{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T21:19:55Z","timestamp":1792790395856,"version":"4.5.0"},"posted":{"date-parts":[[2026,9,7]]},"group-title":"Bioinformatics","reference-count":31,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T00:00:00Z","timestamp":1788739200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"award":["W911NF-22-2-0246"],"award-info":[{"award-number":["W911NF-22-2-0246"]}],"id":[{"id":"https:\/\/ror.org\/05epdh915","id-type":"ROR","asserted-by":"publisher"}]},{"name":"U.S. National Science Foundation","award":["TIP-2448820"],"award-info":[{"award-number":["TIP-2448820"]}],"id":[{"id":"https:\/\/ror.org\/021nxhr62","id-type":"ROR","asserted-by":"crossref"}]},{"name":"U.S. National Science Foundation","award":["DGE-2146755"],"award-info":[{"award-number":["DGE-2146755"]}],"id":[{"id":"https:\/\/ror.org\/021nxhr62","id-type":"ROR","asserted-by":"crossref"}]},{"award":["GM153195"],"award-info":[{"award-number":["GM153195"]}],"id":[{"id":"https:\/\/ror.org\/01cwqze88","id-type":"ROR","asserted-by":"publisher"}]},{"award":["GM102365"],"award-info":[{"award-number":["GM102365"]}],"id":[{"id":"https:\/\/ror.org\/01cwqze88","id-type":"ROR","asserted-by":"publisher"}]},{"award":["AG089509"],"award-info":[{"award-number":["AG089509"]}],"id":[{"id":"https:\/\/ror.org\/01cwqze88","id-type":"ROR","asserted-by":"publisher"}]},{"name":"Burroughs Wellcome Fund","award":["1074128"],"award-info":[{"award-number":["1074128"]}],"id":[{"id":"https:\/\/ror.org\/01d35cw23","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Stanford Graduate Fellowship"},{"name":"Stanford Medical Scholars"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,9,11]]},"abstract":"<jats:label>1<\/jats:label>\n                <jats:title>Abstract<\/jats:title>\n                <jats:p>\n                  Protein engineering has important implications in the bioeconomy, enabling applications in materials, medicine, and energy. A key challenge is designing protein sequences that have a specific form and function. Protein inverse folding seeks to address this challenge by identifying amino acid sequences compatible with a desired protein backbone. This task is central to protein redesign and can provide a sequence-design capability for de novo backbones produced by structure-generation methods. Ideally, inverse folding can provide diverse sequence alternatives, fixed residues or motifs, soft biochemical preferences at selected positions, and candidates that remain experimentally useful. We developed Inverse FoldDir, a controllable inverse-folding method that performs iterative denoising on the amino acid probability simplex. Given a backbone structure, the model updates all positions jointly through a learned Dirichlet flow, supporting full sequence generation, fixed-residue inpainting, and user-defined soft residue priors. On the held-out CATH 4.2 test set, Inverse FoldDir achieved a mean TM-score of 84.5 (on a 0-100 scale) and a mean C\n                  <jats:italic>\u03b1<\/jats:italic>\n                  RMSD of 1.76 \u00c5, compared with 83.3 and 1.86 \u00c5, respectively, for ESM-IF1, the strongest evaluated baseline on both metrics. Denoising trajectory analyses showed that positions commit at different rates and that some residues change identity late in generation, illustrating whole-sequence refinement rather than one-shot prediction or irreversible sequential decoding. We experimentally tested Inverse FoldDir in an anti-GFP nanobody redesign task, where two of 35 redesigned sequences retained reproducible sfGFP-binding signal across independent assay runs with approximately 43% sequence divergence from the native nanobody. Inverse FoldDir is a structure-conditioned protein redesign method that combines structural recovery, user control, experimental validation, and a natural route toward future property-guided sampling.\n                <\/jats:p>","DOI":"10.64898\/2026.09.06.749733","type":"posted-content","created":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T06:00:19Z","timestamp":1788847219000},"source":"Crossref","is-referenced-by-count":0,"title":["Inverse FoldDir: Structure-conditioned Protein Sequence Design by Dirichlet Flow Matching"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-1885-0077","authenticated-orcid":false,"given":"Alp","family":"Tartici","sequence":"first","affiliation":[{"name":"Department of Genetics, Stanford University, Stanford, CA 94305, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mihajlo","family":"Stojkovic","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Stanford University, Stanford, CA 94305, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anru","family":"Tian","sequence":"additional","affiliation":[{"name":"Department of Bioengineering, Stanford University, Stanford, CA 94305, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2948-6211","authenticated-orcid":false,"given":"Michael C.","family":"Jewett","sequence":"additional","affiliation":[{"name":"Department of Bioengineering, Stanford University, Stanford, CA 94305, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3859-2905","authenticated-orcid":false,"given":"Russ B.","family":"Altman","sequence":"additional","affiliation":[{"name":"Department of Genetics, Stanford University, Stanford, CA 94305, USA"},{"name":"Department of Bioengineering, Stanford University, Stanford, CA 94305, USA"},{"name":"Department of Biomedical Data Science, Stanford University, Stanford, CA 94305, USA"},{"name":"Department of Medicine, Stanford University, Stanford, CA 94304, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8144-9157","authenticated-orcid":false,"given":"Bruce J.","family":"Wittmann","sequence":"additional","affiliation":[{"name":"Office of the Chief Scientific Officer, Microsoft, Redmond, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026091620502104000_2026.09.06.749733v2.1","unstructured":"John Ingraham , Vikas Garg , Regina Barzilay , and Tommi Jaakkola . Generative models for graph-based protein design. Advances in neural information processing systems, 32, 2019."},{"key":"2026091620502104000_2026.09.06.749733v2.2","doi-asserted-by":"crossref","unstructured":"Chloe Hsu , Robert Verkuil , Jason Liu , Zeming Lin , Brian Hie , Tom Sercu , Adam Lerer , and Alexander Rives . Learning inverse folding from millions of predicted structures. In International conference on machine learning, pages 8946\u20138970. PMLR, 2022.","DOI":"10.1101\/2022.04.10.487779"},{"key":"2026091620502104000_2026.09.06.749733v2.3","doi-asserted-by":"publisher","DOI":"10.1126\/science.abn2100"},{"key":"2026091620502104000_2026.09.06.749733v2.4","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-05696-3"},{"issue":"1","key":"2026091620502104000_2026.09.06.749733v2.5","first-page":"vbae202","article-title":"AntiFold: improved structure-based antibody design using inverse folding","volume":"5","year":"2025","journal-title":"Bioinformatics Advances"},{"key":"2026091620502104000_2026.09.06.749733v2.6","doi-asserted-by":"publisher","DOI":"10.1126\/science.add2187"},{"key":"2026091620502104000_2026.09.06.749733v2.7","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06415-8"},{"key":"2026091620502104000_2026.09.06.749733v2.8","doi-asserted-by":"crossref","unstructured":"Justas Dauparas , Gyu Rie Lee , Robert Pecoraro , Linna An , Ivan Anishchenko , Cameron Glasscock , and David Baker . Atomic context-conditioned protein sequence design using ligandmpnn. Nature Methods, pages 1\u20137, 2025.","DOI":"10.1038\/s41592-025-02626-1"},{"key":"2026091620502104000_2026.09.06.749733v2.9","unstructured":"Talal Widatalla , Richard W Shuai , Brian Hie , and Possu Huang . Sidechain conditioning and modeling for full-atom protein sequence design with fampnn. In Forty-second International Conference on Machine Learning, 2025."},{"key":"2026091620502104000_2026.09.06.749733v2.10","unstructured":"Zhangyang Gao , Cheng Tan , Pablo Chac\u00f3n , and Stan Z Li . Pifold: Toward effective and efficient protein inverse folding. arXiv preprint arXiv:2209.12643, 2022."},{"key":"2026091620502104000_2026.09.06.749733v2.11","unstructured":"Hannes Stark , Bowen Jing , Chenyu Wang , Gabriele Corso , Bonnie Berger , Regina Barzilay , and Tommi Jaakkola . Dirichlet flow matching with applications to dna sequence design. arXiv preprint arXiv:2402.05841, 2024."},{"key":"2026091620502104000_2026.09.06.749733v2.12","unstructured":"Pavel Avdeyev , Chenlai Shi , Yuhao Tan , Kseniia Dudnyk , and Jian Zhou . Dirichlet diffusion score model for biological sequence generation. In International Conference on Machine Learning, pages 1276\u20131301. PMLR, 2023."},{"issue":"12","key":"2026091620502104000_2026.09.06.749733v2.13","doi-asserted-by":"crossref","first-page":"2577","DOI":"10.1002\/bip.360221211","article-title":"Dictionary of protein secondary structure: pattern recognition of hydrogen-bonded and geometrical features","volume":"22","year":"1983","journal-title":"Biopolymers: Original Research on Biomolecules"},{"key":"2026091620502104000_2026.09.06.749733v2.14","first-page":"500902","article-title":"Allan dos Santos Costa, Maryam Fazel-Zarandi, Tom Sercu, Sal Candido","volume":"2022","year":"2022","journal-title":"Language models of protein sequences at the scale of evolution enable accurate structure prediction. BioRxiv"},{"key":"2026091620502104000_2026.09.06.749733v2.15","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gki524"},{"key":"2026091620502104000_2026.09.06.749733v2.16","unstructured":"Peizhen Bai , Filip Miljkovic , Xianyuan Liu , Leonardo De Maria , Rebecca Croasdale-Wood , Owen Rackham , and Haiping Lu . Mask-prior-guided denoising diffusion improves inverse protein folding. Nature Machine Intelligence, pages 1\u201313, 2025."},{"key":"2026091620502104000_2026.09.06.749733v2.17","first-page":"64331","article-title":"Proteingym: Large-scale benchmarks for protein fitness prediction and design","volume":"36","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2026091620502104000_2026.09.06.749733v2.18","doi-asserted-by":"publisher","DOI":"10.1002\/pro.519"},{"key":"2026091620502104000_2026.09.06.749733v2.19","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.91.12.5426"},{"key":"2026091620502104000_2026.09.06.749733v2.20","doi-asserted-by":"crossref","unstructured":"Saro Passaro , Gabriele Corso , Jeremy Wohlwend , Mateo Reveiz , Stephan Thaler , Vignesh Ram Somnath , Noah Getz , Tally Portnoi , Julien Roy , Hannes Stark , et al. Boltz-2: Towards accurate and efficient binding affinity prediction. BioRxiv, 2025.","DOI":"10.1101\/2025.06.14.659707"},{"key":"2026091620502104000_2026.09.06.749733v2.21","doi-asserted-by":"publisher","DOI":"10.1093\/NAR\/GKAB1061"},{"key":"2026091620502104000_2026.09.06.749733v2.22","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06510-w"},{"key":"2026091620502104000_2026.09.06.749733v2.23","unstructured":"Bowen Jing , Stephan Eismann , Patricia Suriana , Raphael JL Townshend , and Ron Dror . Learning from protein structure with geometric vector perceptrons. arXiv preprint arXiv:2009.01411, 2020."},{"key":"2026091620502104000_2026.09.06.749733v2.24","doi-asserted-by":"crossref","unstructured":"Michel van Kempen , Stephanie S Kim , Charlotte Tumescheit , Milot Mirdita , Cameron LM Gilchrist , Johannes S\u00f6ding , and Martin Steinegger . Foldseek: fast and accurate protein structure search. Biorxiv, pages 2022\u201302, 2022.","DOI":"10.1101\/2022.02.07.479398"},{"key":"2026091620502104000_2026.09.06.749733v2.25","doi-asserted-by":"publisher","DOI":"10.1038\/msb.2008.57"},{"key":"2026091620502104000_2026.09.06.749733v2.26","doi-asserted-by":"crossref","first-page":"8663","DOI":"10.1038\/srep08663","article-title":"High-throughput preparation methods of crude extract for robust cell-free protein synthesis","volume":"5","year":"2015","journal-title":"Scientific Reports"},{"issue":"7","key":"2026091620502104000_2026.09.06.749733v2.27","doi-asserted-by":"crossref","first-page":"2374","DOI":"10.1038\/s41596-022-00799-z","article-title":"Rapid biosynthesis of glycoprotein therapeutics and vaccines from freeze-dried bacterial cell lysates","volume":"18","year":"2023","journal-title":"Nature Protocols"},{"key":"2026091620502104000_2026.09.06.749733v2.28","doi-asserted-by":"publisher","DOI":"10.1002\/bit.20026"},{"key":"2026091620502104000_2026.09.06.749733v2.29","doi-asserted-by":"crossref","first-page":"3478","DOI":"10.1038\/s41467-026-69605-8","article-title":"Design-driven optimization of low-cost reagent formulations for reproducible and high-yielding cell-free gene expression","volume":"17","year":"2026","journal-title":"Nature Communications"},{"key":"2026091620502104000_2026.09.06.749733v2.30","doi-asserted-by":"publisher","DOI":"10.1126\/scitranslmed.abn1252"},{"key":"2026091620502104000_2026.09.06.749733v2.31","doi-asserted-by":"crossref","first-page":"3897","DOI":"10.1038\/s41467-023-38965-w","article-title":"A rapid cell-free expression and screening platform for antibody discovery","volume":"14","year":"2023","journal-title":"Nature Communications"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.09.06.749733","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T03:50:42Z","timestamp":1789617042000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.64898\/2026.09.06.749733"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,7]]},"references-count":31,"URL":"https:\/\/doi.org\/10.64898\/2026.09.06.749733","relation":{},"subject":[],"published":{"date-parts":[[2026,9,7]]},"subtype":"preprint"}}