Foundation models for DNA/RNA and decoding genomic sequence and expression.
34 papers in this topic (ICML 2026).
Arnav Shah, Junzhe Li, Parsa Idehpour, Adibvafa Fallahpour +4
Genomic foundation models have the potential to decode DNA syntax, yet face a fundamental tradeoff. Standard subword tokenizers fragment biologically meaningful motifs such as…
Tingting Chen, Beibei Lin, Zifeng Yuan, Qiran Zou +4
Many scientific problems are underdetermined: multiple distinct hypotheses are equally consistent with the same observations. In such settings, effective inference requires not…
Zipeng Sun, Can Chen, Ye Yuan, Haolun Wu +3
We study offline black-box optimization (BBO), aiming to discover improved designs from an offline dataset of designs and labels, a problem common in robotics, DNA, and materials…
Binghao Liu, Wenzheng Zhao, Zhijie Zheng, Fei Gu
Effective DNA modeling demands the integration of complex patterns such as local motifs, long-range dependencies, and periodic signals. Yet, architectures like CNNs, Transformers,…
Jiafa Ruan, Ruijie Quan, Xu Liyang, Zongxin Yang +1
Predicting transcriptional responses to genetic perturbations is a central problem in functional genomics. In practice, perturbation responses are rarely gene-independent but…
Maxence Gélard, Hakim Benkirane, Thomas Pierrot, Guillaume Richard +1
Oncologists are increasingly relying on multiple modalities to model the complexity of diseases. Within this landscape, transcriptomic and epigenetic data have proven to be…
Yi Fang, Haoran Xu, Jiaxin Han, Sirui Ding +3
Foundation models have revolutionized AI, yet biological applications often repurpose general architectures without accounting for the intrinsic structural and functional…
Tianmeng Hu, Biao Luo, Ke Li
Designing RNA sequences that reliably fold into specific secondary structures is essential for understanding their biological functions but remains a challenging computational…
Taewon Kim, Jihwan Shin, Hyomin Kim, Youngmok Jung +4
DNA language models are increasingly used to represent genomic sequence, yet their effectiveness depends critically on how raw nucleotides are converted into model inputs. Unlike…
McClain Thiel, Angus G. Cunningham, Chris P Barnes
We compare the efficacy and distributional effects of supervised fine-tuning (SFT) and reinforcement learning (RL) post-training for PlasmidGPT, a foundation model for…
Qi Si, Penglei Wang, Yushuai Wu, Yifeng Jiao +4
Predicting spatial gene expression from routine H\&E enables large-scale molecular profiling, yet current models treat this as isolated pointwise tasks, thereby overlooking…
Egor Antipov, Alessandro Palma, Lorenzo Consoli, Stephan Günnemann +2
Estimating density ratios between pairs of intractable data distributions is a core problem in probabilistic modeling, enabling principled comparisons of sample likelihoods under…
Noah Flynn
Designing genetic circuits, which are biological systems capable of programmed behaviors within living cells, remains a laborious, expert-driven process despite decades of…
Daria Ledneva, Mikhail Nuridinov, Denis Kuznetsov
Progress in genomic foundation models is difficult to assess due to fragmented benchmarks, incompatible evaluation protocols, and task-specific reporting. As a result, claims of…
Keunho Byeon, Jin Tae Kwak
Spatial transcriptomics offers spatially resolved gene expression profiling within tissue sections, but its cost and limited throughput hinder large-scale deployment. To extend…
Yifan Lin, Kevin Z. Lin
High-dimensional genomics studies are frequently confounded by unmeasured biological processes that obscure disease-specific signals. While existing workflows can estimate these…
Weiyi Wu, Xinwen Xu, Xingjian Diao, Siting Li +3
Spatial transcriptomics (ST) links gene expression with tissue morphology but remains expensive and low-throughput, motivating surrogates that infer expression from routine…
Cheng Wang, Jinpu Cai, Chongxiao Mao, Yuxuan Wang +4
Geometry-preserving dimension reduction is critical for single-cell transcriptomics, where low-dimensional distances should reflect biological divergence between cell types along…
Akash Pandey, Wei Chen, Sinan Keten
Designing biological sequences such as proteins and DNA for desired properties is challenging due to vast search spaces and limited wet lab evaluation budgets. Current…
Zaikang Lin, Sei Chang, Aaron Zweig, Minseo Kang +3
Modern high-throughput biological datasets containing thousands of perturbations enable large-scale discovery of causal graphs that represent regulatory interactions between…
Akira A Nair, Jaehyun Joo, Jonghyun Lee, Lina Takemaru +4
Genomic language models (gLMs) achieve strong performance across genomic prediction tasks, but their internal biological representations remain poorly understood. Sparse…
Daria Ledneva, Denis Kuznetsov
Genomic foundation models increasingly adopt large language model architectures, yet almost universally rely on fixed tokenization schemes such as $k$-mers, BPE, or single…
Yinhua Piao, Hyomin Kim, Seonghwan Kim, Yunhak Oh +4
Predicting high-dimensional transcriptional responses to genetic perturbations is challenging because signals are sparse and experimental noise is severe. Existing methods often…
Zixun Zhang, Yuncheng Jiang, Yuzhe Zhou, Jiayou Zheng +2
Tertiary structure-based RNA design aims to generate RNA sequences that can fold into desired 3D structures, but remains a challenging problem due to the scarcity of annotated…
Susu Hu, Stefanie Speidel
Inferring spatial transcriptomics (ST) from histology enables scalable histogenomic profiling, yet current methods are largely restricted to single-tissue models. This…
Micaela Elisa Consens, Kevin K Yang, James Brian Hall, Ashley Mae Conard +4
Genome language models (gLM) have the potential to further understanding of regulatory genomics without requiring labeled data. Most gLMs are pretrained using sequence…
Hongxin Xiang, Pengsen Ma, Yunkang Cao, Di Yu +3
Recent genomic foundation models largely adopt large language model architectures that treat DNA as a one-dimensional token sequence. However, exhaustive sequential reading is…
Zhou Zhang, Hanqun Cao, Cheng Tan, Fang Wu +2
Accurate RNA structure modeling remains difficult because RNA backbones are highly flexible, non-canonical interactions are prevalent, and experimentally determined 3D structures…
Yaxuan Song, Jianan Fan, Tianyi Wang, Qiuyue Hu +3
Histopathology whole-slide images (WSIs) are routinely acquired in clinical practice and contain rich tissue morphology but lack direct molecular architecture and functional…
Giovanni Palla, Sudarshan Babu, Payam Dibaeinia, James D Pearce +4
Computational modeling of single-cell gene expression is crucial for understanding cellular processes, but generating realistic expression profiles remains a major challenge. This…
Jiawei Zhang, Kangjun Jin, Shuai Xiao, Jiachen Yang
Measuring single-cell protein abundance is essential for resolving biological mechanisms and disease progression with high resolution. However, due to the high costs and antibody…
Zekuan Shang, Xiaosong Han, Liupu Wang, Wei Du +4
For denoising Spatially Resolved Transcriptomics (SRT) data, existing methods often construct spot and gene graphs to model inter-spot and inter-gene relationships, respectively.…
Jiaxin Qi, Hang Li, Yan Cui, Yuhua Zheng +1
Gene Regulatory Network (GRN) inference is essential for understanding complex cellular mechanisms, rendered tractable through single-cell transcriptomic data. With the emergence…
Xinyu Wang, Ruoyu Wang, Qiangwei Peng, Peijie Zhou +1
Reconstructing dynamical evolution from limited observations is a fundamental challenge in single-cell biology, where dynamic unbalanced optimal transport (OT) provides a…
Metadata from BioTender-max/icml2026-ai-bio (CC0-1.0).