| abstract
| - 1:51:44] <@betahelix> I wish, but today's new target is 541 residues! [01:52:31] <@betahelix> [01:52:47] ty [01:54:13] <@betahelix> anyway... we hope you all enjoy the new Symmetry Puzzle, there is a new blogpost about it: [01:54:25] <@betahelix> [01:55:32] Why no new casp puzzles? [01:56:05] Looks like a suitable one was released yesterday [01:56:28] <@betahelix> New CASP 10 targets will be posted once the organizers stop releasing huge proteins: [01:56:45] <@betahelix> 182 residues is still quite big, don't you think spvincent? [01:57:04] anyone trying T0644? [01:57:13] <@betahelix> especially since that would be an alignment tool puzzle (so there wouldn't be any server models to work with) [01:57:15] Big yes but is all relative. Definitely better than 414! [01:57:27] <@betahelix> or today's 541 target! [01:57:41] The current one is 165: not much difference. [01:57:55] <@jflat06IRC> 165 is already pushing it, though. [01:58:00] <@betahelix> but then 210 isn't much different than 182 :-) [01:58:02] Yes, I saw. Who is that aimed at? [01:58:17] The line is vague [01:58:18] <@betahelix> all the servers can handle over 1000 residues :-([01:58:35] Including R@h [01:58:38] ? [01:58:42] <@betahelix> this is one of the things we need to improve with Foldit... [01:59:03] <@betahelix> yep, Rosetta@Home can handle that no problem [01:59:21] Is it a matter of waiting for a couple more iterations of Morre's law? [01:59:33] *Moore [01:59:36] <@betahelix> but don't fret... I am very confident that we'll soon have too many CASP 10 puzzles to deal with ;-) [02:00:10] True but I wish they'd space them out a bit more evenly. [02:00:32] <@betahelix> I think it's a matter of hiring someone to work explicitly on optimizing Foldit for larger proteins [02:00:38] <@jflat06IRC> it would need to be more than a couple - the runtime per residue doesn't scale linearly [02:00:51] <@betahelix> Yeah, sadly the organizers rarely have us in mind :-([02:00:58] <@jflat06IRC> that, and we have people using legacy hardware [02:01:12] <@jflat06IRC> such as a feedback by a person running windows 2000.... [02:01:20] <@betahelix> although they did push some CASP ROLL deadlines just for us after I begged them to! [02:01:40] <@betahelix> I'm still using Windows 98! j/k [02:01:56] thank you beta, rofl [02:02:14] Actually I was wondering about the difference between All groups and Server only. Who, other than FoldIt, would be included in the former group but not the latter? [02:02:23] <@betahelix> well, they had 4 deadlines in 3 days and I was all: WTF? you trying to kill us?! [02:02:50] <@betahelix> Labs using MD or any physics-based method that takes forever... [02:03:09] <@betahelix> although they are even more limited by size than Foldit! (~100 residues is usually their max) [02:04:04] <@betahelix> I do think that if we can have 2-3 CASP puzzles up all summer and 1-2 non-CASP puzzles, that would be ideal... rather than 4 CASP 10 puzzles up every single day... right? [02:04:23] <@betahelix> Hopefully these symmetry puzzles are fun! [02:04:26] Variety is the spice of life. [02:04:39] <@jflat06IRC> we might even have symmetric casp puzzles... you never know [02:05:41] <@betahelix> man, I hope that 541 residue beast isn't a multimer! :-P [02:05:51] <@MikeCassidyToo> i hate sheets - i should be able to change it to something else [02:05:51] interesting. Are you both involved in looking at the R@h results and selecting the best? [02:06:05] <@jflat06IRC> well i'm definitely not - donno about beta [02:06:13] <@jflat06IRC> but he's got enough on his plate, i think. [02:07:58] <@betahelix> The Baker Lab has an entire CASP team working on both the Rosetta@Home server and the "All Group" targets... I tried doing both for CASP 9 and it almost killed me so I'm staying away from them this year ;-) [02:09:16] Sounds rather frantic I must say if you've only got a couple of days between target release and submitting a model. [02:10:43] <@betahelix> no no no, the server is automated (that's the whole point) so all the work for that is done before the CASP season starts... but sometimes you have to tweak stuff as CASP goes along. There used to be a strong correlation between quality of models and time (they would get better as CASP progressed and bugs were fixed) [02:11:55] <@betahelix> The "all group" targets is where lab members spend/waste the most time during CASP... often trying really hard but rarely doing better than what the server had already come up with in less than 3 days! [02:12:19] I was under the impression that you manuallyintervened at some point to select the most promising results. [02:13:20] Should have read your previous post first :). think I understand a little better now. [02:13:43] <@betahelix> I remember spending 2 weeks on a CASP 9 target that drove me mad and made me phsycially ill, only to find out that there was a template for it but our filter had a bug in it and so we didn't have it (and that target was impossible without it) Boy was I pissed when the native came out for that one! [02:15:08] But how, if its not automated, do you work on All Group targets. [02:15:31] Where are the 3 templates for CASP 10. Does anyone know? [02:15:32] What do the CASP team at Baker lab do to make predictions? Are they sitting at computers or doing lab work of some kind? [02:16:31] <@betahelix> to be honest, most labs (that aren't using physics-based methods) just run their automated methods for longer... there are very few groups that add in any Human Intervention. I think that's why they renamed it this year from "Human Targets" to "All Group" [02:16:32] Malcolm if you are on puzzle 552, they are in the alignment tool [02:16:45] <@betahelix> @susume all computer work [02:16:45] @M: Actions -> Show alignment [02:17:09] are they using foldit? [02:17:28] <@jflat06IRC> lab work in the sense of actually experimentally dealing with the structures would be rather odd for a structure prediction competition, lol [02:18:00] <@jflat06IRC> that is to say, cheating [02:18:20] <@betahelix> rarely... the Baker Lab only used Foldit last year for the Refinement Category (which starts in late July) and a couple CASP 9 targets. You have to remember: we are very poor Foldit players ;-) [02:19:49] <@betahelix> ok gang, I gotta go... enjoy the new symmetry puzzle! [02:20:01] thanks beta! [02:20:13] tx beta. [02:20:26] <@betahelix> of course! Thank you for folding! Take care everyone... bye [02:20:39] ty [02:20:41] bye [02:20:54] bye beta [02:21:50] always interesting to hear from the horses mouth [02:22:49] <@MikeCassidyToo> I assume this talk will be posted? [02:24:09] Are these talks normally posted? Don't think so. Not that I've got any objection.
|
![[RDF Data]](/fct/images/sw-rdf-blue.png)