RNA language models predict mutations that improve RNA function.

Autor: Shulgina Y; Innovative Genomics Institute, University of California, Berkeley, CA, USA.; Department of Molecular and Cell Biology, University of California, Berkeley, CA, USA.; California Institute for Quantitative Biosciences, University of California, Berkeley, CA, USA., Trinidad MI; Innovative Genomics Institute, University of California, Berkeley, CA, USA.; Howard Hughes Medical Institute, University of California, Berkeley, CA, USA., Langeberg CJ; Innovative Genomics Institute, University of California, Berkeley, CA, USA.; Department of Molecular and Cell Biology, University of California, Berkeley, CA, USA.; California Institute for Quantitative Biosciences, University of California, Berkeley, CA, USA., Nisonoff H; Center for Computational Biology, University of California, Berkeley, CA, United States., Chithrananda S; Innovative Genomics Institute, University of California, Berkeley, CA, USA.; Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA, USA., Skopintsev P; Innovative Genomics Institute, University of California, Berkeley, CA, USA.; California Institute for Quantitative Biosciences, University of California, Berkeley, CA, USA., Nissley AJ; Department of Chemistry, University of California, Berkeley, CA, USA., Patel J; Innovative Genomics Institute, University of California, Berkeley, CA, USA., Boger RS; Innovative Genomics Institute, University of California, Berkeley, CA, USA.; Biophysics Graduate Program, University of California, Berkeley, CA, USA., Shi H; Innovative Genomics Institute, University of California, Berkeley, CA, USA.; Howard Hughes Medical Institute, University of California, Berkeley, CA, USA., Yoon PH; Innovative Genomics Institute, University of California, Berkeley, CA, USA.; Department of Molecular and Cell Biology, University of California, Berkeley, CA, USA.; Department of Chemistry, University of California, Berkeley, CA, USA., Doherty EE; Innovative Genomics Institute, University of California, Berkeley, CA, USA.; California Institute for Quantitative Biosciences, University of California, Berkeley, CA, USA., Pande T; Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA, USA., Iyer AM; Department of Physics, University of California, Berkeley, CA, USA., Doudna JA; Innovative Genomics Institute, University of California, Berkeley, CA, USA.; Department of Molecular and Cell Biology, University of California, Berkeley, CA, USA.; California Institute for Quantitative Biosciences, University of California, Berkeley, CA, USA.; Howard Hughes Medical Institute, University of California, Berkeley, CA, USA.; Department of Chemistry, University of California, Berkeley, CA, USA.; MBIB Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA.; Gladstone Institutes, University of California, San Francisco, CA, USA., Cate JHD; Innovative Genomics Institute, University of California, Berkeley, CA, USA.; Department of Molecular and Cell Biology, University of California, Berkeley, CA, USA.; California Institute for Quantitative Biosciences, University of California, Berkeley, CA, USA.; Department of Chemistry, University of California, Berkeley, CA, USA.; MBIB Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA.

Publikováno v: BioRxiv : the preprint server for biology [bioRxiv] 2024 Sep 16. Date of Electronic Publication: 2024 Sep 16.

TransCDR: a deep learning model for enhancing the generalizability of drug activity prediction through transfer learning and multimodal data fusion.

Autor: Xia, Xiaoqiong¹ (AUTHOR), Zhu, Chaoyu² (AUTHOR), Zhong, Fan² (AUTHOR) zonefan@163.com, Liu, Lei^2,3 (AUTHOR) liulei_sibs@163.com

Publikováno v: BMC Biology. 10/9/2024, Vol. 22 Issue 1, p1-20. 20p.

CycPeptMP: enhancing membrane permeability prediction of cyclic peptides with multi-level molecular features and data augmentation.

Autor: Li, Jianan¹ (AUTHOR), Yanagisawa, Keisuke^1,2 (AUTHOR), Akiyama, Yutaka^1,2 (AUTHOR) akiyama@c.titech.ac.jp

Publikováno v: Briefings in Bioinformatics. Sep2024, Vol. 25 Issue 5, p1-12. 12p.

A Human Feedback Strategy for Photoresponsive Molecules in Drug Delivery: Utilizing GPT-2 and Time-Dependent Density Functional Theory Calculations.

Autor: Hu, Junjie¹ (AUTHOR) j.hu@imperial.ac.uk, Wu, Peng² (AUTHOR) wp141@nxu.edu.cn, Wang, Shiyi³ (AUTHOR) s.wang22@imperial.ac.uk, Wang, Binju⁴ (AUTHOR) wangbinju2018@xmu.edu.cn, Yang, Guang^3,5,6,7 (AUTHOR) wp141@nxu.edu.cn

Publikováno v: Pharmaceutics. Aug2024, Vol. 16 Issue 8, p1014. 11p.

Transfer learning across different chemical domains: virtual screening of organic materials with deep learning models pretrained on small molecule and chemical reaction data.

Autor: Zhang, Chengwei¹ (AUTHOR), Zhai, Yushuang¹ (AUTHOR), Gong, Ziyang² (AUTHOR), Duan, Hongliang³ (AUTHOR), She, Yuan-Bin¹ (AUTHOR), Yang, Yun-Fang¹ (AUTHOR), Su, An^1,2 (AUTHOR) ansu@zjut.edu.cn

Publikováno v: Journal of Cheminformatics. 7/30/2024, Vol. 16 Issue 1, p1-13. 13p.