MacroGuide: Topological Guidance for Macrocycle Generation

Alicja Maksymiuk; Alexandre Duplessis; Michael Bronstein; Alexander Tong; Fernanda Duarte; İsmail İlkan Ceylan

cs.LGFeb 16, 2026

MacroGuide: Topological Guidance for Macrocycle Generation

Authors: Alicja Maksymiuk, Alexandre Duplessis, Michael Bronstein, Alexander Tong, Fernanda Duarte, İsmail İlkan Ceylan

Organizations: University of Oxford · AITHYRA · ENS Ulm, PSL · TU Wien

Abstract

Macrocycles are ring-shaped molecules that offer a promising alternative to small-molecule drugs due to their enhanced selectivity and binding affinity against difficult targets. Despite their chemical value, they remain underexplored in generative modeling, likely owing to their scarcity in public datasets and the challenges of enforcing topological constraints in standard deep generative models. We introduce MacroGuide: Topological Guidance for Macrocycle Generation, a diffusion guidance mechanism that uses Persistent Homology to steer the sampling of pretrained molecular generative models toward the generation of macrocycles, in both unconditional and conditional (protein pocket) settings. At each denoising step, MacroGuide constructs a Vietoris-Rips complex from atomic positions and promotes ring formation by optimizing persistent homology features. Empirically, applying MacroGuide to pretrained diffusion models increases macrocycle generation rates from 1% to 99%, while matching or exceeding state-of-the-art performance on key quality metrics such as chemical validity, diversity, and PoseBusters checks.

Figures & tables

Panel of Figure 1 — Figure 1: Method overview. MacroGuide drives the denoising trajectory towards macrocyclic structures using updates from a topological objective.

Panel of Figure 2 — Figure 2: Examples of generated macrocycles. Top: Unconditional generation. Bottom: Protein conditioning. Bottom right: This molecule was specifically optimized to be bicyclic (two rings). Molecule fragments appear transparent when hidden by parts of the protein pocket.

Figure 3: Topological guidance for diffusion-based macrocycle generation.

Metrics ( $\uparrow$ ; [0-1])	MolDiff (no guid.)	MolDiff (finetuned)	Naive (12 atoms)	Naive (14 atoms)	Naive (16 atoms)	Torus noise initialization	MolDiff+ MacroGuide (ours)
Validity	0.991	0.994	0.937	0.930	0.918	0.993	0.989
Connectivity	0.958	0.993	0.985	0.990	0.987	0.960	0.999
Successfulness	0.949	0.987	0.923	0.921	0.906	0.953	0.988
Out of successful:
Macrocycles	0.053	0.851	0.370	0.364	0.369	0.054	0.997

Table 1: Performance of unconditional macrocycle generation. Results obtained from 1000 molecules with 30 heavy atoms.

Metrics ( $\uparrow$ ; [0-1])	MolSnapper (no guid.)	MolSnapper (finetuned)	Naive (12 atoms)	Naive (14 atoms)	Naive (16 atoms)	MolSnapper+ MacroGuide (ours)
Validity	0.858	0.795	0.819	0.791	0.763	0.925
Connectivity	1.000	1.000	1.000	1.000	1.000	1.000
Successfulness	0.858	0.795	0.819	0.791	0.763	0.925
Out of successful:
Macrocycles	0.003	0.180	0.013	0.000	0.003	0.995

Table 2: Performance of macrocycle generation with protein conditioning.

Metrics ( $\uparrow$ ; [0-1])	MolDiff (no guid.)	+ MacroGuide (ours)
Diversity	0.707	0.771
Novelty	1.000	1.000
Uniqueness	1.000	1.000
All PoseBusters tests	0.663	0.805
Bond lengths	0.977	0.990
Bond angles	0.949	0.987

Table 3: Unconditional macrocycle quality metrics. Values were obtained by generating molecules until at least 1000 macrocycles were found to ensure reliable and comparable estimates.

Metrics ( $\uparrow$ ; [0-1])	MolSnapper (no guid.)	+ MacroGuide (ours)
Diversity	0.626	0.712
Novelty	1.000	1.000
Uniqueness	1.000	1.000
All PoseBusters tests	0.440	0.575
Ligand PoseBusters	0.539	0.626
Bond lengths	0.844	0.860

Table 4: Protein-conditioned macrocycle quality metrics.

Metrics ( $\uparrow$ ; [0-1])	MolDiff + MacroGuide	MolSnapper + MacroGuide
Validity	0.998	0.821
Connectivity	0.931	1.000
Successfulness	0.929	0.821
Out of successful:
Bicyclic molecules	0.970	0.895

Table 5: Performance of bicyclic molecule generation in unconditional and conditional settings. A molecule is considered bicyclic if it has at least two chordless cycles of at least 12 atoms each. Results obtained from 1000 molecules with 45 heavy atoms.

Figure 4: Performance of MolDiff with increasing molecular size. Adding

H_{0}

guidance term improves performance for large molecule sizes. Results obtained from

200

samples each.

Figure 5: Median max cycle size as a function of the target death. The empirical results are compared to the theoretical formulas for

\ell=1.0

and

\ell=1.5

, the minimum and maximum typical bond lengths, respectively. Results are computed for

200

samples of 30 heavy atoms, with each target size

d^{\star}

being constrained in the relaxed form of an interval

[d^{\star}-0.05,d^{\star}+0.05]

, sampled at 0.1 intervals.

Figure 6: Runtime comparison. MacroGuide produces only a small computational overhead that can be further reduced by applying guidance only every

k

steps.

Figure 7: Key topological features throughout denoising . Maximum

H_{0}

death (i.e. the longest distance to the closest neighbor over all atoms), and birth and death of the maximum-death

H_{1}

component (largest cycle).

Appendix figures & tables21 assets

Supplementary material from the paper’s appendix.

Appendix

Panel of Figure 8 — Figure 8: Proof geometry: crown-shaped $n$ -gon ( $n=12$ ). The inner polygon (dashed blue) determines the filtration death time $d$ . The effective side length $\ell^{\prime}$ is derived from the bond length $\ell$ and the interior bond angle.

Panel of Figure 9 — Figure 9: Impact of cycle shape on $H_{1}$ death $(n=16)$ . In an elongated elliptical macrocycle, the death time $d_{ellipse}$ is significantly reduced compared to $d_{circle}.$ The death times were obtained numerically using torch_topological .

Panel of Figure 10 — Figure 10: Failure mode analysis. Comparison of optimization dynamics under Equation 9 . (a) Symmetric gradients cause ”unzipping.” (b) Masked gradients preserve structure.

Figure 11: Topological features (no square on

F^{H_{1}}_{\mathrm{birth}}

) for individual runs (left) and averaged runs (right).

Figure 12: Topological features without guidance

Figure 13: Topological features with squared

F^{H_{1}}_{\mathrm{birth}}

for individual runs (left) and averaged runs (right).

Figure 14: Gradient statistics (no square on

F^{H_{1}}_{\mathrm{birth}}

) for individual runs (left) and averaged runs (right).

Figure 15: Gradient statistics with squared

F^{H_{1}}_{\mathrm{birth}}

for individual runs (left) and averaged runs (right).

Panel of Figure 16 — Figure 16: Visualizations of generated molecules in the unconditional setting.

Panel of Figure 17 — Figure 17: Visualizations of generated molecules in the protein-conditioned setting. The top parts of molecules are less visible because they are obstructed by a semi-transparent protein pocket.

Metrics ( $\uparrow$ ; [0-1])	MolDiff + MacroGuide	MolSnapper + MacroGuide
Validity	$\pm{.003}$	$\pm{.008}$
Connectivity	$\pm{.001}$	$\pm{.000}$
Successfulness	$\pm{.003}$	$\pm{.008}$
Out of successful:
Macrocycles	$\pm{.002}$	$\pm{.003}$
Out of macrocycles:

Appendix

Table 6: Standard deviations of unconditional and protein-conditioned macrocycle generation performance. The last 6 values do not appear for MolDiff as the metrics are defined only in the protein-conditioning setting. Variances for unguided MolDiff and MolSnapper are not reported as generating multiple sets of 1000 macrocycles proved computationally prohibitive due to the very low baseline macrocycle success rates.

Metrics ( $\uparrow$ ; [0-1])	MolDiff + MacroGuide (ours)	No $H_{1}$ birth	No $H_{0}$	No $H_{1}$ birth and no $H_{0}$
Validity	0.989	0.990	0.990	0.990
Connectivity	0.999	0.954	0.863	0.022
Successfulness	0.988	0.944	0.854	0.022
Out of successful:
Macrocycles	0.997	0.075	0.995	0.091
Out of macrocycles:

Appendix

Table 7: Ablations of different guidance terms in the unconditional setting. The metrics most affected by the ablation are in bold. Some metrics are not reported because not enough successful macrocycles were produced. Results were obtained from sets of 1000 molecules.

Metrics ( $\uparrow$ ; [0-1])	MolSnapper + MacroGuide (ours)	No $H_{1}$ birth	No $H_{0}$	No $H_{1}$ birth and no $H_{0}$
Validity	0.925	0.903	0.921	0.929
Connectivity	1.000	1.000	1.000	1.000
Successfulness	0.925	0.903	0.921	0.929
Out of successful:
Macrocycles	0.995	0.078	0.989	0.016
Out of macrocycles:

Appendix

Table 8: Ablations of different guidance terms in the conditional setting. The metrics most affected by the ablation are in bold. Some metrics are not reported because not enough successful macrocycles were produced. Results were obtained from sets of 1000 molecules.

Metrics ( $\uparrow$ ; [0-1])	MolDiff + MacroGuide (ours)	+ $H_{1}$ birth square	No $H_{1}$ death square	No $H_{0}$ death square
Validity	0.989	0.981	0.924	0.991
Connectivity	0.999	0.985	1.000	1.000
Successfulness	0.988	0.966	0.924	0.991
Out of successful:
Macrocycles	0.997	0.633	0.998	1.000
Out of macrocycles:

Appendix

Table 9: Influence of the square on each guidance term in the unconditional setting. The metrics most affected by the ablation are in bold. Results were obtained from sets of 1000 molecules.

Metrics ( $\uparrow$ ; [0-1])	MolSnapper + MacroGuide (ours)	+ $H_{1}$ birth square	No $H_{1}$ death square	No $H_{0}$ death square
Validity	0.925	0.914	0.883	0.915
Connectivity	1.000	1.000	1.000	1.000
Successfulness	0.925	0.914	0.883	0.915
Out of successful:
Macrocycles	0.995	0.521	0.998	0.991
Out of macrocycles:

Appendix

Table 10: Influence of the square on each guidance term in the conditional setting. The metrics most affected by the ablation are in bold. Results were obtained from sets of 1000 molecules.

Metrics ( $\uparrow$ ; [0-1])	0.1	0.5	MolDiff + MacroGuide 1.0 (ours)	1.5	2.0
Validity	0.994	0.995	0.989	0.991	0.992
Connectivity	0.999	0.996	0.999	0.996	0.988
Successfulness	0.993	0.991	0.988	0.987	0.980
Out of successful:
Macrocycles	0.769	0.967	0.997	0.990	0.754
Out of macrocycles:

Appendix

Table 11: Influence of guidance strength on performance in the unconditional setting. The original results from Table 3 correspond to the strength of 1. Results were obtained from 1000 samples.

Metrics ( $\uparrow$ ; [0-1])	0.1	0.5	MolSnapper + MacroGuide 1.0 (ours)	1.5	2.0
Validity	0.924	0.933	0.925	0.876	0.891
Connectivity	1.000	1.000	1.000	1.000	1.000
Successfulness	0.924	0.933	0.925	0.876	0.891
Out of successful:
Macrocycles	0.411	0.867	0.995	0.995	0.845
Out of macrocycles:

Appendix

Table 12: Influence of guidance strength on performance in the conditional setting. The original results from Table 4 correspond to the strength of 1. Results were obtained from 1000 samples.

Method	C	N	O	F	P	S	Cl
MolDiff (no guid.)	0.7978	0.0798	0.1089	0.0011	0.0000	0.0113	0.0011
+ MacroGuide (ours)	0.8785	0.0477	0.0722	0.0001	0.0000	0.0014	0.0001
MolSnapper (no guid.)	0.7508	0.1749	0.0714	0.0002	0.0000	0.0024	0.0003
+ MacroGuide (ours)	0.7540	0.1921	0.0483	0.0000	0.0000	0.0051	0.0005

Appendix

Table 13: Atom distribution of generated macrocycles. Represented as a fraction of all atoms.

Method	3-cycles ( $\downarrow$ )	4-cycles ( $\downarrow$ )	5-cycles	6-cycles	7-cycles	8-cycles	9-cycles
MolDiff (no guid.)	0.054	0.022	0.482	2.552	0.154	0.022	1.885
+ MacroGuide (ours)	0.065	0.022	0.449	1.933	0.033	0.003	1.229
MolSnapper (no guid.)	0.258	0.082	1.005	2.919	0.133	0.009	2.216
+ MacroGuide (ours)	0.183	0.077	1.123	2.127	0.039	0.001	1.341

Appendix

Table 14: Ring size distribution in generated macrocycles. Represented as the average number of cycles of a certain size per molecule.

Metrics ( $\uparrow$ ; [0-1])	MolSnapper (no guid.)	Every 1	Every 2	Every 3	Every 4	Every 5
Validity	0.858	0.925	0.930	0.942	0.914	0.940
Connectivity	1.000	1.000	1.000	1.000	1.000	1.000
Successfulness	0.858	0.925	0.930	0.942	0.914	0.940
Out of successful:
Macrocycles	0.003	0.995	0.943	0.911	0.864	0.852
Out of macrocycles:

Appendix

Table 15: Performance of protein-conditioned macrocycle generation with guidance applied every few steps. The first two columns correspond to Table 4 . Values outperforming or matching the baseline MolSnapper metrics are in bold.

Metrics ( $\uparrow$ ; [0-1])	MolSnapper (no guid.)	1000 steps	900 steps	800 steps	700 steps	600 steps	500 steps	400 steps	300 steps	200 steps	100 steps
Validity	0.858	0.925	0.925	0.925	0.910	0.920	0.940	0.905	0.910	0.860	0.840
Connectivity	1.000	1.000	1.000	1.000	1.000	1.000	1.000	1.000	1.000	1.000	1.000
Successfulness	0.858	0.925	0.925	0.925	0.910	0.920	0.940	0.905	0.910	0.860	0.840
Out of successful:
Macrocycles	0.003	0.995	0.995	0.989	0.984	0.995	0.995	1.000	0.995	0.965	0.935
Out of macrocycles:

Appendix

Table 16: Performance of protein-conditioned macrocycle generation with guidance starting late. The number denotes the number of remaining denoising steps when the guidance is applied, out of 1000 steps total. The first two columns correspond to Table 4 . Values outperforming or matching the baseline MolSnapper metrics are in bold. Non-baseline results were obtained from sets of 200 molecules.

Diffusion Model Guidance

Diffusion model guidance steers denoising toward desired conditions, rewards, constraints, or away from unwanted concepts.

See all 362 papers

PepALD: Macrocyclic Peptide Generation via Autoregressive Latent Diffusion
Jun 12, 2026Junming Zhang, Siyu Yi, Wei Ju +1Diffusion Model Alignment Autoregressive Diffusion
College of Computer Science, Sichuan University, Chengdu, 610065, China · School of Mathematics, Sichuan University, Chengdu, 610065, China · School of Artificial Intelligence, Sichuan University, Chengdu, 610065, China +1
Vilya-1: An all-atom foundation model for macrocycle structure prediction and design
Jul 10, 2026Vilya Research, :, Pascal Sturmfels +8Molecular Generation Molecular Property Prediction
Vilya Research
Fine-Tuning Diffusion Models for Molecular Generation via Reinforcement Learning and Fast Sampling
May 31, 2026Guang Lin, Shikui Tu, Lei XuMolecular Optimization Diffusion Model Fine-Tuning
Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China · Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen, Guangdong, China

Jun 12, 2026J/K move · Enter open · S save

PepALD: Macrocyclic Peptide Generation via Autoregressive Latent Diffusion

Junming Zhang, Siyu Yi, Wei Ju, Zhonghui Gu

College of Computer Science, Sichuan University, Chengdu, 610065, China · School of Mathematics, Sichuan University, Chengdu, 610065, China · School of Artificial Intelligence, Sichuan University, Chengdu, 610065, China+1

Diffusion Model Alignment Autoregressive Diffusion Molecular Generation Drug Discovery

Open paper AskPDF arXiv

Macrocyclic peptides are promising therapeutic candidates for intracellular targets, but their design requires simultaneous control over non-natural monomer chemistry, ring topology, membrane permeability, and target binding. Existing SMILES- or HELM-string generative models either operate in long atom-level sequence spaces or treat monomers as symbolic tokens with limited chemical grounding. We introduce PepALD, an Autoregressive Latent Diffusion (ALD) foundation model for de novo macrocyclic peptide generation. The model represents HELM monomers with structured chemical embeddings, generates each residue through context-conditioned diffusion in chemically informed latent space, predicts R-group-aware ring closures during autoregressive generation, and aligns the denoiser to affinity rewards using winner-protected diffusion-adapted preference optimization. In silico experiments demonstrate PepALD's generation quality and reward-optimization performance against representative peptide generation baselines.

Abstract

Diffusion Model Guidance

Explore similar work

PepALD: Macrocyclic Peptide Generation via Autoregressive Latent Diffusion

Vilya-1: An all-atom foundation model for macrocycle structure prediction and design

Fine-Tuning Diffusion Models for Molecular Generation via Reinforcement Learning and Fast Sampling