pith. sign in

arxiv: 2606.12991 · v1 · pith:RYHGNGLSnew · submitted 2026-06-11 · 💻 cs.AI

APCyc: Property-Informed Design of Cyclic Peptides via Automated Cyclization

Yifan Zhao , Lang Qin , Jintai Chen This is my paper

Pith reviewed 2026-06-27 06:45 UTC · model grok-4.3

classification 💻 cs.AI
keywords cyclic peptidesde novo designgenerative modelsproperty optimizationcyclization modelingBayesian guidancepeptide therapeuticsmulti-objective design
0
0 comments X

The pith

APCyc generates cyclic peptides by explicitly modeling cyclization and jointly optimizing multiple physicochemical properties.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper presents APCyc as a way to overcome the failure of linear-peptide generative models to capture cyclization-specific constraints when designing therapeutic cyclic peptides. It expands the residue vocabulary, explicitly encodes cyclization sites and linkage types, and applies Bayesian posterior guidance to steer generation toward target-adapted structures that satisfy several property objectives at once. A sympathetic reader would care because cyclic peptides often show better stability and binding than linear ones, yet de novo design has remained difficult due to the need to choose both sequence and cyclization pattern simultaneously. If the approach works, it produces controllable, property-optimized cyclic peptides for specific protein targets without manual post-processing of linear outputs.

Core claim

APCyc is a target-aware de novo cyclic peptide generation framework that explicitly models cyclization and jointly optimizes multiple essential physicochemical properties. By using an expanded residue vocabulary and explicitly encoding cyclization-site and linkage-type information, APCyc learns cyclization-aware representations and leverages Bayesian posterior guidance to steer sampling toward cyclic peptides satisfying multiple property objectives. Experimental results demonstrate that the model learns target-dependent cyclization preferences and enables effective and controllable multi-property optimization for cyclic peptide design.

What carries the argument

The APCyc framework, which expands the residue vocabulary and encodes cyclization-site and linkage-type information to learn cyclization-aware representations, combined with Bayesian posterior guidance for steering multi-property sampling.

If this is right

  • The model can generate cyclic peptides whose cyclization patterns adapt to specific protein binding pockets.
  • Users can steer generation toward peptides that meet chosen combinations of stability, solubility, and affinity objectives.
  • The learned representations distinguish cyclization preferences that depend on the target protein.
  • Generated sequences require less manual adjustment to form the intended cyclic structure.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same explicit-encoding strategy could be tested on other topologically constrained molecules such as stapled peptides or macrocycles.
  • If the Bayesian guidance scales, the framework might integrate with structure-prediction tools to close the loop between sequence generation and binding validation.
  • Target-dependent cyclization learning suggests the method could generalize to designing peptides for multiple related targets without retraining from scratch.

Load-bearing premise

Expanding the residue vocabulary and explicitly encoding cyclization-site and linkage-type information is sufficient for the model to capture cyclization-specific constraints that linear-peptide-trained models miss.

What would settle it

If side-by-side experiments on held-out targets show that APCyc-generated peptides do not achieve higher rates of valid cyclization or better simultaneous satisfaction of multiple property thresholds than linear-trained baselines, the claim that the explicit encoding captures the missing constraints would be falsified.

Figures

Figures reproduced from arXiv: 2606.12991 by Jintai Chen, Lang Qin, Yifan Zhao.

Figure 1
Figure 1. Figure 1: APCyc Concept. (A) The receptor pocket provides [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Sampling workflow of APCyc for pocket-conditioned cyclic peptide design. APCyc extracts a local receptor pocket [PITH_FULL_IMAGE:figures/full_fig_p004_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Cyclization topology information injection. APCyc [PITH_FULL_IMAGE:figures/full_fig_p005_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Overall comparison across different methods on [PITH_FULL_IMAGE:figures/full_fig_p006_4.png] view at source ↗
read the original abstract

Cyclic peptides represent a promising class of therapeutic compounds in modern drug discovery, often offering improved stability and binding affinity. However, the de novo design of cyclic peptides remains challenging because methods must identify pocket-adaptive cyclization patterns and linkage sites while simultaneously controlling drug-relevant properties. This challenge is particularly pronounced for recent generative models trained predominantly on linear peptide data, which may fail to capture cyclization-specific constraints. To address the limitation, we introduce APCyc, a target-aware de novo cyclic peptide generation framework that explicitly models cyclization and jointly optimizes multiple essential physicochemical properties. By using an expanded residue vocabulary and explicitly encoding cyclization-site and linkage-type information, APCyc learns cyclization-aware representations and leverages Bayesian posterior guidance to steer sampling toward cyclic peptides satisfying multiple property objectives. Experimental results demonstrate that our model learns target-dependent cyclization preferences, and enables effective and controllable multi-property optimization for cyclic peptide design. The source code of this paper is available at https://github.com/HKUSTGZ-ML4Health-Lab/APCyc.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 1 minor

Summary. The paper introduces APCyc, a target-aware de novo cyclic peptide generation framework. It expands the residue vocabulary and explicitly encodes cyclization-site and linkage-type information to learn cyclization-aware representations, then applies Bayesian posterior guidance to steer sampling toward peptides satisfying multiple physicochemical property objectives. The central claim is that experimental results demonstrate the model learns target-dependent cyclization preferences (distinct from linear-peptide models) and enables effective, controllable multi-property optimization for cyclic peptide design.

Significance. If the target-dependent learning claim holds with supporting evidence, the work would address a recognized limitation of linear-peptide generative models and provide a practical tool for designing cyclic peptides with improved stability and binding properties. The explicit encoding plus Bayesian guidance approach is a reasonable architectural choice, and the public code release is a positive contribution.

major comments (2)
  1. [Abstract] Abstract: The assertion that APCyc 'learns target-dependent cyclization preferences' rests on unspecified 'experimental results' but supplies no quantitative cross-target cyclization statistics, ablation removing target conditioning while retaining the explicit encoding, or attention/activation analysis. Without such evidence the claim that the model acquires target-conditioned patterns (rather than simply applying the hand-crafted encoding) does not follow and is load-bearing for the paper's novelty.
  2. [Abstract] Abstract: No baselines, validation metrics, dataset sizes, or experimental protocol details are reported, making it impossible to assess whether the claimed multi-property optimization is effective or controllable. This absence prevents evaluation of the central empirical claim.
minor comments (1)
  1. [Abstract] The GitHub link for source code is provided, which aids reproducibility.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the detailed feedback on the abstract. We agree that the abstract would be strengthened by incorporating more specific quantitative details and experimental information to better substantiate the central claims. We address each major comment below and will revise the abstract accordingly.

read point-by-point responses

  1. Referee: [Abstract] Abstract: The assertion that APCyc 'learns target-dependent cyclization preferences' rests on unspecified 'experimental results' but supplies no quantitative cross-target cyclization statistics, ablation removing target conditioning while retaining the explicit encoding, or attention/activation analysis. Without such evidence the claim that the model acquires target-conditioned patterns (rather than simply applying the hand-crafted encoding) does not follow and is load-bearing for the paper's novelty.

    Authors: We acknowledge that the abstract does not explicitly reference the supporting quantitative evidence. The manuscript reports experimental results demonstrating target-dependent cyclization patterns distinct from linear-peptide models, with supporting details in the results and analysis sections. To address the concern, we will revise the abstract to briefly cite key quantitative cross-target statistics and reference the ablation and attention analyses already present in the full paper. This will make the claim more self-contained without altering the underlying experiments. revision: yes

  2. Referee: [Abstract] Abstract: No baselines, validation metrics, dataset sizes, or experimental protocol details are reported, making it impossible to assess whether the claimed multi-property optimization is effective or controllable. This absence prevents evaluation of the central empirical claim.

    Authors: We agree that the abstract lacks these specifics, which limits immediate assessment. The full manuscript details the dataset, baselines, metrics, and protocol in the methods and experiments sections. We will revise the abstract to concisely include dataset size, primary baselines, key validation metrics, and a high-level protocol summary to enable better evaluation of the multi-property optimization results. revision: yes

Circularity Check

0 steps flagged

No circularity: claims rest on experimental outcomes, not self-referential derivations

full rationale

The paper introduces APCyc as a framework that expands residue vocabulary and explicitly encodes cyclization-site and linkage-type information, then states that experimental results demonstrate target-dependent cyclization preferences and multi-property optimization. No equations, parameter-fitting steps, or self-citations are shown that reduce any prediction or uniqueness claim back to the inputs by construction. The central assertions are presented as outcomes of unspecified experiments rather than mathematical identities or fitted renamings, making the derivation chain self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Only abstract available; no free parameters, axioms, or invented entities are described.

pith-pipeline@v0.9.1-grok · 5710 in / 974 out tokens · 20396 ms · 2026-06-27T06:45:46.847584+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

60 extracted references · 9 canonical work pages · 3 internal anchors

  1. [1]

    Benjamin Alexander Albert, Yunxiao Yang, Xiaoshan M Shao, Dipika Singh, Kellie N Smith, Valsamo Anagnostou, and Rachel Karchin. 2023. Deep neural networks predict class I major histocompatibility complex epitope presentation and transfer learn neoepitope immunogenicity.Nature machine intelligence5, 8 (2023), 861–872

    2023

  2. [2]

    Rebecca F Alford, Andrew Leaver-Fay, Jeliazko R Jeliazkov, Matthew J O’Meara, Frank P DiMaio, Hahnbeom Park, Maxim V Shapovalov, P Douglas Renfrew, Vikram K Mulligan, Kalli Kappel, et al . 2017. The Rosetta all-atom energy function for macromolecular modeling and design.Journal of chemical theory and computation13, 6 (2017), 3031–3048

    2017

  3. [3]

    Valentin Amrhein, Sander Greenland, and Blake McShane. 2019. Scientists rise up against statistical significance.Nature567, 7748 (2019), 305–307. Yifan Zhao, Lang Qin, and Jintai Chen

    2019

  4. [4]

    Arpit Bansal, Hong-Min Chu, Avi Schwarzschild, Soumyadip Sengupta, Micah Goldblum, Jonas Geiping, and Tom Goldstein. 2023. Universal guidance for diffusion models. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition. 843–852

    2023

  5. [5]

    Fan Bao, Min Zhao, Zhongkai Hao, Peiyao Li, Chongxuan Li, and Jun Zhu. 2022. Equivariant energy-guided sde for inverse molecular design.arXiv preprint arXiv:2209.15408(2022)

    work page arXiv 2022

  6. [6]

    Edmon Begoli, Tanmoy Bhattacharya, and Dimitri Kusnezov. 2019. The need for uncertainty quantification in machine-assisted medical decision making.Nature Machine Intelligence1, 1 (2019), 20–23

    2019

  7. [7]

    Suhaas Bhat, Kalyan Palepu, Lauren Hong, Joey Mao, Tianzheng Ye, Rema Iyer, Lin Zhao, Tianlai Chen, Sophia Vincoff, Rio Watson, et al. 2025. De novo design of peptide binders to conformationally diverse targets with contrastive language modeling.Science Advances11, 4 (2025), eadr8638

    2025

  8. [8]

    Arun Chandramohan, Hubert Josien, Tsz Ying Yuen, Ruchia Duggal, Diana Spiegelberg, Lin Yan, Yu-Chi Angela Juang, Lan Ge, Pietro G Aronica, Hung Yi Kristal Kaan, et al. 2024. Design-rules for stapled peptides with in vivo activity and their application to Mdm2/X antagonists.Nature communications15, 1 (2024), 489

    2024

  9. [9]

    Sidhartha Chaudhury, Sergey Lyskov, and Jeffrey J Gray. 2010. PyRosetta: a script-based interface for implementing molecular modeling algorithms using Rosetta.Bioinformatics26, 5 (2010), 689–691

    2010

  10. [10]

    Hyungjin Chung, Jeongsol Kim, Michael T Mccann, Marc L Klasky, and Jong Chul Ye. 2022. Diffusion posterior sampling for general noisy inverse problems.arXiv preprint arXiv:2209.14687(2022)

    work page internal anchor Pith review Pith/arXiv arXiv 2022

  11. [11]

    1999.Mathematical methods of statistics

    Harald Cramér. 1999.Mathematical methods of statistics. Vol. 9. Princeton university press

    1999

  12. [12]

    Kaycie Deyle, Xu-Dong Kong, and Christian Heinis. 2017. Phage selection of cyclic peptides for application in research and drug development.Accounts of chemical research50, 8 (2017), 1866–1874

    2017

  13. [13]

    Prafulla Dhariwal and Alexander Nichol. 2021. Diffusion models beat gans on image synthesis.Advances in neural information processing systems34 (2021), 8780–8794

    2021

  14. [14]

    Edward M Driggers, Stephen P Hale, Jinbo Lee, and Nicholas K Terrett. 2008. The exploration of macrocycles for drug discovery—an underexploited structural class.Nature Reviews Drug Discovery7, 7 (2008), 608–624

    2008

  15. [15]

    Peter Ertl, Bernhard Rohde, and Paul Selzer. 2000. Fast calculation of molecular polar surface area as a sum of fragment-based contributions and its application to the prediction of drug transport properties.Journal of medicinal chemistry43, 20 (2000), 3714–3717

    2000

  16. [16]

    Keld Fosgerau and Torsten Hoffmann. 2015. Peptide therapeutics: current status and future directions.Drug discovery today20, 1 (2015), 122–128

    2015

  17. [17]

    Diego Garcia Jimenez, Vasanthanathan Poongavanam, and Jan Kihlberg. 2023. Macrocycles in drug discovery—learning from the past for the future.Journal of medicinal chemistry66, 8 (2023), 5377–5396

    2023

  18. [18]

    Zuojun Guo, Bo Li, Li-Tien Cheng, Shenggao Zhou, J Andrew McCammon, and Jianwei Che. 2015. Identification of protein–ligand binding sites by the level-set variational implicit-solvent approach.Journal of Chemical Theory and Computation11, 2 (2015), 753–765

    2015

  19. [19]

    Christian Heinis, Trevor Rutherford, Stephan Freund, and Greg Winter. 2009. Phage-encoded combinatorial chemical libraries based on bicyclic peptides.Na- ture chemical biology5, 7 (2009), 502–507

    2009

  20. [20]

    Jonathan Ho and Tim Salimans. 2022. Classifier-free diffusion guidance.arXiv preprint arXiv:2207.12598(2022)

    work page internal anchor Pith review Pith/arXiv arXiv 2022

  21. [21]

    Xinjian Ji, Alexander L Nielsen, and Christian Heinis. 2024. Cyclic peptides for drug development.Angewandte Chemie136, 3 (2024), e202308251

    2024

  22. [22]

    Dapeng Jiang, Xiangzhe Kong, Jiaqi Han, Rui Jiao, Wenbing Huang, Stefano Ermon, Jianzhu Ma, and Yang Liu. 2025. Zero-Shot Cyclic Peptide Design via Composable Geometric Constraints. InProceedings of the 42nd International Conference on Machine Learning

    2025

  23. [23]

    John Jumper, Richard Evans, Alexander Pritzel, Tim Green, Michael Figurnov, Olaf Ronneberger, Kathryn Tunyasuvunakool, Russ Bates, Augustin Žídek, Anna Potapenko, et al. 2021. Highly accurate protein structure prediction with Al- phaFold.nature596, 7873 (2021), 583–589

    2021

  24. [24]

    Kelly L Keeling, Okki Cho, Denis B Scanlon, Grant W Booker, Andrew D Abell, and Kate L Wegener. 2016. The key position: influence of staple location on constrained peptide conformation and binding.Organic & biomolecular chemistry 14, 41 (2016), 9731–9735

    2016

  25. [25]

    Taegwan Kim, Eunbee Baek, and Jonghoon Kim. 2025. Exploring Macrocyclic Chemical Space: Strategies and Technologies for Drug Discovery.Pharmaceuti- cals18, 5 (2025), 617

    2025

  26. [26]

    Xiangzhe Kong, Wenbing Huang, and Yang Liu. 2023. End-to-end full-atom antibody design.arXiv preprint arXiv:2302.00203(2023)

    work page arXiv 2023

  27. [27]

    Xiangzhe Kong, Yinjun Jia, Wenbing Huang, and Yang Liu. 2024. Full-atom peptide design with geometric latent diffusion.Advances in Neural Information Processing Systems37 (2024), 74808–74839

    2024

  28. [28]

    Jack Kyte and Russell F Doolittle. 1982. A simple method for displaying the hydropathic character of a protein.Journal of molecular biology157, 1 (1982), 105–132

    1982

  29. [29]

    Jolene L Lau and Michael K Dunn. 2018. Therapeutic peptides: Historical perspec- tives, current development trends, and future directions.Bioorganic & medicinal chemistry26, 10 (2018), 2700–2707

    2018

  30. [30]

    Fuyi Li, Cong Wang, Xudong Guo, Tatsuya Akutsu, Geoffrey I Webb, Lachlan JM Coin, Lukasz Kurgan, and Jiangning Song. 2023. ProsperousPlus: a one-stop and comprehensive platform for accurate protease-specific substrate cleavage prediction and machine-learning model construction.Briefings in Bioinformatics 24, 6 (2023), bbad372

    2023

  31. [31]

    Jiahan Li, Tong Chen, Shitong Luo, Chaoran Cheng, Jiaqi Guan, Ruihan Guo, Sheng Wang, Ge Liu, Jian Peng, and Jianzhu Ma. 2024. Hotspot-driven peptide de- sign via multi-fragment autoregressive extension.arXiv preprint arXiv:2411.18463 (2024)

    work page arXiv 2024

  32. [32]

    Jiahan Li, Chaoran Cheng, Zuofan Wu, Ruihan Guo, Shitong Luo, Zhizhou Ren, Jian Peng, and Jianzhu Ma. 2024. Full-atom peptide design based on multi-modal flow matching.arXiv preprint arXiv:2406.00735(2024)

    work page arXiv 2024

  33. [33]

    Jianan Li, Keisuke Yanagisawa, and Yutaka Akiyama. 2024. CycPeptMP: en- hancing membrane permeability prediction of cyclic peptides with multi-level molecular features and data augmentation.Briefings in Bioinformatics25, 5 (2024)

    2024

  34. [34]

    Xinting Li, Timothy W Craven, and Paul M Levine. 2022. Cyclic peptide screening methods for preclinical drug discovery: miniperspective.Journal of Medicinal Chemistry65, 18 (2022), 11913–11926

    2022

  35. [35]

    Haitao Lin, Odin Zhang, Huifeng Zhao, Dejun Jiang, Lirong Wu, Zicheng Liu, Yufei Huang, and Stan Z Li. 2024. Ppflow: Target-aware peptide design with torsional flow matching.arXiv preprint arXiv:2405.06642(2024)

    work page arXiv 2024

  36. [36]

    Lei Liu, Liu Yang, Suqi Cao, Zhigang Gao, Bin Yang, Guoqing Zhang, Ruixin Zhu, and Dingfeng Wu. 2024. CyclicPepedia: a knowledge base of natural and synthetic cyclic peptides.Briefings in Bioinformatics25, 3 (2024), bbae190

    2024

  37. [37]

    David J Newman and Gordon M Cragg. 2016. Natural products as sources of new drugs from 1981 to 2014.Journal of natural products79, 3 (2016), 629–661

    2016

  38. [38]

    Doogie Oh, Yongdoo Park, and Jongseong Kim. 2025. De novo generation of peptide binders with desired properties by deep generative models reinforced through enrichment of focused sets for iterative fine-tuning.Chemical Commu- nications(2025)

    2025

  39. [39]

    Laszlo Otvos Jr and John D Wade. 2014. Current challenges in peptide-based drug discovery. 62 pages

    2014

  40. [40]

    Jaspreet Pannu, Doni Bloomfield, Alex Zhu, Robert MacKnight, Gabe Gomes, Anita Cicero, and Thomas V Inglesby. 2024. Prioritizing high-consequence biological capabilities in evaluations of artificial intelligence models.arXiv preprint arXiv:2407.13059(2024)

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  41. [41]

    Keyue Qiu, Yuxuan Song, Jie Yu, Hongbo Ma, Ziyao Cao, Zhilong Zhang, Yushuai Wu, Mingyue Zheng, Hao Zhou, and Wei-Ying Ma. 2024. Empower Structure- Based Molecule Optimization with Gradient Guided Bayesian Flow Networks. arXiv preprint arXiv:2411.13280(2024)

    work page arXiv 2024

  42. [42]

    Theresa A Ramelot, Jonathan Palmer, Gaetano T Montelione, and Gaurav Bhard- waj. 2023. Cell-permeable chameleonic peptides: Exploiting conformational dynamics in de novo cyclic peptide design.Current opinion in structural biology 80 (2023), 102603

    2023

  43. [43]

    Stephen A Rettie, Katelyn V Campbell, Asim K Bera, Alex Kang, Simon Ko- zlov, Yensi Flores Bueso, Joshmyn De La Cruz, Maggie Ahlrichs, Suna Cheng, Stacey R Gerben, et al. 2025. Cyclic peptide structure prediction and design using AlphaFold2.Nature Communications16, 1 (2025), 4730

    2025

  44. [44]

    Stephen A Rettie, David Juergens, Victor Adebomi, Yensi Flores Bueso, Qinqin Zhao, Alexandria N Leveille, Andi Liu, Asim K Bera, Joana A Wilms, Alina Üffing, et al. 2025. Accurate de novo design of high-affinity protein-binding macrocycles using deep learning.Nature Chemical Biology(2025), 1–9

    2025

  45. [45]

    Vıctor Garcia Satorras, Emiel Hoogeboom, and Max Welling. 2021. E (n) equi- variant graph neural networks. InInternational conference on machine learning. PMLR, 9323–9332

    2021

  46. [46]

    Tiara Natasha Binte Sayuti, Kakuly Mittal, Tan Lai Heng, and Jagath C Rajapakse

  47. [47]

    Target-aware latent diffusion model for design of apoptosis-inducing anticancer peptides.Computers in Biology and Medicine199 (2025), 111286

    2025

  48. [48]

    Petra Schneider, W Patrick Walters, Alleyn T Plowright, Norman Sieroka, Jennifer Listgarten, Robert A Goodnow Jr, Jasmin Fisher, Johanna M Jansen, José S Duca, Thomas S Rush, et al. 2020. Rethinking drug design in the artificial intelligence era.Nature reviews drug discovery19, 5 (2020), 353–364

    2020

  49. [49]

    Kristof T Schütt, Huziel E Sauceda, P-J Kindermans, Alexandre Tkatchenko, and K-R Müller. 2018. Schnet–a deep learning architecture for molecules and materials.The Journal of chemical physics148, 24 (2018)

    2018

  50. [50]

    Pietro Sormanni, Francesco A Aprile, and Michele Vendruscolo. 2015. The CamSol method of rational design of protein mutants with enhanced solubility. Journal of molecular biology427, 2 (2015), 478–490

    2015

  51. [51]

    Eric J Topol. 2019. High-performance medicine: the convergence of human and artificial intelligence.Nature medicine25, 1 (2019), 44–56. APCyc: Property-Informed Design of Cyclic Peptides via Automated Cyclization

    2019

  52. [52]

    Oleg Trott and Arthur J Olson. 2010. AutoDock Vina: improving the speed and accuracy of docking with a new scoring function, efficient optimization, and multithreading.Journal of computational chemistry31, 2 (2010), 455–461

    2010

  53. [53]

    Fabio Urbina, Filippa Lentzos, Cédric Invernizzi, and Sean Ekins. 2022. Dual use of artificial-intelligence-powered drug discovery.Nature machine intelligence4, 3 (2022), 189–191

    2022

  54. [54]

    Patrick Vlieghe, Vincent Lisowski, Jean Martinez, and Michel Khrestchatisky

  55. [55]

    Synthetic therapeutic peptides: science and market.Drug discovery today 15, 1-2 (2010), 40–56

    2010

  56. [56]

    Fanhao Wang, Yuzhe Wang, Laiyi Feng, Changsheng Zhang, and Luhua Lai. 2024. Target-specific de novo peptide binder design with DiffPepBuilder.Journal of Chemical Information and Modeling64, 24 (2024), 9135–9149

    2024

  57. [57]

    Scott A Wildman and Gordon M Crippen. 1999. Prediction of physicochemi- cal parameters by atomic contributions.Journal of chemical information and computer sciences39, 5 (1999), 868–873

    1999

  58. [58]

    Ziyi Yang, Hanyuan Xie, Yinjun Jia, Xiangzhe Kong, Jiqing Zheng, Ziting Zhang, Yang Liu, Lei Liu, and Yanyan Lan. 2025. CPSea: Large-scale cyclic peptide– protein complex dataset for machine learning in cyclic peptide design. InAd- vances in Neural Information Processing Systems. Datasets and Benchmarks Track

    2025

  59. [59]

    Xiaoyu Zhou, Meng Li, Yifan Xiao, Jing Li, Dong Xue, Zhen Zheng, Jian Ma, and Quanquan Gu. 2025. Designing Cyclic Peptides via Harmonic Stochastic Differential Equations with Atom–Bond Modeling. InProceedings of the 42nd International Conference on Machine Learning

    2025

  60. [60]

    Alessandro Zorzi, Kaycie Deyle, and Christian Heinis. 2017. Cyclic peptide therapeutics: past, present and future.Current opinion in chemical biology38 (2017), 24–29. A Proof of Proposition 3.1 Proof. Let 𝑔∈SE( 3) denote a rigid transformation acting on equivariant coordinates as 𝑔( x)= Rx + twithR ∈SO( 3). Invariant latent features remain unchanged. Inva...

    2017