Advancing mathematics by guiding human intuition with AI

Davies, A.E.; Veličković, Petar; Buesing, Lars; Blackwell, Sam; Zheng, Daniel; Tomašev, Nenad; Tanburn, Richard; Battaglia, Peter W.; Blundell, Charles; Juhász, András; Lackenby, Marc; Williamson, Geordie; Hassabis, Demis; Kohli, Pushmeet

doi:10.1038/s41586-021-04086-x

Cited by 290 publications

(189 citation statements)

References 21 publications

Supporting

Mentioning

188

Contrasting

Unclassified

Order By: Relevance

“…The advent of these modern computational techniques is adding a further dimension and alternative to toxicity testing panels. These emerging tools effectively analyze multidimensional data, may recognize patterns, and formulate reasonable conjectures [ 111 ], generating a new paradigm for the early stages of peptide drug development.…”

Section: Computational Tools and Databases For Hemolytic Activity Pre...mentioning

confidence: 99%

Traditional and Computational Screening of Non-Toxic Peptides and Approaches to Improving Selectivity

et al. 2022

View full text Add to dashboard Cite

Peptides have positively impacted the pharmaceutical industry as drugs, biomarkers, or diagnostic tools of high therapeutic value. However, only a handful have progressed to the market. Toxicity is one of the main obstacles to translating peptides into clinics. Hemolysis or hemotoxicity, the principal source of toxicity, is a natural or disease-induced event leading to the death of vital red blood cells. Initial screenings for toxicity have been widely evaluated using erythrocytes as the gold standard. More recently, many online databases filled with peptide sequences and their biological meta-data have paved the way toward hemolysis prediction using user-friendly, fast-access machine learning-driven programs. This review details the growing contributions of in silico approaches developed in the last decade for the large-scale prediction of erythrocyte lysis induced by peptides. After an overview of the pharmaceutical landscape of peptide therapeutics, we highlighted the relevance of early hemolysis studies in drug development. We emphasized the computational models and algorithms used to this end in light of historical and recent findings in this promising field. We benchmarked seven predictors using peptides from different data sets, having 7–35 amino acids in length. According to our predictions, the models have scored an accuracy over 50.42% and a minimal Matthew’s correlation coefficient over 0.11. The maximum values for these statistical parameters achieved 100.0% and 1.00, respectively. Finally, strategies for optimizing peptide selectivity were described, as well as prospects for future investigations. The development of in silico predictive approaches to peptide toxicity has just started, but their important contributions clearly demonstrate their potential for peptide science and computer-aided drug design. Methodology refinement and increasing use will motivate the timely and accurate in silico identification of selective, non-toxic peptide therapeutics.

show abstract

Section: Computational Tools and Databases For Hemolytic Activity Pre...mentioning

confidence: 99%

Traditional and Computational Screening of Non-Toxic Peptides and Approaches to Improving Selectivity

et al. 2022

View full text Add to dashboard Cite

show abstract

“…(2) help formulate new conjectures and find easier formulae (q.v. recent collaboration on how AI can help with mathematical intuition [36])? (3) help with new pathways in a proof?…”

Section: The Landscape Of Mathematicsmentioning

confidence: 99%

From the String Landscape to the Mathematical Landscape: a Machine-Learning Outlook

He¹

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…To engineers, the desire for theories is why neural networks designed by them and trained by error back-propagation methods work so well, especially for those called deep learning with excellent performances in recent years. The unravelling of this "black box" is vital to the instruction of parameter setting, the explanation of scientific or mathematical applications (such as Davies et al (2021) and Jumper et al (2021)), and the further development with proper guidance.…”

Section: Introductionmentioning

confidence: 99%

Theoretical Exploration of Solutions of Feedforward ReLU Networks

Huang¹

2022

Preprint

View full text Add to dashboard Cite

This paper aims to interpret the mechanism of feedforward ReLU networks by exploring their solutions for piecewise linear functions through basic rules. The constructed solutions should be universal enough to explain the network architectures of engineering. In order for that, we borrow the methodology of theoretical physics to develop the theories. Some of the consequences of our theories include: Under geometric backgrounds, the solutions of both three-layer networks and deep-layer networks are presented, and the solution universality is ensured by several ways; We give clear and intuitive interpretations of each component of network architectures, such as the parameter-sharing mechanism for multi-output, the function of each layer, the advantage of deep layers, the redundancy of parameters, and so on. We explain three typical network architectures: the subnetwork of last three layers of convolutional networks, multi-layer feedforward networks, and the decoder of autoencoders. This paper is expected to provide a basic foundation of theories of feedforward ReLU networks for further investigations.

show abstract

Advancing mathematics by guiding human intuition with AI

Cited by 290 publications

References 21 publications

Traditional and Computational Screening of Non-Toxic Peptides and Approaches to Improving Selectivity

Traditional and Computational Screening of Non-Toxic Peptides and Approaches to Improving Selectivity

From the String Landscape to the Mathematical Landscape: a Machine-Learning Outlook

Theoretical Exploration of Solutions of Feedforward ReLU Networks

Contact Info

Product

Resources

About