检索结果-内蒙古大学图书馆

ReLSO: A Transformer-based Model for Latent Space Optimization and Generation of Proteins

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Castro, Egbert Godavarthi, Abhinav Rubinfien, Julian Givechian, Kevin Bhaskar, Dhananjay Krishnaswamy, Smita Computational Biology and Bioinformatics Program Yale University New HavenCT06511 United States Department of Applied Mathematics Yale University New HavenCT06511 United States Department of Genetics Yale University New HavenCT06511 United States Department of Computer Science Yale University New HavenCT06511 United States

The development of powerful natural language models have increased the ability to learn meaningful representations of protein sequences. In addition, advances in high-throughput mutagenesis, directed evolution, and next-generation sequencing have allowed for the accumulation of large amounts of labeled fitness data. Leveraging these two trends, we introduce Regularized Latent Space Optimization (ReLSO), a deep transformer-based autoencoder which features a highly structured latent space that is trained to jointly generate sequences as well as predict fitness. Through regularized prediction heads, ReLSO introduces a powerful protein sequence encoder and novel approach for efficient fitness landscape traversal. Using ReLSO, we explicitly model the sequence-function landscape of large labeled datasets and generate new molecules by optimizing within the latent space using gradient-based methods. We evaluate this approach on several publicly-available protein datasets, including variant sets of anti-ranibizumab and GFP. We observe a greater sequence optimization efficiency (increase in fitness per optimization step) by ReLSO compared to other approaches, where ReLSO more robustly generates high-fitness sequences. Furthermore, the attention-based relationships learned by the jointly-trained ReLSO models provides a potential avenue towards sequence-level fitness attribution information. © 2022, CC BY-NC-ND.

关键词： Proteins

Autonomous Electron Tomography Reconstruction with Machine Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Millsaps, William Schwartz, Jonathan Di, Zichao Wendy Jiang, Yi Hovden, Robert Department of Nuclear Engineering & Radiological Sciences University of Michigan Ann ArborMI United States Department of Materials Science and Engineering University of Michigan Ann ArborMI United States Mathematics and Computer Science Division Argonne National Laboratory LemontIL United States Advanced Photon Source Facility Argonne National Laboratory LemontIL United States Applied Physics Program University of Michigan Ann ArborMI United States

This manuscript is published in Microscopy and Microanalysis (DOI: 10.1093/micmic/ozad083). Modern electron tomography has progressed to higher resolution at lower doses by leveraging compressed sensing methods that minimize total variation (TV). However, these sparsity-emphasized reconstruction algorithms introduce tunable parameters that greatly influence the reconstruction quality. Here, Pareto front analysis shows that high-quality tomograms are reproducibly achieved when TV minimization is heavily weighted. However, in excess, compressed sensing tomography creates overly smoothed 3D reconstructions. Adding momentum to the gradient descent during reconstruction reduces the risk of over-smoothing and better ensures that compressed sensing is well behaved. For simulated data, the tedious process of tomography parameter selection is efficiently solved using Bayesian optimization with Gaussian processes. In combination, Bayesian optimization with momentum-based compressed sensing greatly reduces the required compute time-an 80% reduction was observed for the 3D reconstruction of SrTiO3 nanocubes. Automated parameter selection is necessary for large scale tomographic simulations that enable the 3D characterization of a wider range of inorganic and biological materials. © 2023, CC BY.

关键词： Compressed sensing

3D imaging lipidometry in single cell by in-flow holographic tomography

学校读者我要写书评

暂无评论

Opto-Electronic Advances 2023年第1期6卷 10-25页

作者： Daniele Pirone Daniele Sirico Lisa Miccio Vittorio Bianco Martina Mugnano Danila del Giudice Gianandrea Pasquinelli Sabrina Valente Silvia Lemma Luisa Iommarini Ivana Kurelac Pasquale Memmolo Pietro Ferraro CNR-ISASI Institute of Applied Sciences and Intelligent Systems“E.Caianiello”Via Campi Flegrei 34PozzuoliNapoli 80078Italy Department of Electrical Engineering and Information Technologies University of Naples“FedericoⅡ”via Claudio 21Napoli 80125Italy Department of Chemical Materials and Production Engineering of the University of Naples FedericoⅡPiazzale Tecchio 80Napoli 80125Italy Department of Mathematics and Physics University of Campania“Luigi Vanvitelli”Caserta 81100Italy Biotechnology and Methods in Laboratory Medicine Department of ExperimentalDiagnostic and Specialty Medicine(DIMES)University of BolognaBologna 40126Italy Subcellular Nephro-Vascular Diagnostic Program Pathology Unit S.Orsola IRCCSUniversity of BolognaBologna 40126Italy Unit of Medical Genetics Department of Medical and Surgical Sciences(DIMEC)University of BolognaVia Massarenti 9Bologna 40138Italy Study and Research Center on Gynecological Neoplasias Department of Medical and Surgical Sciences(DIMEC)University of BolognaVia Massarenti 9Bologna 40138Italy Center for Applied Biomedical Research(CRBA) University of BolognaBologna 40138Italy Department of Pharmacy and Biotechnology(FABIT) University of BolognaBologna 40126Italy

The most recent discoveries in the biochemical field are highlighting the increasingly important role of lipid droplets(LDs)in several regulatory mechanisms in living *** are dynamic organelles and therefore their complete characterization in terms of number,size,spatial positioning and relative distribution in the cell volume can shed light on the roles played by *** now,fluorescence microscopy and transmission electron microscopy are assessed as the gold standard methods for identifying LDs due to their high sensitivity and ***,such methods generally only provide 2D assays and partial ***,both can be destructive and with low productivity,thus limiting analysis of large cell numbers in a *** we demonstrate for the first time the capability of 3D visualization and the full LD characterization in high-throughput with a tomographic phase-contrast flow-cytometer,by using ovarian cancer cells and monocyte cell lines as models.A strategy for retrieving significant parameters on spatial correlations and LD 3D positioning inside each cell volume is *** information gathered by this new method could allow more in depth understanding and lead to new discoveries on how LDs are correlated to cellular functions.

关键词： lipid droplets label-free phase-contrast imaging in-flow tomography 3D imaging

Machine learning based non-Newtonian fluid model with molecular fidelity

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Lei, Huan Wu, Lei Weinan, E. Department of Computational Mathematics Science & Engineering Department of Statistics & Probability Michigan State University MI48824 United States Department of Mathematics and Program in Applied and Computational Mathematics Princeton University NJ08544 United States

We introduce a machine-learning-based framework for constructing continuum non-Newtonian fluid dynamics model directly from a micro-scale description. Polymer solution is used as an example to demonstrate the essential ideas. To faithfully retain molecular fidelity, we establish a micro-macro correspondence via a set of encoders for the micro-scale polymer configurations and their macro-scale counterparts, a set of nonlinear conformation tensors. The dynamics of these conformation tensors can be derived from the micro-scale model and the relevant terms can be parametrized using machine learning. The final model, named the deep non-Newtonian model (DeePN2), takes the form of conventional non-Newtonian fluid dynamics models, with a new form of the objective tensor derivative. Numerical results demonstrate the accuracy of DeePN2. Copyright © 2020, The Authors. All rights reserved.

关键词： Viscous flow

Isotope effects in x-ray absorption spectra of liquid water

学校读者我要写书评

暂无评论

Physical Review B 2020年第11期102卷 115155-115155页

作者： Chunyi Zhang Linfeng Zhang Jianhang Xu Fujie Tang Biswajit Santra Xifan Wu Department of Physics Temple University Philadelphia Pennsylvania 19122 USA Program in Applied and Computational Mathematics Princeton University Princeton New Jersey 08544 USA

The isotope effects in x-ray absorption spectra of liquid water are studied by a many-body approach within electron-hole excitation theory. The molecular structures of both light and heavy water are modeled by path-integral molecular dynamics based on the advanced deep-learning technique. The neural network is trained on ab initio data obtained with SCAN density functional theory. The experimentally observed isotope effect in x-ray absorption spectra is reproduced semiquantitatively in theory. Compared to the spectrum in normal water, the blueshifted and less pronounced pre- and main-edge in heavy water reflect that the heavy water is more structured at short- and intermediate-range of the hydrogen-bond network. In contrast, the isotope effect on the spectrum is negligible at post-edge, which is consistent with the identical long-range ordering in both liquids as observed in the diffraction experiment.

关键词： Atomic & molecular structure Electronic excitation & ionization Water Density functional calculations Electronic structure First-principles calculations Machine learning Molecular dynamics X-ray absorption spectroscopy

ZERO KINETIC UNDERCOOLING LIMIT IN THE SUPERCOOLED STEFAN PROBLEM

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Baker, Graeme Shkolnikov, Mykhaylo Program in Applied & Computational Mathematics Princeton University PrincetonNJ08544 United States ORFE Department Bendheim Center for Finance Program in Applied & Computational Mathematics Princeton University PrincetonNJ08544 United States

We study the solutions of the one-phase supercooled Stefan problem with kinetic undercooling, which describes the freezing of a supercooled liquid, in one spatial dimension. Assuming that the initial temperature lies between the equilibrium freezing point and the characteristic invariant temperature throughout the liquid our main theorem shows that, as the kinetic undercooling parameter tends to zero, the free boundary converges to the (possibly irregular) free boundary in the supercooled Stefan problem without kinetic undercooling, whose uniqueness has been recently established in [DNS19], [LS18b]. The key tools in the proof are a Feynman-Kac formula, which expresses the free boundary in the problem with kinetic undercooling through a local time of a reflected process, and a resulting comparison principle for the free boundaries with different kinetic undercooling *** Codes 80A22, 35B44, 60H30 Copyright © 2020, The Authors. All rights reserved.

关键词： Supercooling

Understanding degeneracy of two-point correlation functions via debye random media

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Skolnick, Murray Torquato, Salvatore Department of Chemistry Princeton University PrincetonNJ08544 United States Department of Chemistry Department of Physics Princeton Institute for the Science and Technology of Materials Program in Applied and Computational Mathematics Princeton University PrincetonNJ08544 United States

It is well-known that the degeneracy of two-phase microstructures with the same volume fraction and two-point correlation function S2(r) is generally infinite. To elucidate the degeneracy problem explicitly, we examine Debye random media, which are entirely defined by a purely exponentially decaying two-point correlation function S2(r). In this work, we consider three different classes of Debye random media. First, we generate the "most probable" class using the Yeong-Torquato construction algorithm [Yeong and Torquato, Phys. Rev. E, 57, 495 (1998)]. A second class of Debye random media is obtained by demonstrating that the corresponding two-point correlation functions are effectively realized in the first three space dimensions by certain models of overlapping, polydisperse spheres. A third class is obtained by using the Yeong-Torquato algorithm to construct Debye random media that are constrained to have an unusual prescribed pore-size probability density function. We structurally discriminate these three classes of Debye random media from one another by ascertaining their other statistical descriptors, including the pore-size, surface correlation, chordlength probability density, and lineal-path functions. We also compare and contrast the percolation thresholds as well as the diffusion and fluid transport properties of these degenerate Debye random media. We find that these three classes of Debye random media are generally distinguished by the aforementioned descriptors and their microstructures are also visually distinct from one another. Our work further confirms the well-known fact that scattering information is insufficient to determine the effective physical properties of two-phase media. Additionally, our findings demonstrate the importance of the other two-point descriptors considered here in the design of materials with a spectrum of physical properties. © 2021, CC BY-SA.

关键词： Random processes

Towards a mathematical understanding of neural network-based machine learning: What we know and what we don't

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Weinan, E. Ma, Chao Wojtowytsch, Stephan Wu, Lei Department of Mathematics Princeton University United States Program in Applied and Computational Mathematics Princeton University United States Department of Mathematics Stanford University United States Beijing Institute of Big Data Research China

Forecasting high-frequency spatio-temporal wind power with dimensionally reduced echo state networks

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Huang, Huang Castruccio, Stefano Genton, Marc G. Statistics Program King Abdullah University of Science and Technology Thuwal 23955-6900 Saudi Arabia Department of Applied and Computational Mathematics and Statistics University of Notre Dame Notre DameIN46556 United States

Fast and accurate hourly forecasts of wind speed and power are crucial in quan-tifying and planning the energy budget in the electric grid. Modeling wind at a high resolution brings forth considerable challenges given its turbulent and highly nonlin-ear dynamics. In developing countries, where wind farms over a large domain are currently under construction or consideration, this is even more challenging given the necessity of modeling wind over space as well. In this work, we propose a machine learning approach to model the nonlinear hourly wind dynamics in Saudi Arabia with a domain-specific choice of knots to reduce the spatial dimensionality. Our re-sults show that for locations highlighted as wind abundant by a previous work, our approach results in an 11% improvement in the two-hour-ahead forecasted power against operational standards in the wind energy sector, yielding a saving of nearly one million US dollars over a year under current market prices in Saudi Arabia. © 2021, CC BY.

关键词： Wind power