The DOI matches its Crossref record; 161 of the 163 references it cites were found in a registry or an index, and 1 are not checked yet.
Base-resolution models of transcription-factor binding reveal soft motif syntax
Open accessPublished version of a preprint
Abstract
The arrangement (syntax) of transcription factor (TF) binding motifs is an important part of the cis-regulatory code, yet remains elusive. We introduce a deep learning model, BPNet, that uses DNA sequence to predict base-resolution chromatin immunoprecipitation (ChIP)-nexus binding profiles of pluripotency TFs. We develop interpretation tools to learn predictive motif representations and identify soft syntax rules for cooperative TF binding interactions. Strikingly, Nanog preferentially binds with helical periodicity, and TFs often cooperate in a directional manner, which we validate using clustered regularly interspaced short palindromic repeat (CRISPR)-induced point mutations. Our model represents a powerful general approach to uncover the motifs and syntax of cis-regulatory sequences in genomics data.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The BPNet architecture has been used widely in genomics and represents a very strong default architecture for modeling small-sized datasets from scratch through supervised learning.”
From Nucleotide Transformer: building and evaluating robust foundation models for human genomics (2025) · cites this paper as [9]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Machine-learning models trained to predict function from DNA sequences have been successful at characterizing regulatory syntax and interpreting genetic variant effects.”
From Predicting RNA-seq coverage from DNA sequence as a unifying model of gene regulation (2025) · cites this paper as [7]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Thus far, such models have focused on assays in which measured activity is proportional to local sequencing read counts.”
From Predicting RNA-seq coverage from DNA sequence as a unifying model of gene regulation (2025) · cites this paper as [7]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Finer resolution has potential benefits when the data support it15, but would extend the sequence length entering the quadratic complexity MHA and make the model engineering intractable on currently available hardware.”
From Effective gene expression prediction from sequence by integrating long-range interactions (2021) · cites this paper as [15]
The cited source says what the claim attributes to it.
In the citing paper
“Additionally, a deep learning algorithm applied to binding of pluripotency TFs at base resolution in mouse embryonic stem cells (ESCs) suggested a “soft motif syntax” whereby TFs help each other to bind directly to the enhancer with a lenient distance-dependency between binding sites [98].”
From Transcriptional enhancers and their communication with gene promoters (2021) · cites this paper as [98]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
VMD: visual molecular dynamics
Humphrey, W., Dalke, A., & Schulten, K. (1996) · Journal of Molecular Graphics · doi:10.1016/0263-7855(96)00018-5 · Cited by 66,952
The Sequence Alignment/Map format and SAMtools
Li, H., Handsaker, B., Wysoker, A., Fennell, T., Ruan, J., Homer, N., Marth, G., Abecasis, G., Durbin, R., & 1000 Genome Project Data Processing Subgroup (2009) · Bioinformatics · doi:10.1093/bioinformatics/btp352 · Cited by 62,041
Fast and accurate short read alignment with Burrows-Wheeler transform
Li, H., & Durbin, R. (2009) · Bioinformatics · doi:10.1093/bioinformatics/btp324 · Cited by 58,607
Cutadapt removes adapter sequences from high-throughput sequencing reads
Martin, M. (2011) · EMBnet.journal · doi:10.14806/ej.17.1.200 · Cited by 33,889
Kimura, M. (1980) · Journal of Molecular Evolution · doi:10.1007/bf01731581 · Cited by 29,778
BEDTools: a flexible suite of utilities for comparing genomic features
Quinlan, A. R., & Hall, I. M. (2010) · Bioinformatics · doi:10.1093/bioinformatics/btq033 · Cited by 27,437
Ultrafast and memory-efficient alignment of short DNA sequences to the human genome.
Langmead, B., Trapnell, C., Pop, M., & Salzberg, S. L. (2009) · Genome Biology · doi:10.1186/gb-2009-10-3-r25 · Cited by 21,849
Hierarchical Grouping to Optimize an Objective Function
Ward, J. H. (1963) · Journal of the American Statistical Association · doi:10.1080/01621459.1963.10500845 · Cited by 21,341
Research works printed but not linked: 1
- Shrikumar, A. et al. TF-MoDISco v0.4.2.2-alpha: technical note. Preprint at arXiv https://arxiv.org/abs/1811.00416 (2018). · arXiv
Cited by
Sorted by citations
Items 101–200 of 654
Dual-role transcription factors stabilize intermediate expression levels
He, J., Huo, X., Pei, G., Jia, Z., Yan, Y., Yu, J., Qu, H., Xie, Y., Yuan, J., Zheng, Y., et al. (2024) · Cell · doi:10.1016/j.cell.2024.03.023 · Cited by 46
Genome access is transcription factor-specific and defined by nucleosome position
Grand, R. S., Pregnolato, M., Baumgartner, L., Hoerner, L., Burger, L., & Schübeler, D. (2024) · Molecular Cell · doi:10.1016/j.molcel.2024.08.009 · Cited by 49
Enhancer reprogramming: critical roles in cancer and promising therapeutic strategies
Yang, J., Zhou, F., Luo, X., Fang, Y., Wang, X., Liu, X., Xiao, R., Jiang, D., Tang, Y., Yang, G., et al. (2025) · Cell Death Discovery · doi:10.1038/s41420-025-02366-3 · Cited by 56
Zhang, Y., Wang, Z., Zeng, Y., Liu, Y., Xiong, S., Wang, M., Zhou, J., & Zou, Q. (2021) · Briefings in Bioinformatics · doi:10.1093/bib/bbab525 · Cited by 46
Transcriptional Regulation and Implications for Controlling Hox Gene Expression
Afzal, Z., & Krumlauf, R. K. (2022) · Journal of Developmental Biology · doi:10.3390/jdb10010004 · Cited by 51
“Therefore, for a deep level of understanding of how Hox-responsive enhancers work, it is important to understand how many and what kinds of TFs bind to an enhancer, the rules or syntax of their spacing and organization, the positions of nearby motifs and the identity of motifs that can serve to synergize or antagonize…”
BackgroundEvolution of transcription factor binding through sequence variations and turnover of binding sitesPreprint
Krieger, G., Lupo, O., Wittkopp, P. J., & Barkai, N. (2022) · Genome Research · doi:10.1101/gr.276715.122 · Cited by 50
“…include changes in nucleosome positioning (Mirny 2010; Sun et al. 2015), variations affecting binding of a cooperating TF (Stefflova et al. 2013; Avsec et al. 2021), or variations in promoter regions surrounding the motif, perhaps recognized by TF regions outside the DBD (Brodsky et al. 2020).”
Decoding enhancer complexity with machine learning and high-throughput discovery
Smith, G. D., Ching, W. H., Cornejo‐Páramo, P., & Wong, E. S. W. (2023) · Genome biology · doi:10.1186/s13059-023-02955-4 · Cited by 48
Cazares, T. A., Rizvi, F. W., Iyer, B., Chen, X., Kotliar, M., Bejjani, A. T., Wayman, J. A., Donmez, O. A., Wronowski, B., Parameswaran, S., et al. (2023) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1010863 · Cited by 44
“Furthermore, 555 BPnet’s base-pair resolved architecture has already been tested on TF ChIP-seq [67] and 556 appears well-poised to leverage highly-resolved ATAC-seq as model input, too.”
BackgroundMethodEnhancer-driven cell type comparison reveals similarities between the mammalian and bird pallium
Hecker, N., Kempynck, N., Mauduit, D., Abaffyová, D., Vandepoel, R., Dieltiens, S., Borm, L. E., Sarropoulos, I., González‐Blas, C. B., Man, J. D., et al. (2025) · Science · doi:10.1126/science.adp3957 · Cited by 51
Domain-adaptive neural networks improve cross-species prediction of transcription factor bindingPreprint
Cochran, K., Srivastava, D., Shrikumar, A., Balsubramani, A., Hardison, R. C., Kundaje, A. B., & Mahony, S. (2022) · Genome Research · doi:10.1101/gr.275394.121 · Cited by 42
“We chose neural networks due to their ability to learn arbitrarily complex predictive sequence patterns (Avsec et al. 2020).”
Self-citationLearning the Regulatory Code of Gene Expression
Zrimec, J., Buric, F., Kokina, M., García, V., & Zelezniak, A. (2021) · Frontiers in Molecular Biosciences · doi:10.3389/fmolb.2021.673363 · Cited by 45
“Due to the inherent capability of DNNs to learn predictive motif representations, rules for cooperative TF binding interactions (Avsec et al., 2021) and higher-order sequence features, such as secondary motifs and local sequence context (Zeng et al., 2016), as well as genotypic variation effects…”
BackgroundPioneer activity distinguishes activating from non‐activating SOX2 binding sites
Maresca, M., van den Brand, T., Li, H., Teunissen, H., Davies, J. O. J., & de Wit, E. (2023) · The EMBO Journal · doi:10.15252/embj.2022113150 · Cited by 39
From computational models of the splicing code to regulatory mechanisms and therapeutic implications
Capitanchik, C., Wilkins, O. G., Wagner, N., Gagneur, J., & Ule, J. (2024) · Nature Reviews Genetics · doi:10.1038/s41576-024-00774-2 · Cited by 45
“More complex in silico mutagenesis experiments have been used in the context of gene regulation to explore the impact of inserting transcription factor motifs into a random sequence context and the positional relationships between multiple motifs for different proteins 105,106 .”
Self-citationGenomics enters the deep learning era
Routhier, E., & Mozziconacci, J. (2022) · PeerJ · doi:10.7717/peerj.13613 · Cited by 45
Zhang, Z., Feng, F., Qiu, Y., & Liu, J. (2023) · Nucleic Acids Research · doi:10.1093/nar/gkad436 · Cited by 40
“motifs or reflect other sequence binding patterns such as co-binding patterns [31, 32].”
BackgroundInterpreting cis-regulatory mechanisms from genomic deep neural networks using surrogate models
Seitz, E. E., McCandlish, D. M., Kinney, J. B., & Koo, P. K. (2024) · Nature Machine Intelligence · doi:10.1038/s42256-024-00851-5 · Cited by 42
“8, y was computed using the profile contribution score defined in the original paper 5 .”
InfluentialDeep learning the cis-regulatory code of chromatin dynamics during cellular reprogrammingPreprint
Nair, S., Ameen, M., Sundaram, L., Pampari, A., Schreiber, J. M., Balsubramani, A., Wang, Y. X., Burns, D., Blau, H. M., Karakikes, I., et al. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.10.04.560808 · Cited by 38
Self-citationLee, N. K., Tang, Z., Toneyan, S., & Koo, P. K. (2023) · Genome biology · doi:10.1186/s13059-023-02941-w · Cited by 41
Multitissue H3K27ac profiling of GTEx samples links epigenomic variation to disease
Hou, L., Xiong, X., Park, Y., Boix, C. A., James, B. T., Sun, N., He, L., Patel, A., Zhang, Z., Molinié, B., et al. (2023) · Nature Genetics · doi:10.1038/s41588-023-01509-5 · Cited by 44
“Future research could increase the power by augmenting sample sizes or utilizing deep models to borrow regulation information across the genome 67,68 .”
BackgroundWang, K., Zeng, X., Zhou, J., Liu, F., Luan, X., & Wang, X. (2024) · Briefings in Bioinformatics · doi:10.1093/bib/bbae195 · Cited by 35
The single-molecule accessibility landscape of newly replicated mammalian chromatin
Ostrowski, M. S., Yang, M. G., McNally, C. P., Abdulhay, N. J., Wang, S., Renduchintala, K., Irkliyenko, I., Biran, A., Chew, B. T. L., Midha, A. D., et al. (2024) · Cell · doi:10.1016/j.cell.2024.10.039 · Cited by 35
Ramstein, G. P., & Buckler, E. S. (2022) · Genome Biology · doi:10.1186/s13059-022-02747-2 · Cited by 34
Unlocking gene regulation with sequence-to-function models
Sasse, A., Chikina, M. D., & Mostafavi, S. (2024) · Nature Methods · doi:10.1038/s41592-024-02331-5 · Cited by 40
Ranking reprogramming factors for cell differentiation
Hammelman, J., Patel, T., Closser, M., Wichterle, H., & Gifford, D. K. (2022) · Nature Methods · doi:10.1038/s41592-022-01522-2 · Cited by 34
Yeo, R. W., Zhou, O. Y., Zhong, B. L., Sun, E., Negredo, P. N., Nair, S., Sharmin, M., Ruetz, T. J., Wilson, M., Kundaje, A. B., et al. (2023) · Nature Aging · doi:10.1038/s43587-023-00449-3 · Cited by 37
Self-citationMany transcription factor families have evolutionarily conserved binding motifs in plants
Zenker, S., Wulf, D., Meierhenrich, A., Viehöver, P., Becker, S., Eisenhut, M., Stracke, R., Weißhaar, B., & Bräutigam, A. (2025) · PLANT PHYSIOLOGY · doi:10.1093/plphys/kiaf205 · Cited by 34
“Competition at binding sites and different binding affinities may also provide an explanation for the still substantial gap in predictability of gene expression from sequence and from binding events alone (Li et al. 2018; Avsec et al. 2021; de Almeida et al. 2022).”
Wang, Y. X., Palla, A. R., Ho, A. T. V., Robinson, D. C. L., Ravichandran, M., Markov, G. J., Mai, T., Still, C., Balsubramani, A., Nair, S., et al. (2025) · Cell stem cell · doi:10.1016/j.stem.2025.05.012 · Cited by 39
Self-citationA survey on algorithms to characterize transcription factor binding sites
Tognon, M., Giugno, R., & Pinello, L. (2023) · Briefings in Bioinformatics · doi:10.1093/bib/bbad156 · Cited by 32
Towards in silico CLIP-seq: predicting protein-RNA interaction via sequence-to-signal learning
Horlacher, M., Wagner, N., Moyon, L., Kuret, K., Goedert, N., Salvatore, M., Ule, J., Gagneur, J., Winther, O., & Marsico, A. (2023) · Genome biology · doi:10.1186/s13059-023-03015-7 · Cited by 33
“Note that the proposed generalization of Integrated Gradients to output probability vectors is in analogy to Avsec et al.’s generalization of DeepLIFT [56] scores, described in [2].”
BackgroundMethodResultInfluentialSelf-citationDaSilva, L. F., Senan, S., Patel, Z. M., Reddy, A. J., Gabbita, S., Nussbaum, Z., Córdova, C. M. V., Wenteler, A., Weber, N., Tunjic, T. M., et al. (2024) · doi:10.1101/2024.02.01.578352 · Cited by 32
“ChromBPNet consists of two convolutional neural networks that are similar in structure to BPNet 46 .”
Epigenomic insights into common human disease pathology
Bell, C. G. (2024) · Cellular and Molecular Life Sciences · doi:10.1007/s00018-024-05206-2 · Cited by 36
“Moving forward, computational methods, as opposed to experimental data, will be increasingly used to predict effectors, such as neural network Deep Learning (DL) for de novo prediction of cell-type-specific chromatin organization [130], or DL for TF binding prediction [131].”
MethodUsing machine learning to enhance and accelerate synthetic biology
Rai, K., Wang, Y., O’Connell, R. W., Patel, A. B., & Bashor, C. J. (2024) · Current Opinion in Biomedical Engineering · doi:10.1016/j.cobme.2024.100553 · Cited by 35
fastISM: performant in silico saturation mutagenesis for convolutional neural networks
Nair, S., Shrikumar, A., Schreiber, J. M., & Kundaje, A. B. (2022) · Bioinformatics · doi:10.1093/bioinformatics/btac135 · Cited by 34
Self-citationDecoding the PITX2-controlled genetic network in atrial fibrillation
Steimle, J. D., Canozo, F. J. G., Park, M., Kadow, Z. A., Samee, M. A. H., & Martin, J. F. (2022) · JCI Insight · doi:10.1172/jci.insight.158895 · Cited by 33
“335 The combination of TFs present in each CM type and the binding sites present at a CRE dictate 336 the regulatory grammars acting on the target transcript (21).”
BackgroundTranscription factor condensates and signaling driven transcription
Mann, R., & Notani, D. (2023) · Nucleus · doi:10.1080/19491034.2023.2205758 · Cited by 39
“The recurring motifs act cooperatively to support Nanog’s binding on active enhancers, hence its phase separation [126].”
BackgroundSystematic assessment of ISWI subunits shows that NURF creates local accessibility for CTCF
Iurlaro, M., Masoni, F., Flyamer, I. M., Wirbelauer, C., Iskar, M., Burger, L., Giorgetti, L., & Schübeler, D. (2024) · Nature Genetics · doi:10.1038/s41588-024-01767-x · Cited by 35
Interpreting cis-regulatory interactions from large-scale deep neural networks
Toneyan, S., & Koo, P. K. (2024) · Nature Genetics · doi:10.1038/s41588-024-01923-3 · Cited by 38
Base-resolution prediction of transcription factor binding signals by a deep learning framework
Zhang, Q., He, Y., Wang, S., Chen, Z., Guo, Z., Cui, Z., Liu, Q., & Huang, D.-S. (2022) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1009941 · Cited by 33
“To measure the performance of our proposed framework FCNsignal, several existing state-ofthe-art methods were used, including MEME [12], STREME [13], DanQ [29], DeepCNN [53], FCNA [31], FCNA, BPNet [33], DeepEmbed [54], Deopen [55], LSGKM [56] and DeltaSVM [57].”
BackgroundMethodKotha, S. R., & Staller, M. V. (2023) · Genetics · doi:10.1093/genetics/iyad131 · Cited by 36
“Intersection of the improved mechanistic predictor and convolutional neural network models improves prediction accuracy.”
BackgroundMethodYin, C., Castillo-Hair, S. M., Byeon, G. W., Bromley, P., Meuleman, W. R. A., & Seelig, G. (2025) · Cell Systems · doi:10.1016/j.cels.2025.101302 · Cited by 35
Annotating the genome at single-nucleotide resolution with DNA foundation models
de Almeida, B. P., Dalla-Torre, H., Richard, G., Blum, C. F., Hexemer, L., Gélard, M., Mendoza‐Revilla, J., Tang, Z., Marin, F. I., Emms, D., et al. (2025) · Nature Methods · doi:10.1038/s41592-025-02881-2 · Cited by 39
“Finally, we compared SegmentNT with two other popular, small CNN architectures in genomics developed for nucleotide-resolution tasks that do not use pre-trained models: BPNet [38] and SpliceAI [39] that proved successful in modeling transcription-factor binding and splicing, respectively.”
Studying transcription factor function in the genome at molecular resolution
Krebs, A. R. (2021) · Trends in Genetics · doi:10.1016/j.tig.2021.03.008 · Cited by 28
Designing realistic regulatory DNA with autoregressive language modelsPreprint
Lal, A., Garfield, D., Biancalani, T., & Eraslan, G. (2024) · Genome Research · doi:10.1101/gr.279142.124 · Cited by 38
High-throughput biochemistry in RNA sequence space: predicting structure and function
Marklund, E., Ke, Y., & Greenleaf, W. J. (2023) · Nature Reviews Genetics · doi:10.1038/s41576-022-00567-5 · Cited by 30
“Deep learning models can also be used as ‘oracles’ by carrying out in silico experiments with a trained deep learning model 93 to test different mechanistic hypotheses (Fig.”
Deep-learning prediction of gene expression from personal genomes
Drusinsky, S., Whalen, S., & Pollard, K. S. (2026) · Genome biology · doi:10.1186/s13059-025-03926-7 · Cited by 40
“Models that predict RNA levels from DNA sequences show tremendous promise for decoding tissue-specific gene regulatory mechanisms [1–5], revealing the genetic architecture of traits [6–10], and interpreting noncoding genetic variation [10, 11].”
High-Resolution Mapping of Multiway Enhancer-Promoter Interactions Regulating Pathogen Detection
Vangala, P., Murphy, R., Quinodoz, S. A., Gellatly, K. J., McDonel, P. E., Guttman, M., & Garber, M. G. (2020) · Molecular Cell · doi:10.1016/j.molcel.2020.09.005 · Cited by 29
“Recent applications of deep learning techniques showpromising possibilities in modeling TFBM interactions (Avsec et al., 2020).”
BackgroundCongenital anemia reveals distinct targeting mechanisms for master transcription factor GATA1
Ludwig, L. S., Lareau, C. A., Bao, E. L., Liu, N., Utsugisawa, T., Tseng, A. M., Myers, S. A., Verboon, J. M., Ulirsch, J. C., Luo, W., et al. (2022) · Blood · doi:10.1182/blood.2021013753 · Cited by 30
Self-citationInterpreting neural networks for biological sequences by learning stochastic masks
Linder, J., Fleur, A. L., Chen, Z., Ljubetič, A., Baker, D. A., Kannan, S., & Seelig, G. (2022) · Nature Machine Intelligence · doi:10.1038/s42256-021-00428-6 · Cited by 25
“Deep Neural Networks have successfully been applied to a diverse set of biological sequence prediction problems, including predicting transcription factor binding (Alipanahi et al., 2015; Avsec et al., 2021; Eraslan et al., 2019; Movva et al., 2019), chromatin modification and accessibility (Zhou et al.”
BackgroundDissecting the cis-regulatory syntax of transcription initiation with deep learningPreprint
Cochran, K., Yin, M., Mantripragada, A., Schreiber, J. M., Marinov, G. K., Shah, S. R., Yu, H., Lis, J. T., & Kundaje, A. B. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.05.28.596138 · Cited by 36
“ProCapNet’s architecture is based on the BPNet model previously developed to predict base-resolution TF binding profiles 57 .”
InfluentialSelf-citationIdentification of mammalian transcription factors that bind to inaccessible chromatin
Pop, R. T., Pisante, A., Nagy, D., Martin, P. C. N., Mikheeva, L. A., Hayat, A., Ficz, G., & Zabet, N. R. (2023) · Nucleic Acids Research · doi:10.1093/nar/gkad614 · Cited by 30
Computational and experimental methods for classifying variants of unknown clinical significance.Preprint
Spielmann, M., & Kircher, M. (2022) · PubMed · doi:10.1101/mcs.a006196 · Cited by 28
Designing DNA With Tunable Regulatory Activity Using Discrete DiffusionPreprint
Sarkar, A., Durán, A., Yu, Y., Lin, D.-W., Kang, Y., Somia, N., Mantilla, P., Zhou, J., Nagai, M., Tang, Z., et al. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.05.23.595630 · Cited by 35
Wu, J., He, K., Mao, R., Shang, X., & Cambria, E. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103283 · Cited by 29
A cis-regulatory lexicon of DNA motif combinations mediating cell-type-specific gene regulation
Donohue, L. K. H., Guo, M. G., Zhao, Y., Jung, N., Bussat, R. T., Kim, D. S., Neela, P. H., Kellman, L. N., Garcia, O. S., Meyers, R. M., et al. (2022) · Cell Genomics · doi:10.1016/j.xgen.2022.100191 · Cited by 25
A multimodal conversational agent for DNA, RNA and protein tasks
de Almeida, B. P., Richard, G., Dalla-Torre, H., Blum, C. F., Hexemer, L., Pandey, P., Laurent, S., Rajesh, C., Lopez, M., Laterre, A., et al. (2025) · Nature Machine Intelligence · doi:10.1038/s42256-025-01047-1 · Cited by 50
“https://doi.org/10.1038/s42256-025-01047-1 have been widely applied for sequence models, notably in the case of DNA 7,46 , this has never been done for multimodal models where the output is expressed in natural language such as ChatNT.”
InfluentialSasaki, T., Ro, K., Caillieux, E., Manabe, R., Bohl‐Viallefond, G., Baduel, P., Colot, V., Kakutani, T., & Quadrana, L. (2022) · The EMBO Journal · doi:10.15252/embj.2021110070 · Cited by 22
“Clustering of short-sequence motifs may imply that VANCs interact with DNA as homomultimers, similarly to the mode of action described for some transcription factors (Avsec et al, 2021).”
Computational tools for inferring transcription factor activity
Hecker, D., Lauber, M., Ardakani, F. B., Ashrafiyan, S., Manz, Q., Kersting, J., Hoffmann, M., Schulz, M. H., & List, M. (2023) · PROTEOMICS · doi:10.1002/pmic.202200462 · Cited by 27
Integrative computational epigenomics to build data-driven gene regulation hypotheses
Chen, T., & Tyagi, S. (2020) · GigaScience · doi:10.1093/gigascience/giaa064 · Cited by 21
Decoding biology with massively parallel reporter assays and machine learningPreprint
Fleur, A. L., Shi, Y., & Seelig, G. (2024) · Genes & Development · doi:10.1101/gad.351800.124 · Cited by 29
“3C, right; Shrikumar et al. 2019; Carter et al. 2020; Lundberg et al. 2020; Avsec et al. 2021; Linder et al. 2022b).”
BackgroundContext transcription factors establish cooperative environments and mediate enhancer communication
Kribelbauer, J. F., Pushkarev, O., Gardeux, V., Faltejsková, K., Russeil, J., van Mierlo, G., & Deplancke, B. (2024) · Nature Genetics · doi:10.1038/s41588-024-01892-7 · Cited by 27
Decoding sequence determinants of gene expression in diverse cellular and disease states
Lal, A., Karollus, A., Gunsalus, L. M., Garfield, D., Nair, S., Tseng, A. M., Gordon, M. G., Blischak, J., Geijn, B. V. D., Bhangale, T., et al. (2026) · Nature Methods · doi:10.1038/s41592-026-03102-0 · Cited by 34
“Recently, modeling the genomic context up to hundreds of kilobases has enabled effective prediction of bulk cap analysis of gene expression (CAGE-seq) (Avsec et al. 2021) and RNA-seq (Linder et al. 2023) profiles.”
InfluentialAutomated classification of cellular expression in multiplexed imaging data with Nimbus
(2025) · doi:10.1038/s41592-025-02826-9 · Cited by 24
“This volume of data is needed to prevent overfitting, and underpins the success of recent efforts to predict protein structures 31 , identify transcription factor binding sites 32 and segment cells 17 .”
Towards a better understanding of TF-DNA binding prediction from genomic features
Wang, Z., Gong, M., Liu, Y., Xiong, S., Wang, M., Zhou, J., & Zhang, Y. (2022) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2022.105993 · Cited by 24
Tseng, A. M., Shrikumar, A., & Kundaje, A. B. (2020) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2020.06.11.147272 · Cited by 24
Self-citationGenetic architecture of human brain evolution
Fair, T., & Pollen, A. A. (2023) · Current Opinion in Neurobiology · doi:10.1016/j.conb.2023.102710 · Cited by 24
Enhancers display constrained sequence flexibility and context-specific modulation of motif functionPreprint
Reiter, F., de Almeida, B. P., & Stark, A. (2023) · Genome Research · doi:10.1101/gr.277246.122 · Cited by 27
Transcriptional regulation in plants: Using omics data to crack the cis-regulatory code
Zemlyanskaya, E. V., Dolgikh, V. A., Levitsky, V. G., & Mironova, V. (2021) · Current Opinion in Plant Biology · doi:10.1016/j.pbi.2021.102058 · Cited by 22
GraphTGI: an attention-based graph embedding model for predicting TF-target gene interactions
Du, Z., Wu, Y.-H., Huang, Y., Chen, J., Pan, G.-Q., Hu, L., You, Z., & Li, J. (2022) · Briefings in Bioinformatics · doi:10.1093/bib/bbac148 · Cited by 23
Characterization of sequence determinants of enhancer function using natural genetic variation
Yang, M. G., Ling, E., Cowley, C. J., Greenberg, M. E., & Vierbuchen, T. (2022) · eLife · doi:10.7554/elife.76500 · Cited by 25
“In the future, using deep learning or other sophisticated approaches to analyze these data could provide further insight into more complex sequence features (i.e. beyond the presence or absence of specific k-mers) that underlie TF binding and enhancer activity (Avsec et al., 2021).”
Deep learning in regulatory genomics: from identification to design
Hu, X., Fernie, A. R., & Yan, J. (2023) · Current Opinion in Biotechnology · doi:10.1016/j.copbio.2022.102887 · Cited by 25
Zheng, W., Fong, J. H. C., Wan, Y. K., Chu, A. H. Y., Huang, Y., Wong, A. S. L., & Ho, J. W. K. (2023) · Cell Systems · doi:10.1016/j.cels.2023.10.011 · Cited by 22
Naqvi, S., Kim, S., Tabatabaee, S., Pampari, A., Kundaje, A., Pritchard, J. K., & Wysocka, J. (2025) · Cell Genomics · doi:10.1016/j.xgen.2025.100780 · Cited by 18
“Top CWMs output from TF-MoDISCO were matched to their genomic locations by adapting a previously described procedure 6,7 that considers both the Jaccardian similarity between a CWM and a test sequence as well as that sequence’s overall contribution score.”
Self-citationLi, H., & Guan, Y. (2021) · Genome Research · doi:10.1101/gr.269613.120 · Cited by 22
“Transcription factors (TFs) play a fundamental role in regulating gene expression via binding to specific DNA sequences (Badis et al. 2009; Vaquerizas et al. 2009; Jolma et al. 2013).”
Modelling and design of transcriptional enhancers
Winter, S. D., Konstantakos, V., & Aerts, S. (2025) · Nature Reviews Bioengineering · doi:10.1038/s44222-025-00280-y · Cited by 21
“Similarly, BPNet 68 predicts TF binding but its output is more sophisticated than DeepBind; it takes 1-kb DNA sequences as input and separately predicts ChIP–nexus binding profile shape and coverage at single base pair resolution.”
InfluentialThe human proteome with direct physical access to DNA
Trendel, J., Trendel, S., Sha, S., Greulich, F., Goll, S., Wudy, S. I., Kleigrewe, K., Kubicek, S., Uhlenhaut, N. H., & Küster, B. (2025) · Cell · doi:10.1016/j.cell.2025.04.037 · Cited by 22
Diversification and Functional Evolution of HOX Proteins
Singh, N. P., & Krumlauf, R. K. (2022) · Frontiers in Cell and Developmental Biology · doi:10.3389/fcell.2022.798812 · Cited by 26
“, ChIP-seq, ATAC-seq, massive parallel reporter assays and single cell transcriptomics) (Zhen and Andolfatto, 2012; Paul et al., 2014; He et al., 2015; Gasperskaja and Kucinskas, 2017; Avsec et al., 2021).”
MethodIn silico discovery of repetitive elements as key sequence determinants of 3D genome folding
Gunsalus, L. M., Keiser, M. J., & Pollard, K. S. (2023) · Cell Genomics · doi:10.1016/j.xgen.2023.100410 · Cited by 22
“Deep learning models perform well in predicting enhancer activity [16,17], transcription factor binding [18], gene expression [19], and genome folding [20,21] from sequence, with newer models increasing scale and incorporating epigenetic assays to provide cell type-specific context [22–24].”
MethodXu, C., Kleinschmidt, H., Yang, J., Leith, E. M., Johnson, J. K., Tan, S., Mahony, S., & Bai, L. (2024) · Molecular Cell · doi:10.1016/j.molcel.2024.06.022 · Cited by 21
Catta-Preta, R., Lindtner, S., Ypsilanti, A. R., Seban, N., Price, J. D., Abnousi, A., Su-Feher, L., Wang, Y., Cichewicz, K., Boerma, S. A., et al. (2024) · Developmental Cell · doi:10.1016/j.devcel.2024.10.004 · Cited by 21
CREsted: modeling genomic and synthetic cell-type-specific enhancers across tissues and species
Kempynck, N., Winter, S. D., Blaauw, C. H., Konstantakos, V., Ekşi, E. C., Dieltiens, S., Abaffyová, D., Bercier, V., Taskiran, I. I., Hulselmans, G. J., et al. (2026) · Nature Methods · doi:10.1038/s41592-026-03057-2 · Cited by 29
“Sequence-to-function models 12 take in genomic sequences and predict a variety of genomic assays, including TF binding 9 , chromatin accessibility 4,6–8, 13 , enhancer activity CREsted allows for nucleotide-level explanations using gradient-based methods 37 and in silico mutagenesis (ISM) 3,6 ,…”
Assessment and Optimization of Explainable Machine Learning Models Applied to Transcriptomic Data
Zhao, Y., Shao, J., & Asmann, Y. W. (2022) · Genomics Proteomics & Bioinformatics · doi:10.1016/j.gpb.2022.07.003 · Cited by 21
“Benefit-ing from these model explainers, computational biologists discovered the syntax of transcription factor (TF) binding motifs by interpreting models trained to predict chromatin accessibility [19,20]; and screened for cancer marker genes from models of cancer type classification [21–23].”
MethodNeuronMotif: Deciphering cis-regulatory codes by layer-wise demixing of deep neural networks
Zheng, W., Hua, K., Wei, L., Ma, S., Jiang, R., Zhang, X., Li, Y., Wong, W. H., & Wang, X. (2023) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2216698120 · Cited by 21
“Some tools like TF-MoDISco (15) further attempt to align the subsequences based on their ISs to estimate the motif PWM (25).”
InfluentialMartin, V., Zhuang, F., Zhang, Y., Pinheiro, K., & Gordân, R. (2023) · Nucleic Acids Research · doi:10.1093/nar/gkad872 · Cited by 20
“Pairs of cooperating TFs can be identified using large-scale in vitro assays, such as CAP-SELEX ( 12 ) , or from in vivo chromatin immunoprecipitation data combined with deep learning modeling ( 49 ) .”
BackgroundMethodPredictive analyses of regulatory sequences with EUGENe
Klie, A., Laub, D., Talwar, J. V., Stites, H., Jores, T., Solvason, J. J., Farley, E. K., & Carter, H. K. (2023) · Nature Computational Science · doi:10.1038/s43588-023-00544-w · Cited by 24
“We have also implemented a ProfileModule for BPNet-style 30 training, in which models produce multiple tensor outputs (or ‘heads’), accept optional control inputs and use multiple loss functions 67 .”
BackgroundMethodInfluentialMLSNet: a deep learning model for predicting transcription factor binding sites
Zhang, Y., Wang, Z., Ge, F., Wang, X., Zhang, Y., Li, S., Guo, Y., Song, J., & Yu, D. (2024) · Briefings in Bioinformatics · doi:10.1093/bib/bbae489 · Cited by 23
EpiGePT: a Pretrained Transformer model for epigenomicsPreprint
Gao, Z., Liu, Q., Zeng, W., Jiang, R., & Wong, W. H. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.07.15.549134 · Cited by 20
Deep learning and CRISPR-Cas13d ortholog discovery for optimized RNA targeting
Wei, J., Lotfy, P., Faizi, K., Baungaard, S., Gibson, E., Wang, E., Slabodkin, H., Kinnaman, E., Chandrasekaran, S., Kitano, H., et al. (2021) · doi:10.1101/2021.09.14.460134 · Cited by 67
“32 ● Long short-term memory recurrent neural network (LSTM): LSTM units – [16, 32,64,128], dense layer units – [8, 16, 32], number of recurrent dense layes – [0,1,2,3], dropout rate – [0.”
BackgroundDeep profiling of gene expression across 18 human cancers
Qiu, W., Dincer, A. B., Janizek, J. D., Çelik, S., Pittet, M. J., Naxerova, K., & Lee, S. (2024) · Nature Biomedical Engineering · doi:10.1038/s41551-024-01290-8 · Cited by 25
Chromatin-dependent motif syntax defines differentiation trajectories
Durdu, S., Iskar, M., Isbel, L., Hoerner, L., Wirbelauer, C., Burger, L., Heß, D., Iešmantavičius, V., & Schübeler, D. (2025) · Molecular Cell · doi:10.1016/j.molcel.2025.07.005 · Cited by 19
Schaepe, J. M., Fries, T., Doughty, B. R., Ramalingam, V., Liu, B. B., Crocker, O. J., Marinov, G. K., Hinks, M. M., Marklund, E., & Greenleaf, W. J. (2025) · Cell · doi:10.1016/j.cell.2025.11.008 · Cited by 23
Single-Cell Epigenomics Reveals Mechanisms of Cancer Progression
LaFave, L. M., Savage, R. E., & Buenrostro, J. D. (2022) · Annual Review of Cancer Biology · doi:10.1146/annurev-cancerbio-070620-094453 · Cited by 20
Dissecting Plant Gene Functions Using CRISPR Toolsets for Crop Improvement
Zhang, R., Li, B., Yang, Z.-G., Huang, J., Sun, W.-H., Bhanbhro, N., Liu, W., & Chen, K. (2022) · Journal of Agricultural and Food Chemistry · doi:10.1021/acs.jafc.2c01754 · Cited by 20
CVD-associated SNPs with regulatory potential reveal novel non-coding disease genes
Zhu, C., Baumgarten, N., Wu, M., Wang, Y., Das, A. P., Kaur, J., Ardakani, F. B., Duong, T. T., Pham, D. M., Duda, M., et al. (2023) · Human Genomics · doi:10.1186/s40246-023-00513-4 · Cited by 19
“To predict TF binding, different approaches exist using position weight matrices (PWMs) [14, 15], that are available for the majority of human TFs, or more complex methods such as deep learning-based models [16, 17], which are currently more limited due to lack of TF-specific data.”
BackgroundKathail, P., Shuai, R. W., Chung, R., Ye, C., Loeb, G. B., & Ioannidis, N. M. (2024) · Genome biology · doi:10.1186/s13059-024-03335-2 · Cited by 28
Uncovering tissue-specific binding features from differential deep learning
Phuycharoen, M., Zarrineh, P., Bridoux, L., Amin, S., Losa, M., Chen, K., Bobola, N., & Rattray, M. (2020) · Nucleic Acids Research · doi:10.1093/nar/gkaa009 · Cited by 19
Short tandem repeats bind transcription factors to tune eukaryotic gene expressionPreprint
Horton, C. A., Alexandari, A. M., Hayes, M. G. B., Marklund, E., Schaepe, J. M., Aditham, A. K., Shah, N., Shrikumar, A., Afek, A., Greenleaf, W. J., et al. (2022) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2022.05.24.493321 · Cited by 20
Self-citationWetzel, J. L., Zhang, K., & Singh, M. (2022) · Genome Research · doi:10.1101/gr.276606.122 · Cited by 20
“Further, these data have been used to train machine learning models to uncover cooperative TF binding and other regulatory “grammars” (Avsec et al. 2021; Miraldi et al. 2021) and to predict the impact of mutations within noncoding regions of the genome (Zhou and Troyanskaya 2015; Martin et al.”
MethodFlashzoi: an enhanced Borzoi for accelerated genomic analysis
Hingerl, J., Karollus, A., & Gagneur, J. (2025) · Bioinformatics · doi:10.1093/bioinformatics/btaf467 · Cited by 28
“Moreover, Enformer and Borzoi have been used as foundation models, i.e. as models upon which further models can be built for more specific tasks including personal gene expression (Drusinsky et al. 2024) as well as single-cell gene expression and accessibility (Schwessinger et al. 2023, Hingerl et al. 2024, Lal et al.…”
InfluentialSelf-citationThe role of single-cell genomics in human genetics
Sreenivasan, V. K. A., Balachandran, S., & Spielmann, M. (2022) · Journal of Medical Genetics · doi:10.1136/jmedgenet-2022-108588 · Cited by 19
Pratt, H., Andrews, G., Shedd, N., Phalke, N. N., Li, T., Pampari, A., Jensen, M., Wen, C. H., Gandal, M. J., Geschwind, D. H., et al. (2024) · Science Advances · doi:10.1126/sciadv.adj4452 · Cited by 21
“Machine learning approaches, particularly deep neural networks, are powerful tools for predicting how sequence influences TF binding and chromatin accessibility ( 103 ).”
BackgroundSelf-citation
Metadata
- Authors
- Avsec, Ž., Weilert, M., Shrikumar, A., Krueger, S., Alexandari, A., Dalal, K., Fropf, R., McAnany, C., Gagneur, J., Kundaje, A., & Zeitlinger, J.
- Affiliations
- Google DeepMind (United Kingdom) (GB)
- Stowers Institute for Medical Research (US)
- Stanford University (US)
- Technical University of Munich (DE)
- Corresponding author
- Kundaje, Anshul
- Zeitlinger, Julia
- ORCID
- Venue
- Nature Genetics
- Published
- 2021-02-18
- Volume
- 53
- Issue
- 3
- Pages
- 354-366
- ISSN
- 1061-4036 (ISSN-L)
- 1546-1718
- PMC
- PMC8812996
- OpenAlex
- W3130819465
- Cited by
- 610
- References
- 163
- Citations by year
- 2026: 118 · 2025: 108 · 2024: 124 · 2023: 102 · 2022: 90 · 2021: 49
- FWCI
- 29.88
- Type
- journal article
- Language
- en
- Open access
- green
- doi.org
- Licence
- Locations
- Nature Genetics (publishedVersion)
- bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by-nc)
- PubMed (publishedVersion)
- PubMed Central (acceptedVersion)
- Funders
- U.S. Department of Health & Human Services | NIH | National Human Genome Research Institute (1R01HG010211, 1U01HG009431, 1R01HG009674)
- Howard Hughes Medical Institute (International Student Research Fellowship)
- U.S. Department of Health & Human Services | NIH | National Institute of General Medical Sciences (1DP2GM123485)
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Genomics and Chromatin Dynamics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Gene Regulatory Network Analysis
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Epigenetics and DNA Methylation
- Keywords
- transcription factor binding, pluripotency transcription factors, Nanog, helical periodicity, explainable deep learning
- MeSH terms
- Mouse Embryonic Stem Cells, Nanog Homeobox Protein, Deep Learning, Animals, Binding Sites, Transcription Factors, Reproducibility of Results, Neural Networks, Computer, Computational Biology, Chromatin Immunoprecipitation, Octamer Transcription Factor-3, Mice, SOXB1 Transcription Factors, Nucleotide Motifs, Clustered Regularly Interspaced Short Palindromic Repeats
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
