揭开AlphaFold的面纱，整合多聚体复合物中的实验和预测-动脉网

Unmasking AlphaFold to integrate experiments and predictions in multimeric complexes

Nature 等信源发布 2024-10-09 12:40



可切换为仅中文







AbstractSince the release of AlphaFold, researchers have actively refined its predictions and attempted to integrate it into existing pipelines for determining protein structures. These efforts have introduced a number of functionalities and optimisations at the latest Critical Assessment of protein Structure Prediction edition (CASP15), resulting in a marked improvement in the prediction of multimeric protein structures.

摘要自从AlphaFold发布以来，研究人员积极改进其预测，并试图将其整合到现有的确定蛋白质结构的管道中。这些努力在最新的蛋白质结构预测关键评估版（CASP15）中引入了许多功能和优化，从而显着改善了多聚体蛋白质结构的预测。

However, AlphaFold’s capability of predicting large protein complexes is still limited and integrating experimental data in the prediction pipeline is not straightforward. In this study, we introduce AF_unmasked to overcome these limitations. Our results demonstrate that AF_unmasked can integrate experimental information to build larger or hard to predict protein assemblies with high confidence.

然而，AlphaFold预测大型蛋白质复合物的能力仍然有限，将实验数据整合到预测管道中并不简单。在这项研究中，我们引入AF\U unmasked来克服这些限制。我们的结果表明，AF\u unmasked可以整合实验信息，以高可信度构建更大或难以预测的蛋白质组装体。

The resulting predictions can help interpret and augment experimental data. This approach generates high quality (DockQ score > 0.8) structures even when little to no evolutionary information is available and imperfect experimental structures are used as a starting point. AF_unmasked is developed and optimised to fill incomplete experimental structures (structural inpainting), which may provide insights into protein dynamics.

由此产生的预测可以帮助解释和增加实验数据。这种方法产生高质量（DockQ得分>0.8）结构，即使很少或没有进化信息可用，并且不完美的实验结构被用作起点。AF\u unmasked经过开发和优化，以填充不完整的实验结构（结构修复），这可能提供对蛋白质动力学的见解。

In summary, AF_unmasked provides an easy-to-use method that efficiently integrates experiments to predict large protein complexes more confidently..

总之，AF\u unmasked提供了一种易于使用的方法，可以有效地整合实验，以更自信地预测大型蛋白质复合物。。

IntroductionSince the release of AlphaFold (v2)1 in 2020, part of the computational structural biology community has worked to improve AlphaFold and to expand its functionalities, also in ways its creators had not initially envisioned. This is a challenging avenue of research, as it involves manipulating a deep neural network in ways that may yield unpredictable results.

简介自2020年AlphaFold（v2）1发布以来，计算结构生物学界的一部分一直致力于改进AlphaFold并扩展其功能，这也是其创作者最初没有设想的方式。这是一个具有挑战性的研究途径，因为它涉及到以可能产生不可预测结果的方式操纵深度神经网络。

Interpretation of neural networks is also notoriously hard.The authors of a recent study have theorised that the neural network performs a sampling technique on a learned energy landscape2. According to this theory, the first block of layers (the Evoformer module) identifies a neighborhood within this landscape that closely approximates a reasonable minimum.

神经网络的解释也是出了名的困难。最近一项研究的作者从理论上认为，神经网络在学习的能源景观上执行采样技术2。根据这一理论，第一块层（Evoformer模块）确定了该景观中接近合理最小值的邻域。

The second block (the structural module), known for its ability to accurately predict the quality of predictions1,2, performs an energy minimisation within the identified neighborhood to generate atomic structures. More recently, targeting the energy minimisation in this second step has been a main strategy to improve AlphaFold.

第二块（结构模块）以其准确预测预测质量的能力而闻名1,2，在确定的邻域内执行能量最小化以产生原子结构。最近，在第二步中以能量最小化为目标一直是改进AlphaFold的主要策略。

The main focus at the latest edition of the Critical Assessment of protein Structure Prediction (CASP15) was to assess the progress in the assembly category since AlphaFold-Multimer3 had been released. The best ranking groups applied mainly two strategies: either they (i) introduced stochastic noise into the neural network while generating thousands of models for each target4, or (ii) created and selected better/deeper Multiple Sequence Alignments (MSAs) as input to the Evoformer module5.

最新版《蛋白质结构预测关键评估》（CASP15）的主要重点是评估自AlphaFold-Multimer3发布以来组装类别的进展。排名最好的小组主要应用两种策略：要么（i）在为每个目标生成数千个模型的同时将随机噪声引入神经网络4，要么（ii）创建并选择更好/更深的多序列比对（MSA）作为输入到Evoformer模块5。

If the prediction task is indeed one of energy minimisation, the first approach would help sampling AlphaFold’s energy function more efficiently and extensively. The second approach could be interpreted as an attempt to start the sampling p.

如果预测任务确实是能量最小化，那么第一种方法将有助于更有效和更广泛地采样AlphaFold的能量函数。第二种方法可以解释为尝试开始采样p。

Data availability

数据可用性

The source data underlying Figs. 2, 3c, 5c–d and Supplementary Figs. S1–S15 are provided as a Source Data file. All the predicted structures, along with log files, inputs and templates are available with [https://doi.org/10.17044/scilifelab.24198669]. ChimeraX sessions for the analyses of Cryo-EM test cases are available with [https://doi.org/10.17044/scilifelab.25653297].

图2、3c、5c–d和补充图S1–S15的基础源数据作为源数据文件提供。所有预测的结构以及日志文件、输入和模板都可以通过[https://doi.org/10.17044/scilifelab.24198669]。ChimeraX会话可用于分析低温EM测试案例[https://doi.org/10.17044/scilifelab.25653297]。

Supplementary movies referenced in text are available as Supplementary data files. Deposited PDB structures referenced in the text are: 7ALW, 7QIJ, 4K2H, 5IU0, 1QVR, 5OG1, 6RN3, 7PGU, 6OB3, 1NF1, 3PEG. Source data are provided with this paper..

文本中引用的补充电影可作为补充数据文件使用。本文中引用的沉积PDB结构是：7ALW，7QIJ，4K2H，5IU0，1QVR，5OG1，6RN3，7PGU，6OB3，1NF1，3PEG。本文提供了源数据。。

Code availability

代码可用性

The source code, installation instructions, user manual and examples are available on GitHub: github.com/clami66/AF_unmasked, [https://doi.org/10.5281/zenodo.13364959]61. A Jupyter notebook is available to run the tool on Google Colab or similar: [https://github.com/clami66/AF_unmasked/tree/notebook]..

GitHub上提供了源代码、安装说明、用户手册和示例：GitHub.com/clami66/AF\u unmasked[https://doi.org/10.5281/zenodo.13364959]61、Jupyter笔记本可用于在Google Colab或类似工具上运行该工具：[https://github.com/clami66/AF_unmasked/tree/notebook]。。

ReferencesJumper, J. et al. Highly accurate protein structure prediction with AlphaFold. Nature 596, 583–589 (2021).Article

ReferencesJumper，J。等人。使用AlphaFold进行高度准确的蛋白质结构预测。自然596583-589（2021）。文章

ADS

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Roney, J. P. & Ovchinnikov, S. State-of-the-art estimation of protein model accuracy using AlphaFold. Phys. Rev. Lett. 129, 238101 (2022).Article

Roney，J.P。＆Ovchinnikov，S。使用AlphaFold对蛋白质模型准确性的最新估计。物理。Lett牧师。129238101（2022）。文章

ADS

PubMed

Google Scholar

谷歌学者

Evans, R. et al. Protein complex prediction with AlphaFold-Multimer. BioRxiv https://doi.org/10.1101/2021.10.04.463034 (2021).Wallner, B. AFsample: Improving multimer prediction with alphafold using massive sampling. Bioinformatics 39, btad573 (2023).Committee, C. CASP15: Book of Abstracts.

Evans，R。等人。使用AlphaFold多聚体预测蛋白质复合物。生物十四https://doi.org/10.1101/2021.10.04.463034（2021年）。。生物信息学39，btad573（2023）。委员会，C.CASP15：摘要书。

https://predictioncenter.org/casp15/doc/CASP15_Abstracts.pdf (2022).Bryant, P. et al. Predicting the structure of large protein complexes using Alphafold and Monte Carlo tree search. Nat. Commun. 13, 6028 (2022).Article .

https://predictioncenter.org/casp15/doc/CASP15_Abstracts.pdf（2022年）。Bryant，P.等人。使用Alphafold和蒙特卡罗树搜索预测大型蛋白质复合物的结构。国家公社。。文章。

ADS

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Perrakis, A. & Sixma, T. K. AI revolutions in biology: the joys and perils of AlphaFold. EMBO Rep. 22, e54046 (2021).Article

Perrakis，A.＆Sixma，T.K.AI生物学革命：AlphaFold的欢乐与危险。。文章

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Terwilliger, T. C. et al. AlphaFold predictions are valuable hypotheses, and accelerate but do not replace experimental structure determination. bioRxiv https://doi.org/10.1101/2022.11.21.517405 (2022).Liebschner, D. Using predicted models in Phenix. Acta Cryst. 75, 861–877 (2019).

Terwilliger，T.C.等人的AlphaFold预测是有价值的假设，可以加速但不能取代实验结构的确定。生物十四https://doi.org/10.1101/2022.11.21.517405（2022年）。Liebschner，D。在Phenix中使用预测模型。晶体学报。75861-877（2019）。

Google Scholar

谷歌学者

Terwilliger, T. C. et al. Accelerating crystal structure determination with iterative AlphaFold prediction. Acta Crystallogr. Sec. D. Struct. Biol. 79, 234–242 (2023).Article

Terwilliger，T.C.等人，《用迭代α折叠预测加速晶体结构测定》。晶体学报。第D节结构。生物学79234-242（2023）。文章

ADS

Google Scholar

谷歌学者

Terwilliger, T. C. et al. Improved AlphaFold modeling with implicit experimental information. Nat. Methods 19, 1376–1382 (2022).Article

Terwilliger，T.C.等人利用隐含的实验信息改进了AlphaFold建模。自然方法191376-1382（2022）。文章

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Ahdritz, G. et al. OpenFold: Retraining AlphaFold2 yields new insights into its learning mechanisms and capacity for generalization. bioRxiv https://www.biorxiv.org/content/10.1101/2022.11.20.517210 (2022).Li, Z. et al. Uni-fold: An open-source platform for developing protein folding models beyond Alphafold.

Ahdritz，G。等人。OpenFold：对AlphaFold2进行再训练，可以对其学习机制和泛化能力产生新的见解。生物十四https://www.biorxiv.org/content/10.1101/2022.11.20.517210（2022年）。Li，Z。等人。Uni-fold：一个开源平台，用于开发Alphafold以外的蛋白质折叠模型。

bioRxiv https://www.biorxiv.org/content/10.1101/2022.08.04.502811v3.full.pdf (2022).Stahl, K., Brock, O. & Rappsilber, J. Modelling protein complexes with crosslinking mass spectrometry and deep learning. bioRxiv https://doi.org/10.1101/2023.06.07.544059 (2023).Mirabello, C. & Wallner, B. DockQv2: Improved automatic quality measure forprotein multimers, nucleic acids and small molecules.

生物十四https://www.biorxiv.org/content/10.1101/2022.08.04.502811v3.full.pdf（2022年）。Stahl，K.，Brock，O。＆Rappsilber，J。用交联质谱和深度学习对蛋白质复合物进行建模。生物十四https://doi.org/10.1101/2023.06.07.544059（2023年）。Mirabello，C。＆Wallner，B。DockQv2：改进的蛋白质多聚体，核酸和小分子的自动质量测量。

Bioinformatics. btae586 https://doi.org/10.1093/bioinformatics/btae586 (2024).Yin, R. & Pierce, B. G. Evaluation of Alphafold antibody-antigen modeling with implications for improving predictive accuracy. bioRxiv 33, e4865 (2023).Gray, J. J. et al. Protein–protein docking with simultaneous optimization of rigid-body displacement and side-chain conformations.

生物信息学。btae586https://doi.org/10.1093/bioinformatics/btae586（2024年）。Yin，R。＆Pierce，B.G。评估Alphafold抗体-抗原模型，对提高预测准确性具有重要意义。bioRxiv 33，e4865（2023）。Gray，J.J.等人。蛋白质-蛋白质对接，同时优化刚体位移和侧链构象。

J. Mol. Biol. 331, 281–299 (2003).Article .

J.分子生物学。331, 281-299 (2003).第[UNK]条。

PubMed

Google Scholar

谷歌学者

Lensink, M. F. & Wodak, S. J. Docking, scoring, and affinity prediction in Capri. Proteins Struct. Funct. Bioinforma. 81, 2082–2095 (2013).Article

Lensink，M.F。＆Wodak，S.J。Capri。蛋白质结构中的对接，评分和亲和力预测。函数。生物信息学。812082-2095（2013）。文章

Google Scholar

谷歌学者

Basu, S. & Wallner, B. DockQ: a quality measure for protein-protein docking models. PLoS ONE 11, e0161879 (2016).Article

Basu，S。＆Wallner，B。DockQ：蛋白质-蛋白质对接模型的质量度量。PLoS ONE 11，e0161879（2016）。文章

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Zidek, A. AlphaFold v2.3.0 Release Notes and CASP15 Models. https://github.com/deepmind/alphafold/blob/main/docs/technical_note_v2.3.0.md (2022).Pak, M. A. et al. Using AlphaFold to predict the impact of single mutations on protein stability and function. PLoS ONE 18, e0282689 (2023).Article .

Zidek，A。AlphaFold v2.3.0发行说明和CASP15模型。https://github.com/deepmind/alphafold/blob/main/docs/technical_note_v2.3.0.md（2022年）。Pak，M.A.等人使用AlphaFold预测单个突变对蛋白质稳定性和功能的影响。PLoS ONE 18，e0282689（2023）。文章。

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Mao, Y. et al. The small subunit of Rubisco and its potential as an engineering target. J. Exp. Bot. 74, 543–561 (2023).Article

Mao，Y.等人。Rubisco的小亚基及其作为工程目标的潜力。J、实验Bot 74543-561（2023）。文章

PubMed

Google Scholar

谷歌学者

Valegård, K., Hasse, D., Andersson, I. & Gunn, L. H. Structure of rubisco from arabidopsis thaliana in complex with 2-carboxyarabinitol-1,5-bisphosphate. Acta Crystallogr. D. Struct. Biol. 74, 1–9 (2018).Article

Valegård，K.，Hasse，D.，Andersson，I。＆Gunn，L.H。拟南芥rubisco与2-羧基阿拉伯硝基-1,5-二磷酸复合物的结构。晶体学报。D、结构。生物学杂志74,1-9（2018）。文章

ADS

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Yin, Y. et al. Structural basis for aggregate dissolution and refolding by the mycobacterium tuberculosis ClpB-DnaK bi-chaperone system. Cell Rep. 35, 109166 (2021).Article

Yin，Y.等人。结核分枝杆菌ClpB-DnaK双分子伴侣系统聚集体溶解和重折叠的结构基础。Cell Rep.35109166（2021）。文章

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Kędzierska-Mieszkowska, S. & Zolkiewski, M. Hsp100 molecular chaperone clpb and its role in virulence of bacterial pathogens. Int. J. Mol. Sci. 22, 5319 (2021).Article

Kędzierska-Mieszkowska，S。＆Zolkiewski，M。Hsp100分子伴侣clpb及其在细菌病原体毒力中的作用。Int.J.Mol.Sci。225319（2021）。文章

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Katikaridis, P., Bohl, V. & Mogk, A. Resisting the heat: bacterial disaggregases rescue cells from devastating protein aggregation. Front. Mol. Biosci. 8, 681439 (2021).Article

Katikaridis，P.，Bohl，V。＆Mogk，A。耐热：细菌解聚拯救细胞免受破坏性蛋白质聚集。正面。摩尔生物科学。。文章

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Avellaneda, M. J. et al. Processive extrusion of polypeptide loops by a hsp100 disaggregase. Nature 578, 317–320 (2020).Article

Avellaneda，M.J.等人。通过hsp100解聚酶进行多肽环的过程性挤出。自然578317-320（2020）。文章

ADS

PubMed

Google Scholar

谷歌学者

Mazal, H., Iljina, M., Riven, I. & Haran, G. Ultrafast pore-loop dynamics in a AAA+ machine point to a Brownian-ratchet mechanism for protein translocation. Sci. Adv. 7, eabg4674 (2021).Article

Mazal，H.，Iljina，M.，Riven，I。＆Haran，G。AAA+机器中的超快孔环动力学指向蛋白质易位的布朗棘轮机制。科学。Adv.7，eabg4674（2021）。文章

ADS

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Uchihashi, T. et al. Dynamic structural states of ClpB involved in its disaggregation function. Nat. Commun. 9, 2147 (2018).Article

Uchihashi，T。等人。ClpB的动态结构状态涉及其分解功能。国家公社。92147（2018）。文章

ADS

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Deville, C., Franke, K., Mogk, A., Bukau, B. & Saibil, H. R. Two-step activation mechanism of the ClpB disaggregase for sequential substrate threading by the main ATPase motor. Cell Rep. 27, 3433–3446.e4 (2019).Article

Deville，C.，Franke，K.，Mogk，A.，Bukau，B。＆Saibil，H.R。ClpB解聚酶的两步激活机制，用于主ATPase马达的顺序底物穿线。Cell Rep.273433–3446.e4（2019）。文章

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Rizo, A. N. et al. Structural basis for substrate gripping and translocation by the ClpB AAA+ disaggregase. Nat. Commun. 10, 1–12 (2019).Article

Rizo，A.N.等人。ClpB-AAA+解聚酶对底物抓取和转运的结构基础。国家公社。10,1-12（2019）。文章

Google Scholar

谷歌学者

Yu, H. et al. ATP hydrolysis-coupled peptide translocation mechanism of Mycobacterium tuberculosis ClpB. Proc. Natl Acad. Sci. USA 115, E9560–E9569 (2018).Article

Yu，H。等。结核分枝杆菌ClpB的ATP水解偶联肽易位机制。程序。国家科学院。科学。美国115，E9560–E9569（2018）。文章

MathSciNet

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Deville, C. et al. Structural pathway of regulated substrate transfer and threading through an hsp100 disaggregase. Sci. Adv. 3, e1701726 (2017).Article

Deville，C。等人。调节底物转移和穿过hsp100解聚酶的结构途径。科学。Adv.3，e1701726（2017）。文章

ADS

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Haslberger, T. et al. M domains couple the ClpB threading motor with the DnaK chaperone activity. Mol. Cell 25, 247–260 (2007).Article

Haslberger，T。等人的M域将ClpB线程马达与DnaK伴侣活性偶联。。文章

PubMed

Google Scholar

谷歌学者

Oguchi, Y. et al. A tightly regulated molecular toggle controls AAA+ disaggregase. Nat. Struct. Mol. Biol. 19, 1338–1346 (2012).Article

Oguchi，Y。等人。严格调节的分子开关控制AAA+解聚酶。自然结构。分子生物学。191338-1346（2012）。文章

PubMed

Google Scholar

谷歌学者

Rosenzweig, R., Moradi, S., Zarrine-Afsar, A., Glover, J. R. & Kay, L. E. Unraveling the mechanism of protein disaggregation through a ClpB-DnaK interaction. Science 339, 1080–1083 (2013).Article

Rosenzweig，R.，Moradi，S.，Zarrine Afsar，A.，Glover，J.R。＆Kay，L.E。通过ClpB-DnaK相互作用揭示蛋白质解聚的机制。《科学》3391080–1083（2013）。文章

ADS

PubMed

Google Scholar

谷歌学者

Carroni, M. et al. Head-to-tail interactions of the coiled-coil domains regulate ClpB activity and cooperation with hsp70 in protein disaggregation. Elife 3, e02481 (2014).Article

Carroni，M。等人。卷曲螺旋结构域的头尾相互作用调节ClpB活性以及与hsp70在蛋白质解聚中的合作。Elife 3，e02481（2014）。文章

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Mazal, H. et al. Tunable microsecond dynamics of an allosteric switch regulate the activity of a AAA+ disaggregation machine. Nat. Commun. 10, 1438 (2019).Article

。国家公社。101438（2019）。文章

ADS

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Rosenzweig, R. et al. Clpb n-terminal domain plays a regulatory role in protein disaggregation. Proc. Natl Acad. Sci. USA 112, E6872–E6881 (2015).Article

Rosenzweig，R。等人。Clpb n末端结构域在蛋白质解聚中起调节作用。程序。国家科学院。科学。美国112，E6872–E6881（2015）。文章

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Bergoug, M. et al. Neurofibromin structure, functions and regulation. Cells 9, 2365 (2020).Article

Bergoug，M。等人。神经纤维蛋白的结构，功能和调节。细胞92365（2020）。文章

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Gutmann, D. H., Wood, D. L. & Collins, F. S. Identification of the neurofibromatosis type 1 gene product. Proc. Natl Acad. Sci. USA 88, 9658–9662 (1991).Article

Gutmann，D.H.，Wood，D.L。和Collins，F.S。鉴定神经纤维瘤病1型基因产物。程序。国家科学院。科学。美国889658–9662（1991）。文章

ADS

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Ratner, N. & Miller, S. J. A RASopathy gene commonly mutated in cancer: the neurofibromatosis type 1 tumour suppressor. Nat. Rev. Cancer 15, 290–301 (2015).Article

Ratner，N。＆Miller，S.J。一种在癌症中常见突变的RASopathy基因：神经纤维瘤病1型肿瘤抑制因子。《国家癌症评论》15290-301（2015）。文章

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Naschberger, A., Baradaran, R., Rupp, B. & Carroni, M. The structure of neurofibromin isoform 2 reveals different functional states. Nature 599, 315–319 (2021).Article

Naschberger，A.，Baradaran，R.，Rupp，B。＆Carroni，M。神经纤维蛋白同工型2的结构揭示了不同的功能状态。自然599315-319（2021）。文章

ADS

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Lupton, C. J. et al. The cryo-EM structure of the human neurofibromin dimer reveals the molecular basis for neurofibromatosis type 1. Nat. Struct. Mol. Biol. 28, 982–988 (2021).Article

Lupton，C.J。等人。人神经纤维蛋白二聚体的冷冻电镜结构揭示了1型神经纤维瘤病的分子基础。自然结构。分子生物学。28982-988（2021）。文章

PubMed

Google Scholar

谷歌学者

Chaker-Margot, M. et al. Structural basis of activation of the tumor suppressor protein neurofibromin. Mol. Cell 82, 1288–1296.e5 (2022).Young, L. C. et al. Destabilizing NF1 variants act in a dominant negative manner through neurofibromin dimerization. Proc. Natl Acad. Sci. USA 120, e2208960120 (2023).Article .

Chaker-Margot，M.等人。肿瘤抑制蛋白神经纤维蛋白激活的结构基础。分子细胞821288-1296.e5（2022）。Young，L.C.等人。不稳定的NF1变体通过神经纤维蛋白二聚化以显性负性方式起作用。程序。国家科学院。科学。美国120，e2208960120（2023）。文章。

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Zhang, Y. & Skolnick, J. TM-align: a protein structure alignment algorithm based on the tm-score. Nucleic acids Res. 33, 2302–2309 (2005).Article

Zhang，Y。＆Skolnick，J。TM align：基于TM评分的蛋白质结构比对算法。核酸研究332302-2309（2005）。文章

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Mirabello, C. lDDT-align: A Tool to Align Protein Structures While Maximizing lddt. https://github.com/clami66/lDDT_align (2022).Li, Z., Nguyen, S. P., Xu, D. & Shang, Y. Protein loop modeling using deep generative adversarial network. In 2017 IEEE 29th International Conference on Tools with Artificial Intelligence (ICTAI).

Mirabello，C。lDDT-align：一种在最大化lDDT的同时对齐蛋白质结构的工具。https://github.com/clami66/lDDT_align（2022年）。Li，Z.，Nguyen，S.P.，Xu，D。＆Shang，Y。使用深度生成对抗网络进行蛋白质环建模。2017年IEEE第29届人工智能工具国际会议（ICTAI）。

1085–1091 (IEEE, 2017).Anand, N. & Huang, P. Generative modeling for protein structures. Adv. Neural Inform. Process. Syst. https://doi.org/10.1038/s41587-023-02115-w (2018).Wang, J. et al. Scaffolding protein functional sites using deep learning. Science 377, 387–394 (2022).Article .

1085-1091（IEEE，2017）。Anand，N。＆Huang，P。蛋白质结构的生成建模。高级神经信息。过程。系统。https://doi.org/10.1038/s41587-023-02115-w（2018年）。Wang，J。等人。使用深度学习构建蛋白质功能位点。科学377387-394（2022）。文章。

ADS

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Baek, M. et al. Accurate prediction of protein structures and interactions using a three-track neural network. Science 373, 871–876 (2021).Article

Baek，M.等人，《使用三轨神经网络精确预测蛋白质结构和相互作用》，《科学》373871–876（2021）。文章

ADS

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Lai, B., McPartlon, M. & Xu, J. End-to-end deep structure generative model for protein design. bioRxiv https://doi.org/10.1101/2022.07.09.499440 (2022).Zhang, C. et al. Framedipt: Se (3) diffusion model for protein structure inpainting. bioRxiv https://doi.org/10.1101/2023.11.21.568057 (2023).Collins, K.

Lai，B.，McPartlon，M。＆Xu，J。蛋白质设计的端到端深层结构生成模型。生物十四https://doi.org/10.1101/2022.07.09.499440（2022年）。Zhang，C。等。Framedipt：用于蛋白质结构修复的Se（3）扩散模型。生物十四https://doi.org/10.1101/2023.11.21.568057（2023年）。柯林斯，K。

W. et al. Dockground resource for protein recognition studies. Protein Sci. 31, e4481 (2022).Article .

W、等人。用于蛋白质识别研究的DockRound资源。。31，e4481（2022）。文章。

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Mukherjee, S. & Zhang, Y. Mm-align: a quick algorithm for aligning multiple-chain protein complex structures using iterative dynamic programming. Nucleic Acids Res. 37, e83–e83 (2009).Article

Mukherjee，S。＆Zhang，Y。Mm align：使用迭代动态规划对齐多链蛋白质复杂结构的快速算法。核酸研究37，e83–e83（2009）。文章

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

van Kempen, M. et al. Foldseek: fast and accurate protein structure search. Biorxiv https://doi.org/10.1101/2022.02.07.479398 (2022).Wallner, B. Improved multimer prediction using massive sampling with Alphafold in casp15. Proteins Struct. Function Bioinform. 91, 1734–1746 (2023).Zhang, Y.

van Kempen，M.等人，《Foldseek：快速准确的蛋白质结构搜索》。生物十四https://doi.org/10.1101/2022.02.07.479398（2022年）。Wallner，B。在casp15中使用Alphafold进行大规模采样，改进了多聚体预测。蛋白质结构。功能Bioinform。911734-1746（2023）。张，Y。

& Skolnick, J. Scoring function for automated assessment of protein structure template quality. Proteins Struct. Funct. Bioinform. 57, 702–710 (2004).Article .

&Skolnick，J。用于自动评估蛋白质结构模板质量的评分功能。蛋白质结构。函数。生物信息。57702-710（2004）。文章。

Google Scholar

谷歌学者

Pintilie, G. et al. Measurement of atom resolvability in cryo-em maps with q-scores. Nat. Methods 17, 328–334 (2020).Article

Pintilie，G。等人。用q分数测量低温电磁图中的原子分辨率。自然方法17328-334（2020）。文章

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Mirabello, C. Alphafold unmasked: integration of experiments and predictions in multimeric complexes. Zenodo https://doi.org/10.5281/zenodo.13364959 (2024).Download referencesAcknowledgementsThis work was funded by SciLifeLab as a Technology Development Project (BeyondFold), and by the SciLifeLab platforms National Bioinformatics Infrastructure Sweden (NBIS), Cellular and Molecular Imaging (CMI), and Integrated Structural Biology (ISB).

Mirabello，C。Alphafold unmasked：在多聚体复合物中整合实验和预测。泽诺多https://doi.org/10.5281/zenodo.13364959（2024年）。下载参考文献致谢这项工作由SciLifeLab作为技术开发项目（BeyondFold）以及瑞典国家生物信息学基础设施（NBIS），细胞和分子成像（CMI）和综合结构生物学（ISB）的SciLifeLab平台资助。

CM is financially supported by the Knut and Alice Wallenberg (KAW) Foundation as part of NBIS at SciLifeLab. SA is financially supported by KAW grant KAW2021.0347 to MC. MC is financially supported by SciLifeLab as part of the Cryo-EM National Infrastructure Unit and by the Stiftelsen för Strategisk Forskning (SSF) grant RIF-21.

CM由Knut和Alice Wallenberg（KAW）基金会作为SciLifeLab NBIS的一部分提供财政支持。SA由KAW grant KAW2021.0347向MC提供财务支持。MC由SciLifeLab作为Cryo-EM国家基础设施部门的一部分以及Stiftelsen för Strategisk Forskning（SSF）grant RIF-21提供财务支持。

BW is financially supported by KAW as part of the WASP-DDLS joint program. Computations were performed at NSC Tetralith provided by the National Academic Infrastructure for Supercomputing in Sweden (NAISS) and the Swedish National Infrastructure for Computing (SNIC), partially funded by the Swedish Research Council through grant agreements no.

作为WASP-DDLS联合计划的一部分，BW得到了KAW的财政支持。计算是在瑞典国家超级计算学术基础设施（NAISS）和瑞典国家计算基础设施（SNIC）提供的NSC Tetralith上进行的，部分资金由瑞典研究委员会通过第号赠款协议提供。

2022-06725 and no. 2018-05973, and at NSC BerzeLiUs provided by the National Supercomputer Centre (NSC) and funded by KAW. We would also like to thank Dr. Nicholas Pearce, Dr. Yogesh Kalakoti, Dr. Tim Schulte, Dr. Piotr Draczkowski and Nicholas Debouver for useful feedback throughout the study and during the development of manuscript and code.FundingOpen access funding provided by Linköping University.Author informationAuthors and AffiliationsDept of Physics, Chemistry and Biology, National Bioinformatics Infrastructure Sweden, Science for Life Laboratory, Linköping University, 581 83, Linköping, SwedenClaudio MirabelloDept of Physics, Chemistry and Biology,.

2022-06725和编号2018-05973，以及由国家超级计算机中心（NSC）提供并由KAW资助的NSC BerzeLiUs。我们还要感谢Nicholas Pearce博士，Yogesh Kalakoti博士，Tim Schulte博士，Piotr Draczkowski博士和Nicholas Debouver博士在整个研究过程中以及在手稿和代码开发过程中提供的有用反馈。。作者信息作者和附属机构瑞典国家生物信息学基础设施物理，化学和生物学研究所，生命科学实验室，林克平大学，581 83，林克平，瑞典物理，化学和生物学研究所，。

PubMed Google ScholarBjörn WallnerView author publicationsYou can also search for this author in

PubMed Google ScholarBjörn WallnerView作者出版物您也可以在

PubMed Google ScholarBjörn NystedtView author publicationsYou can also search for this author in

PubMed Google ScholarBjörn NystedtView作者出版物您也可以在

PubMed Google ScholarStavros AzinasView author publicationsYou can also search for this author in

PubMed Google ScholarMarta CarroniView author publicationsYou can also search for this author in

PubMed Google ScholarMarta CarroniView作者出版物您也可以在

PubMed Google ScholarContributionsC.M. and B.W. conceived the study. C.M. designed and implemented the tool, performed analyses of results, developed the manuscript, supervised the project. B.N. supervised the project development and provided funding. S.A. and M.C. performed analyses of Cryo-EM test cases.

PubMed谷歌学术贡献中心。M、 B.W.构思了这项研究。C、 M.设计并实施了该工具，对结果进行了分析，编写了手稿，监督了该项目。B、 N.监督项目开发并提供资金。S、 A.和M.C.对低温电磁测试案例进行了分析。

M.C. supervised the Cryo-EM analyses and developed the manuscript.Corresponding authorCorrespondence to.

M、 C.监督Cryo-EM分析并编写了手稿。对应作者对应。

Claudio Mirabello.Ethics declarations

克劳迪奥·米拉贝洛。道德宣言

Competing interests

相互竞争的利益

The authors declare no competing interests.

作者声明没有利益冲突。

Peer review

同行评审

Peer review information

同行评审信息

Nature Communications thanks the anonymous reviewers for their contribution to the peer review of this work. A peer review file is available.

Nature Communications感谢匿名审稿人对这项工作的同行评审做出的贡献。可以获得同行评审文件。

Additional informationPublisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.Supplementary informationSupplementary InformationPeer Review FileDescription of Additional Supplementary FilesSupplementary Movie 1Supplementary Movie 2Supplementary Movie 3Reporting SummarySource dataSource DataRights and permissions.

Additional informationPublisher的注释Springer Nature在已发布地图和机构隶属关系中的管辖权主张方面保持中立。补充信息补充信息同行评审文件其他补充文件的描述补充电影1补充电影2补充电影3报告摘要源数据源数据权限和权限。

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made.

开放获取本文是根据知识共享署名4.0国际许可证授权的，该许可证允许以任何媒体或格式使用，共享，改编，分发和复制，只要您对原始作者和来源给予适当的信任，提供知识共享许可证的链接，并指出是否进行了更改。

The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.

To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/..

要查看此许可证的副本，请访问http://creativecommons.org/licenses/by/4.0/..

Reprints and permissionsAbout this articleCite this articleMirabello, C., Wallner, B., Nystedt, B. et al. Unmasking AlphaFold to integrate experiments and predictions in multimeric complexes.

转载和许可本文引用本文Mirabello，C.，Wallner，B.，Nystedt，B。等人揭露AlphaFold以整合多聚体复合物中的实验和预测。

Nat Commun 15, 8724 (2024). https://doi.org/10.1038/s41467-024-52951-wDownload citationReceived: 13 May 2024Accepted: 26 September 2024Published: 09 October 2024DOI: https://doi.org/10.1038/s41467-024-52951-wShare this articleAnyone you share the following link with will be able to read this content:Get shareable linkSorry, a shareable link is not currently available for this article.Copy to clipboard.

《国家公社》158724（2024）。https://doi.org/10.1038/s41467-024-52951-wDownload引文接收日期：2024年5月13日接受日期：2024年9月26日发布日期：2024年10月9日OI：https://doi.org/10.1038/s41467-024-52951-wShare本文与您共享以下链接的任何人都可以阅读此内容：获取可共享链接对不起，本文目前没有可共享的链接。。

Provided by the Springer Nature SharedIt content-sharing initiative

由Springer Nature SharedIt内容共享计划提供

CommentsBy submitting a comment you agree to abide by our Terms and Community Guidelines. If you find something abusive or that does not comply with our terms or guidelines please flag it as inappropriate.

评论通过提交评论，您同意遵守我们的条款和社区指南。如果您发现有虐待行为或不符合我们的条款或准则，请将其标记为不合适。

全球产业链接平台

重庆市渝北区金星科技大厦A区5楼512室

联系电话：023-67139735（重庆）

关于我们

产品服务