_version_ 1866908995467345920
author Golkar, Siavash
Kovalic, Jake
Morales, Irina Espejo
Sledzieski, Samuel
Li, Minhuan
Sokolova, Ksenia
Krawezik, Geraud
Bietti, Alberto
Gibbs, Claudia Skok
Klypa, Roman
Xiong, Shengwei
Lanusse, Francois
Parker, Liam
Cho, Kyunghyun
Cranmer, Miles
Hehir, Tom
McCabe, Michael
Meyer, Lucas
Morel, Rudy
Mukhopadhyay, Payel
Pettee, Mariel
Qu, Helen
Shen, Jeff
Fouhey, David
Sotoudeh, Hadi
Mulligan, Vikram
Cossio, Pilar
Hanson, Sonya M.
Jones, Alisha N.
Troyanskaya, Olga G.
Ho, Shirley
author_facet Golkar, Siavash
Kovalic, Jake
Morales, Irina Espejo
Sledzieski, Samuel
Li, Minhuan
Sokolova, Ksenia
Krawezik, Geraud
Bietti, Alberto
Gibbs, Claudia Skok
Klypa, Roman
Xiong, Shengwei
Lanusse, Francois
Parker, Liam
Cho, Kyunghyun
Cranmer, Miles
Hehir, Tom
McCabe, Michael
Meyer, Lucas
Morel, Rudy
Mukhopadhyay, Payel
Pettee, Mariel
Qu, Helen
Shen, Jeff
Fouhey, David
Sotoudeh, Hadi
Mulligan, Vikram
Cossio, Pilar
Hanson, Sonya M.
Jones, Alisha N.
Troyanskaya, Olga G.
Ho, Shirley
contents Biological function emerges from coupled constraints across sequence, structure, regulation, evolution, and cellular context, yet most foundation models in biology are trained within one modality or for a fixed forward task. We present MIMIC, a generative multimodal foundation model trained on our newly curated and aligned dataset, LORE, linking nucleic acid, protein, evolutionary, structural, regulatory, and semantic/contextual modalities within partially observed biomolecular states. MIMIC uses a split-track encoder-decoder architecture to condition on arbitrary subsets of observed modalities and reconstruct or generate missing components of molecular state across the genome, transcriptome, and proteome. Multimodal conditioning consistently improves MIMIC's sequence reconstruction relative to sequence-only inputs, while its learned representations enable state-of-the-art performance on RNA and protein downstream tasks. MIMIC achieves state-of-the-art splicing prediction, and its joint generative formulation enables isoform-aware inference that further improves performance. Beyond prediction, the same generative framework supports constrained design. For RNA, MIMIC identifies corrective edits in a clinically relevant HBB splice-disrupting mutation without reverting it by using evolutionary and structural signals. For proteins, jointly conditioning on shape and surface chemistry of PD-L1 and hACE2 binding sites produces diverse, high-confidence sequences with strong in silico support for target binding. Finally, MIMIC uses experimental context as semantic conditioning to model assay-dependent RNA chemical probing, rather than treating context as a fixed output. Together, these results position MIMIC's aligned multimodal generative modeling as a strong foundation for unifying representation learning, conditional prediction, and constrained biomolecular design within a single model.
format Preprint
id arxiv_https___arxiv_org_abs_2604_24506
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MIMIC: A Generative Multimodal Foundation Model for Biomolecules
Golkar, Siavash
Kovalic, Jake
Morales, Irina Espejo
Sledzieski, Samuel
Li, Minhuan
Sokolova, Ksenia
Krawezik, Geraud
Bietti, Alberto
Gibbs, Claudia Skok
Klypa, Roman
Xiong, Shengwei
Lanusse, Francois
Parker, Liam
Cho, Kyunghyun
Cranmer, Miles
Hehir, Tom
McCabe, Michael
Meyer, Lucas
Morel, Rudy
Mukhopadhyay, Payel
Pettee, Mariel
Qu, Helen
Shen, Jeff
Fouhey, David
Sotoudeh, Hadi
Mulligan, Vikram
Cossio, Pilar
Hanson, Sonya M.
Jones, Alisha N.
Troyanskaya, Olga G.
Ho, Shirley
Artificial Intelligence
Machine Learning
Biological function emerges from coupled constraints across sequence, structure, regulation, evolution, and cellular context, yet most foundation models in biology are trained within one modality or for a fixed forward task. We present MIMIC, a generative multimodal foundation model trained on our newly curated and aligned dataset, LORE, linking nucleic acid, protein, evolutionary, structural, regulatory, and semantic/contextual modalities within partially observed biomolecular states. MIMIC uses a split-track encoder-decoder architecture to condition on arbitrary subsets of observed modalities and reconstruct or generate missing components of molecular state across the genome, transcriptome, and proteome. Multimodal conditioning consistently improves MIMIC's sequence reconstruction relative to sequence-only inputs, while its learned representations enable state-of-the-art performance on RNA and protein downstream tasks. MIMIC achieves state-of-the-art splicing prediction, and its joint generative formulation enables isoform-aware inference that further improves performance. Beyond prediction, the same generative framework supports constrained design. For RNA, MIMIC identifies corrective edits in a clinically relevant HBB splice-disrupting mutation without reverting it by using evolutionary and structural signals. For proteins, jointly conditioning on shape and surface chemistry of PD-L1 and hACE2 binding sites produces diverse, high-confidence sequences with strong in silico support for target binding. Finally, MIMIC uses experimental context as semantic conditioning to model assay-dependent RNA chemical probing, rather than treating context as a fixed output. Together, these results position MIMIC's aligned multimodal generative modeling as a strong foundation for unifying representation learning, conditional prediction, and constrained biomolecular design within a single model.
title MIMIC: A Generative Multimodal Foundation Model for Biomolecules
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2604.24506