From chemical compounds to herbal interventions: a transfer learning-based perturbational transcriptome prediction framework for cancer drug discovery

References

1. 1.↵
   2. Wang K,
   3. Chen Q,
   4. Shao Y,
   5. Yin S,
   6. Liu C,
   7. Liu Y, et al.

   Anticancer activities of TCM and their active components against tumor metastasis. Biomed Pharmacother. 2021; 133: 111044.
2. 2.
   2. Xiang Y,
   3. Guo Z,
   4. Zhu P,
   5. Chen J,
   6. Huang Y.

   Traditional Chinese medicine as a cancer treatment: modern perspectives of ancient but advanced science. Cancer Med. 2019; 8: 1958–75.

   OpenUrlPubMed
3. 3.↵
   2. Wang Y,
   3. Zhang Q,
   4. Chen Y,
   5. Liang CL,
   6. Liu H,
   7. Qiu F, et al.

   Antitumor effects of immunity-enhancing traditional Chinese medicine. Biomed Pharmacother. 2020; 121: 109570.
4. 4.↵
   2. Hasin Y,
   3. Seldin M,
   4. Lusis A.

   Multi-omics approaches to disease. Genome Biol. 2017; 18: 83.

   OpenUrlCrossRefPubMed
5. 5.
   2. Lamb J,
   3. Crawford ED,
   4. Peck D,
   5. Modell JW,
   6. Blat IC,
   7. Wrobel MJ, et al.

   The Connectivity Map: using gene-expression signatures to connect small molecules, genes, and disease. Science. 2006; 313: 1929–35.

   OpenUrlAbstract/FREE Full Text
6. 6.
   2. Iorio F,
   3. Bosotti R,
   4. Scacheri E,
   5. Belcastro V,
   6. Mithbaokar P,
   7. Ferriero R, et al.

   Discovery of drug mode of action and drug repositioning from transcriptional responses. Proc Natl Acad Sci U S A. 2010; 107: 14621–6.

   OpenUrlAbstract/FREE Full Text
7. 7.↵
   2. Hou JY,
   3. Wu JR,
   4. Xu D,
   5. Chen YB,
   6. Shang DD,
   7. Liu S, et al.

   Integration of transcriptomics and system pharmacology to reveal the therapeutic mechanism underlying Qingfei Xiaoyan Wan to treat allergic asthma. J Ethnopharmacol. 2021; 278: 114302.
8. 8.↵
   2. Li S,
   3. Zhang B,
   4. Zhang N.

   Network target for screening synergistic drug combinations with application to traditional Chinese medicine. BMC Syst Biol. 2011; 5: S10.

   OpenUrlPubMed
9. 9.
   2. Li S.

   Mapping ancient remedies: applying a network approach to traditional Chinese medicine. Science. 2015; 350: S72–4.

   OpenUrl
10. 10.↵
    2. Li S,
    3. Zhang B.

    Traditional Chinese medicine network pharmacology: theory, methodology and application. Chin J Nat Med. 2013; 11: 110–20.

    OpenUrlPubMed
11. 11.↵
    2. Liu Q,
    3. Zhang D,
    4. Wang B,
    5. Zhao W,
    6. Zhang T,
    7. Sutcharitchan C, et al.

    Network pharmacology: advancing the application of large language models in traditional Chinese medicine research. Sci Tradit Chin Med. 2025; 3: 113–23.

    OpenUrl
12. 12.
    2. Zhang P,
    3. Zhang D,
    4. Zhou W,
    5. Wang L,
    6. Wang B,
    7. Zhang T, et al.

    Network pharmacology: towards the artificial intelligence-based precision traditional Chinese medicine. Brief Bioinform. 2024; 25: bbad518.
13. 13.
    2. Zhong C,
    3. Liu Q,
    4. Guo S,
    5. Sun D,
    6. Wang B,
    7. Hu S, et al.

    A computational-based new treatment strategy with three-armed RCT on mycoplasma pneumoniae pneumonia in children. Chin Med. 2025; 20: 97.

    OpenUrlPubMed
14. 14.
    2. Wang B,
    3. Kong D,
    4. Yang Z,
    5. Kang J,
    6. Sun D,
    7. Duan X, et al.

    Revealing the mechanisms of compound Kushen injection on oxidative stress regulation in the treatment of radiation-induced lung injury. Engineering. 2025; 55: 254–68.

    OpenUrl
15. 15.
    2. Zhang S,
    3. Yang K,
    4. Liu Z,
    5. Lai X,
    6. Yang Z,
    7. Zeng J, et al.

    DrugAI: a multi-view deep learning model for predicting drug–target activating/inhibiting mechanisms. Brief Bioinform. 2023; 24: bbac526.
16. 16.↵
    2. Wang B,
    3. Zhang T,
    4. Liu Q,
    5. Sutcharitchan C,
    6. Zhou Z,
    7. Zhang D, et al.

    Elucidating the role of artificial intelligence in drug development from the perspective of drug-target interactions. J Pharm Anal. 2025; 15: 101144.
17. 17.↵
    2. Subramanian A,
    3. Narayan R,
    4. Corsello SM,
    5. Peck DD,
    6. Natoli TE,
    7. Lu X, et al.

    A next generation connectivity map: L1000 platform and the first 1,000,000 profiles. Cell. 2017; 171: 1437–52.e17.

    OpenUrlCrossRefPubMed
18. 18.↵
    2. Xu Y,
    3. Fleming S,
    4. Tegtmeyer M,
    5. McCarroll SA,
    6. Babadi M.

    Explainable modeling of single-cell perturbation data using attention and sparse dictionary learning. Cell Syst. 2025; 16: 101245.
19. 19.↵
    2. Yu H,
    3. Qian W,
    4. Song Y,
    5. Welch JD.

    PerturbNet predicts single-cell responses to unseen chemical and genetic perturbations. Mol Syst Biol. 2025; 21: 960–82.

    OpenUrlCrossRefPubMed
20. 20.↵
    2. Lotfollahi M,
    3. Wolf FA,
    4. Theis FJ.

    scGen predicts single-cell perturbation responses. Nat Methods. 2019; 16: 715–21.

    OpenUrlCrossRefPubMed
21. 21.↵
    2. Lotfollahi M,
    3. Klimovskaia Susmelj A,
    4. De Donno C,
    5. Hetzel L,
    6. Ji Y,
    7. Ibarra IL, et al.

    Predicting cellular responses to complex perturbations in high-throughput screens. Mol Syst Biol. 2023; 19: e11517.
22. 22.↵
    2. Qi X,
    3. Zhao L,
    4. Tian C,
    5. Li Y,
    6. Chen ZL,
    7. Huo P, et al.

    Predicting transcriptional responses to novel chemical perturbations using deep generative model for drug discovery. Nat Commun. 2024; 15: 9256.

    OpenUrlCrossRefPubMed
23. 23.↵
    2. Weininger D.

    SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules. J Chem Inf Comput Sci. 1988; 28: 31–6.

    OpenUrlCrossRefWeb of Science
24. 24.↵
    2. He S,
    3. Zhu Y,
    4. Tavakol DN,
    5. Ye H,
    6. Lao YH,
    7. Zhu Z, et al.

    Squidiff: predicting cellular development and responses to perturbations using a diffusion model. Nat Methods. 2026; 23: 65–77.

    OpenUrlPubMed
25. 25.
    2. Song Z,
    3. Zheng C,
    4. Li J,
    5. Xie L,
    6. Xiang Y.

    Benchmarking diffusion models for predicting perturbed cellular responses. In: 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop: Biosecurity Safeguards for Generative AI; 2025.
26. 26.↵
    2. Shang E,
    3. Wei Y,
    4. Roeder K.

    Predicting the unseen: a diffusion-based debiasing framework for transcriptional response prediction at single-cell resolution. Proc Natl Acad Sci U S A. 2025; 122: e2525268122.
27. 27.↵
    2. Wang B,
    3. Pan B,
    4. Zhang T,
    5. Liu Q,
    6. Li S.

    Transfer learning and permutation-invariance improving predicting genome-wide, cell-specific and directional interventions effects of complex systems. Adv Sci (Weinh). 2025; 12: e09456.
28. 28.↵
    2. Wu Z,
    3. Wang Z,
    4. Chang X,
    5. Chen X,
    6. Ding Q,
    7. Fu R, et al.

    Prioritizing pathway signature using deep learning approach: a novel strategy for traditional Chinese medicine formula generation and optimization. Brief Bioinform. 2025; 26: bbaf403.
29. 29.↵
    2. Liu Q,
    3. Chen Z,
    4. Wang B,
    5. Pan B,
    6. Zhang Z,
    7. Shen M, et al.

    Leveraging network target theory for efficient prediction of drug-disease interactions: a transfer learning approach. Adv Sci. 2025; 12: 2409130.
30. 30.↵
    2. Weiss K,
    3. Khoshgoftaar TM,
    4. Wang D.

    A survey of transfer learning. J Big Data. 2016; 3: 9.

    OpenUrl
31. 31.↵
    2. Park M,
    3. Park SM,
    4. Lee H,
    5. Kim A,
    6. Kim NS,
    7. Kim YR, et al.

    KORE-Map 1.0: Korean medicine Omics Resource Extension Map on transcriptome data of tonifying herbal medicine. Sci Data. 2024; 11: 974.

    OpenUrlPubMed
32. 32.↵
    2. Park M,
    3. Seo EH,
    4. Yi JM,
    5. Cha S.

    Discovery and prediction study of the dominant pharmacological action organ of Aconitum carmichaeli Debeaux using multiple bioinformatic analyses. Int J Mol Sci. 2024; 25: 10219.
33. 33.↵
    2. Vaswani A,
    3. Shazeer N,
    4. Parmar N,
    5. Uszkoreit J,
    6. Jones L,
    7. Gomez AN, et al.

    Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, Curran Associates Inc., Red Hook, NY, USA. 2017; 30.
34. 34.↵
    2. Barrett T,
    3. Wilhite SE,
    4. Ledoux P,
    5. Evangelista C,
    6. Kim IF,
    7. Tomashevsky M, et al.

    NCBI GEO: archive for functional genomics data sets—update. Nucleic Acids Res. 2013; 41: D991–5.

    OpenUrlCrossRefPubMedWeb of Science
35. 35.↵
    2. Kim S,
    3. Chen J,
    4. Cheng T,
    5. Gindulyte A,
    6. He J,
    7. He S, et al.

    PubChem 2025 update. Nucleic Acids Res. 2025; 53: D1516–25.

    OpenUrlCrossRefPubMed
36. 36.↵
    2. Sun FY,
    3. Hoffmann J,
    4. Verma V,
    5. Tang J.

    InfoGraph: unsupervised and semi-supervised graph-level representation learning via mutual information maximization. In: International Conference on Learning Representations; 2020.
37. 37.↵
    2. Fang S,
    3. Dong L,
    4. Liu L,
    5. Guo J,
    6. Zhao L,
    7. Zhang J, et al.

    HERB: a high-throughput experiment- and reference-guided database of traditional Chinese medicine. Nucleic Acids Res. 2021; 49: D1197–206.

    OpenUrlCrossRefPubMed
38. 38.↵
    2. Taud H,
    3. Mas JF.

    Multilayer perceptron (MLP). In: Geomatic approaches for modeling land change scenarios. Springer; 2017. p. 451–5.
39. 39.↵
    2. Aldi F,
    3. Hadi F,
    4. Rahmi NA,
    5. Defit S.

    Standardscaler’s potential in enhancing breast cancer accuracy using machine learning. J Appl Eng Technol Sci. 2023; 5: 401–13.

    OpenUrl
40. 40.↵
    2. Loshchilov I,
    3. Hutter F.

    Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101, 2017.
41. 41.↵
    2. Lever J,
    3. Krzywinski M,
    4. Altman N.

    Logistic regression. Nat Methods. 2016; 13: 541–2.

    OpenUrlCrossRef
42. 42.↵
    2. Segal MR.

    Machine learning benchmarks and random forest regression. In: Center for Bioinformatics and Molecular Biostatistics. University of California, San Francisco; 2004.
43. 43.↵
    2. Zhang F,
    3. O’Donnell LJ.

    Support vector regression. In: Machine learning. Amsterdam, The Netherlands: Elsevier; 2020. p. 123–40.
44. 44.↵
    2. Yang J,
    3. Zhou K,
    4. Li Y,
    5. Liu Z.

    Generalized out-of-distribution detection: a survey. Int J Comput Vis. 2024; 132: 5635–62.

    OpenUrl
45. 45.↵
    2. Shi K,
    3. Xiao Y,
    4. Dong Y,
    5. Wang D,
    6. Xie Y,
    7. Tu J, et al.

    Protective effects of Atractylodis lancea rhizoma on lipopolysaccharide-induced acute lung injury via TLR4/NF-κB and Keap1/Nrf2 signaling pathways in vitro and in vivo. Int J Mol Sci. 2022; 23: 16134.
46. 46.↵
    2. Chen L,
    3. Yang J,
    4. Zhao SJ,
    5. Li TS,
    6. Jiao RQ,
    7. Kong LD.

    Atractylodis rhizoma water extract attenuates fructose-induced glomerular injury in rats through anti-oxidation to inhibit TRPC6/p-CaMK4 signaling. Phytomedicine. 2021; 91: 153643.
47. 47.↵
    2. Zou J,
    3. Li W,
    4. Wang G,
    5. Fang S,
    6. Cai J,
    7. Wang T, et al.

    Hepatoprotective effects of Huangqi decoction (Astragali Radix and Glycyrrhizae Radix et Rhizoma) on cholestatic liver injury in mice: involvement of alleviating intestinal microbiota dysbiosis. J Ethnopharmacol. 2021; 267: 113544.
48. 48.
    2. Li Y,
    3. Wang C,
    4. Jin Y,
    5. Chen H,
    6. Cao M,
    7. Li W, et al.

    Huang-Qi San improves glucose and lipid metabolism and exerts protective effects against hepatic steatosis in high fat diet-fed rats. Biomed Pharmacother. 2020; 126: 109734.
49. 49.↵
    2. Wang D,
    3. Li R,
    4. Wei S,
    5. Gao S,
    6. Xu Z,
    7. Liu H, et al.

    Metabolomics combined with network pharmacology exploration reveals the modulatory properties of Astragali Radix extract in the treatment of liver fibrosis. Chin Med. 2019; 14: 30.

    OpenUrlPubMed
50. 50.↵
    2. Peng Y,
    3. Zhu G,
    4. Ma Y,
    5. Huang K,
    6. Chen G,
    7. Liu C, et al.

    Network pharmacology-based prediction and pharmacological validation of effects of Astragali Radix on acetaminophen-induced liver injury. Front Med (Lausanne). 2022; 9: 697644.
51. 51.↵
    2. Lu Z,
    3. Zhou M.

    Preliminary study on clinical application law of common anticancer Chinese medicine. Pract Clin J Integr Tradit Chin West Med. 2023; 23: 122–8.

    OpenUrl
52. 52.↵
    2. Zhao X.

    Clinical effect observation of Jingling oral liquid on attention deficit hyperactivity disorder. Clin Res Pract. 2017; 2: 100–1.

    OpenUrl
53. 53.
    2. Huang RB,
    3. Ge SH,
    4. Fang CS.

    Clinical therapeutic effect analysis of treating pediatric Tourette’s disease by combined use of tiapride and Jingling oral liquid. China Foreign Med Treat. 2017; 36: 137–9.142.

    OpenUrl
54. 54.↵
    2. Hao W,
    3. Guan X,
    4. Feng S,
    5. Liu M,
    6. Cheng Y,
    7. Jing S, et al.

    Effect of Jingling oral liquid on attention deficit hyperactivity disorder in children with epilepsy and its effect on serum dat and DRD2 levels. J Changchun Univ Chin Med. 2020; 36: 507–10.

    OpenUrl
55. 55.↵
    2. Sharma V,
    3. Sharma P,
    4. Singh TG.

    Therapeutic potential of transient receptor potential (TRP) channels in psychiatric disorders. J Neural Transm. 2024; 131: 1025–37.

    OpenUrlPubMed
56. 56.↵
    2. Noori T,
    3. Sahebgharani M,
    4. Sureda A,
    5. Sobarzo-Sanchez E,
    6. Fakhri S,
    7. Shirooie S.

    Targeting PI3K by natural products: a potential therapeutic strategy for attention-deficit hyperactivity disorder. Curr Neuropharmacol. 2022; 20: 1564–78.

    OpenUrlPubMed
57. 57.↵
    2. Corona JC.

    Role of oxidative stress and neuroinflammation in attention-deficit/hyperactivity disorder. Antioxidants (Basel). 2020; 9: 1039.

    OpenUrlPubMed
58. 58.↵
    2. Nicotera AG,
    3. Amore G,
    4. Saia MC,
    5. Vinci M,
    6. Musumeci A,
    7. Chiavetta V, et al.

    Fibroblast growth factor receptor 2 (FGFR2), a new gene involved in the genesis of autism spectrum disorder. Neuromolecular Med. 2023; 25: 650–6.

    OpenUrlPubMed
59. 59.↵
    2. Stevens HE,
    3. Scuderi S,
    4. Collica SC,
    5. Tomasi S,
    6. Horvath TL,
    7. Vaccarino FM.

    Neonatal loss of FGFR2 in astroglial cells affects locomotion, sociability, working memory, and glia-neuron interactions in mice. Transl Psychiatry. 2023; 13: 89.

    OpenUrlPubMed
60. 60.↵
    2. Gruber RC,
    3. Wirak GS,
    4. Blazier AS,
    5. Lee L,
    6. Dufault MR,
    7. Hagan N, et al.

    BTK regulates microglial function and neuroinflammation in human stem cell models and mouse models of multiple sclerosis. Nat Commun. 2024; 15: 10116.
61. 61.↵
    2. Tsai SJ.

    Effects of interleukin-1beta polymorphisms on brain function and behavior in healthy and psychiatric disease conditions. Cytokine Growth Factor Rev. 2017; 37: 89–97.

    OpenUrlCrossRefPubMed