Josh Abramson, Jonas Adler, Jack Dunger, Richard Evans, Tim Green, Alexander Pritzel, Olaf Ronneberger, Lindsay Willmore et al.
Nature·
2024·
cited by 15,361
Predicting the joint 3D structures of biomolecular complexes (proteins with ligands, nucleic acids, ions and antibodies) previously required separate specialized tools with limited accuracy. AlphaFold 3 addresses this unified modelling problem.
Justas Dauparas, Ivan V. Anishchenko, Nathaniel R. Bennett, Hua Bai, Robert J. Ragotte, Lukas F. Milles, Basile I. M. Wicky, Alexis Courbet et al.
Science·
2022·
cited by 2,049
Designing amino acid sequences that fold into target protein structures relied on physically based approaches such as Rosetta rather than deep learning.
Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton
Communications of the ACM·
2017·
cited by 106,345
Software & Coding
Advanced Neural Network Applications
solved
importance 8/10
scale stated
Accurately classifying 1.2 million high-resolution images into 1000 categories, a task previous methods handled poorly.
Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun
IEEE Computer Society Conference on Computer Vision and Pattern Recognition·
2016·
cited by 221,134
Software & Coding
Advanced Neural Network Applications
solved
importance 8/10
scale stated
Very deep neural networks were difficult to train, blocking accuracy gains from increased depth in visual recognition.
Daniel J. Mankowitz, Andrea Michi, Anton Zhernov, Marco Gelmi, Marco Selvi, Cosmin Păduraru, Edouard Leurent, Shariq Iqbal et al.
Nature·
2023·
cited by 175
Software & Coding
Evolutionary Algorithms and Applications
solved
importance 8/10
scale stated
Improving the efficiency of fundamental sorting routines had stalled for both human scientists and computational approaches.
Rémi Lam, Álvaro Sánchez‐González, Matthew Willson, Peter Wirnsberger, Meire Fortunato, Ferran Alet, Suman V. Ravuri, Timo Ewalds et al.
Science·
2023·
cited by 1,416
Producing accurate 10-day global weather forecasts, traditionally requiring heavy compute rather than learning from historical weather data.
Nilmani Singh, Stephan Lane, Tianhao Yu, Jingxia Lu, Adrianna Ramos, Haiyang Cui, Huimin Zhao
Nature Communications·
2025·
cited by 111
Engineering proteins with desired functions is slow, expensive, and dependent on specialist expertise.
Bertrand Rouet‐Leduc, Claudia Hulbert
Nature Communications·
2024·
cited by 91
Detecting methane point-source emissions from satellites was limited by trade-offs between coverage, resolution and detection accuracy.
Fang Wan, Marcelo D. T. Torres, Jacqueline J Peng, César de la Fuente‐Núñez
Nature Biomedical Engineering·
2024·
cited by 189
Medicine & Health
Antimicrobial Peptides and Activities
ai assisted
importance 8/10
scale stated
Antibiotic resistance requires new antimicrobial candidates; the work mines proteomes of extinct organisms for antibiotic peptides.
Wei Hui Zheng, Yang Li, Chengxin Zhang, Xiaogen Zhou, Robin Pearce, Eric W. Bell, Xiaoqiang Huang, Yang Zhang
Proteins Structure Function and Bioinformatics·
2021·
cited by 61
Predicting 3D protein structures from sequence, especially hard free-modelling (FM) targets without templates, in CASP14.
Kim Huat Goh, Le Wang, Adrian Yong Kwang Yeow, Hermione Mei Niang Poh, Ke Li, Joannas Jie Lin Yeow, Gamaliel Yu Heng Tan
Nature Communications·
2021·
cited by 412
Medicine & Health
Machine Learning in Healthcare
ai assisted
importance 8/10
scale stated
Sepsis is a leading cause of hospital death and hard to predict early because its signs resemble less critical conditions.
Pranav Rajpurkar, Chloe P. O’Connell, Amit Schechter, Nishit Asnani, Jason J. Li, Amirhossein Kiani, Robyn L. Ball, Marc Mendelson et al.
npj Digital Medicine·
2020·
cited by 136
Medicine & Health
COVID-19 diagnosis using AI
ai assisted
importance 8/10
scale stated
TB in HIV-positive patients often goes undiagnosed, and chest x-ray diagnosis is difficult due to atypical presentation and radiologist shortages.
Jinbo Xu, Sheng Wang
Proteins Structure Function and Bioinformatics·
2019·
cited by 132
Predicting 3D protein structures from sequence alone, especially for free-modeling targets without templates, was a major unsolved challenge.
Jie Hou, Tianqi Wu, Renzhi Cao, Jianlin Jack Cheng
Proteins Structure Function and Bioinformatics·
2019·
cited by 162
Predicting protein 3D structures from sequence, including template-free (ab initio) cases where no similar known structure exists.
Kai Cao, Yingda Xia, Jiawen Yao, Xu Han, Lukáš Lambert, Tingting Zhang, Wei Tang, Gang Jin et al.
Nature Medicine·
2023·
cited by 354
Medicine & Health
AI in cancer detection
partially solved
importance 8/10
scale stated
Pancreatic ductal adenocarcinoma is typically detected late and inoperable, and identifying it on non-contrast CT was long considered impossible.
Yukun Zhou, Mark A. Chia, Siegfried K. Wagner, Murat Seçkin Ayhan, Dominic J. Williamson, Robbert Struyven, Timing Liu, Moucheng Xu et al.
Nature·
2023·
cited by 975
Medicine & Health
Retinal Imaging and Analysis
partially solved
importance 8/10
scale stated
AI models for retinal image analysis typically require large labeled datasets and are task-specific, limiting generalizable detection of eye and systemic diseases.
Sang-Yeong Cho, Sun–Hwa Kim, Si‐Hyuck Kang, Si-Hyuck Kang, Kyong Joon Lee, Dongjun Choi, Seungjin Kang, Seungjin Kang et al.
Scientific Reports·
2021·
cited by 85
Medicine & Health
Artificial Intelligence in Healthcare
ai assisted
importance 8/10
scale stated
Cardiovascular risk prediction models needed assessment and improvement using large, complex healthcare data for primary prevention.
Wei Hui Zheng, Qiqige Wuyun, Yang Li, Quancheng Liu, Xiaogen Zhou, Chunxiang Peng, Yiheng Zhu, Lydia Freddolino et al.
Nature Biotechnology·
2025·
cited by 99
Accurately predicting atomic-level 3D structures of large multidomain proteins remains challenging for deep-learning methods alone.
Md Ishtyaq Mahmud, Muntasir Mamun, Ahmed Abdelgawad
International Conference on Signal Processing and Integrated Networks (SPIN)·
2023·
cited by 44
Breast cancer, common and dangerous in women and men, needs accurate detection from histopathology images containing phenotypic data.
Markus Orsi, Boon Shing Loh, Cheng Weng, Wee Han Ang, Angelo Frei
Angewandte Chemie International Edition·
2023·
cited by 44
Medicine & Health
Computational Drug Discovery Methods
solved
importance 8/10
scale stated
Antimicrobial resistance and a stalled antibiotic pipeline make new antimicrobial compounds urgently needed; metal complexes are promising but understudied.
Vanessa Smer-Barreto, Andrea Quintanilla, Richard J. R. Elliott, John C. Dawson, Jiugeng Sun, Víctor M. Campa, Álvaro Lorente‐Macías, Asier Unciti‐Broceta et al.
Nature Communications·
2023·
cited by 130
Medicine & Health
Telomeres, Telomerase, and Senescence
partially solved
importance 8/10
scale stated
Only a few senolytics (drugs eliminating senescent cells) are known, and experimental screening for new ones is costly.
Vijil Chenthamarakshan, Samuel C. Hoffman, David Owen, Petra Lukacik, Claire M. Strain-Damerell, D. Fearon, Tika R. Malla, Anthony Tumber et al.
Science Advances·
2023·
cited by 51
Medicine & Health
Computational Drug Discovery Methods
partially solved
importance 8/10
scale stated
Discovering small-molecule inhibitors for emerging drug targets when target structure or known active molecules are unavailable.
Peter G. Mikhael, Jeremy Wohlwend, Adam Yala, Ludvig Karstens, Justin Xiang, Angelo K. Takigami, Patrick Bourgouin, PuiYee Chan et al.
Journal of Clinical Oncology·
2023·
cited by 285
Medicine & Health
AI in cancer detection
partially solved
importance 8/10
scale stated
Most eligible people are not screened for lung cancer, and tools for personalized future risk from a single LDCT were lacking.
Amil Merchant, Simon Batzner, Samuel S. Schoenholz, Muratahan Aykol, Gowoon Cheon, Ekin D. Cubuk
Nature·
2023·
cited by 1,471
Discovery of inorganic crystals for applications from microchips to batteries and photovoltaics has been bottlenecked by expensive trial-and-error approaches.