Functional evaluation and clinical classification of BRCA2 variants DOI Creative Commons
Huaizhi Huang, Chunling Hu, Jie Na

et al.

Nature, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 8, 2025

Germline BRCA2 loss-of function variants, which can be identified through clinical genetic testing, predispose to several cancers1–5. However, variants of uncertain significance limit the utility test results. Thus, there is a need for functional characterization and classification all facilitate management individuals with these variants. Here we analysed possible single-nucleotide from exons 15 26 that encode DNA-binding domain hotspot pathogenic missense To enable this, used saturation genome editing CRISPR–Cas9-based knock-in endogenous targeting human haploid HAP1 cells6. The assay was calibrated relative nonsense silent validated using benign standards ClinVar results homology-directed repair assay7. Variants (6,959 out 6,960 evaluated) were assigned seven categories pathogenicity based on VarCall Bayesian model8. Single-nucleotide loss-of-function associated increased risks breast cancer ovarian cancer. integrated into models ClinGen, American College Medical Genetics Genomics, Association Molecular Pathology9 Using this approach, 91% classified as or likely benign. These improve variant. Results comprehensive evaluation particularly significance, provide useful resource who carry such

Language: Английский

The Reactome Pathway Knowledgebase 2024 DOI Creative Commons
M Orlic-Milacic, Deidre Beavers,

Patrick Conley

et al.

Nucleic Acids Research, Journal Year: 2023, Volume and Issue: 52(D1), P. D672 - D678

Published: Nov. 6, 2023

The Reactome Knowledgebase (https://reactome.org), an Elixir and GCBR core biological data resource, provides manually curated molecular details of a broad range normal disease-related processes. Processes are annotated as ordered network transformations in single consistent model. thus functions both digital archive human processes tool for discovering functional relationships such gene expression profiles or somatic mutation catalogs from tumor cells. Here we review progress towards annotation the entire proteome, targeted disease-causing genetic variants proteins small-molecule drugs pathway context, supporting explicit cell- tissue-specific pathways. Finally, briefly discuss issues involved making more fully interoperable with other related resources Gene Ontology maintaining resulting community resource network.

Language: Английский

Citations

408
Opportunities and Challenges for Machine Learning-Assisted Enzyme Engineering DOI Creative Commons
Jason Yang, Francesca-Zhoufan Li, Frances H. Arnold

et al.

ACS Central Science, Journal Year: 2024, Volume and Issue: 10(2), P. 226 - 241

Published: Feb. 5, 2024

Enzymes can be engineered at the level of their amino acid sequences to optimize key properties such as expression, stability, substrate range, and catalytic efficiency-or even unlock new activities not found in nature. Because search space possible proteins is vast, enzyme engineering usually involves discovering an starting point that has some desired activity followed by directed evolution improve its "fitness" for a application. Recently, machine learning (ML) emerged powerful tool complement this empirical process. ML models contribute (1) discovery functional annotation known protein or generating novel with functions (2) navigating fitness landscapes optimization mappings between associated values. In Outlook, we explain how complements discuss future potential improved outcomes.

Language: Английский

Citations

72
A guide to artificial intelligence for cancer researchers DOI
Raquel Pérez-López, Narmin Ghaffari Laleh, Faisal Mahmood

et al.

Nature reviews. Cancer, Journal Year: 2024, Volume and Issue: 24(6), P. 427 - 441

Published: May 16, 2024

Language: Английский

Citations

72
Advancing genome editing with artificial intelligence: opportunities, challenges, and future directions DOI Creative Commons

Shriniket Dixit,

Anant Kumar, Kathiravan Srinivasan

et al.

Frontiers in Bioengineering and Biotechnology, Journal Year: 2024, Volume and Issue: 11

Published: Jan. 8, 2024

Clustered regularly interspaced short palindromic repeat (CRISPR)-based genome editing (GED) technologies have unlocked exciting possibilities for understanding genes and improving medical treatments. On the other hand, Artificial intelligence (AI) helps achieve more precision, efficiency, affordability in tackling various diseases, like Sickle cell anemia or Thalassemia. AI models been use designing guide RNAs (gRNAs) CRISPR-Cas systems. Tools DeepCRISPR, CRISTA, DeepHF capability to predict optimal a specified target sequence. These predictions take into account multiple factors, including genomic context, Cas protein type, desired mutation on-target/off-target scores, potential off-target sites, impacts of on gene function phenotype. aid optimizing different technologies, such as base, prime, epigenome editing, which are advanced techniques introduce precise programmable changes DNA sequences without relying homology-directed repair pathway donor templates. Furthermore, AI, collaboration with precision medicine, enables personalized treatments based genetic profiles. analyzes patients' data identify mutations, variations, biomarkers associated diseases Cancer, Diabetes, Alzheimer's, etc. However, several challenges persist, high costs, suitable delivery methods CRISPR cargoes, ensuring safety clinical applications. This review explores AI's contribution CRISPR-based addresses existing challenges. It also discusses areas future research AI-driven technologies. The integration opens up new genetics, biomedicine, healthcare, significant implications human health.

Language: Английский

Citations

44
Whole genome sequencing in clinical practice DOI Creative Commons
Frederik Otzen Bagger,

Line Borgwardt,

Andreas Sand Jespersen

et al.

BMC Medical Genomics, Journal Year: 2024, Volume and Issue: 17(1)

Published: Jan. 29, 2024

Abstract Whole genome sequencing (WGS) is becoming the preferred method for molecular genetic diagnosis of rare and unknown diseases identification actionable cancer drivers. Compared to other methods, WGS captures most genomic variation eliminates need sequential testing. Whereas, laboratory requirements are similar conventional genetics, amount data large requires a comprehensive computational storage infrastructure in order facilitate processing within clinically relevant timeframe. The output single analyses roughly 5 MIO variants interpretation involves specialized staff collaborating with clinical specialists provide standard care reports. Although field continuously refining standards variant classification, there still unresolved issues associated application. review provides an overview practice - describing technology current applications as well challenges connected processing, reporting.

Language: Английский

Citations

44
Artificial Intelligence in Oncology: Current Landscape, Challenges, and Future Directions DOI Open Access

William Lotter,

Michael J. Hassett, Nikolaus Schultz

et al.

Cancer Discovery, Journal Year: 2024, Volume and Issue: 14(5), P. 711 - 726

Published: March 21, 2024

Artificial intelligence (AI) in oncology is advancing beyond algorithm development to integration into clinical practice. This review describes the current state of field, with a specific focus on integration. AI applications are structured according cancer type and domain, focusing four most common cancers tasks detection, diagnosis, treatment. These encompass various data modalities, including imaging, genomics, medical records. We conclude summary existing challenges, evolving solutions, potential future directions for field.

Language: Английский

Citations

36
The power and pitfalls of AlphaFold2 for structure prediction beyond rigid globular proteins DOI
Vinayak Agarwal, Andrew C. McShan

Nature Chemical Biology, Journal Year: 2024, Volume and Issue: 20(8), P. 950 - 959

Published: June 21, 2024

Language: Английский

Citations

30
Oxidative cyclization reagents reveal tryptophan cation–π interactions DOI
Xiao Xie, Patrick J. Moon, Steven W. M. Crossley

et al.

Nature, Journal Year: 2024, Volume and Issue: 627(8004), P. 680 - 687

Published: March 6, 2024

Language: Английский

Citations

27
Advances in AI for Protein Structure Prediction: Implications for Cancer Drug Discovery and Development DOI Creative Commons
Xinru Qiu, H. Li, Greg Ver Steeg

et al.

Biomolecules, Journal Year: 2024, Volume and Issue: 14(3), P. 339 - 339

Published: March 12, 2024

Recent advancements in AI-driven technologies, particularly protein structure prediction, are significantly reshaping the landscape of drug discovery and development. This review focuses on question how these technological breakthroughs, exemplified by AlphaFold2, revolutionizing our understanding function changes underlying cancer improve approaches to counter them. By enhancing precision speed at which targets identified candidates can be designed optimized, technologies streamlining entire development process. We explore use AlphaFold2 development, scrutinizing its efficacy, limitations, potential challenges. also compare with other algorithms like ESMFold, explaining diverse methodologies employed this field practical effects differences for application specific algorithms. Additionally, we discuss broader applications including prediction complex structures generative design novel proteins.

Language: Английский

Citations

27
Guiding questions to avoid data leakage in biological machine learning applications DOI
Judith Bernett, David B. Blumenthal, Dominik G. Grimm

et al.

Nature Methods, Journal Year: 2024, Volume and Issue: 21(8), P. 1444 - 1453

Published: Aug. 1, 2024

Language: Английский

Citations

24