Theoretical models - Revision history

Eric Martz: /* 2024 CASP 16 */

2026-01-03T19:55:34Z

2024 CASP 16

← Older revision		Revision as of 19:55, 3 January 2026
Line 55:		Line 55:
	===2024 CASP 16===		===2024 CASP 16===

	AlphaFold 2 & 3 have largely solved prediction of protein monomers and domains, "with barely any space for further improvements at the backbone level except for very specific details, irregular secondary structures, and mutational effects that remain challenging to predict."<ref>PMID: 41088961</ref>		Overall, on all fronts, AF3's modeling capabilities are at or close to the state of the art.<ref name="abriata" /> Prediction of protein oligomer complex assemblies "remains an unsolved challenge."<ref>PMID: 41170922</ref>
			AlphaFold 2 & 3 have largely solved prediction of protein monomers and domains, "with barely any space for further improvements at the backbone level except for very specific details, irregular secondary structures, and mutational effects that remain challenging to predict."<ref name="abriata">PMID: 41088961</ref> For prediction of protein oligomer assemblies, AlphaFold-based methods "show progress, though complex topologies and in particular antibody-antigen interactions are still difficult. Notably, a priori knowledge of stoichiometry significantly aids assembly prediction. Protein-'''ligand''' co-folding with AF3 demonstrated strong potential for pose prediction, outperforming many participants and some dedicated docking tools in baseline tests, but several caveats hold as discussed. Ligand '''affinity''' prediction is totally unreliable. Nucleic acid structure prediction lags considerably ...."<ref name="abriata" />

	===2022: CASP 15===		===2022: CASP 15===

Eric Martz: /* CASP */

2026-01-03T19:43:54Z

CASP

← Older revision		Revision as of 19:43, 3 January 2026
Line 51:		Line 51:
	The success of structure prediction methods is assessed biannually in the ''Critical Assessment of techniques for protein Structure Prediction'' ([[CASP]]) competitions<ref>[http://predictioncenter.gc.ucdavis.edu/ Critical Assessment of techniques for protein Structure Prediction (CASP)].</ref>. Crystallographers submit sequences which they have solved, but for which the structures have not yet been published. Modelers predict the structures which are then compared with subsequently published structures. Beginning in CASP5 (2002), the ability to predict [[Intrinsically Disordered Protein\|intrinsic disorder]] was included<ref>PMID: 19774619</ref>. Assessment of CASP results is done in a '''double-blind''' manner: the predictors do not have access to the empirical structures, and the assessors do not know the identities of the predictors, which are coded.		The success of structure prediction methods is assessed biannually in the ''Critical Assessment of techniques for protein Structure Prediction'' ([[CASP]]) competitions<ref>[http://predictioncenter.gc.ucdavis.edu/ Critical Assessment of techniques for protein Structure Prediction (CASP)].</ref>. Crystallographers submit sequences which they have solved, but for which the structures have not yet been published. Modelers predict the structures which are then compared with subsequently published structures. Beginning in CASP5 (2002), the ability to predict [[Intrinsically Disordered Protein\|intrinsic disorder]] was included<ref>PMID: 19774619</ref>. Assessment of CASP results is done in a '''double-blind''' manner: the predictors do not have access to the empirical structures, and the assessors do not know the identities of the predictors, which are coded.

	There have also been competitions to predict protein-protein docking interactions<ref>[http://www.ebi.ac.uk/msd-srv/capri/ CAPRI: Critical Assessment of PRediction of Interactions].</ref> More recently, AlphaFold Multimer and AlphaFold 3 attempt to predict protein oligomers.		There have also been competitions to predict protein-protein docking interactions<ref>[http://www.ebi.ac.uk/msd-srv/capri/ CAPRI: Critical Assessment of PRediction of Interactions].</ref>. More recently, AlphaFold Multimer and AlphaFold 3 attempt to predict protein oligomers.

			===2024 CASP 16===

			AlphaFold 2 & 3 have largely solved prediction of protein monomers and domains, "with barely any space for further improvements at the backbone level except for very specific details, irregular secondary structures, and mutational effects that remain challenging to predict."<ref>PMID: 41088961</ref>

	===2022: CASP 15===		===2022: CASP 15===

Eric Martz: /* CASP */

2026-01-03T19:31:32Z

CASP

← Older revision		Revision as of 19:31, 3 January 2026
Line 51:		Line 51:
	The success of structure prediction methods is assessed biannually in the ''Critical Assessment of techniques for protein Structure Prediction'' ([[CASP]]) competitions<ref>[http://predictioncenter.gc.ucdavis.edu/ Critical Assessment of techniques for protein Structure Prediction (CASP)].</ref>. Crystallographers submit sequences which they have solved, but for which the structures have not yet been published. Modelers predict the structures which are then compared with subsequently published structures. Beginning in CASP5 (2002), the ability to predict [[Intrinsically Disordered Protein\|intrinsic disorder]] was included<ref>PMID: 19774619</ref>. Assessment of CASP results is done in a '''double-blind''' manner: the predictors do not have access to the empirical structures, and the assessors do not know the identities of the predictors, which are coded.		The success of structure prediction methods is assessed biannually in the ''Critical Assessment of techniques for protein Structure Prediction'' ([[CASP]]) competitions<ref>[http://predictioncenter.gc.ucdavis.edu/ Critical Assessment of techniques for protein Structure Prediction (CASP)].</ref>. Crystallographers submit sequences which they have solved, but for which the structures have not yet been published. Modelers predict the structures which are then compared with subsequently published structures. Beginning in CASP5 (2002), the ability to predict [[Intrinsically Disordered Protein\|intrinsic disorder]] was included<ref>PMID: 19774619</ref>. Assessment of CASP results is done in a '''double-blind''' manner: the predictors do not have access to the empirical structures, and the assessors do not know the identities of the predictors, which are coded.

	There ~~are~~ also competitions to predict protein-protein docking interactions<ref>[http://www.ebi.ac.uk/msd-srv/capri/ CAPRI: Critical Assessment of PRediction of Interactions].</ref>		There have also been competitions to predict protein-protein docking interactions<ref>[http://www.ebi.ac.uk/msd-srv/capri/ CAPRI: Critical Assessment of PRediction of Interactions].</ref> More recently, AlphaFold Multimer and AlphaFold 3 attempt to predict protein oligomers.

	===2022: CASP 15===		===2022: CASP 15===

Eric Martz: /* See Also */

2023-09-29T00:06:33Z

Eric Martz: /* 2022: CASP 15 */

2023-08-16T23:35:27Z

2022: CASP 15

← Older revision		Revision as of 23:35, 16 August 2023
Line 55:		Line 55:
	===2022: CASP 15===		===2022: CASP 15===

	Overall, AlphaFold2 continued to "convincingly outperform all other methods" when various methods were compared using "fully automated mode with default parameter settings, without any manual interventions"<ref name="bhattacharya">PMID: 37523536</ref>. AlphaFold2 predictions had a mean [[Calculating GDT TS\|GDT-TS]] score of 73. ESMFold, which is not based upon multiple sequence alignments, attained second best for backbone positioning (mean GDT-TS 61.6), outperforming RoseTTAFold (which is MSA based) for >80% of cases<ref name="bhattacharya" />. Individual domains were reliably predicted in the 19 multidomain targets, but predictions of domain orientations were less successful<ref name="bhattacharya" />. As an example, AlphaFold 2 achieved the best prediction for one large multi-domain target T1154, but the GDT-TS was only 24<ref name="bhattacharya" />. There is considerable room for improvement in prediction of side-chain positioning: while AlphaFold2 was most successful, its mean GDC-SC score fell short of 50<ref name="bhattacharya" />. Targets in CASP 15 (2022) included several new categories: 12 with RNA<ref name="rna">PMID: 37162955</ref><ref name="rna2">PMID: 37466021</ref>, some ligand protein complexes, and 41 quaternary assembly protein complexes<ref name="casp15new">PMID: 37306011</ref>. "... for the vast majority of proteins and protein complexes, AlphaFold can produce a model close to experimental quality."<ref name="elofsson">PMID: 37060758</ref>. The success rate for overall fold and interface prediction in complexes was 90%, vs. 31% in CASP 14<ref name="assemblies">PMID: 37503072</ref>. This was "largely due to the incorporation of DeepMind's AF2-Multimer approach into custom-built prediction pipelines"<ref name="assemblies" />.		Overall, AlphaFold2 continued to "convincingly outperform all other methods" when various methods were compared using "fully automated mode with default parameter settings, without any manual interventions"<ref name="bhattacharya">PMID: 37523536</ref>. AlphaFold2 predictions had a mean [[Calculating GDT TS\|GDT-TS]] score of 73 (100 meaning perfect, and 0, meaningless). ESMFold, which is not based upon multiple sequence alignments, attained second best for backbone positioning (mean GDT-TS 61.6), outperforming RoseTTAFold (which is MSA based) for >80% of cases<ref name="bhattacharya" />. Individual domains were reliably predicted in the 19 multidomain targets, but predictions of domain orientations were less successful<ref name="bhattacharya" />. As an example, AlphaFold 2 achieved the best prediction for one large multi-domain target T1154, but the GDT-TS was only 24<ref name="bhattacharya" />. There is considerable room for improvement in prediction of side-chain positioning: while AlphaFold2 was most successful, its mean GDC-SC score fell short of 50<ref name="bhattacharya" />. Targets in CASP 15 (2022) included several new categories: 12 with RNA<ref name="rna">PMID: 37162955</ref><ref name="rna2">PMID: 37466021</ref>, some ligand protein complexes, and 41 quaternary assembly protein complexes<ref name="casp15new">PMID: 37306011</ref>. "... for the vast majority of proteins and protein complexes, AlphaFold can produce a model close to experimental quality."<ref name="elofsson">PMID: 37060758</ref>. The success rate for overall fold and interface prediction in complexes was 90%, vs. 31% in CASP 14<ref name="assemblies">PMID: 37503072</ref>. This was "largely due to the incorporation of DeepMind's AF2-Multimer approach into custom-built prediction pipelines"<ref name="assemblies" />.

	===2020: CASP 14===		===2020: CASP 14===

Eric Martz: /* 2022: CASP 15 */

2023-08-16T23:34:24Z

2022: CASP 15

← Older revision		Revision as of 23:34, 16 August 2023
Line 55:		Line 55:
	===2022: CASP 15===		===2022: CASP 15===

	Overall, AlphaFold2 continued to "convincingly outperform all other methods" when various methods were compared using "fully automated mode with default parameter settings, without any manual interventions"<ref name="bhattacharya">PMID: 37523536</ref>. AlphaFold2 predictions had a mean [[Calculating GDT TS\|GDT-TS]] score of 73. ESMFold, which is not based upon multiple sequence alignments, attained second best for backbone positioning (mean GDT-TS 61.6), outperforming RoseTTAFold (which is MSA based) for >80% of cases<ref name="bhattacharya" />. Individual domains were reliably predicted in the 19 multidomain targets, but predictions of domain orientations ~~was~~ less successful<ref name="bhattacharya" />. As an example, AlphaFold 2 achieved the best prediction for one large multi-domain target T1154, but the GDT-TS was only 24<ref name="bhattacharya" />. There is considerable room for improvement in prediction of side-chain positioning: while AlphaFold2 was most successful, its mean GDC-SC score fell short of 50<ref name="bhattacharya" />. Targets in CASP 15 (2022) included several new categories: 12 with RNA<ref name="rna">PMID: 37162955</ref><ref name="rna2">PMID: 37466021</ref>, some ligand protein complexes, and 41 quaternary assembly protein complexes<ref name="casp15new">PMID: 37306011</ref>. "... for the vast majority of proteins and protein complexes, AlphaFold can produce a model close to experimental quality."<ref name="elofsson">PMID: 37060758</ref>. The success rate for overall fold and interface prediction in complexes was 90%, vs. 31% in CASP 14<ref name="assemblies">PMID: 37503072</ref>. This was "largely due to the incorporation of DeepMind's AF2-Multimer approach into custom-built prediction pipelines"<ref name="assemblies" />.		Overall, AlphaFold2 continued to "convincingly outperform all other methods" when various methods were compared using "fully automated mode with default parameter settings, without any manual interventions"<ref name="bhattacharya">PMID: 37523536</ref>. AlphaFold2 predictions had a mean [[Calculating GDT TS\|GDT-TS]] score of 73. ESMFold, which is not based upon multiple sequence alignments, attained second best for backbone positioning (mean GDT-TS 61.6), outperforming RoseTTAFold (which is MSA based) for >80% of cases<ref name="bhattacharya" />. Individual domains were reliably predicted in the 19 multidomain targets, but predictions of domain orientations were less successful<ref name="bhattacharya" />. As an example, AlphaFold 2 achieved the best prediction for one large multi-domain target T1154, but the GDT-TS was only 24<ref name="bhattacharya" />. There is considerable room for improvement in prediction of side-chain positioning: while AlphaFold2 was most successful, its mean GDC-SC score fell short of 50<ref name="bhattacharya" />. Targets in CASP 15 (2022) included several new categories: 12 with RNA<ref name="rna">PMID: 37162955</ref><ref name="rna2">PMID: 37466021</ref>, some ligand protein complexes, and 41 quaternary assembly protein complexes<ref name="casp15new">PMID: 37306011</ref>. "... for the vast majority of proteins and protein complexes, AlphaFold can produce a model close to experimental quality."<ref name="elofsson">PMID: 37060758</ref>. The success rate for overall fold and interface prediction in complexes was 90%, vs. 31% in CASP 14<ref name="assemblies">PMID: 37503072</ref>. This was "largely due to the incorporation of DeepMind's AF2-Multimer approach into custom-built prediction pipelines"<ref name="assemblies" />.

	===2020: CASP 14===		===2020: CASP 14===

Eric Martz: /* 2022: CASP 15 */

2023-08-16T21:50:07Z

2022: CASP 15

← Older revision		Revision as of 21:50, 16 August 2023
Line 55:		Line 55:
	===2022: CASP 15===		===2022: CASP 15===

	Overall, AlphaFold2 continued to "convincingly outperform all other methods" when various methods were compared using "fully automated mode with default parameter settings, without any manual interventions"<ref name="bhattacharya">PMID: 37523536</ref>. AlphaFold2 predictions had a mean [[Calculating GDT TS\|GDT-TS]] score of 73. ESMFold, which is not based upon multiple sequence alignments, attained second best for backbone positioning (mean GDT-TS 61.6), outperforming RoseTTAFold (which is MSA based) for >80% of cases<ref name="bhattacharya" />. Individual domains were reliably predicted in the 19 multidomain targets, but predictions of domain orientations was less successful<ref name="bhattacharya" />. As an example, AlphaFold 2 achieved the best prediction for one large multi-domain target T1154, but the GDT-TS was only 24<ref name="bhattacharya" /> There is considerable room for improvement in prediction of side-chain positioning: while AlphaFold2 was most successful, its mean GDC-SC score fell short of 50<ref name="bhattacharya" />. Targets in CASP 15 (2022) included several new categories: 12 with RNA<ref name="rna">PMID: 37162955</ref><ref name="rna2">PMID: 37466021</ref>, some ligand protein complexes, and 41 quaternary assembly protein complexes<ref name="casp15new">PMID: 37306011</ref>. "... for the vast majority of proteins and protein complexes, AlphaFold can produce a model close to experimental quality."<ref name="elofsson">PMID: 37060758</ref>. The success rate for overall fold and interface prediction in complexes was 90%, vs. 31% in CASP 14<ref name="assemblies">PMID: 37503072</ref>. This was "largely due to the incorporation of DeepMind's AF2-Multimer approach into custom-built prediction pipelines"<ref name="assemblies" />.		Overall, AlphaFold2 continued to "convincingly outperform all other methods" when various methods were compared using "fully automated mode with default parameter settings, without any manual interventions"<ref name="bhattacharya">PMID: 37523536</ref>. AlphaFold2 predictions had a mean [[Calculating GDT TS\|GDT-TS]] score of 73. ESMFold, which is not based upon multiple sequence alignments, attained second best for backbone positioning (mean GDT-TS 61.6), outperforming RoseTTAFold (which is MSA based) for >80% of cases<ref name="bhattacharya" />. Individual domains were reliably predicted in the 19 multidomain targets, but predictions of domain orientations was less successful<ref name="bhattacharya" />. As an example, AlphaFold 2 achieved the best prediction for one large multi-domain target T1154, but the GDT-TS was only 24<ref name="bhattacharya" />. There is considerable room for improvement in prediction of side-chain positioning: while AlphaFold2 was most successful, its mean GDC-SC score fell short of 50<ref name="bhattacharya" />. Targets in CASP 15 (2022) included several new categories: 12 with RNA<ref name="rna">PMID: 37162955</ref><ref name="rna2">PMID: 37466021</ref>, some ligand protein complexes, and 41 quaternary assembly protein complexes<ref name="casp15new">PMID: 37306011</ref>. "... for the vast majority of proteins and protein complexes, AlphaFold can produce a model close to experimental quality."<ref name="elofsson">PMID: 37060758</ref>. The success rate for overall fold and interface prediction in complexes was 90%, vs. 31% in CASP 14<ref name="assemblies">PMID: 37503072</ref>. This was "largely due to the incorporation of DeepMind's AF2-Multimer approach into custom-built prediction pipelines"<ref name="assemblies" />.

	===2020: CASP 14===		===2020: CASP 14===

Eric Martz: /* 2022: CASP 15 */

2023-08-16T21:49:38Z

2022: CASP 15

← Older revision		Revision as of 21:49, 16 August 2023
Line 55:		Line 55:
	===2022: CASP 15===		===2022: CASP 15===

	Overall, AlphaFold2 continued to "convincingly outperform all other methods" when various methods were compared using "fully automated mode with default parameter settings, without any manual interventions"<ref name="bhattacharya">PMID: 37523536</ref>. AlphaFold2 predictions had a mean [[Calculating GDT TS\|GDT-TS]] score of 73. ESMFold, which is not based upon multiple sequence alignments, attained second best for backbone positioning, outperforming RoseTTAFold (which is MSA based) for >80% of cases ~~(mean GDT-TS 61.6)~~<ref name="bhattacharya" />. Individual domains were reliably predicted in the 19 multidomain targets, but predictions of domain orientations was less successful<ref name="bhattacharya" />. As an example, AlphaFold 2 achieved the best prediction for one large multi-domain target T1154, but the GDT-TS was only 24<ref name="bhattacharya" /> There is considerable room for improvement in prediction of side-chain positioning: while AlphaFold2 was most successful, its mean GDC-SC score fell short of 50<ref name="bhattacharya" />. Targets in CASP 15 (2022) included several new categories: 12 with RNA<ref name="rna">PMID: 37162955</ref><ref name="rna2">PMID: 37466021</ref>, some ligand protein complexes, and 41 quaternary assembly protein complexes<ref name="casp15new">PMID: 37306011</ref>. "... for the vast majority of proteins and protein complexes, AlphaFold can produce a model close to experimental quality."<ref name="elofsson">PMID: 37060758</ref>. The success rate for overall fold and interface prediction in complexes was 90%, vs. 31% in CASP 14<ref name="assemblies">PMID: 37503072</ref>. This was "largely due to the incorporation of DeepMind's AF2-Multimer approach into custom-built prediction pipelines"<ref name="assemblies" />.		Overall, AlphaFold2 continued to "convincingly outperform all other methods" when various methods were compared using "fully automated mode with default parameter settings, without any manual interventions"<ref name="bhattacharya">PMID: 37523536</ref>. AlphaFold2 predictions had a mean [[Calculating GDT TS\|GDT-TS]] score of 73. ESMFold, which is not based upon multiple sequence alignments, attained second best for backbone positioning (mean GDT-TS 61.6), outperforming RoseTTAFold (which is MSA based) for >80% of cases<ref name="bhattacharya" />. Individual domains were reliably predicted in the 19 multidomain targets, but predictions of domain orientations was less successful<ref name="bhattacharya" />. As an example, AlphaFold 2 achieved the best prediction for one large multi-domain target T1154, but the GDT-TS was only 24<ref name="bhattacharya" /> There is considerable room for improvement in prediction of side-chain positioning: while AlphaFold2 was most successful, its mean GDC-SC score fell short of 50<ref name="bhattacharya" />. Targets in CASP 15 (2022) included several new categories: 12 with RNA<ref name="rna">PMID: 37162955</ref><ref name="rna2">PMID: 37466021</ref>, some ligand protein complexes, and 41 quaternary assembly protein complexes<ref name="casp15new">PMID: 37306011</ref>. "... for the vast majority of proteins and protein complexes, AlphaFold can produce a model close to experimental quality."<ref name="elofsson">PMID: 37060758</ref>. The success rate for overall fold and interface prediction in complexes was 90%, vs. 31% in CASP 14<ref name="assemblies">PMID: 37503072</ref>. This was "largely due to the incorporation of DeepMind's AF2-Multimer approach into custom-built prediction pipelines"<ref name="assemblies" />.

	===2020: CASP 14===		===2020: CASP 14===

Eric Martz: /* 2022: CASP 15 */

2023-08-16T21:47:57Z

2022: CASP 15

← Older revision		Revision as of 21:47, 16 August 2023
Line 55:		Line 55:
	===2022: CASP 15===		===2022: CASP 15===

	Overall, AlphaFold2 continued to "convincingly outperform all other methods" when various methods were compared using "fully automated mode with default parameter settings, without any manual interventions"<ref name="bhattacharya">PMID: 37523536</ref>. AlphaFold2 predictions had a mean [[Calculating GDT TS\|GDT-TS]] score of 73. ESMFold, which is not based upon multiple sequence alignments, attained second best for backbone positioning, outperforming RoseTTAFold (which is MSA based) for >80% of cases (mean GDT-TS 61.6)<ref name="bhattacharya" />. Individual domains were reliably predicted in the 19 multidomain targets, but predictions of domain orientations was less successful<ref name="bhattacharya" />. Targets in CASP 15 (2022) included several new categories: 12 with RNA<ref name="rna">PMID: 37162955</ref><ref name="rna2">PMID: 37466021</ref>, some ligand protein complexes, and 41 quaternary assembly protein complexes<ref name="casp15new">PMID: 37306011</ref>. "... for the vast majority of proteins and protein complexes, AlphaFold can produce a model close to experimental quality."<ref name="elofsson">PMID: 37060758</ref>. The success rate for overall fold and interface prediction in complexes was 90%, vs. 31% in CASP 14<ref name="assemblies">PMID: 37503072</ref>. This was "largely due to the incorporation of DeepMind's AF2-Multimer approach into custom-built prediction pipelines"<ref name="assemblies" />.		Overall, AlphaFold2 continued to "convincingly outperform all other methods" when various methods were compared using "fully automated mode with default parameter settings, without any manual interventions"<ref name="bhattacharya">PMID: 37523536</ref>. AlphaFold2 predictions had a mean [[Calculating GDT TS\|GDT-TS]] score of 73. ESMFold, which is not based upon multiple sequence alignments, attained second best for backbone positioning, outperforming RoseTTAFold (which is MSA based) for >80% of cases (mean GDT-TS 61.6)<ref name="bhattacharya" />. Individual domains were reliably predicted in the 19 multidomain targets, but predictions of domain orientations was less successful<ref name="bhattacharya" />. As an example, AlphaFold 2 achieved the best prediction for one large multi-domain target T1154, but the GDT-TS was only 24<ref name="bhattacharya" /> There is considerable room for improvement in prediction of side-chain positioning: while AlphaFold2 was most successful, its mean GDC-SC score fell short of 50<ref name="bhattacharya" />. Targets in CASP 15 (2022) included several new categories: 12 with RNA<ref name="rna">PMID: 37162955</ref><ref name="rna2">PMID: 37466021</ref>, some ligand protein complexes, and 41 quaternary assembly protein complexes<ref name="casp15new">PMID: 37306011</ref>. "... for the vast majority of proteins and protein complexes, AlphaFold can produce a model close to experimental quality."<ref name="elofsson">PMID: 37060758</ref>. The success rate for overall fold and interface prediction in complexes was 90%, vs. 31% in CASP 14<ref name="assemblies">PMID: 37503072</ref>. This was "largely due to the incorporation of DeepMind's AF2-Multimer approach into custom-built prediction pipelines"<ref name="assemblies" />.

	===2020: CASP 14===		===2020: CASP 14===

Eric Martz: /* 2022: CASP 15 */

2023-08-16T21:42:33Z

2022: CASP 15

← Older revision		Revision as of 21:42, 16 August 2023
Line 55:		Line 55:
	===2022: CASP 15===		===2022: CASP 15===

	Overall, AlphaFold2 continued to "convincingly outperform all other methods" when various methods were compared using "fully automated mode with default parameter settings, without any manual interventions"<ref name="bhattacharya">PMID: 37523536</ref>. AlphaFold2 predictions had a mean [[Calculating GDT TS\|GDT-TS]] score of 73. ESMFold, which is not based upon multiple sequence alignments, attained second best for backbone positioning, outperforming RoseTTAFold (which is MSA based) for >80% of cases (mean GDT-TS 61.6)<ref name="bhattacharya" />. Targets in CASP 15 (2022) included several new categories: 12 with RNA<ref name="rna">PMID: 37162955</ref><ref name="rna2">PMID: 37466021</ref>, some ligand protein complexes, and 41 quaternary assembly protein complexes<ref name="casp15new">PMID: 37306011</ref>. "... for the vast majority of proteins and protein complexes, AlphaFold can produce a model close to experimental quality."<ref name="elofsson">PMID: 37060758</ref>. The success rate for overall fold and interface prediction in complexes was 90%, vs. 31% in CASP 14<ref name="assemblies">PMID: 37503072</ref>. This was "largely due to the incorporation of DeepMind's AF2-Multimer approach into custom-built prediction pipelines"<ref name="assemblies" />.		Overall, AlphaFold2 continued to "convincingly outperform all other methods" when various methods were compared using "fully automated mode with default parameter settings, without any manual interventions"<ref name="bhattacharya">PMID: 37523536</ref>. AlphaFold2 predictions had a mean [[Calculating GDT TS\|GDT-TS]] score of 73. ESMFold, which is not based upon multiple sequence alignments, attained second best for backbone positioning, outperforming RoseTTAFold (which is MSA based) for >80% of cases (mean GDT-TS 61.6)<ref name="bhattacharya" />. Individual domains were reliably predicted in the 19 multidomain targets, but predictions of domain orientations was less successful<ref name="bhattacharya" />. Targets in CASP 15 (2022) included several new categories: 12 with RNA<ref name="rna">PMID: 37162955</ref><ref name="rna2">PMID: 37466021</ref>, some ligand protein complexes, and 41 quaternary assembly protein complexes<ref name="casp15new">PMID: 37306011</ref>. "... for the vast majority of proteins and protein complexes, AlphaFold can produce a model close to experimental quality."<ref name="elofsson">PMID: 37060758</ref>. The success rate for overall fold and interface prediction in complexes was 90%, vs. 31% in CASP 14<ref name="assemblies">PMID: 37503072</ref>. This was "largely due to the incorporation of DeepMind's AF2-Multimer approach into custom-built prediction pipelines"<ref name="assemblies" />.

	===2020: CASP 14===		===2020: CASP 14===

← Older revision		Revision as of 00:06, 29 September 2023
Line 147:		Line 147:

	==See Also==		==See Also==
			*[[AlphaFold/Index]], a list of pages in Proteopedia about Alphafold.
	*[[Calculating GDT TS]]		*[[Calculating GDT TS]]
	* Theoretical models displayed in Proteopedia must be clearly identified: see [[Proteopedia:Policy#Theoretical Models]] using methods explained at [[Proteopedia:Cookbook#Theoretical Models]].		* Theoretical models displayed in Proteopedia must be clearly identified: see [[Proteopedia:Policy#Theoretical Models]] using methods explained at [[Proteopedia:Cookbook#Theoretical Models]].