DATASCI 221: Computational Biology: AI in biology

An article by Vivien Marx published in the Nature Methods August 2024 issue, Focus on advanced AI in biology, on ongoing efforts to develop guidance, training and policies for the use of AI in science.
Citation: Marx V. 2024. Quest for AI literacy. Nature Methods 21:1412–1415.

An argument that risks from AI in basic biology research can be addressed with basic education in AI ethics combined with community governance measures that are tailored to the needs of individual research communities.
Citation: Prunkl C. 2024. AI meets biology: a call for community governance. Nature Methods 21: 1407–1408.

An outline of the strengths and limitations of generative AI tools for academic writing, including brainstorming/topic formation, searching, synthesizing, and writing.

A news feature from PNAS describing how, by combining automation and AI, labs could see big boosts in speed, efficiency, and even creativity. Examples include LBNL and Carnegie-Mellon's Cloud Lab.
Citation: Adam D. 2024. The automated lab of tomorrow. Proceedings of the National Academy of Sciences 121: e2406320121.

An overview of IML methods and evaluation techniques and a discussion of common pitfalls encountered when applying IML methods to computational biology problems.
Citation: Chen V, Yang M, Cui W, Kim JS, Talwalkar A, Ma J. 2024. Applying interpretable machine learning in computational biology—pitfalls, recommendations and opportunities for new developments. Nature Methods 21: 1454–1461.

Guidance on best practices and key resources for adapting language models for biology.
Citation: Simon E, Swanson K, Zou J. 2024. Language models for biological research: a primer. Nature Methods 21: 1422–1429.

An article from Annual Review of Biomedical Engineering on the application of AI to cancer diagnosis and personalized treatment.
Citation: Lorenzo G, Ahmed SR, Hormuth DA, Vaughn B, Kalpathy-Cramer J, Solorio L, Yankeelov TE, Gomez H. 2024. Patient-Specific, Mechanistic Models of Tumor Growth Incorporating Artificial Intelligence and Big Data. Annual Review of Biomedical Engineering 26: 529–560.

How AI is providing new insights about the underpinnings of disease, the aging process, and the potential ability to forecast an individual’s health trajectory.
Citation: Topol EJ. 2024. The revolution in high-throughput proteomics and AI. Science 385: eads5749.

This review discusses the use of AI in the three pillars of drug discovery: diseases, targets, and therapeutic modalities, with a focus on small-molecule drugs.
Citation: Hasselgren C, Oprea TI. 2024. Artificial Intelligence for Drug Discovery: Are We There Yet? Annual Review of Pharmacology and Toxicology 64: 527–550.

Applying AI to develop gene sequence-to-function models will transform our understanding of gene regulation and open new avenues for discovering disease mechanisms.
Citation: Sasse A, Chikina M, Mostafavi S. 2024. Unlocking gene regulation with sequence-to-function models. Nature Methods 21: 1374–1377.

A review of the use of machine learning techniques to exploit neuroimaging data for clinical care and research, providing an overview of clinical applications and their contribution to fundamental computational neuroscience.
Citation: Nenning K-H, Langs G. 2022. Machine learning in neuroimaging: from research to clinical practice. Die Radiologie 62: 1–10.

AI will help facilitate "programmable biology" through molecular and cellular engineering.
Citation: Abudayyeh OO, Gootenberg JS. 2024. Programmable biology through artificial intelligence: from nucleic acids to proteins to cells. Nature Methods 21: 1384–1386.

A Science News article by Robert F. Service about using AI to design novel proteins for vaccines, cancer treatments, environmental remediation, and more.
Citation: Service RF. 2024. AI designer proteins could transform medicine and materials. Science 386: 260-261.

An overview from the Royal Swedish Academy of Sciences about the 2024 Nobel Prize laureates in chemistry: Demis Hassabis and John M. Jumper have successfully utilised artificial intelligence in their program Alphafold2 to predict the structure of almost all known proteins; David Baker has learned how to master life’s building blocks and create entirely new proteins such as Top7.