadline for abstract submission is tomorrow (Fri 31 Jan). > > Thank you very much, > > Lennart. > > > --------------8<----------------8<------------------8<------------- > Over the last year the GenABEL project has seen a considerable > number of improvements. These improvements do not only consist of > updates to the existing packages of the GenABEL suite, but are also > manifest in the way the development process is being handled and > the way the packages are made available to the users. > > On our poster we will demonstrate the newly implemented features in > the various packages of the GenABEL suite. We also welcome a new > member to the GenABEL family: OmicABEL, a package for rapid > mixed-model based genome-wide association analysis of multiple > traits (think metabolomics, glycomics, etc.). > > Recently we started using the open source Jenkins Continuous > Integration server to help us release software of higher > quality. Jenkins is a framework that automatically runs several > tests (e.g. static code analysis, checks for memory leaks) for each > of our packages. It builds and tests each project after a new commit > in our version control system. This allows us to detect problems in > the code at an early stage, before they bug the user. > > After the GenABEL package, ProbABEL is the second package that is > available as a Debian package. This means that users of upcoming > Debian releases will be able to install ProbABEL with a simple click > of a button or a single command. Moreover, since many other Linux > distributions like Ubuntu and Linux Mint are derived from Debian, > users of these distributions automatically benefit as well. > > In the coming year more packages are expected to be added the > GenABEL suite as well as continued efforts to improve the existing > ones. Moreover, we plan to increase both the ease of installation as > well as the visibility of the GenABEL suite by adding more packages > into both the Debian and Red Hat Enterprise Linux repositories (as > well as derivatives like CentOS and Scientific Linux). > --------------8<----------------8<------------------8<------------- > > > > > > > > > > > > > _______________________________________________ > genabel-devel mailing list > genabel-devel at lists.r-forge.r-project.org > https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/genabel-devel > -- ----------------------------------------------------------------- L.C. Karssen Utrecht The Netherlands lennart at karssen.org http://blog.karssen.org Stuur mij aub geen Word of Powerpoint bestanden! Zie http://www.gnu.org/philosophy/no-word-attachments.nl.html ------------------------------------------------------------------ -------------- next part -------------- A non-text attachment was scrubbed... Name: signature.asc Type: application/pgp-signature Size: 230 bytes Desc: OpenPGP digital signature URL: