{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T18:17:21Z","timestamp":1793038641091,"version":"4.5.0"},"posted":{"date-parts":[[2024,12,15]]},"group-title":"Bioinformatics","reference-count":137,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2025,11,3]]},"abstract":"<jats:p>\n                  Characterizing human proteins remains a major challenge: approximately 29% of human proteins lack experimentally validated functions and even well-annotated proteins often lack context-specific phenotypic insights. To enable universal modeling of protein phenotypes, we present P\n                  <jats:sc>ro<\/jats:sc>\n                  C\n                  <jats:sc>yon<\/jats:sc>\n                  , a multimodal foundation model that utilizes protein sequence, structure, and natural language for generating and predicting protein phenotypes across diverse knowledge domains. P\n                  <jats:sc>ro<\/jats:sc>\n                  C\n                  <jats:sc>yon<\/jats:sc>\n                  is trained on our novel dataset, P\n                  <jats:sc>ro<\/jats:sc>\n                  C\n                  <jats:sc>yon<\/jats:sc>\n                  -I\n                  <jats:sc>nstruct<\/jats:sc>\n                  , with 33 million protein phenotype instructions. On dozens of benchmarking tasks, P\n                  <jats:sc>ro<\/jats:sc>\n                  C\n                  <jats:sc>yon<\/jats:sc>\n                  performs competitively against single-modal and multimodal models. Further, P\n                  <jats:sc>ro<\/jats:sc>\n                  C\n                  <jats:sc>yon<\/jats:sc>\n                  conditionally retrieves proteins via mechanisms of action of small molecule drugs and disease contexts, and it generates candidate phenotypic descriptions for poorly characterized proteins, including those implicated in Parkinson\u2019s disease that were identified after P\n                  <jats:sc>ro<\/jats:sc>\n                  C\n                  <jats:sc>yon<\/jats:sc>\n                  \u2019s knowledge cutoff date. We experimentally confirm P\n                  <jats:sc>ro<\/jats:sc>\n                  C\n                  <jats:sc>yon<\/jats:sc>\n                  \u2019s predictions in multiple sclerosis using post-mortem brain RNA-seq, identifying novel MS genes and elucidating associated pathway mechanisms consistent with cortical pathology. P\n                  <jats:sc>ro<\/jats:sc>\n                  C\n                  <jats:sc>yon<\/jats:sc>\n                  paves the way toward a general approach to generate functional insights into the human proteome.\n                <\/jats:p>","DOI":"10.1101\/2024.12.10.627665","type":"posted-content","created":{"date-parts":[[2024,12,18]],"date-time":"2024-12-18T06:40:40Z","timestamp":1734504040000},"source":"Crossref","is-referenced-by-count":10,"title":["ProCyon: A multimodal foundation model for protein phenotypes"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-1675-5313","authenticated-orcid":false,"given":"Owen","family":"Queen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yepeng","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert","family":"Calef","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Valentina","family":"Giunchiglia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianlong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"George","family":"Dasoulas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"LeAnn","family":"Tai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gianmarco","family":"Abbadessa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Owain","family":"Howell","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michelle M.","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yasha","family":"Ektefaie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ayush","family":"Noori","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ildiko","family":"Farkas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joseph","family":"Brown","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tom","family":"Cobley","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karin","family":"Hrovatin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tom","family":"Hartvigsen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fabian J.","family":"Theis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bradley L.","family":"Pentelute","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James","family":"Zou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vikram","family":"Khurana","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1198-7563","authenticated-orcid":false,"given":"David","family":"Owen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0414-1225","authenticated-orcid":false,"given":"Richard","family":"Nicholas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7113-9630","authenticated-orcid":false,"given":"Manolis","family":"Kellis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8530-7228","authenticated-orcid":false,"given":"Marinka","family":"Zitnik","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2024122005253417000_2024.12.10.627665v1.1","doi-asserted-by":"publisher","DOI":"10.1093\/bfgp\/eln033"},{"key":"2024122005253417000_2024.12.10.627665v1.2","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-022-01454-x"},{"key":"2024122005253417000_2024.12.10.627665v1.3","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1009818"},{"key":"2024122005253417000_2024.12.10.627665v1.4","doi-asserted-by":"publisher","DOI":"10.1038\/s41587-022-01316-z"},{"key":"2024122005253417000_2024.12.10.627665v1.5","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-04115-9"},{"key":"2024122005253417000_2024.12.10.627665v1.6","doi-asserted-by":"publisher","DOI":"10.1016\/j.cels.2021.05.012"},{"key":"2024122005253417000_2024.12.10.627665v1.7","doi-asserted-by":"crossref","unstructured":"Zheng, F. et al. Interpretation of cancer mutations using a multiscale map of protein systems. Science 374, eabf3067 (2021).","DOI":"10.1126\/science.abf3067"},{"key":"2024122005253417000_2024.12.10.627665v1.8","doi-asserted-by":"crossref","unstructured":"Uhl\u00e9n, M. , et al. Tissue-based map of the human proteome. Science 347, 1260419 (2015).","DOI":"10.1126\/science.347.6227.1274-c"},{"key":"2024122005253417000_2024.12.10.627665v1.9","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-024-02341-3"},{"key":"2024122005253417000_2024.12.10.627665v1.10","doi-asserted-by":"crossref","unstructured":"Kwon, J. J. , Pan, J. , Gonzalez, G. , Hahn, W. C. & Zitnik, M . On knowing a gene: A distributional hypothesis of gene function. Cell Systems (2024).","DOI":"10.1016\/j.cels.2024.04.008"},{"key":"2024122005253417000_2024.12.10.627665v1.11","doi-asserted-by":"publisher","DOI":"10.1038\/nmeth.2340"},{"key":"2024122005253417000_2024.12.10.627665v1.12","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-019-1727-y"},{"key":"2024122005253417000_2024.12.10.627665v1.13","first-page":"1024","article-title":"The 2022 report on the human proteome from the hupo human proteome project","volume":"22","year":"2022","journal-title":"Journal of Proteome Research"},{"key":"2024122005253417000_2024.12.10.627665v1.14","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jproteome.3c00591"},{"key":"2024122005253417000_2024.12.10.627665v1.15","unstructured":"Abramson, J. et al. Accurate structure prediction of biomolecular interactions with alphafold 3. Nature 1\u20133 (2024)."},{"key":"2024122005253417000_2024.12.10.627665v1.16","doi-asserted-by":"publisher","DOI":"10.1126\/science.ade2574"},{"key":"2024122005253417000_2024.12.10.627665v1.17","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2016239118"},{"key":"2024122005253417000_2024.12.10.627665v1.18","doi-asserted-by":"crossref","unstructured":"Hayes, T. et al. Simulating 500 million years of evolution with a language model 2024.07.01.600583 (2024).","DOI":"10.1101\/2024.07.01.600583"},{"key":"2024122005253417000_2024.12.10.627665v1.19","first-page":"25244","article-title":"Multi-scale representation learning on proteins","volume":"34","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2024122005253417000_2024.12.10.627665v1.20","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00647-z"},{"key":"2024122005253417000_2024.12.10.627665v1.21","unstructured":"Zhang, Z. , et al. Protein representation learning by geometric structure pretraining. In The Eleventh International Conference on Learning Representations (2023)."},{"key":"2024122005253417000_2024.12.10.627665v1.22","doi-asserted-by":"crossref","unstructured":"Xu, H. , Woicik, A. , Poon, H. , Altman, R. B. & Wang, S . Multilingual translation for zeroshot biomedical classification using biotranslator. Nature Communications 14, 738 (2023).","DOI":"10.1038\/s41467-023-36476-2"},{"key":"2024122005253417000_2024.12.10.627665v1.23","unstructured":"Xu, M. , Yuan, X. , Miret, S. & Tang, J . Protst: Multi-modality learning of protein sequences and biomedical texts. In International Conference on Machine Learning, 38749\u201338767 (PMLR, 2023)."},{"key":"2024122005253417000_2024.12.10.627665v1.24","doi-asserted-by":"crossref","unstructured":"Zhuo, L. et al. ProtLLM: An interleaved protein-language LLM with protein-as-word pretraining. In Ku, L.-W. , Martins, A. & Srikumar, V . (eds.) Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 8950\u20138963 (Association for Computational Linguistics, Bangkok, Thailand, 2024).","DOI":"10.18653\/v1\/2024.acl-long.484"},{"key":"2024122005253417000_2024.12.10.627665v1.25","unstructured":"Achiam, J. , et al. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"2024122005253417000_2024.12.10.627665v1.26","doi-asserted-by":"publisher","DOI":"10.1093\/NAR\/GKAC1052"},{"key":"2024122005253417000_2024.12.10.627665v1.27","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkac888"},{"key":"2024122005253417000_2024.12.10.627665v1.28","unstructured":"Liang, P. P. , Wu, C. , Morency, L.-P. & Salakhutdinov, R . Towards understanding and mitigating social biases in language models. In International Conference on Machine Learning, 6565\u20136576 (PMLR, 2021)."},{"key":"2024122005253417000_2024.12.10.627665v1.29","unstructured":"Algaba, A. , et al. Large language models reflect human citation patterns with a heightened citation bias. arXiv:2405.15739 (2024)."},{"key":"2024122005253417000_2024.12.10.627665v1.30","doi-asserted-by":"crossref","unstructured":"Gallifant, J. et al. Language models are surprisingly fragile to drug names in biomedical benchmarks. arXiv preprint arXiv:2406.12066 (2024).","DOI":"10.18653\/v1\/2024.findings-emnlp.726"},{"key":"2024122005253417000_2024.12.10.627665v1.31","doi-asserted-by":"publisher","DOI":"10.1016\/j.cels.2023.04.007"},{"key":"2024122005253417000_2024.12.10.627665v1.32","doi-asserted-by":"crossref","unstructured":"Kong, J. et al. Prediction of immunotherapy response using mutations to cancer protein assemblies. Science Advances 10, eado9746 (2024).","DOI":"10.1126\/sciadv.ado9746"},{"key":"2024122005253417000_2024.12.10.627665v1.33","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2019.03.010"},{"key":"2024122005253417000_2024.12.10.627665v1.34","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-31532-9"},{"key":"2024122005253417000_2024.12.10.627665v1.35","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-51801-z"},{"key":"2024122005253417000_2024.12.10.627665v1.36","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-07813-2"},{"key":"2024122005253417000_2024.12.10.627665v1.37","unstructured":"Zhang, K. et al. A generalist vision\u2013language foundation model for diverse biomedical tasks. Nature Medicine 1\u201313 (2024)."},{"key":"2024122005253417000_2024.12.10.627665v1.38","unstructured":"Xu, H. et al. A whole-slide foundation model for digital pathology from real-world data. Nature 1\u20138 (2024)."},{"key":"2024122005253417000_2024.12.10.627665v1.39","unstructured":"Dubey, A. , et al. The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)."},{"key":"2024122005253417000_2024.12.10.627665v1.40","doi-asserted-by":"publisher","DOI":"10.1093\/NAR\/GKAC1000"},{"key":"2024122005253417000_2024.12.10.627665v1.41","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/28.1.235"},{"key":"2024122005253417000_2024.12.10.627665v1.42","unstructured":"Wei, J. , et al. Finetuned language models are zero-shot learners (2022). ArXiv:2109.01652 [cs]."},{"key":"2024122005253417000_2024.12.10.627665v1.43","unstructured":"Chung, H. W. , et al. Scaling instruction-finetuned language models (2022). ArXiv:2210.11416 [cs]."},{"key":"2024122005253417000_2024.12.10.627665v1.44","unstructured":"Dai, W. et al. Instructblip: towards general-purpose vision-language models with instruction tuning. In Proceedings of the 37th International Conference on Neural Information Processing Systems, NIPS \u201923 (Curran Associates Inc., Red Hook, NY, USA, 2024)."},{"key":"2024122005253417000_2024.12.10.627665v1.45","doi-asserted-by":"crossref","unstructured":"Honovich, O. , Scialom, T. , Levy, O. & Schick, T. Unnatural instructions: Tuning language models with (almost) no human labor (2022). ArXiv:2212.09689 [cs].","DOI":"10.18653\/v1\/2023.acl-long.806"},{"key":"2024122005253417000_2024.12.10.627665v1.46","unstructured":"Longpre, S. , et al. The flan collection: Designing data and methods for effective instruction tuning (2023). ArXiv:2301.13688 [cs]."},{"key":"2024122005253417000_2024.12.10.627665v1.47","unstructured":"Thul, P. J. et al. A subcellular map of the human proteome. Science 356, eaal3321 (2017)."},{"key":"2024122005253417000_2024.12.10.627665v1.48","doi-asserted-by":"publisher","DOI":"10.1002\/humu.23155"},{"key":"2024122005253417000_2024.12.10.627665v1.49","doi-asserted-by":"publisher","DOI":"10.1006\/jmbi.1990.9999"},{"key":"2024122005253417000_2024.12.10.627665v1.50","unstructured":"Ko, Y. S. , Parkinson, J. & Wang, W . Benchmarking text-integrated protein language model embeddings and embedding fusion on diverse downstream tasks. bioRxiv (2024). https:\/\/www.biorxiv.org\/content\/early\/2024\/08\/26\/2024.08.24.609531.full.pdf."},{"key":"2024122005253417000_2024.12.10.627665v1.51","unstructured":"Zheng, C. , Zhou, H. , Meng, F. , Zhou, J. & Huang, M . Large language models are not robust multiple choice selectors. In The Twelfth International Conference on Learning Representations (2023)."},{"key":"2024122005253417000_2024.12.10.627665v1.52","doi-asserted-by":"crossref","unstructured":"American Psychiatric Association, D., American Psychiatric Association, D., et al. Diagnostic and statistical manual of mental disorders: DSM-5, vol. 5 (American psychiatric association Washington, DC, 2013).","DOI":"10.1176\/appi.books.9780890425596"},{"key":"2024122005253417000_2024.12.10.627665v1.53","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkw1037"},{"key":"2024122005253417000_2024.12.10.627665v1.54","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2024.05.031"},{"key":"2024122005253417000_2024.12.10.627665v1.55","doi-asserted-by":"publisher","DOI":"10.1128\/mbio.01966-14"},{"key":"2024122005253417000_2024.12.10.627665v1.56","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkh121"},{"key":"2024122005253417000_2024.12.10.627665v1.57","first-page":"46595","article-title":"Judging llm-as-a-judge with mt-bench and chatbot arena","volume":"36","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2024122005253417000_2024.12.10.627665v1.58","unstructured":"Anthropic. Claude 3.5 sonnet (2024)."},{"key":"2024122005253417000_2024.12.10.627665v1.59","unstructured":"Kaplan, J. , et al. Scaling laws for neural language models. arXiv preprint arXiv:2001.08361 (2020)."},{"key":"2024122005253417000_2024.12.10.627665v1.60","doi-asserted-by":"crossref","unstructured":"Tseng, Y.-M. , et al. Two tales of persona in llms: A survey of role-playing and personalization. arXiv preprint arXiv:2406.01171 (2024).","DOI":"10.18653\/v1\/2024.findings-emnlp.969"},{"key":"2024122005253417000_2024.12.10.627665v1.61","doi-asserted-by":"publisher","DOI":"10.1002\/pro.5116"},{"key":"2024122005253417000_2024.12.10.627665v1.62","doi-asserted-by":"publisher","DOI":"10.1016\/j.carres.2011.09.012"},{"key":"2024122005253417000_2024.12.10.627665v1.63","doi-asserted-by":"publisher","DOI":"10.1007\/s12010-013-0497-3"},{"key":"2024122005253417000_2024.12.10.627665v1.64","doi-asserted-by":"publisher","DOI":"10.3390\/ph17020243"},{"key":"2024122005253417000_2024.12.10.627665v1.65","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkad976"},{"key":"2024122005253417000_2024.12.10.627665v1.66","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-25772-4"},{"key":"2024122005253417000_2024.12.10.627665v1.67","doi-asserted-by":"crossref","unstructured":"Zhang, G. et al. Rapid de novo discovery of peptidomimetic affinity reagents for human angiotensin converting enzyme 2. Communications Chemistry 5, 8 (2022).","DOI":"10.1038\/s42004-022-00625-3"},{"key":"2024122005253417000_2024.12.10.627665v1.68","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2020.05.034"},{"key":"2024122005253417000_2024.12.10.627665v1.69","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-2180-5"},{"key":"2024122005253417000_2024.12.10.627665v1.70","doi-asserted-by":"publisher","DOI":"10.1165\/rcmb.2020-0322PS"},{"key":"2024122005253417000_2024.12.10.627665v1.71","doi-asserted-by":"crossref","unstructured":"Brown, J. S. , et al. Unsupervised machine learning leads to an abiotic picomolar peptide ligand (2023).","DOI":"10.26434\/chemrxiv-2023-tws4n"},{"key":"2024122005253417000_2024.12.10.627665v1.72","doi-asserted-by":"crossref","unstructured":"Cai, Y. , An, S. S. A. & Kim, S . Mutations in presenilin 2 and its implications in alzheimer\u2019s disease and other dementia-associated disorders. Clinical interventions in aging 1163\u20131172 (2015).","DOI":"10.2147\/CIA.S85808"},{"key":"2024122005253417000_2024.12.10.627665v1.73","doi-asserted-by":"publisher","DOI":"10.3390\/cells9102166"},{"key":"2024122005253417000_2024.12.10.627665v1.74","doi-asserted-by":"crossref","unstructured":"Ge, M. et al. Role of calcium homeostasis in alzheimer\u2019s disease. Neuropsychiatric Disease and Treatment 18, 487 (2022).","DOI":"10.2147\/NDT.S350939"},{"key":"2024122005253417000_2024.12.10.627665v1.75","doi-asserted-by":"publisher","DOI":"10.1038\/nature14892"},{"key":"2024122005253417000_2024.12.10.627665v1.76","doi-asserted-by":"publisher","DOI":"10.1016\/j.stemcr.2023.05.018"},{"key":"2024122005253417000_2024.12.10.627665v1.77","doi-asserted-by":"crossref","unstructured":"Zhou, B. et al. Notch signaling pathway: architecture, disease, and therapeutics. Signal transduction and targeted therapy 7, 95 (2022).","DOI":"10.1038\/s41392-022-00934-y"},{"key":"2024122005253417000_2024.12.10.627665v1.78","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1304171110"},{"key":"2024122005253417000_2024.12.10.627665v1.79","unstructured":"U.S. Food and Drug Administration. Label for WELLBUTRIN SR (NDA No. 020358, Supplement No. 068) (2024). Accessed: August 14, 2024."},{"key":"2024122005253417000_2024.12.10.627665v1.80","unstructured":"U.S. Food and Drug Administration. Label for ZYBAN (NDA No. 020711, Supplement No. 052) (2021). Accessed: August 14, 2024."},{"key":"2024122005253417000_2024.12.10.627665v1.81","doi-asserted-by":"publisher","DOI":"10.1021\/acschemneuro.7b00055"},{"key":"2024122005253417000_2024.12.10.627665v1.82","doi-asserted-by":"crossref","unstructured":"Clark, A. et al. Bupropion mediated effects on depression, attention deficit hyperactivity disorder, and smoking cessation. Health Psychology Research 11 (2023).","DOI":"10.52965\/001c.81043"},{"key":"2024122005253417000_2024.12.10.627665v1.83","unstructured":"Aslam, S. P. , Leslie, S. W. & Morris, J . Nicotine addiction and smoking: Health effects and interventions. In: StatPearls [Internet]. StatPearls Publishing (2024). Available from: https:\/\/www.ncbi.nlm.nih.gov\/books\/NBK537066\/."},{"key":"2024122005253417000_2024.12.10.627665v1.84","unstructured":"Arif, H. & Suma P. , C. Depression. In: StatPearls [Internet]. StatPearls Publishing (2024). Available from: https:\/\/www.ncbi.nlm.nih.gov\/books\/NBK430847."},{"key":"2024122005253417000_2024.12.10.627665v1.85","doi-asserted-by":"publisher","DOI":"10.1101\/cshperspect.a009399"},{"key":"2024122005253417000_2024.12.10.627665v1.86","doi-asserted-by":"publisher","DOI":"10.1016\/j.cels.2016.12.011"},{"key":"2024122005253417000_2024.12.10.627665v1.87","doi-asserted-by":"publisher","DOI":"10.1126\/science.1129462"},{"key":"2024122005253417000_2024.12.10.627665v1.88","doi-asserted-by":"publisher","DOI":"10.1016\/j.febslet.2004.03.063"},{"key":"2024122005253417000_2024.12.10.627665v1.89","doi-asserted-by":"publisher","DOI":"10.1038\/s41531-020-00149-4"},{"key":"2024122005253417000_2024.12.10.627665v1.90","doi-asserted-by":"publisher","DOI":"10.31887\/DCNS.2017.19.1\/rpal"},{"key":"2024122005253417000_2024.12.10.627665v1.91","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkac1046"},{"key":"2024122005253417000_2024.12.10.627665v1.92","doi-asserted-by":"publisher","DOI":"10.1186\/s40035-017-0071-y"},{"key":"2024122005253417000_2024.12.10.627665v1.93","doi-asserted-by":"crossref","unstructured":"Zhang, W. , Xiao, D. , Mao, Q. & Xia, H . Role of neuroinflammation in neurodegeneration development. Signal transduction and targeted therapy 8, 267 (2023).","DOI":"10.1038\/s41392-023-01486-5"},{"key":"2024122005253417000_2024.12.10.627665v1.94","doi-asserted-by":"publisher","DOI":"10.1089\/ars.2009.2490"},{"key":"2024122005253417000_2024.12.10.627665v1.95","unstructured":"Consortium, T. G. O. et al. The gene ontology knowledgebase in 2023. GENETICS 224, iyad031 (2023)."},{"key":"2024122005253417000_2024.12.10.627665v1.96","doi-asserted-by":"publisher","DOI":"10.1093\/NAR\/GKAD1025"},{"key":"2024122005253417000_2024.12.10.627665v1.97","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkn582"},{"key":"2024122005253417000_2024.12.10.627665v1.98","doi-asserted-by":"publisher","DOI":"10.1093\/NAR\/GKAA913"},{"key":"2024122005253417000_2024.12.10.627665v1.99","doi-asserted-by":"publisher","DOI":"10.1093\/NAR\/GKAC993"},{"key":"2024122005253417000_2024.12.10.627665v1.100","doi-asserted-by":"crossref","unstructured":"Pi\u00f1ero, J., et al. The disgenet knowledge platform for disease genomics: 2019 update. Nucleic Acids Research gk z1021 (2019).","DOI":"10.1093\/nar\/gkz1021"},{"key":"2024122005253417000_2024.12.10.627665v1.101","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gky1151"},{"key":"2024122005253417000_2024.12.10.627665v1.102","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkx1037"},{"key":"2024122005253417000_2024.12.10.627665v1.103","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkad944"},{"key":"2024122005253417000_2024.12.10.627665v1.104","unstructured":"Zhou, C . et al. Lima: Less is more for alignment (2023). ArXiv:2305.11206 [cs]."},{"key":"2024122005253417000_2024.12.10.627665v1.105","unstructured":"Chan, S. C. Y. et al. Data distributional properties drive emergent in-context learning in transformers (2022). ArXiv:2205.05055 [cs]."},{"key":"2024122005253417000_2024.12.10.627665v1.106","unstructured":"Xie, S. M. , et al. Doremi: Optimizing data mixtures speeds up language model pretraining (2023). ArXiv:2305.10429 [cs]."},{"key":"2024122005253417000_2024.12.10.627665v1.107","doi-asserted-by":"crossref","unstructured":"107. Shin, S. , et al. On the effect of pretraining corpora on in-context learning by a large-scale language model (2022). ArXiv:2204.13509 [cs].","DOI":"10.18653\/v1\/2022.naacl-main.380"},{"key":"2024122005253417000_2024.12.10.627665v1.108","unstructured":"Touvron, H. et al. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"2024122005253417000_2024.12.10.627665v1.109","unstructured":"Liu, H. , Li, C. , Wu, Q. & Lee, Y. J . Visual instruction tuning. In NeurIPS (2023)."},{"key":"2024122005253417000_2024.12.10.627665v1.110","unstructured":"Xue, L. , et al. xgen-mm (blip-3): A family of open large multimodal models. arXiv preprint arXiv:2408.08872 (2024)."},{"key":"2024122005253417000_2024.12.10.627665v1.111","unstructured":"Koh, J. Y. , Salakhutdinov, R. & Fried, D . Grounding language models to images for multimodal inputs and outputs (2023)."},{"key":"2024122005253417000_2024.12.10.627665v1.112","first-page":"23716","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"2024122005253417000_2024.12.10.627665v1.113","unstructured":"Vaswani, A. et al. Attention is all you need. In Vaswani2017AttentionIA (2017)."},{"key":"2024122005253417000_2024.12.10.627665v1.114","doi-asserted-by":"crossref","unstructured":"Sennrich, R. , Haddow, B. & Birch, A . Neural machine translation of rare words with subword units. In Erk, K. & Smith, N. A. (eds.) Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 1715\u20131725 (Association for Computational Linguistics, Berlin, Germany, 2016).","DOI":"10.18653\/v1\/P16-1162"},{"key":"2024122005253417000_2024.12.10.627665v1.115","unstructured":"Luo, S. et al. One transformer can understand both 2d & 3d molecular data. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023 (OpenReview.net, 2023)."},{"key":"2024122005253417000_2024.12.10.627665v1.116","unstructured":"Radford, A. et al. Learning transferable visual models from natural language supervision. In International conference on machine learning, 8748\u20138763 (PMLR, 2021)."},{"key":"2024122005253417000_2024.12.10.627665v1.117","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-07421-0"},{"key":"2024122005253417000_2024.12.10.627665v1.118","doi-asserted-by":"crossref","unstructured":"Vijayakumar, A. et al. Diverse beam search for improved description of complex scenes. In Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018).","DOI":"10.1609\/aaai.v32i1.12340"},{"key":"2024122005253417000_2024.12.10.627665v1.119","doi-asserted-by":"crossref","unstructured":"Wang, Y. et al. Super-NaturalInstructions: Generalization via declarative instructions on 1600+ NLP tasks. In Goldberg, Y. , Kozareva, Z. & Zhang, Y . (eds.) Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 5085\u20135109 (Association for Computational Linguistics, Abu Dhabi, United Arab Emirates, 2022).","DOI":"10.18653\/v1\/2022.emnlp-main.340"},{"key":"2024122005253417000_2024.12.10.627665v1.120","unstructured":"Karamcheti, S. , et al. Prismatic vlms: Investigating the design space of visually-conditioned language models. In International Conference on Machine Learning (ICML) (2024)."},{"key":"2024122005253417000_2024.12.10.627665v1.121","unstructured":"Oord, A. v. d., Li, Y. & Vinyals, O . Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)."},{"key":"2024122005253417000_2024.12.10.627665v1.122","unstructured":"Chen, T. , Kornblith, S. , Norouzi, M. & Hinton, G . A simple framework for contrastive learning of visual representations. In International Conference on Machine Learning, 1597\u20131607 (PMLR, 2020)."},{"key":"2024122005253417000_2024.12.10.627665v1.123","doi-asserted-by":"crossref","unstructured":"He, K. , Fan, H. , Wu, Y. , Xie, S. & Girshick, R . Momentum contrast for unsupervised visual representation learning. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 9729\u20139738 (2020).","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"2024122005253417000_2024.12.10.627665v1.124","doi-asserted-by":"crossref","unstructured":"Li, S. , et al. Pytorch distributed: Experiences on accelerating data parallel training. arXiv preprint arXiv:2006.15704 (2020).","DOI":"10.14778\/3415478.3415530"},{"key":"2024122005253417000_2024.12.10.627665v1.125","doi-asserted-by":"crossref","unstructured":"Rajbhandari, S. , Rasley, J. , Ruwase, O. & He, Y. Zero: Memory optimizations toward training trillion parameter models. In SC20: International Conference for High Performance Computing, Networking, Storage and Analysis, 1\u201316 (IEEE, 2020).","DOI":"10.1109\/SC41405.2020.00024"},{"key":"2024122005253417000_2024.12.10.627665v1.126","doi-asserted-by":"crossref","unstructured":"McInnes, L. , Healy, J. & Melville, J . Umap: Uniform manifold approximation and projection for dimension reduction. arXiv preprint arXiv:1802.03426 (2018).","DOI":"10.21105\/joss.00861"},{"key":"2024122005253417000_2024.12.10.627665v1.127","doi-asserted-by":"crossref","unstructured":"Dusart, P. et al. A tissue centric atlas of cell type transcriptome enrichment signatures. bioRxiv 2023\u201301 (2023).","DOI":"10.1101\/2023.01.10.520698"},{"key":"2024122005253417000_2024.12.10.627665v1.128","unstructured":"Zhang*, T. , Kishore*, V. , Wu*, F. , Weinberger, K. Q. & Artzi, Y . Bertscore: Evaluating text generation with bert. In International Conference on Learning Representations (2020)."},{"key":"2024122005253417000_2024.12.10.627665v1.129","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-neuro-061010-113613"},{"key":"2024122005253417000_2024.12.10.627665v1.130","doi-asserted-by":"publisher","DOI":"10.1007\/s12192-020-01101-4"},{"key":"2024122005253417000_2024.12.10.627665v1.131","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkt1113"},{"key":"2024122005253417000_2024.12.10.627665v1.132","doi-asserted-by":"publisher","DOI":"10.3390\/ijms19092603"},{"key":"2024122005253417000_2024.12.10.627665v1.133","doi-asserted-by":"crossref","unstructured":"Chen, Z. , Downing, S. & Tzanakakis, E. S . Four decades after the discovery of regenerating islet-derived (reg) proteins: current understanding and challenges. Frontiers in cell and developmental biology 7, 235 (2019).","DOI":"10.3389\/fcell.2019.00235"},{"key":"2024122005253417000_2024.12.10.627665v1.134","doi-asserted-by":"publisher","DOI":"10.1007\/s12035-023-03802-0"},{"key":"2024122005253417000_2024.12.10.627665v1.135","doi-asserted-by":"crossref","unstructured":"Cheng, J. et al. Accurate proteome-wide missense variant effect prediction with alphamissense. Science 381, eadg7492 (2023).","DOI":"10.1126\/science.adg7492"},{"key":"2024122005253417000_2024.12.10.627665v1.136","unstructured":"Bains, N. & Abdijadid, S . Major depressive disorder. In: StatPearls [Internet]. StatPearls Publishing (2024). Available from: https:\/\/www.ncbi.nlm.nih.gov\/books\/NBK559078\/."},{"key":"2024122005253417000_2024.12.10.627665v1.137","doi-asserted-by":"publisher","DOI":"10.1093\/NAR\/GKAB1061"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2024.12.10.627665","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T07:40:55Z","timestamp":1768462855000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.1101\/2024.12.10.627665"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,15]]},"references-count":137,"URL":"https:\/\/doi.org\/10.1101\/2024.12.10.627665","relation":{},"subject":[],"published":{"date-parts":[[2024,12,15]]},"subtype":"preprint"}}