From owner-chemistry@ccl.net Thu Jun 27 03:54:00 2024 From: "Chris Swain swain,,mac.com" To: CCL Subject: CCL: AlphaFold 3 vs AutoDock Vina Message-Id: <-55183-240627035331-25724-Fn2JCyQd2qkIbF2EtIgKiQ#server.ccl.net> X-Original-From: Chris Swain Content-Type: multipart/alternative; boundary="Apple-Mail=_D432163A-4DAB-40E3-A4FB-F748CE0576FF" Date: Thu, 27 Jun 2024 08:53:16 +0100 Mime-Version: 1.0 (Mac OS X Mail 16.0 \(3696.120.41.1.8\)) Sent to CCL by: Chris Swain [swain^mac.com] --Apple-Mail=_D432163A-4DAB-40E3-A4FB-F748CE0576FF Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset=utf-8 Hi, I=E2=80=99m not sure what the non-drug-like compounds are, but if they = are things like co-factors they should be included. Cheers Chris > On 26 Jun 2024, at 21:56, Oleg Trott trott#caa.columbia.edu = wrote: >=20 > I'm not familiar with this dataset personally. But someone alerted me > that it has many non-drug-like compounds that are common in the PDB, > but not very relevant in drug discovery. Perhaps they should be > excluded from the tests? --Apple-Mail=_D432163A-4DAB-40E3-A4FB-F748CE0576FF Content-Transfer-Encoding: quoted-printable Content-Type: text/html; charset=utf-8 Hi,

I=E2=80= =99m not sure what the non-drug-like compounds are, but if they are = things like co-factors they should be included.

Cheers

Chris

On 26 = Jun 2024, at 21:56, Oleg Trott trott#caa.columbia.edu <owner-chemistry===ccl.net> wrote:

I'm not familiar with this = dataset personally. But someone alerted me
that it has many non-drug-like compounds that are common in = the PDB,
but not very = relevant in drug discovery. Perhaps they should be
excluded from the = tests?

= --Apple-Mail=_D432163A-4DAB-40E3-A4FB-F748CE0576FF-- From owner-chemistry@ccl.net Thu Jun 27 09:29:00 2024 From: "Frank Neese neese^kofo.mpg.de" To: CCL Subject: CCL: Announcement of the release of ORCA 6.0 Message-Id: <-55184-240627092643-15790-yl89/vkKpCRn5d/eqto+/A,,server.ccl.net> X-Original-From: "Frank Neese" Date: Thu, 27 Jun 2024 09:26:41 -0400 Sent to CCL by: "Frank Neese" [neese,,kofo.mpg.de] Dear CCL community! The ORCA quantum chemistry program suite has grown into one of the largest and most widely used quantum chemistry packages world-wide and we are most grateful for your ongoing support and enthusiasm! ORCA gives academic users (for free; download from https://lnkd.in/eF6nxi98) and industrial users (via licenses obtained from FAccTs; https://www.faccts.de/) to state of the art methodology that is an exceptionally powerful companion to experimental studies. After almost exactly 3 years of exceptionally hard work, the development team is very excited to announce that ORCA 6.0.0 will be released on Thursday, July 25th, 2024 As for ORCA 5 before, there will be a *two day* online release event on July 25th and 26th, 2024. The release event will start with an overview of the changes in the code, benchmarks and the new features followed by more detailed talks that highlight and explain the new features. Since ORCA has tens of thousands of users world-wide, we will stream the release event twice: one time in the morning (probably 8:00 CET) which will allow our users in the western hemisphere to attend and one time in evening (probably around 18:00 CET) such that our users in the eastern hemisphere can attend. As last time, the talks will be pre-recorded and the respective experts will be online for vivid and lively online discussion during the stream. We will post the details on the online access to the meeting will be made available at the ORCA forum in due course and will also announce it on social media. ORCA 6 is a major turning point for the ORCA project and will pave the way into the future. Hence, please stay tuned and we hope that we see many of you at the release event! Best wishes, Frank Neese on behalf of the ORCA development team. From owner-chemistry@ccl.net Thu Jun 27 12:57:00 2024 From: "tim_mail{}ukr.net" To: CCL Subject: CCL: AlphaFold 3 vs AutoDock Vina Message-Id: <-55185-240627070050-32232-fyJNvJc29KFmWgycSVUSkg[-]server.ccl.net> X-Original-From: tim_mail[#]ukr.net Content-Type: multipart/alternative; boundary="=-QEPZYT2OZ6FGZndtIuaz" Date: Thu, 27 Jun 2024 14:00:37 +0300 MIME-Version: 1.0 Sent to CCL by: tim_mail,+,ukr.net --=-QEPZYT2OZ6FGZndtIuaz Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: binary Content-Length: 6703 I'd like to even strenghten the point about cross-validation/clustering and more cautious testing. Some time ago we've shown that even k-fold split based on random selection may still give over-optimistic accuracy metrics: https://onlinelibrary.wiley.com/doi/abs/10.1002/jcc.26831 And indeed, groupping compounds/proteins by their similaritites (in a sense), and then placing dissimilar compounds/proteins into train and test sets seems to be more conservative strategy. Best regards, Tymofii Sent to CCL by: Oleg Trott [trott^^^caa.columbia.edu] Brian, What I'm suggesting is this: 1. Proteins in the test dataset should be grouped by sequence similarity (If you have compute to burn, you can skip this and basically put each protein in its own cluster) 2. For each cluster, training should be re-done using only proteins that are unrelated to the cluster. This will give us a "generalization accuracy" for AF3 (generalization to unrelated proteins). I'm not familiar with this dataset personally. But someone alerted me that it has many non-drug-like compounds that are common in the PDB, but not very relevant in drug discovery. Perhaps they should be excluded from the tests? Oleg ===== Oleg Trott, PhD https://olegtrott.com On Wed, Jun 26, 2024 at 1:26 PM Bennion, Brian bennion1]|[llnl.gov wrote: > > I am fairly new in this area so my apologies. > Will k-fold cross validation split datasets by similarity as well as identity? The example in your post while very helpful to understand your point is highly simplified. > > Would C and C' for instance be seperated into different sets as well as multiple instances of C? > > Scaffold splitting when done properly will ensure that highly similar (tanimoto scores) compounds are not found in training/validation/test sets. > > Thanks for any help understanding this aspect of the conversation. > > brian > > > ________________________________ > From: owner-chemistry+bennion1==llnl.gov,+,ccl.net on behalf of Oleg Trott trott : caa.columbia.edu > Sent: Wednesday, June 26, 2024 7:52 AM > To: Bennion, Brian > Subject: CCL: AlphaFold 3 vs AutoDock Vina > > > Sent to CCL by: Oleg Trott [trott:+:caa.columbia.edu] > Thanks! > > I hope someone re-runs DeepMind's calculations, with the same > settings, but using k-fold cross-validation (like what I did at > Columbia), where test and training sets are never related. This will > show how well (or poorly, as the case may be) the method generalizes > to unrelated proteins. > > > ===== > Oleg Trott, PhD > https://urldefense.us/v3/__https://olegtrott.com__;!!G2kpM7uM-TzIFchu!3p9TdSkPvlWY7spLCzdrw8ASHbUvjjQkZpSPJgXQot5uraSuaKWuMsila-ZjHKBC7-m92fJQpzmB6YRJ3LAZt4GZGA$ > > > > > > On Tue, Jun 25, 2024 at 11:31 AM Aydin Manzouri aydin.manzouri ~~ > gmail.com wrote: > > > > Truly insightful. Thanks a lot. > > > > On Tue, Jun 25, 2024 at 1:59 AM Oleg Trott trott[-]caa.columbia.edu wrote: > >> > >> > >> Sent to CCL by: "Oleg Trott" [trott-$-caa.columbia.edu] > >> Hello, everyone! > >> > >> DeepMind's new AlphaFold 3 attempts to predict protein-ligand binding, and > >> their publication compares it to AutoDock Vina (which I built). But their > >> methodology seems strange. > >> > >> I wrote up my comments in a blog post. If you have an interest in AI and/or > >> docking, I hope you'll find it insightful. > >> > >> https://urldefense.us/v3/__https://olegtrott.substack.com/p/are-alphafolds-new-results-a-miracle__;!!G2kpM7uM-TzIFchu!3p9TdSkPvlWY7spLCzdrw8ASHbUvjjQkZpSPJgXQot5uraSuaKWuMsila-ZjHKBC7-m92fJQpzmB6YRJ3LAhjWUW2Q$ >> E-mail to subscribers: CHEMISTRY*_*ccl.net or use:>> > >> E-mail to administrators: CHEMISTRY-REQUEST*_*ccl.net or use> https://urldefense.us/v3/__http://www.ccl.net/cgi-bin/ccl/send_ccl_message__;!!G2kpM7uM-TzIFchu!3p9TdSkPvlWY7spLCzdrw8ASHbUvjjQkZpSPJgXQot5uraSuaKWuMsila-ZjHKBC7-m92fJQpzmB6YRJ3LDKQAR6UA$> https://urldefense.us/v3/__http://www.ccl.net/cgi-bin/ccl/send_ccl_message__;!!G2kpM7uM-TzIFchu!3p9TdSkPvlWY7spLCzdrw8ASHbUvjjQkZpSPJgXQot5uraSuaKWuMsila-ZjHKBC7-m92fJQpzmB6YRJ3LDKQAR6UA$> https://urldefense.us/v3/__http://www.ccl.net/chemistry/sub_unsub.shtml__;!!G2kpM7uM-TzIFchu!3p9TdSkPvlWY7spLCzdrw8ASHbUvjjQkZpSPJgXQot5uraSuaKWuMsila-ZjHKBC7-m92fJQpzmB6YRJ3LCPWW2CVw$ > > Before posting, check wait time at: https://urldefense.us/v3/__http://www.ccl.net__;!!G2kpM7uM-TzIFchu!3p9TdSkPvlWY7spLCzdrw8ASHbUvjjQkZpSPJgXQot5uraSuaKWuMsila-ZjHKBC7-m92fJQpzmB6YRJ3LDlpU830Q$ > > Job: https://urldefense.us/v3/__http://www.ccl.net/jobs__;!!G2kpM7uM-TzIFchu!3p9TdSkPvlWY7spLCzdrw8ASHbUvjjQkZpSPJgXQot5uraSuaKWuMsila-ZjHKBC7-m92fJQpzmB6YRJ3LDCTKWjAQ$ > Conferences: https://urldefense.us/v3/__http://server.ccl.net/chemistry/announcements/conferences/__;!!G2kpM7uM-TzIFchu!3p9TdSkPvlWY7spLCzdrw8ASHbUvjjQkZpSPJgXQot5uraSuaKWuMsila-ZjHKBC7-m92fJQpzmB6YRJ3LBXlUqlyg$ > > Search Messages: https://urldefense.us/v3/__http://www.ccl.net/chemistry/searchccl/index.shtml__;!!G2kpM7uM-TzIFchu!3p9TdSkPvlWY7spLCzdrw8ASHbUvjjQkZpSPJgXQot5uraSuaKWuMsila-ZjHKBC7-m92fJQpzmB6YRJ3LBf0PQAiw$> https://urldefense.us/v3/__http://www.ccl.net/spammers.txt__;!!G2kpM7uM-TzIFchu!3p9TdSkPvlWY7spLCzdrw8ASHbUvjjQkZpSPJgXQot5uraSuaKWuMsila-ZjHKBC7-m92fJQpzmB6YRJ3LCPNHBrUw$ > > RTFI: https://urldefense.us/v3/__http://www.ccl.net/chemistry/aboutccl/instructions/__;!!G2kpM7uM-TzIFchu!3p9TdSkPvlWY7spLCzdrw8ASHbUvjjQkZpSPJgXQot5uraSuaKWuMsila-ZjHKBC7-m92fJQpzmB6YRJ3LDZHrMutQ$http://www.ccl.net/cgi-bin/ccl/send_ccl_messagehttp://www.ccl.net/chemistry/sub_unsub.shtmlhttp://www.ccl.net/spammers.txt--=-QEPZYT2OZ6FGZndtIuaz Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: base64 PGh0bWw+PGJvZHk+PHNwYW4gc3R5bGU9ImRpc3BsYXk6YmxvY2s7IiBjbGFzcz0ieGZtXzcyNTM4 ODczIj48ZGl2PjxzcGFuIHN0eWxlPSJmb250LXNpemU6MTJwdDtsaW5lLWhlaWdodDoxNHB0O2Zv bnQtZmFtaWx5OkFyaWFsOyIgY2xhc3M9InhmbWMxIj5JJ2QgbGlrZSB0byBldmVuIHN0cmVuZ2h0 ZW4gdGhlIHBvaW50IGFib3V0IGNyb3NzLXZhbGlkYXRpb24vY2x1c3RlcmluZyBhbmQgbW9yZSBj YXV0aW91cyB0ZXN0aW5nLjwvc3Bhbj48YnIvPjwvZGl2Pg0KPGRpdj48c3BhbiBzdHlsZT0iZm9u dC1zaXplOjEycHQ7bGluZS1oZWlnaHQ6MTRwdDtmb250LWZhbWlseTpBcmlhbDsiIGNsYXNzPSJ4 Zm1jMSI+U29tZSB0aW1lIGFnbyB3ZSd2ZSBzaG93biB0aGF0IGV2ZW4gay1mb2xkIHNwbGl0IGJh c2VkIG9uIHJhbmRvbSBzZWxlY3Rpb24gbWF5IHN0aWxsIGdpdmUgb3Zlci1vcHRpbWlzdGljIGFj Y3VyYWN5IG1ldHJpY3M6PGJyIGRhdGEtbWNlLWJvZ3VzPSIxIi8+PC9zcGFuPjwvZGl2Pg0KPGRp dj48c3BhbiBzdHlsZT0iZm9udC1zaXplOjEycHQ7bGluZS1oZWlnaHQ6MTRwdDtmb250LWZhbWls eTpBcmlhbDsiIGNsYXNzPSJ4Zm1jMSI+PHNwYW4gc3R5bGU9ImZvbnQtZmFtaWx5OkFyaWFsO2Zv bnQtc2l6ZToxMnB0O2xpbmUtaGVpZ2h0OjE0cHQ7Ij5odHRwczovL29ubGluZWxpYnJhcnkud2ls ZXkuY29tL2RvaS9hYnMvMTAuMTAwMi9qY2MuMjY4MzE8L3NwYW4+PC9zcGFuPjwvZGl2Pg0KPGRp dj48c3BhbiBzdHlsZT0iZm9udC1zaXplOjEycHQ7bGluZS1oZWlnaHQ6MTRwdDtmb250LWZhbWls eTpBcmlhbDsiIGNsYXNzPSJ4Zm1jMSI+QW5kIGluZGVlZCwgZ3JvdXBwaW5nIGNvbXBvdW5kcy9w cm90ZWlucyBieSB0aGVpciBzaW1pbGFyaXRpdGVzIChpbiBhIHNlbnNlKSwgYW5kIHRoZW4gcGxh Y2luZyA8L3NwYW4+PC9kaXY+DQo8ZGl2PjxzcGFuIHN0eWxlPSJmb250LXNpemU6MTJwdDtsaW5l LWhlaWdodDoxNHB0O2ZvbnQtZmFtaWx5OkFyaWFsOyIgY2xhc3M9InhmbWMxIj5kaXNzaW1pbGFy IDwvc3Bhbj48c3BhbiBzdHlsZT0iZm9udC1zaXplOjEycHQ7bGluZS1oZWlnaHQ6MTRwdDtmb250 LWZhbWlseTpBcmlhbDsiPmNvbXBvdW5kcy9wcm90ZWlucyBpbnRvIHRyYWluIGFuZCB0ZXN0IHNl dHMgc2VlbXMgdG8gYmUgbW9yZSBjb25zZXJ2YXRpdmUgc3RyYXRlZ3kuPC9zcGFuPjxici8+PC9k aXY+DQo8ZGl2PjxzcGFuIHN0eWxlPSJmb250LXNpemU6MTJwdDtsaW5lLWhlaWdodDoxNHB0O2Zv bnQtZmFtaWx5OkFyaWFsOyI+PGJyIGRhdGEtbWNlLWJvZ3VzPSIxIi8+PC9zcGFuPjwvZGl2Pg0K PGRpdj48c3BhbiBzdHlsZT0iZm9udC1zaXplOjEycHQ7bGluZS1oZWlnaHQ6MTRwdDtmb250LWZh bWlseTpBcmlhbDsiPjxiciBkYXRhLW1jZS1ib2d1cz0iMSIvPjwvc3Bhbj48L2Rpdj4NCjxkaXY+ PHNwYW4gc3R5bGU9ImZvbnQtc2l6ZToxMnB0O2xpbmUtaGVpZ2h0OjE0cHQ7Zm9udC1mYW1pbHk6 QXJpYWw7Ij48YnIgZGF0YS1tY2UtYm9ndXM9IjEiLz48L3NwYW4+PC9kaXY+DQo8ZGl2PjxzcGFu IHN0eWxlPSJmb250LXNpemU6MTJwdDtsaW5lLWhlaWdodDoxNHB0O2ZvbnQtZmFtaWx5OkFyaWFs OyI+QmVzdCByZWdhcmRzLDxiciBkYXRhLW1jZS1ib2d1cz0iMSIvPjwvc3Bhbj48L2Rpdj4NCjxk aXY+PHNwYW4gc3R5bGU9ImZvbnQtc2l6ZToxMnB0O2xpbmUtaGVpZ2h0OjE0cHQ7Zm9udC1mYW1p bHk6QXJpYWw7Ij5UeW1vZmlpPGJyIGRhdGEtbWNlLWJvZ3VzPSIxIi8+PC9zcGFuPjwvZGl2Pg0K PGRpdj48YnIvPjwvZGl2Pg0KPGRpdj48aT48c3BhbiBzdHlsZT0iZm9udC1zaXplOjEwcHQ7bGlu ZS1oZWlnaHQ6MTJwdDsiPjxzcGFuIHN0eWxlPSJmb250LWZhbWlseTpBcmlhbDsiPjxici8+PC9z cGFuPjxzcGFuIHN0eWxlPSJmb250LWZhbWlseTpBcmlhbDsiPjwvc3Bhbj48L3NwYW4+PC9pPjwv ZGl2Pg0KPGRpdj48YnIvPjwvZGl2Pg0KPGJsb2NrcXVvdGUgc3R5bGU9ImJvcmRlci1sZWZ0OjFw eCBzb2xpZCAjY2NjY2NjO21hcmdpbjowcHggMHB4IDBweCAwLjhleDtwYWRkaW5nLWxlZnQ6MWV4 OyI+DQo8ZGl2IHN0eWxlPSJkaXNwbGF5OmJsb2NrOyI+DQo8cHJlIHN0eWxlPSJtYXJnaW46NXB4 IDA7Ij5TZW50IHRvIENDTCBieTogT2xlZyBUcm90dCBbdHJvdHReXl5jYWEuY29sdW1iaWEuZWR1 XQ0KQnJpYW4sDQoNCldoYXQgSSdtIHN1Z2dlc3RpbmcgaXMgdGhpczoNCg0KMS4gUHJvdGVpbnMg aW4gdGhlIHRlc3QgZGF0YXNldCBzaG91bGQgYmUgZ3JvdXBlZCBieSBzZXF1ZW5jZQ0Kc2ltaWxh cml0eSAoSWYgeW91IGhhdmUgY29tcHV0ZSB0byBidXJuLCB5b3UgY2FuIHNraXAgdGhpcyBhbmQN CmJhc2ljYWxseSBwdXQgZWFjaCBwcm90ZWluIGluIGl0cyBvd24gY2x1c3RlcikNCg0KMi4gRm9y IGVhY2ggY2x1c3RlciwgdHJhaW5pbmcgc2hvdWxkIGJlIHJlLWRvbmUgdXNpbmcgb25seSBwcm90 ZWlucw0KdGhhdCBhcmUgdW5yZWxhdGVkIHRvIHRoZSBjbHVzdGVyLg0KDQpUaGlzIHdpbGwgZ2l2 ZSB1cyBhICJnZW5lcmFsaXphdGlvbiBhY2N1cmFjeSIgZm9yIEFGMyAoZ2VuZXJhbGl6YXRpb24N CnRvIHVucmVsYXRlZCBwcm90ZWlucykuDQoNCkknbSBub3QgZmFtaWxpYXIgd2l0aCB0aGlzIGRh dGFzZXQgcGVyc29uYWxseS4gQnV0IHNvbWVvbmUgYWxlcnRlZCBtZQ0KdGhhdCBpdCBoYXMgbWFu eSBub24tZHJ1Zy1saWtlIGNvbXBvdW5kcyB0aGF0IGFyZSBjb21tb24gaW4gdGhlIFBEQiwNCmJ1 dCBub3QgdmVyeSByZWxldmFudCBpbiBkcnVnIGRpc2NvdmVyeS4gUGVyaGFwcyB0aGV5IHNob3Vs ZCBiZQ0KZXhjbHVkZWQgZnJvbSB0aGUgdGVzdHM/DQoNCk9sZWcNCj09PT09DQpPbGVnIFRyb3R0 LCBQaEQNCjxhIGhyZWY9Imh0dHBzOi8vb2xlZ3Ryb3R0LmNvbSIgdGFyZ2V0PSJfYmxhbmsiIHJl bD0ibm9yZWZlcnJlciBub29wZW5lciI+aHR0cHM6Ly9vbGVndHJvdHQuY29tPC9hPg0KDQoNCk9u IFdlZCwgSnVuIDI2LCAyMDI0IGF0IDE6MjbigK9QTSBCZW5uaW9uLCBCcmlhbiBiZW5uaW9uMV18 W2xsbmwuZ292DQombHQ7b3duZXItY2hlbWlzdHJ5LCssY2NsLm5ldCZndDsgd3JvdGU6DQomZ3Q7 DQomZ3Q7IEkgYW0gZmFpcmx5IG5ldyBpbiB0aGlzIGFyZWEgc28gbXkgYXBvbG9naWVzLg0KJmd0 OyBXaWxsIGstZm9sZCBjcm9zcyB2YWxpZGF0aW9uIHNwbGl0IGRhdGFzZXRzIGJ5IHNpbWlsYXJp dHkgYXMgd2VsbCBhcyBpZGVudGl0eT8gIFRoZSBleGFtcGxlIGluIHlvdXIgcG9zdCB3aGlsZSB2 ZXJ5IGhlbHBmdWwgdG8gdW5kZXJzdGFuZCB5b3VyIHBvaW50IGlzIGhpZ2hseSBzaW1wbGlmaWVk Lg0KJmd0Ow0KJmd0OyBXb3VsZCBDIGFuZCBDJyBmb3IgaW5zdGFuY2UgYmUgc2VwZXJhdGVkIGlu dG8gZGlmZmVyZW50IHNldHMgYXMgd2VsbCBhcyBtdWx0aXBsZSBpbnN0YW5jZXMgb2YgQz8NCiZn dDsNCiZndDsgU2NhZmZvbGQgc3BsaXR0aW5nIHdoZW4gZG9uZSBwcm9wZXJseSB3aWxsIGVuc3Vy ZSB0aGF0IGhpZ2hseSBzaW1pbGFyICh0YW5pbW90byBzY29yZXMpIGNvbXBvdW5kcyBhcmUgbm90 IGZvdW5kIGluIHRyYWluaW5nL3ZhbGlkYXRpb24vdGVzdCBzZXRzLg0KJmd0Ow0KJmd0OyBUaGFu a3MgZm9yIGFueSBoZWxwIHVuZGVyc3RhbmRpbmcgdGhpcyBhc3BlY3Qgb2YgdGhlIGNvbnZlcnNh dGlvbi4NCiZndDsNCiZndDsgYnJpYW4NCiZndDsNCiZndDsNCiZndDsgX19fX19fX19fX19fX19f X19fX19fX19fX19fX19fX18NCiZndDsgRnJvbTogb3duZXItY2hlbWlzdHJ5K2Jlbm5pb24xPT1s bG5sLmdvdiwrLGNjbC5uZXQgJmx0O293bmVyLWNoZW1pc3RyeStiZW5uaW9uMT09bGxubC5nb3Ys KyxjY2wubmV0Jmd0OyBvbiBiZWhhbGYgb2YgT2xlZyBUcm90dCB0cm90dCA6IGNhYS5jb2x1bWJp YS5lZHUgJmx0O293bmVyLWNoZW1pc3RyeSwrLGNjbC5uZXQmZ3Q7DQomZ3Q7IFNlbnQ6IFdlZG5l c2RheSwgSnVuZSAyNiwgMjAyNCA3OjUyIEFNDQomZ3Q7IFRvOiBCZW5uaW9uLCBCcmlhbiAmbHQ7 YmVubmlvbjEsKyxsbG5sLmdvdiZndDsNCiZndDsgU3ViamVjdDogQ0NMOiBBbHBoYUZvbGQgMyB2 cyBBdXRvRG9jayBWaW5hDQomZ3Q7DQomZ3Q7DQomZ3Q7IFNlbnQgdG8gQ0NMIGJ5OiBPbGVnIFRy b3R0IFt0cm90dDorOmNhYS5jb2x1bWJpYS5lZHVdDQomZ3Q7IFRoYW5rcyENCiZndDsNCiZndDsg SSBob3BlIHNvbWVvbmUgcmUtcnVucyBEZWVwTWluZCdzIGNhbGN1bGF0aW9ucywgd2l0aCB0aGUg c2FtZQ0KJmd0OyBzZXR0aW5ncywgYnV0IHVzaW5nIGstZm9sZCBjcm9zcy12YWxpZGF0aW9uIChs aWtlIHdoYXQgSSBkaWQgYXQNCiZndDsgQ29sdW1iaWEpLCB3aGVyZSB0ZXN0IGFuZCB0cmFpbmlu ZyBzZXRzIGFyZSBuZXZlciByZWxhdGVkLiBUaGlzIHdpbGwNCiZndDsgc2hvdyBob3cgd2VsbCAo b3IgcG9vcmx5LCBhcyB0aGUgY2FzZSBtYXkgYmUpIHRoZSBtZXRob2QgZ2VuZXJhbGl6ZXMNCiZn dDsgdG8gdW5yZWxhdGVkIHByb3RlaW5zLg0KJmd0Ow0KJmd0Ow0KJmd0OyA9PT09PQ0KJmd0OyBP bGVnIFRyb3R0LCBQaEQNCiZndDsgPGEgaHJlZj0iaHR0cHM6Ly91cmxkZWZlbnNlLnVzL3YzL19f aHR0cHM6Ly9vbGVndHJvdHQuY29tX187ISFHMmtwTTd1TS1UeklGY2h1ITNwOVRkU2tQdmxXWTdz cExDemRydzhBU0hiVXZqalFrWnBTUEpnWFFvdDV1cmFTdWFLV3VNc2lsYS1aakhLQkM3LW05MmZK UXB6bUI2WVJKM0xBWnQ0R1pHQSQiIHRhcmdldD0iX2JsYW5rIiByZWw9Im5vcmVmZXJyZXIgbm9v cGVuZXIiPmh0dHBzOi8vdXJsZGVmZW5zZS51cy92My9fX2h0dHBzOi8vb2xlZ3Ryb3R0LmNvbV9f OyEhRzJrcE03dU0tVHpJRmNodSEzcDlUZFNrUHZsV1k3c3BMQ3pkcnc4QVNIYlV2ampRa1pwU1BK Z1hRb3Q1dXJhU3VhS1d1TXNpbGEtWmpIS0JDNy1tOTJmSlFwem1CNllSSjNMQVp0NEdaR0EkPC9h Pg0KJmd0Ow0KJmd0Ow0KJmd0Ow0KJmd0Ow0KJmd0Ow0KJmd0OyBPbiBUdWUsIEp1biAyNSwgMjAy NCBhdCAxMTozMeKAr0FNIEF5ZGluIE1hbnpvdXJpIGF5ZGluLm1hbnpvdXJpIH5+DQomZ3Q7IGdt YWlsLmNvbSAmbHQ7b3duZXItY2hlbWlzdHJ5Xy1fY2NsLm5ldCZndDsgd3JvdGU6DQomZ3Q7ICZn dDsNCiZndDsgJmd0OyBUcnVseSBpbnNpZ2h0ZnVsLiBUaGFua3MgYSBsb3QuDQomZ3Q7ICZndDsN CiZndDsgJmd0OyBPbiBUdWUsIEp1biAyNSwgMjAyNCBhdCAxOjU54oCvQU0gT2xlZyBUcm90dCB0 cm90dFstXWNhYS5jb2x1bWJpYS5lZHUgJmx0O293bmVyLWNoZW1pc3RyeSpfKmNjbC5uZXQmZ3Q7 IHdyb3RlOg0KJmd0OyAmZ3Q7Jmd0Ow0KJmd0OyAmZ3Q7Jmd0Ow0KJmd0OyAmZ3Q7Jmd0OyBTZW50 IHRvIENDTCBieTogIk9sZWcgIFRyb3R0IiBbdHJvdHQtJC1jYWEuY29sdW1iaWEuZWR1XQ0KJmd0 OyAmZ3Q7Jmd0OyBIZWxsbywgZXZlcnlvbmUhDQomZ3Q7ICZndDsmZ3Q7DQomZ3Q7ICZndDsmZ3Q7 IERlZXBNaW5kJ3MgbmV3IEFscGhhRm9sZCAzIGF0dGVtcHRzIHRvIHByZWRpY3QgcHJvdGVpbi1s aWdhbmQgYmluZGluZywgYW5kDQomZ3Q7ICZndDsmZ3Q7IHRoZWlyIHB1YmxpY2F0aW9uIGNvbXBh cmVzIGl0IHRvIEF1dG9Eb2NrIFZpbmEgKHdoaWNoIEkgYnVpbHQpLiBCdXQgdGhlaXINCiZndDsg Jmd0OyZndDsgbWV0aG9kb2xvZ3kgc2VlbXMgc3RyYW5nZS4NCiZndDsgJmd0OyZndDsNCiZndDsg Jmd0OyZndDsgSSB3cm90ZSB1cCBteSBjb21tZW50cyBpbiBhIGJsb2cgcG9zdC4gSWYgeW91IGhh dmUgYW4gaW50ZXJlc3QgaW4gQUkgYW5kL29yDQomZ3Q7ICZndDsmZ3Q7IGRvY2tpbmcsIEkgaG9w ZSB5b3UnbGwgZmluZCBpdCBpbnNpZ2h0ZnVsLg0KJmd0OyAmZ3Q7Jmd0Ow0KJmd0OyAmZ3Q7Jmd0 OyA8YSBocmVmPSJodHRwczovL3VybGRlZmVuc2UudXMvdjMvX19odHRwczovL29sZWd0cm90dC5z dWJzdGFjay5jb20vcC9hcmUtYWxwaGFmb2xkcy1uZXctcmVzdWx0cy1hLW1pcmFjbGVfXzshIUcy a3BNN3VNLVR6SUZjaHUhM3A5VGRTa1B2bFdZN3NwTEN6ZHJ3OEFTSGJVdmpqUWtacFNQSmdYUW90 NXVyYVN1YUtXdU1zaWxhLVpqSEtCQzctbTkyZkpRcHptQjZZUkozTEFoaldVVzJRJCIgdGFyZ2V0 PSJfYmxhbmsiIHJlbD0ibm9yZWZlcnJlciBub29wZW5lciI+aHR0cHM6Ly91cmxkZWZlbnNlLnVz L3YzL19faHR0cHM6Ly9vbGVndHJvdHQuc3Vic3RhY2suY29tL3AvYXJlLWFscGhhZm9sZHMtbmV3 LXJlc3VsdHMtYS1taXJhY2xlX187ISFHMmtwTTd1TS1UeklGY2h1ITNwOVRkU2tQdmxXWTdzcExD emRydzhBU0hiVXZqalFrWnBTUEpnWFFvdDV1cmFTdWFLV3VNc2lsYS1aakhLQkM3LW05MmZKUXB6 bUI2WVJKM0xBaGpXVVcyUSQ8L2E+ICZndDsmZ3Q7IEUtbWFpbCB0byBzdWJzY3JpYmVyczogQ0hF TUlTVFJZKl8qY2NsLm5ldCBvciB1c2U6Jmd0OyZndDsNCiZndDsgJmd0OyZndDsgRS1tYWlsIHRv IGFkbWluaXN0cmF0b3JzOiBDSEVNSVNUUlktUkVRVUVTVCpfKmNjbC5uZXQgb3IgdXNlJmd0OyAg ICAgICA8YSBocmVmPSJodHRwczovL3VybGRlZmVuc2UudXMvdjMvX19odHRwOi8vd3d3LmNjbC5u ZXQvY2dpLWJpbi9jY2wvc2VuZF9jY2xfbWVzc2FnZV9fOyEhRzJrcE03dU0tVHpJRmNodSEzcDlU ZFNrUHZsV1k3c3BMQ3pkcnc4QVNIYlV2ampRa1pwU1BKZ1hRb3Q1dXJhU3VhS1d1TXNpbGEtWmpI S0JDNy1tOTJmSlFwem1CNllSSjNMREtRQVI2VUEkIiB0YXJnZXQ9Il9ibGFuayIgcmVsPSJub3Jl ZmVycmVyIG5vb3BlbmVyIj5odHRwczovL3VybGRlZmVuc2UudXMvdjMvX19odHRwOi8vd3d3LmNj bC5uZXQvY2dpLWJpbi9jY2wvc2VuZF9jY2xfbWVzc2FnZV9fOyEhRzJrcE03dU0tVHpJRmNodSEz cDlUZFNrUHZsV1k3c3BMQ3pkcnc4QVNIYlV2ampRa1pwU1BKZ1hRb3Q1dXJhU3VhS1d1TXNpbGEt WmpIS0JDNy1tOTJmSlFwem1CNllSSjNMREtRQVI2VUEkPC9hPiZndDsgICAgICAgPGEgaHJlZj0i aHR0cHM6Ly91cmxkZWZlbnNlLnVzL3YzL19faHR0cDovL3d3dy5jY2wubmV0L2NnaS1iaW4vY2Ns L3NlbmRfY2NsX21lc3NhZ2VfXzshIUcya3BNN3VNLVR6SUZjaHUhM3A5VGRTa1B2bFdZN3NwTEN6 ZHJ3OEFTSGJVdmpqUWtacFNQSmdYUW90NXVyYVN1YUtXdU1zaWxhLVpqSEtCQzctbTkyZkpRcHpt QjZZUkozTERLUUFSNlVBJCIgdGFyZ2V0PSJfYmxhbmsiIHJlbD0ibm9yZWZlcnJlciBub29wZW5l ciI+aHR0cHM6Ly91cmxkZWZlbnNlLnVzL3YzL19faHR0cDovL3d3dy5jY2wubmV0L2NnaS1iaW4v Y2NsL3NlbmRfY2NsX21lc3NhZ2VfXzshIUcya3BNN3VNLVR6SUZjaHUhM3A5VGRTa1B2bFdZN3Nw TEN6ZHJ3OEFTSGJVdmpqUWtacFNQSmdYUW90NXVyYVN1YUtXdU1zaWxhLVpqSEtCQzctbTkyZkpR cHptQjZZUkozTERLUUFSNlVBJDwvYT4mZ3Q7ICAgICAgIDxhIGhyZWY9Imh0dHBzOi8vdXJsZGVm ZW5zZS51cy92My9fX2h0dHA6Ly93d3cuY2NsLm5ldC9jaGVtaXN0cnkvc3ViX3Vuc3ViLnNodG1s X187ISFHMmtwTTd1TS1UeklGY2h1ITNwOVRkU2tQdmxXWTdzcExDemRydzhBU0hiVXZqalFrWnBT UEpnWFFvdDV1cmFTdWFLV3VNc2lsYS1aakhLQkM3LW05MmZKUXB6bUI2WVJKM0xDUFdXMkNWdyQi IHRhcmdldD0iX2JsYW5rIiByZWw9Im5vcmVmZXJyZXIgbm9vcGVuZXIiPmh0dHBzOi8vdXJsZGVm ZW5zZS51cy92My9fX2h0dHA6Ly93d3cuY2NsLm5ldC9jaGVtaXN0cnkvc3ViX3Vuc3ViLnNodG1s X187ISFHMmtwTTd1TS1UeklGY2h1ITNwOVRkU2tQdmxXWTdzcExDemRydzhBU0hiVXZqalFrWnBT UEpnWFFvdDV1cmFTdWFLV3VNc2lsYS1aakhLQkM3LW05MmZKUXB6bUI2WVJKM0xDUFdXMkNWdyQ8 L2E+DQomZ3Q7DQomZ3Q7IEJlZm9yZSBwb3N0aW5nLCBjaGVjayB3YWl0IHRpbWUgYXQ6IDxhIGhy ZWY9Imh0dHBzOi8vdXJsZGVmZW5zZS51cy92My9fX2h0dHA6Ly93d3cuY2NsLm5ldF9fOyEhRzJr cE03dU0tVHpJRmNodSEzcDlUZFNrUHZsV1k3c3BMQ3pkcnc4QVNIYlV2ampRa1pwU1BKZ1hRb3Q1 dXJhU3VhS1d1TXNpbGEtWmpIS0JDNy1tOTJmSlFwem1CNllSSjNMRGxwVTgzMFEkIiB0YXJnZXQ9 Il9ibGFuayIgcmVsPSJub3JlZmVycmVyIG5vb3BlbmVyIj5odHRwczovL3VybGRlZmVuc2UudXMv djMvX19odHRwOi8vd3d3LmNjbC5uZXRfXzshIUcya3BNN3VNLVR6SUZjaHUhM3A5VGRTa1B2bFdZ N3NwTEN6ZHJ3OEFTSGJVdmpqUWtacFNQSmdYUW90NXVyYVN1YUtXdU1zaWxhLVpqSEtCQzctbTky ZkpRcHptQjZZUkozTERscFU4MzBRJDwvYT4NCiZndDsNCiZndDsgSm9iOiA8YSBocmVmPSJodHRw czovL3VybGRlZmVuc2UudXMvdjMvX19odHRwOi8vd3d3LmNjbC5uZXQvam9ic19fOyEhRzJrcE03 dU0tVHpJRmNodSEzcDlUZFNrUHZsV1k3c3BMQ3pkcnc4QVNIYlV2ampRa1pwU1BKZ1hRb3Q1dXJh U3VhS1d1TXNpbGEtWmpIS0JDNy1tOTJmSlFwem1CNllSSjNMRENUS1dqQVEkIiB0YXJnZXQ9Il9i bGFuayIgcmVsPSJub3JlZmVycmVyIG5vb3BlbmVyIj5odHRwczovL3VybGRlZmVuc2UudXMvdjMv X19odHRwOi8vd3d3LmNjbC5uZXQvam9ic19fOyEhRzJrcE03dU0tVHpJRmNodSEzcDlUZFNrUHZs V1k3c3BMQ3pkcnc4QVNIYlV2ampRa1pwU1BKZ1hRb3Q1dXJhU3VhS1d1TXNpbGEtWmpIS0JDNy1t OTJmSlFwem1CNllSSjNMRENUS1dqQVEkPC9hPg0KJmd0OyBDb25mZXJlbmNlczogPGEgaHJlZj0i aHR0cHM6Ly91cmxkZWZlbnNlLnVzL3YzL19faHR0cDovL3NlcnZlci5jY2wubmV0L2NoZW1pc3Ry eS9hbm5vdW5jZW1lbnRzL2NvbmZlcmVuY2VzL19fOyEhRzJrcE03dU0tVHpJRmNodSEzcDlUZFNr UHZsV1k3c3BMQ3pkcnc4QVNIYlV2ampRa1pwU1BKZ1hRb3Q1dXJhU3VhS1d1TXNpbGEtWmpIS0JD Ny1tOTJmSlFwem1CNllSSjNMQlhsVXFseWckIiB0YXJnZXQ9Il9ibGFuayIgcmVsPSJub3JlZmVy cmVyIG5vb3BlbmVyIj5odHRwczovL3VybGRlZmVuc2UudXMvdjMvX19odHRwOi8vc2VydmVyLmNj bC5uZXQvY2hlbWlzdHJ5L2Fubm91bmNlbWVudHMvY29uZmVyZW5jZXMvX187ISFHMmtwTTd1TS1U eklGY2h1ITNwOVRkU2tQdmxXWTdzcExDemRydzhBU0hiVXZqalFrWnBTUEpnWFFvdDV1cmFTdWFL V3VNc2lsYS1aakhLQkM3LW05MmZKUXB6bUI2WVJKM0xCWGxVcWx5ZyQ8L2E+DQomZ3Q7DQomZ3Q7 IFNlYXJjaCBNZXNzYWdlczogPGEgaHJlZj0iaHR0cHM6Ly91cmxkZWZlbnNlLnVzL3YzL19faHR0 cDovL3d3dy5jY2wubmV0L2NoZW1pc3RyeS9zZWFyY2hjY2wvaW5kZXguc2h0bWxfXzshIUcya3BN N3VNLVR6SUZjaHUhM3A5VGRTa1B2bFdZN3NwTEN6ZHJ3OEFTSGJVdmpqUWtacFNQSmdYUW90NXVy YVN1YUtXdU1zaWxhLVpqSEtCQzctbTkyZkpRcHptQjZZUkozTEJmMFBRQWl3JCIgdGFyZ2V0PSJf YmxhbmsiIHJlbD0ibm9yZWZlcnJlciBub29wZW5lciI+aHR0cHM6Ly91cmxkZWZlbnNlLnVzL3Yz L19faHR0cDovL3d3dy5jY2wubmV0L2NoZW1pc3RyeS9zZWFyY2hjY2wvaW5kZXguc2h0bWxfXzsh IUcya3BNN3VNLVR6SUZjaHUhM3A5VGRTa1B2bFdZN3NwTEN6ZHJ3OEFTSGJVdmpqUWtacFNQSmdY UW90NXVyYVN1YUtXdU1zaWxhLVpqSEtCQzctbTkyZkpRcHptQjZZUkozTEJmMFBRQWl3JDwvYT4m Z3Q7ICAgICAgIDxhIGhyZWY9Imh0dHBzOi8vdXJsZGVmZW5zZS51cy92My9fX2h0dHA6Ly93d3cu Y2NsLm5ldC9zcGFtbWVycy50eHRfXzshIUcya3BNN3VNLVR6SUZjaHUhM3A5VGRTa1B2bFdZN3Nw TEN6ZHJ3OEFTSGJVdmpqUWtacFNQSmdYUW90NXVyYVN1YUtXdU1zaWxhLVpqSEtCQzctbTkyZkpR cHptQjZZUkozTENQTkhCclV3JCIgdGFyZ2V0PSJfYmxhbmsiIHJlbD0ibm9yZWZlcnJlciBub29w ZW5lciI+aHR0cHM6Ly91cmxkZWZlbnNlLnVzL3YzL19faHR0cDovL3d3dy5jY2wubmV0L3NwYW1t ZXJzLnR4dF9fOyEhRzJrcE03dU0tVHpJRmNodSEzcDlUZFNrUHZsV1k3c3BMQ3pkcnc4QVNIYlV2 ampRa1pwU1BKZ1hRb3Q1dXJhU3VhS1d1TXNpbGEtWmpIS0JDNy1tOTJmSlFwem1CNllSSjNMQ1BO SEJyVXckPC9hPg0KJmd0Ow0KJmd0OyBSVEZJOiA8YSBocmVmPSJodHRwczovL3VybGRlZmVuc2Uu dXMvdjMvX19odHRwOi8vd3d3LmNjbC5uZXQvY2hlbWlzdHJ5L2Fib3V0Y2NsL2luc3RydWN0aW9u cy9fXzshIUcya3BNN3VNLVR6SUZjaHUhM3A5VGRTa1B2bFdZN3NwTEN6ZHJ3OEFTSGJVdmpqUWta cFNQSmdYUW90NXVyYVN1YUtXdU1zaWxhLVpqSEtCQzctbTkyZkpRcHptQjZZUkozTERaSHJNdXRR JCIgdGFyZ2V0PSJfYmxhbmsiIHJlbD0ibm9yZWZlcnJlciBub29wZW5lciI+aHR0cHM6Ly91cmxk ZWZlbnNlLnVzL3YzL19faHR0cDovL3d3dy5jY2wubmV0L2NoZW1pc3RyeS9hYm91dGNjbC9pbnN0 cnVjdGlvbnMvX187ISFHMmtwTTd1TS1UeklGY2h1ITNwOVRkU2tQdmxXWTdzcExDemRydzhBU0hi VXZqalFrWnBTUEpnWFFvdDV1cmFTdWFLV3VNc2lsYS1aakhLQkM3LW05MmZKUXB6bUI2WVJKM0xE WkhyTXV0USQ8L2E+DQomZ3Q7DQomZ3Q7DQoNCg0KDQotPSBUaGlzIGlzIGF1dG9tYXRpY2FsbHkg YWRkZWQgdG8gZWFjaCBtZXNzYWdlIGJ5IHRoZSBtYWlsaW5nIHNjcmlwdCA9LQ0KVG8gcmVjb3Zl ciB0aGUgZW1haWwgYWRkcmVzcyBvZiB0aGUgYXV0aG9yIG9mIHRoZSBtZXNzYWdlLCBwbGVhc2Ug Y2hhbmdlDQp0aGUgc3RyYW5nZSBjaGFyYWN0ZXJzIG9uIHRoZSB0b3AgbGluZSB0byB0aGUgQCBz aWduLiBZb3UgY2FuIGFsc28NCmxvb2sgdXAgdGhlIFgtT3JpZ2luYWwtRnJvbTogbGluZSBpbiB0 aGUgbWFpbCBoZWFkZXIuDQoNCkUtbWFpbCB0byBzdWJzY3JpYmVyczogPGEgaHJlZj0ibWFpbHRv OkNIRU1JU1RSWUBjY2wubmV0IiB0YXJnZXQ9Il9zZWxmIiByZWw9Im5vcmVmZXJyZXIgbm9vcGVu ZXIiPkNIRU1JU1RSWUBjY2wubmV0PC9hPiBvciB1c2U6DQogICAgICA8YSBocmVmPSJodHRwOi8v d3d3LmNjbC5uZXQvY2dpLWJpbi9jY2wvc2VuZF9jY2xfbWVzc2FnZSIgdGFyZ2V0PSJfYmxhbmsi IHJlbD0ibm9yZWZlcnJlciBub29wZW5lciI+aHR0cDovL3d3dy5jY2wubmV0L2NnaS1iaW4vY2Ns L3NlbmRfY2NsX21lc3NhZ2U8L2E+DQoNCkUtbWFpbCB0byBhZG1pbmlzdHJhdG9yczogPGEgaHJl Zj0ibWFpbHRvOkNIRU1JU1RSWS1SRVFVRVNUQGNjbC5uZXQiIHRhcmdldD0iX3NlbGYiIHJlbD0i bm9yZWZlcnJlciBub29wZW5lciI+Q0hFTUlTVFJZLVJFUVVFU1RAY2NsLm5ldDwvYT4gb3IgdXNl DQogICAgICA8YSBocmVmPSJodHRwOi8vd3d3LmNjbC5uZXQvY2dpLWJpbi9jY2wvc2VuZF9jY2xf bWVzc2FnZSIgdGFyZ2V0PSJfYmxhbmsiIHJlbD0ibm9yZWZlcnJlciBub29wZW5lciI+aHR0cDov L3d3dy5jY2wubmV0L2NnaS1iaW4vY2NsL3NlbmRfY2NsX21lc3NhZ2U8L2E+DQoNClN1YnNjcmli ZS9VbnN1YnNjcmliZTogDQogICAgICA8YSBocmVmPSJodHRwOi8vd3d3LmNjbC5uZXQvY2hlbWlz dHJ5L3N1Yl91bnN1Yi5zaHRtbCIgdGFyZ2V0PSJfYmxhbmsiIHJlbD0ibm9yZWZlcnJlciBub29w ZW5lciI+aHR0cDovL3d3dy5jY2wubmV0L2NoZW1pc3RyeS9zdWJfdW5zdWIuc2h0bWw8L2E+DQoN CkJlZm9yZSBwb3N0aW5nLCBjaGVjayB3YWl0IHRpbWUgYXQ6IDxhIGhyZWY9Imh0dHA6Ly93d3cu Y2NsLm5ldCIgdGFyZ2V0PSJfYmxhbmsiIHJlbD0ibm9yZWZlcnJlciBub29wZW5lciI+aHR0cDov L3d3dy5jY2wubmV0PC9hPg0KDQpKb2I6IDxhIGhyZWY9Imh0dHA6Ly93d3cuY2NsLm5ldC9qb2Jz IiB0YXJnZXQ9Il9ibGFuayIgcmVsPSJub3JlZmVycmVyIG5vb3BlbmVyIj5odHRwOi8vd3d3LmNj bC5uZXQvam9iczwvYT4gDQpDb25mZXJlbmNlczogPGEgaHJlZj0iaHR0cDovL3NlcnZlci5jY2wu bmV0L2NoZW1pc3RyeS9hbm5vdW5jZW1lbnRzL2NvbmZlcmVuY2VzLyIgdGFyZ2V0PSJfYmxhbmsi IHJlbD0ibm9yZWZlcnJlciBub29wZW5lciI+aHR0cDovL3NlcnZlci5jY2wubmV0L2NoZW1pc3Ry eS9hbm5vdW5jZW1lbnRzL2NvbmZlcmVuY2VzLzwvYT4NCg0KU2VhcmNoIE1lc3NhZ2VzOiA8YSBo cmVmPSJodHRwOi8vd3d3LmNjbC5uZXQvY2hlbWlzdHJ5L3NlYXJjaGNjbC9pbmRleC5zaHRtbCIg dGFyZ2V0PSJfYmxhbmsiIHJlbD0ibm9yZWZlcnJlciBub29wZW5lciI+aHR0cDovL3d3dy5jY2wu bmV0L2NoZW1pc3RyeS9zZWFyY2hjY2wvaW5kZXguc2h0bWw8L2E+DQoNCklmIHlvdXIgbWFpbCBi b3VuY2VzIGZyb20gQ0NMIHdpdGggNS43LjEgZXJyb3IsIGNoZWNrOg0KICAgICAgPGEgaHJlZj0i aHR0cDovL3d3dy5jY2wubmV0L3NwYW1tZXJzLnR4dCIgdGFyZ2V0PSJfYmxhbmsiIHJlbD0ibm9y ZWZlcnJlciBub29wZW5lciI+aHR0cDovL3d3dy5jY2wubmV0L3NwYW1tZXJzLnR4dDwvYT4NCg0K UlRGSTogPGEgaHJlZj0iaHR0cDovL3d3dy5jY2wubmV0L2NoZW1pc3RyeS9hYm91dGNjbC9pbnN0 cnVjdGlvbnMvIiB0YXJnZXQ9Il9ibGFuayIgcmVsPSJub3JlZmVycmVyIG5vb3BlbmVyIj5odHRw Oi8vd3d3LmNjbC5uZXQvY2hlbWlzdHJ5L2Fib3V0Y2NsL2luc3RydWN0aW9ucy88L2E+DQoNCg0K PC9wcmU+DQo8L2Rpdj4NCjwvYmxvY2txdW90ZT48L3NwYW4+PC9ib2R5PjwvaHRtbD4NCm== --=-QEPZYT2OZ6FGZndtIuaz-- From owner-chemistry@ccl.net Thu Jun 27 13:53:00 2024 From: "maxim totrov max__molsoft.com" To: CCL Subject: CCL: AlphaFold 3 vs AutoDock Vina Message-Id: <-55186-240627125508-3795-38JxFbzyuVIRSM2F80GYCQ===server.ccl.net> X-Original-From: maxim totrov Content-Type: multipart/alternative; boundary="Apple-Mail=_7F5F9951-8AC3-4C84-80E0-307F3D6643F5" Date: Thu, 27 Jun 2024 09:54:50 -0700 Mime-Version: 1.0 (Mac OS X Mail 13.4 \(3608.120.23.2.4\)) Sent to CCL by: maxim totrov [max**molsoft.com] --Apple-Mail=_7F5F9951-8AC3-4C84-80E0-307F3D6643F5 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset=utf-8 > I=E2=80=99m not sure what the non-drug-like compounds are, but if they = are things like co-factors they should be included. Perhaps they can be included, but only proportionally to the very minor = fraction of the overall chemical space that they cover. The problem with co-factors is that they are, in terms of training data = abundance and prediction performance, very unrepresentative of molecules = we work with in real life drug discovery scenarios. Co-factors are a = small number of compounds of rather peculiar chemistry, with highly = conserved recognition motifs that repeat across hundreds if not = thousands of solved complexes in pdb (e.g. ADP: > 3300 complexes in PDB, = FAD: > 2700, NAD > 1700 etc..) - exactly the situation that is easiest = for AF to learn. It was, after all, originally designed to work with = macromolecules built of a small repertoire of monomers, and co-factors = can be viewed as just an extension of this repertoire. It is not really = surprising that the model can capture a limited number of structural = patterns that nature uses again and again for cofactors. Even beyond = cofactors, there are dozens of other ligands that have been = co-crystallized again and again, e.g. some common nonselective kinase = inhibitors (staurosporin, 90 PDBs), benzamidine in serine proteases = etc., for which binding modes can be easily deduced by =E2=80=98homology'.= The question is how well the model can extrapolate whatever it has = learned from such common ligands to the novel chemistries / uncommon = pockets and interaction patterns. Having said this, i think even just modeling the cofactors correctly is = an important step forward for protein structure prediction. It just may = not be quite yet a revolution in CADD... Best regards, Max Totrov >=20 > Cheers >=20 > Chris >=20 >> On 26 Jun 2024, at 21:56, Oleg Trott trott#caa.columbia.edu = > wrote: >>=20 >> I'm not familiar with this dataset personally. But someone alerted me >> that it has many non-drug-like compounds that are common in the PDB, >> but not very relevant in drug discovery. Perhaps they should be >> excluded from the tests? >=20 --Apple-Mail=_7F5F9951-8AC3-4C84-80E0-307F3D6643F5 Content-Transfer-Encoding: quoted-printable Content-Type: text/html; charset=utf-8

I=E2=80=99m not sure what = the non-drug-like compounds are, but if they are things like co-factors = they should be included.

Perhaps they can be included, but only = proportionally to the very minor fraction of the overall chemical space = that they cover.
The problem with co-factors is that they are, = in terms of training data abundance and prediction performance, very = unrepresentative of molecules we work with in real life drug discovery = scenarios. Co-factors  are a small number of compounds of rather = peculiar chemistry, with highly conserved recognition motifs that repeat = across hundreds if not thousands of solved complexes in pdb (e.g. ADP: = > 3300 complexes in PDB, FAD: > 2700, NAD > 1700 etc..) - = exactly the situation that is easiest for AF to learn. It was, after = all, originally designed to work with macromolecules  built of a = small repertoire of monomers, and co-factors can be viewed as just an = extension of this repertoire. It is not really surprising that the model = can capture a limited number of structural patterns that nature uses = again and again for cofactors. Even beyond cofactors, there are dozens = of other ligands that have been co-crystallized again and again, e.g. = some common nonselective kinase inhibitors (staurosporin, 90 PDBs), = benzamidine in serine proteases etc., for which binding modes can be = easily deduced by =E2=80=98homology'.  The question is how well the = model can extrapolate whatever it has learned from such common ligands = to the novel chemistries / uncommon pockets and interaction = patterns.
Having said this, i think even just modeling the = cofactors correctly is an important step forward for protein structure = prediction. It just may not be quite yet a revolution in = CADD...

Best regards,
Max = Totrov


Cheers

Chris

On 26 Jun 2024, at 21:56, Oleg = Trott trott#caa.columbia.edu <owner-chemistry%ccl.net> wrote:

I'm not familiar with this = dataset personally. But someone alerted me
that it has many non-drug-like compounds that are common in = the PDB,
but not very = relevant in drug discovery. Perhaps they should be
excluded from the = tests?


= --Apple-Mail=_7F5F9951-8AC3-4C84-80E0-307F3D6643F5-- From owner-chemistry@ccl.net Thu Jun 27 15:35:01 2024 From: "Oleg Trott trott===caa.columbia.edu" To: CCL Subject: CCL: AlphaFold 3 vs AutoDock Vina Message-Id: <-55187-240627153340-22912-j9m/9/qY8C7Rm2WQAmGA/w:+:server.ccl.net> X-Original-From: Oleg Trott Content-Type: text/plain; charset="UTF-8" Date: Thu, 27 Jun 2024 12:33:13 -0700 MIME-Version: 1.0 Sent to CCL by: Oleg Trott [trott__caa.columbia.edu] > That was a great blog post on AF3 vs. Vina. The hype on AF3 is too strong. Thanks! The same post went pretty viral on LinkedIn yesterday. Getting 200+ likes from mostly scientists was interesting: https://www.linkedin.com/pulse/im-bit-skeptical-alphafold-3-oleg-trott-k7hcc/ ===== Oleg Trott, PhD https://olegtrott.com