OmniSyn unifies target-aware molecular generation and optimization within a synthesis-native LLM framework across the human proteome
- 1Tongji University
Abstract
Designing target-specific bioactive molecules with actionable synthesis routes for the human proteome holds enormous potential for expanding therapeutic discovery, but remains a challenge. Existing target-aware generative models often depend on protein structures and generate molecules before assessing synthetic feasibility. Here we present OmniSyn, a protein-sequence-conditioned Mixture-of-Experts (MoE) language model that couples a task-conditioned interaction module with a synthesis-action decoder to generate molecules with explicit synthesis traces, thereby unifying de novo ligand generation, synthesizability projection and hit-to-lead (H2L) optimization within synthesis-traceable chemical space. OmniSyn is pre-trained with self-distillation and post-trained with task-specific reinforcement learning (RL) to adapt expert routing and optimize molecular properties across design modes. On unseen protein targets from MolGenBench, a real-world drug-discovery benchmark, OmniSyn achieves state-of-the-art performance across de novo design and H2L optimization, including target-awareness and hit-rediscovery metrics, despite relying only on protein sequences rather than three-dimensional (3D) pocket structures. By embedding synthesis planning into the design process, OmniSyn shifts molecular generation from a generate-then-filter paradigm toward design-with-synthesis paradigm, transforming virtual predictions into experimentally actionable candidates. Independent AiZynthFinder evaluation yielded retrosynthetic success rates of 68.47% for de novo generation and 71.92% for H2L optimization, improving over the strongest baselines by 61.3% and 184.2%, respectively, and supporting the synthetic feasibility of OmniSyn-generated molecules. In synthesizability projection, OmniSyn further converts outputs from external generative models into close analogues with improved retrosynthetic feasibility while preserving molecular similarity. Having established strong benchmark performance and external retrosynthetic feasibility, we next applied OmniSyn at human-proteome scale, spanning more than 21,000 targets. Rapid sequence-conditioned sampling enabled the construction of, to our knowledge, the largest human-proteome-scale generative virtual library, comprising 2.7 billion target-specific molecules, each accompanied by model-derived synthesis traces and target-specific prioritization scores. By enabling scalable target-specific molecular design with synthesis-aware generation across the human proteome, OmniSyn opens new opportunities for exploring previously inaccessible therapeutic targets, including those lacking experimentally resolved structures.
Related
- AI-Driven Design of Next-Generation Immunoinformatics Multi-Epitope Subunit Vaccine Targeting the Most Virulent Mpox Proteome: A Structural and Kinetic Validation Framework
- AET5: A transcriptome-guided molecular generation framework with contrastive self-supervised learning
- Mathematical model for visual cortical development based on molecular mechanisms underlying the generation and elimination of dendritic spines
- Multi-granularity Adversarial Generation Integrated Consistency Representation for Chest Low-Contrast-Enhanced CT Synthesis
- Molecular basis of coupled peptidoglycan synthesis by the FtsWIQLB divisome complex from Vibrio cholerae
BibTeX
@misc{z2026omnisyn,
title = {{OmniSyn unifies target-aware molecular generation and optimization within a synthesis-native LLM framework across the human proteome}},
author = {Z. QIN and Y. Li and Y. Zhang and Y. Zhao and H. Y. Koh and Z. Wan and H. Ren and C. Huang and Y. Shi and Z. Wu and Y. Min and J. Yang and X. He and D. Cao},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.02.748775},
url = {https://www.biorxiv.org/content/10.64898/2026.09.02.748775v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - OmniSyn unifies target-aware molecular generation and optimization within a synthesis-native LLM framework across the human proteome
AU - Z. QIN
AU - Y. Li
AU - Y. Zhang
AU - Y. Zhao
AU - H. Y. Koh
AU - Z. Wan
AU - H. Ren
AU - C. Huang
AU - Y. Shi
AU - Z. Wu
AU - Y. Min
AU - J. Yang
AU - X. He
AU - D. Cao
PY - 2026
DA - 2026/09/02
PB - bioRxiv
DO - 10.64898/2026.09.02.748775
UR - https://www.biorxiv.org/content/10.64898/2026.09.02.748775v1
AB - Designing target-specific bioactive molecules with actionable synthesis routes for the human proteome holds enormous potential for expanding therapeutic discovery, but remains a challenge. Existing target-aware generative models often depend on protein structures and generate molecules before assessing synthetic feasibility. Here we present OmniSyn, a protein-sequence-conditioned Mixture-of-Experts (MoE) language model that couples a task-conditioned interaction module with a synthesis-action decoder to generate molecules with explicit synthesis traces, thereby unifying de novo ligand generation, synthesizability projection and hit-to-lead (H2L) optimization within synthesis-traceable chemical space. OmniSyn is pre-trained with self-distillation and post-trained with task-specific reinforcement learning (RL) to adapt expert routing and optimize molecular properties across design modes. On unseen protein targets from MolGenBench, a real-world drug-discovery benchmark, OmniSyn achieves state-of-the-art performance across de novo design and H2L optimization, including target-awareness and hit-rediscovery metrics, despite relying only on protein sequences rather than three-dimensional (3D) pocket structures. By embedding synthesis planning into the design process, OmniSyn shifts molecular generation from a generate-then-filter paradigm toward design-with-synthesis paradigm, transforming virtual predictions into experimentally actionable candidates. Independent AiZynthFinder evaluation yielded retrosynthetic success rates of 68.47% for de novo generation and 71.92% for H2L optimization, improving over the strongest baselines by 61.3% and 184.2%, respectively, and supporting the synthetic feasibility of OmniSyn-generated molecules. In synthesizability projection, OmniSyn further converts outputs from external generative models into close analogues with improved retrosynthetic feasibility while preserving molecular similarity. Having established strong benchmark performance and external retrosynthetic feasibility, we next applied OmniSyn at human-proteome scale, spanning more than 21,000 targets. Rapid sequence-conditioned sampling enabled the construction of, to our knowledge, the largest human-proteome-scale generative virtual library, comprising 2.7 billion target-specific molecules, each accompanied by model-derived synthesis traces and target-specific prioritization scores. By enabling scalable target-specific molecular design with synthesis-aware generation across the human proteome, OmniSyn opens new opportunities for exploring previously inaccessible therapeutic targets, including those lacking experimentally resolved structures.
ER -