J. E. Yukich
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
J. E. Yukich has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Adrian L. Sanborn
Department of Computer Science, Stanford University
1 shared publication Akshay Tambe
Atomic AI
1 shared publication- Alan Frieze
Department of Mathematical Sciences Carnegie Mellon University Pittsburgh Pennsylvania USA
1 shared publication April Schleck
Atomic AI
1 shared publication- Ayah Abdeldayem
Atomic AI
1 shared publication - Brandon M. Anderson
James Franck Institute, University of Chicago, Chicago, Illinois 60637, USA
1 shared publication
Latest Publications
- Open Access
ATOM-1: A Foundation Model for RNA Structure and Function Built on Chemical Mapping Data
RNA-based medicines and RNA-targeting drugs are emerging as promising new approaches for treating disease. Optimizing these therapeutics by naive experimental screening is a time-consuming and expensive process, while rational design requires an accurate understanding of the structure and function of RNA. To address this design challenge, we present ATOM-1, the first RNA foundation model trained on chemical mapping data, enabled by data collection strategies purposely developed for machine learning training. Using small probe neural networks on top of ATOM-1 embeddings, we demonstrate that this model has developed rich internal representations of RNA. Trained on limited amounts of additional data, these small networks achieve state-of-the-art accuracy on key RNA prediction tasks, suggesting that this approach can enable the design of therapies across the RNA landscape.
Open AccessATOM-1: A Foundation Model for RNA Structure and Function Built on Chemical Mapping Data
RNA-based medicines and RNA-targeting drugs are emerging as promising new approaches for treating disease. Optimizing these therapeutics by naive experimental screening is a time-consuming and expensive process, while rational design requires an accurate understanding of the structure and function of RNA. To address this design challenge, we present ATOM-1, the first RNA foundation model trained on chemical mapping data, enabled by data collection strategies purposely developed for machine learning training. Using small probe neural networks on top of ATOM-1 embeddings, we demonstrate that this model has developed rich internal representations of RNA. Trained on limited amounts of additional data, these small networks achieve state-of-the-art accuracy on key RNA prediction tasks, suggesting that this approach can enable the design of therapies across the RNA landscape.
- 27 September 2010
- Published by Springer Nature
- p. 189-199
Laws of Large Numbers and Nearest Neighbor Distances
- 27 September 2010
- Published by Springer Nature
- p. 189-199
Laws of Large Numbers and Nearest Neighbor Distances
- 1 December 1996
- Published by Springer Nature in Combinatorica
- Vol. 16 (4) , 575-586
Worst case asymptotics for some classical optimization problems
- 1 December 1996
- Published by Springer Nature in Combinatorica
- Vol. 16 (4) , 575-586
Worst case asymptotics for some classical optimization problems
- 1 January 1992
- Published by Taylor & Francis in Philosophical Magazine A
- Vol. 65 (1) , 71-84
A simplified probabilistic model of the growth of creep cavitation
We present a simplified probabilistic model for the growth of creep cavitation based upon earlier work of Fariborz, Harlow and Delph. The model is cast in the form of a random differential equation, which is valid for times sufficiently short that the cavities do not cover an appreciable portion of the grain boundary. This equation is solved using a numerical technique due to Bellomo and Pistone in order to obtain the probability density function (p.d.f.) for the distribution of the cavity sizes as a function of time. In physical terms, this is equivalent to determining the normalized cavity size distribution as a function of time. The present model represents the first probabilistically-based model of creep cavity growth for which it has been possible to calculate the probability density function. The results are compared with experimentally measured cavity size distributions. They seem to be in good qualitative agreement with the data for the range of times for which the model is valid, as well as in reasonable quantative agreement in several aspects.
- 1 January 1992
- Published by Taylor & Francis in Philosophical Magazine A
- Vol. 65 (1) , 71-84
A simplified probabilistic model of the growth of creep cavitation
We present a simplified probabilistic model for the growth of creep cavitation based upon earlier work of Fariborz, Harlow and Delph. The model is cast in the form of a random differential equation, which is valid for times sufficiently short that the cavities do not cover an appreciable portion of the grain boundary. This equation is solved using a numerical technique due to Bellomo and Pistone in order to obtain the probability density function (p.d.f.) for the distribution of the cavity sizes as a function of time. In physical terms, this is equivalent to determining the normalized cavity size distribution as a function of time. The present model represents the first probabilistically-based model of creep cavity growth for which it has been possible to calculate the probability density function. The results are compared with experimentally measured cavity size distributions. They seem to be in good qualitative agreement with the data for the range of times for which the model is valid, as well as in reasonable quantative agreement in several aspects.