5sfm: Difference between revisions
No edit summary |
No edit summary |
||
| (One intermediate revision by the same user not shown) | |||
| Line 1: | Line 1: | ||
== | ==CRYSTAL STRUCTURE OF HUMAN PHOSPHODIESTERASE 10 IN COMPLEX WITH n3cn1c(nc(n1)c2ccccc2)cc3NC(=O)c5c(C(=O)N4CCOCC4)cnn5C, micromolar IC50=0.0012349== | ||
<StructureSection load='5sfm' size='340' side='right'caption='[[5sfm]], [[Resolution|resolution]] 2.16Å' scene=''> | <StructureSection load='5sfm' size='340' side='right'caption='[[5sfm]], [[Resolution|resolution]] 2.16Å' scene=''> | ||
== Structural highlights == | == Structural highlights == | ||
<table><tr><td colspan='2'>[[5sfm]] is a 4 chain structure with sequence from [https://en.wikipedia.org/wiki/Homo_sapiens Homo sapiens]. Full crystallographic information is available from [http://oca.weizmann.ac.il/oca-bin/ocashort?id=5SFM OCA]. For a <b>guided tour on the structure components</b> use [https://proteopedia.org/fgij/fg.htm?mol=5SFM FirstGlance]. <br> | <table><tr><td colspan='2'>[[5sfm]] is a 4 chain structure with sequence from [https://en.wikipedia.org/wiki/Homo_sapiens Homo sapiens]. Full crystallographic information is available from [http://oca.weizmann.ac.il/oca-bin/ocashort?id=5SFM OCA]. For a <b>guided tour on the structure components</b> use [https://proteopedia.org/fgij/fg.htm?mol=5SFM FirstGlance]. <br> | ||
</td></tr><tr id='ligand'><td class="sblockLbl"><b>[[Ligand|Ligands:]]</b></td><td class="sblockDat" id="ligandDat"><scene name='pdbligand=CME:S,S-(2-HYDROXYETHYL)THIOCYSTEINE'>CME</scene>, <scene name='pdbligand=ILN:1-methyl-4-(morpholine-4-carbonyl)-N-[(4S)-2-phenyl[1,2,4]triazolo[1,5-c]pyrimidin-7-yl]-1H-pyrazole-5-carboxamide'>ILN</scene>, <scene name='pdbligand=MG:MAGNESIUM+ION'>MG</scene>, <scene name='pdbligand=ZN:ZINC+ION'>ZN</scene></td></tr> | </td></tr><tr id='method'><td class="sblockLbl"><b>[[Empirical_models|Method:]]</b></td><td class="sblockDat" id="methodDat">X-ray diffraction, [[Resolution|Resolution]] 2.16Å</td></tr> | ||
<tr id='ligand'><td class="sblockLbl"><b>[[Ligand|Ligands:]]</b></td><td class="sblockDat" id="ligandDat"><scene name='pdbligand=CME:S,S-(2-HYDROXYETHYL)THIOCYSTEINE'>CME</scene>, <scene name='pdbligand=ILN:1-methyl-4-(morpholine-4-carbonyl)-N-[(4S)-2-phenyl[1,2,4]triazolo[1,5-c]pyrimidin-7-yl]-1H-pyrazole-5-carboxamide'>ILN</scene>, <scene name='pdbligand=MG:MAGNESIUM+ION'>MG</scene>, <scene name='pdbligand=ZN:ZINC+ION'>ZN</scene></td></tr> | |||
<tr id='resources'><td class="sblockLbl"><b>Resources:</b></td><td class="sblockDat"><span class='plainlinks'>[https://proteopedia.org/fgij/fg.htm?mol=5sfm FirstGlance], [http://oca.weizmann.ac.il/oca-bin/ocaids?id=5sfm OCA], [https://pdbe.org/5sfm PDBe], [https://www.rcsb.org/pdb/explore.do?structureId=5sfm RCSB], [https://www.ebi.ac.uk/pdbsum/5sfm PDBsum], [https://prosat.h-its.org/prosat/prosatexe?pdbcode=5sfm ProSAT]</span></td></tr> | <tr id='resources'><td class="sblockLbl"><b>Resources:</b></td><td class="sblockDat"><span class='plainlinks'>[https://proteopedia.org/fgij/fg.htm?mol=5sfm FirstGlance], [http://oca.weizmann.ac.il/oca-bin/ocaids?id=5sfm OCA], [https://pdbe.org/5sfm PDBe], [https://www.rcsb.org/pdb/explore.do?structureId=5sfm RCSB], [https://www.ebi.ac.uk/pdbsum/5sfm PDBsum], [https://prosat.h-its.org/prosat/prosatexe?pdbcode=5sfm ProSAT]</span></td></tr> | ||
</table> | </table> | ||
| Line 13: | Line 14: | ||
We release a new, high quality data set of 1162 PDE10A inhibitors with experimentally determined binding affinities together with 77 PDE10A X-ray co-crystal structures from a Roche legacy project. This data set is used to compare the performance of different 2D- and 3D-machine learning (ML) as well as empirical scoring functions for predicting binding affinities with high throughput. We simulate use cases that are relevant in the lead optimization phase of early drug discovery. ML methods perform well at interpolation, but poorly in extrapolation scenarios-which are most relevant to a real-world application. Moreover, we find that investing into the docking workflow for binding pose generation using multi-template docking is rewarded with an improved scoring performance. A combination of 2D-ML and 3D scoring using a modified piecewise linear potential shows best overall performance, combining information on the protein environment with learning from existing SAR data. | We release a new, high quality data set of 1162 PDE10A inhibitors with experimentally determined binding affinities together with 77 PDE10A X-ray co-crystal structures from a Roche legacy project. This data set is used to compare the performance of different 2D- and 3D-machine learning (ML) as well as empirical scoring functions for predicting binding affinities with high throughput. We simulate use cases that are relevant in the lead optimization phase of early drug discovery. ML methods perform well at interpolation, but poorly in extrapolation scenarios-which are most relevant to a real-world application. Moreover, we find that investing into the docking workflow for binding pose generation using multi-template docking is rewarded with an improved scoring performance. A combination of 2D-ML and 3D scoring using a modified piecewise linear potential shows best overall performance, combining information on the protein environment with learning from existing SAR data. | ||
A high quality, industrial data set for binding affinity prediction: performance comparison in different early drug discovery scenarios.,Tosstorff A, Rudolph MG, Cole JC, Reutlinger M, Kramer C, Schaffhauser H, Nilly A, Flohr A, Kuhn B J Comput Aided Mol Des. 2022 Oct;36(10):753-765. doi: 10.1007/s10822-022-00478-x., Epub 2022 Sep 25. PMID:36153472<ref>PMID:36153472</ref> | A high quality, industrial data set for binding affinity prediction: performance comparison in different early drug discovery scenarios.,Tosstorff A, Rudolph MG, Cole JC, Reutlinger M, Kramer C, Schaffhauser H, Nilly A, Flohr A, Kuhn B J Comput Aided Mol Des. 2022 Oct;36(10):753-765. doi: 10.1007/s10822-022-00478-x. , Epub 2022 Sep 25. PMID:36153472<ref>PMID:36153472</ref> | ||
From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine.<br> | From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine.<br> | ||