{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,15]],"date-time":"2025-08-15T02:00:12Z","timestamp":1755223212361,"version":"3.43.0"},"reference-count":49,"publisher":"Wiley","issue":"5","license":[{"start":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T00:00:00Z","timestamp":1745280000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["92249303"],"award-info":[{"award-number":["92249303"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Protein Science"],"published-print":{"date-parts":[[2025,5]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Deep learning methods have played an increasingly pivotal role in advancing side\u2010chain packing and mutation effect prediction (\u0394\u0394<jats:italic>G<\/jats:italic>) for protein complexes. Although these two tasks are inherently closely related, they are typically treated separately in practice. Furthermore, the lack of effective post\u2010processing in most approaches results in sub\u2010optimal refinement of generated conformations, limiting the plausibility of the predicted conformations. In this study, we introduce an integrated framework, PackPPI, which employs a diffusion model and a proximal optimization algorithm to improve side\u2010chain prediction for protein complexes while using learned representations to predict \u0394\u0394<jats:italic>G<\/jats:italic>. The results demonstrate that PackPPI achieved the lowest atom RMSD (0.9822) on the CASP15 dataset. The proximal optimization algorithm effectively reduces spatial clashes between side\u2010chain atoms while maintaining a low\u2010energy landscape. Furthermore, PackPPI achieves state\u2010of\u2010the\u2010art performance in predicting binding affinity changes induced by multi\u2010point mutations on the SKEMPI v2.0 dataset. These findings underscore the potential of PackPPI as a robust and versatile computational tool for protein design and engineering. The implementation of PackPPI is available at <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/github.com\/Jackz915\/PackPPI\">https:\/\/github.com\/Jackz915\/PackPPI<\/jats:ext-link>.<\/jats:p>","DOI":"10.1002\/pro.70110","type":"journal-article","created":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T08:45:27Z","timestamp":1745311527000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["<scp>PackPPI<\/scp>: An integrated framework for protein\u2013protein complex side\u2010chain packing and <scp>\u0394\u0394<i>G<\/i><\/scp> prediction based on diffusion model"],"prefix":"10.1002","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-5943-0975","authenticated-orcid":false,"given":"Jingkai","family":"Zhang","sequence":"first","affiliation":[{"name":"State Key Laboratory of Biocontrol School of Life Sciences, Sun Yat\u2010sen University  Guangzhou China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanyan","family":"Xiong","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Biocontrol School of Life Sciences, Sun Yat\u2010sen University  Guangzhou China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2025,4,22]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0258173"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1089\/106652702760277336"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-023-00701-3"},{"key":"e_1_2_9_5_1","unstructured":"BakerJ XiaH WangY et al.Proximal implicit ODE solvers for accelerating learning neural ODEs. arxiv preprint arxiv:2204.08621.2022."},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCBB.2023.3262119"},{"key":"e_1_2_9_7_1","first-page":"2984","volume-title":"Conference on learning theory PMLR","author":"Chen Y","year":"2022"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.biochem.77.062906.171838"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1002\/prot.24555"},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.1002\/prot.25030"},{"key":"e_1_2_9_11_1","unstructured":"GaneaOE HuangX BunneC et al.Independent se (3)\u2010equivariant models for end\u2010to\u2010end rigid protein docking. arxiv preprint arxiv:2111.07786.2021."},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btaa234"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bty635"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCBB.2022.3233627"},{"key":"e_1_2_9_15_1","first-page":"46","article-title":"Side\u2010chain packing using SE (3)\u2010transformer","volume":"2021","author":"Jindal A","year":"2022","journal-title":"Pacific Symposium on Biocomputing"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-03819-2"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1006342"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1002\/prot.22488"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1002\/prot.26237"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1002\/prot.26617"},{"key":"e_1_2_9_21_1","unstructured":"LiangJ ChenY.A proximal algorithm for sampling. Arxiv preprint: 2202.139752022."},{"key":"e_1_2_9_22_1","unstructured":"LinZ AkinH RaoR et al.Language models of protein sequences at the scale of evolution enable accurate structure prediction. BioRxiv: 2022: 5009022022."},{"key":"e_1_2_9_23_1","first-page":"120","volume-title":"IEEE international conference on bioinformatics and biomedicine (BIBM)","author":"Liu D","year":"2023"},{"key":"e_1_2_9_24_1","first-page":"48994","article-title":"Predicting mutational effects on protein\u2013protein binding via a side\u2010chain diffusion probabilistic model","volume":"36","author":"Liu S","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1009284"},{"key":"e_1_2_9_26_1","doi-asserted-by":"crossref","unstructured":"LuoS SuY WuZ et al.Rotamer density estimator is an unsupervised learner of the effect of mutations on protein\u2010protein interaction. bioRxiv: 2023.02. 28.5301372023.","DOI":"10.1101\/2023.02.28.530137"},{"key":"e_1_2_9_27_1","unstructured":"MaJ ZhaoP XuT et al.Reducing atomic clashes in geometric diffusion models for 3D structure\u2010based drug design.2023."},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cam.2015.06.002"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.1002\/prot.26311"},{"key":"e_1_2_9_30_1","doi-asserted-by":"crossref","unstructured":"MukhopadhyayA KadanA McMasterB et al.ZymePackNet: rotamer\u2010sampling free graph neural network method for protein sidechain prediction. bioRxiv: 2023.05.05.5396482023.","DOI":"10.1101\/2023.05.05.539648"},{"key":"e_1_2_9_31_1","unstructured":"PengJ HosurR BergerB et al.iTreePack: protein complex side\u2010chain packing by dual decomposition. Arxiv Preprint:1504.054672015."},{"key":"e_1_2_9_32_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jpclett.3c02679"},{"key":"e_1_2_9_33_1","doi-asserted-by":"publisher","DOI":"10.1002\/prot.26705"},{"key":"e_1_2_9_34_1","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkab273"},{"key":"e_1_2_9_35_1","doi-asserted-by":"publisher","DOI":"10.1039\/9781788016544"},{"key":"e_1_2_9_36_1","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gki387"},{"key":"e_1_2_9_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.str.2011.03.019"},{"key":"e_1_2_9_38_1","doi-asserted-by":"publisher","DOI":"10.1002\/wcms.1448"},{"key":"e_1_2_9_39_1","doi-asserted-by":"publisher","DOI":"10.1002\/pro.2829"},{"key":"e_1_2_9_40_1","unstructured":"SongY Sohl\u2010DicksteinJ KingmaDP et al.Score\u2010based generative modeling through stochastic differential equations. Arxiv preprint: 2011.134562020."},{"key":"e_1_2_9_41_1","first-page":"20503","volume-title":"International conference on machine learning","author":"St\u00e4rk H","year":"2022"},{"key":"e_1_2_9_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2020.08.012"},{"key":"e_1_2_9_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csbj.2020.02.007"},{"key":"e_1_2_9_44_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-0149-6"},{"key":"e_1_2_9_45_1","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbac330"},{"key":"e_1_2_9_46_1","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbad257"},{"key":"e_1_2_9_47_1","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbad310"},{"key":"e_1_2_9_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.isci.2020.100939"},{"key":"e_1_2_9_49_1","first-page":"48150","article-title":"Diffpack: a torsional diffusion model for autoregressive protein side\u2010chain packing","volume":"36","author":"Zhang Y","year":"2024","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_2_9_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3614893"}],"container-title":["Protein Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/pro.70110","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,11]],"date-time":"2025-08-11T12:38:47Z","timestamp":1754915927000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/pro.70110"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,22]]},"references-count":49,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,5]]}},"alternative-id":["10.1002\/pro.70110"],"URL":"https:\/\/doi.org\/10.1002\/pro.70110","archive":["Portico"],"relation":{},"ISSN":["0961-8368","1469-896X"],"issn-type":[{"type":"print","value":"0961-8368"},{"type":"electronic","value":"1469-896X"}],"subject":[],"published":{"date-parts":[[2025,4,22]]},"assertion":[{"value":"2024-11-04","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-03-17","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-04-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70110"}}