{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,11]],"date-time":"2026-10-11T12:46:53Z","timestamp":1791722813137,"version":"4.3.4"},"reference-count":40,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T00:00:00Z","timestamp":1791504000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computational Biology and Chemistry"],"published-print":{"date-parts":[[2027,2]]},"DOI":"10.1016\/j.compbiolchem.2026.109438","type":"journal-article","created":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T15:12:24Z","timestamp":1790867544000},"page":"109438","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"P2","title":["Mechanistic interpretability of a plant genomic foundation model: Data probes, causal interventions, and motif-grounded features"],"prefix":"10.1016","volume":"126","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5342-1499","authenticated-orcid":false,"given":"Ihor","family":"Kendiukhov","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.compbiolchem.2026.109438_b1","series-title":"Understanding intermediate layers using linear classifier probes","author":"Alain","year":"2017"},{"issue":"10","key":"10.1016\/j.compbiolchem.2026.109438_b2","doi-asserted-by":"crossref","first-page":"1196","DOI":"10.1038\/s41592-021-01252-x","article-title":"Effective gene expression prediction from sequence by integrating long-range interactions","volume":"18","author":"Avsec","year":"2021","journal-title":"Nature Methods"},{"key":"10.1016\/j.compbiolchem.2026.109438_b3","series-title":"Annual Meeting of the Association for Computational Linguistics","article-title":"What do neural machine translation models learn about morphology?","author":"Belinkov","year":"2017"},{"key":"10.1016\/j.compbiolchem.2026.109438_b4","article-title":"Towards monosemanticity: Decomposing language models with dictionary learning","author":"Bricken","year":"2023","journal-title":"Transform. Circuits Thread"},{"issue":"5","key":"10.1016\/j.compbiolchem.2026.109438_b5","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbab060","article-title":"Explainability in transformer models for functional genomics","volume":"22","author":"Clauwaert","year":"2021","journal-title":"Brief. Bioinform."},{"key":"10.1016\/j.compbiolchem.2026.109438_b6","doi-asserted-by":"crossref","DOI":"10.52202\/075280-0719","article-title":"Towards automated circuit discovery for mechanistic interpretability","volume":"36","author":"Conmy","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.compbiolchem.2026.109438_b7","unstructured":"Cunningham, H., Ewart, A., Riggs, L., Huben, R., Sharkey, L., 2023. Sparse Autoencoders Find Highly Interpretable Features in Language Models. In: International Conference on Learning Representations."},{"key":"10.1016\/j.compbiolchem.2026.109438_b8","series-title":"The Nucleotide Transformer: Building and Evaluating Robust Foundation Models for Human Genomics","author":"Dalla-Torre","year":"2023"},{"key":"10.1016\/j.compbiolchem.2026.109438_b9","series-title":"Conference of the North American Chapter of the Association for Computational Linguistics","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.compbiolchem.2026.109438_b10","series-title":"Toy models of superposition","author":"Elhage","year":"2022"},{"key":"10.1016\/j.compbiolchem.2026.109438_b11","series-title":"Scaling and evaluating sparse autoencoders","author":"Gao","year":"2024"},{"key":"10.1016\/j.compbiolchem.2026.109438_b12","series-title":"Gemma: Open models based on gemini research and technology","author":"Gemma Team","year":"2024"},{"key":"10.1016\/j.compbiolchem.2026.109438_b13","article-title":"Dissecting recall of factual associations in auto-regressive language models","author":"Geva","year":"2023","journal-title":"Conf. Empir. Methods Nat. Lang. Process."},{"key":"10.1016\/j.compbiolchem.2026.109438_b14","doi-asserted-by":"crossref","unstructured":"Hewitt, J., Manning, C.D., 2019. A Structural Probe for Finding Syntax in Word Representations. In: Annual Conference of the North American Chapter of the Association for Computational Linguistics.","DOI":"10.18653\/v1\/N19-1419"},{"issue":"15","key":"10.1016\/j.compbiolchem.2026.109438_b15","doi-asserted-by":"crossref","first-page":"2112","DOI":"10.1093\/bioinformatics\/btab083","article-title":"DNABERT: pre-trained bidirectional encoder representations from transformers model for DNA-language in genome","volume":"37","author":"Ji","year":"2021","journal-title":"Bioinformatics"},{"issue":"8","key":"10.1016\/j.compbiolchem.2026.109438_b16","doi-asserted-by":"crossref","first-page":"msac174","DOI":"10.1093\/molbev\/msac174","article-title":"TimeTree 5: an expanded resource for species divergence times","volume":"39","author":"Kumar","year":"2022","journal-title":"Mol. Biol. Evol."},{"key":"10.1016\/j.compbiolchem.2026.109438_b17","series-title":"Numerical Ecology","author":"Legendre","year":"2012"},{"issue":"6637","key":"10.1016\/j.compbiolchem.2026.109438_b18","doi-asserted-by":"crossref","first-page":"1123","DOI":"10.1126\/science.ade2574","article-title":"Evolutionary-scale prediction of atomic-level protein structure with a language model","volume":"379","author":"Lin","year":"2023","journal-title":"Science"},{"issue":"2","key":"10.1016\/j.compbiolchem.2026.109438_b19","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1016\/j.molp.2024.12.006","article-title":"PDLLMs: A group of tailored DNA large language models for analyzing plant genomes","volume":"18","author":"Liu","year":"2025","journal-title":"Mol. Plant"},{"issue":"3","key":"10.1016\/j.compbiolchem.2026.109438_b20","doi-asserted-by":"crossref","first-page":"426","DOI":"10.1046\/j.1365-313X.2003.01971.x","article-title":"High-resolution mapping of BPC binding sites in arabidopsis","volume":"37","author":"Meister","year":"2004","journal-title":"Plant J."},{"issue":"1","key":"10.1016\/j.compbiolchem.2026.109438_b21","doi-asserted-by":"crossref","first-page":"835","DOI":"10.1038\/s42003-024-06465-2","article-title":"A foundational large language model for edible plant genomes","volume":"7","author":"Mendoza-Revilla","year":"2024","journal-title":"Commun. Biol."},{"key":"10.1016\/j.compbiolchem.2026.109438_b22","doi-asserted-by":"crossref","DOI":"10.52202\/068431-1262","article-title":"Locating and editing factual associations in GPT","volume":"35","author":"Meng","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.compbiolchem.2026.109438_b23","unstructured":"Nanda, N., Chan, L., Lieberum, T., Smith, J., Steinhardt, J., 2023. Progress measures for grokking via mechanistic interpretability. In: International Conference on Learning Representations."},{"key":"10.1016\/j.compbiolchem.2026.109438_b24","article-title":"HyenaDNA: Long-range genomic sequence modeling at single nucleotide resolution","volume":"36","author":"Nguyen","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"3","key":"10.1016\/j.compbiolchem.2026.109438_b25","doi-asserted-by":"crossref","DOI":"10.23915\/distill.00024.001","article-title":"Zoom in: An introduction to circuits","volume":"5","author":"Olah","year":"2020","journal-title":"Distill"},{"key":"10.1016\/j.compbiolchem.2026.109438_b26","article-title":"In-context learning and induction heads","author":"Olsson","year":"2022","journal-title":"Transform. Circuits Thread"},{"key":"10.1016\/j.compbiolchem.2026.109438_b27","article-title":"Evaluating protein transfer learning with TAPE","volume":"32","author":"Rao","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"D1","key":"10.1016\/j.compbiolchem.2026.109438_b28","doi-asserted-by":"crossref","first-page":"D174","DOI":"10.1093\/nar\/gkad1059","article-title":"JASPAR 2024: 20th anniversary of the open-access database of transcription factor binding profiles","volume":"52","author":"Rauluseviciute","year":"2024","journal-title":"Nucleic Acids Res."},{"issue":"15","key":"10.1016\/j.compbiolchem.2026.109438_b29","doi-asserted-by":"crossref","DOI":"10.1073\/pnas.2016239118","article-title":"Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences","volume":"118","author":"Rives","year":"2021","journal-title":"Proc. Natl. Acad. Sci."},{"key":"10.1016\/j.compbiolchem.2026.109438_b30","unstructured":"Schiff, Y., Kao, C.-H., Gokaslan, A., Dao, T., Gu, A., Kuleshov, V., 2024. Caduceus: Bi-Directional Equivariant Long-Range DNA Sequence Modeling. In: International Conference on Machine Learning."},{"issue":"5956","key":"10.1016\/j.compbiolchem.2026.109438_b31","doi-asserted-by":"crossref","first-page":"1112","DOI":"10.1126\/science.1178534","article-title":"The B73 maize genome: Complexity, diversity, and dynamics","volume":"326","author":"Schnable","year":"2009","journal-title":"Science"},{"key":"10.1016\/j.compbiolchem.2026.109438_b32","article-title":"Scaling monosemanticity: Extracting interpretable features from Claude 3 Sonnet","author":"Templeton","year":"2024","journal-title":"Transform. Circuits Thread"},{"key":"10.1016\/j.compbiolchem.2026.109438_b33","series-title":"Annual Meeting of the Association for Computational Linguistics","article-title":"BERT rediscovers the classical NLP pipeline","author":"Tenney","year":"2019"},{"issue":"D1","key":"10.1016\/j.compbiolchem.2026.109438_b34","first-page":"D1104","article-title":"PlantRegMap: charting functional regulatory maps in plants","volume":"48","author":"Tian","year":"2020","journal-title":"Nucleic Acids Res."},{"key":"10.1016\/j.compbiolchem.2026.109438_b35","article-title":"Investigating gender bias in language models using causal mediation analysis","volume":"33","author":"Vig","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.compbiolchem.2026.109438_b36","doi-asserted-by":"crossref","unstructured":"Vig, J., Madani, A., Varshney, L.R., Xiong, C., Socher, R., Naik, N.F., 2021. BERTology Meets Biology: Interpreting Attention in Protein Language Models. In: International Conference on Learning Representations.","DOI":"10.1101\/2020.06.26.174417"},{"key":"10.1016\/j.compbiolchem.2026.109438_b37","unstructured":"Wang, K., Variengien, A., Conmy, A., Shlegeris, B., Steinhardt, J., 2023. Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 Small. In: International Conference on Learning Representations."},{"issue":"4","key":"10.1016\/j.compbiolchem.2026.109438_b38","doi-asserted-by":"crossref","first-page":"386","DOI":"10.1093\/pcp\/pch055","article-title":"Dof domain proteins: plant-specific transcription factors associated with diverse phenomena unique to plants","volume":"45","author":"Yanagisawa","year":"2004","journal-title":"Plant Cell Physiol."},{"key":"10.1016\/j.compbiolchem.2026.109438_b39","doi-asserted-by":"crossref","DOI":"10.1038\/s42256-024-00946-z","article-title":"PlantRNA-FM: A plant RNA foundation model for exploring functional RNA landscapes in plants","author":"Yu","year":"2024","journal-title":"Nat. Mach. Intell."},{"key":"10.1016\/j.compbiolchem.2026.109438_b40","unstructured":"Zhou, Z., Ji, Y., Li, W., Dutta, P., Davuluri, R., Liu, H., 2024. DNABERT-2: Efficient Foundation Model and Benchmark For Multi-Species Genome. In: International Conference on Machine Learning."}],"container-title":["Computational Biology and Chemistry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1476927126005657?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1476927126005657?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,10,11]],"date-time":"2026-10-11T12:32:04Z","timestamp":1791721924000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1476927126005657"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,2]]},"references-count":40,"alternative-id":["S1476927126005657"],"URL":"https:\/\/doi.org\/10.1016\/j.compbiolchem.2026.109438","relation":{},"ISSN":["1476-9271"],"issn-type":[{"value":"1476-9271","type":"print"}],"subject":[],"published":{"date-parts":[[2027,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Mechanistic interpretability of a plant genomic foundation model: Data probes, causal interventions, and motif-grounded features","name":"articletitle","label":"Article Title"},{"value":"Computational Biology and Chemistry","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.compbiolchem.2026.109438","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"109438"}}