اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدNote: Variational Encoding of Protein Dynamics Benefits from Maximizing Latent Autocorrelation
37
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
As deep Variational Auto-Encoder (VAE) frameworks become more widely used for modeling biomolecular simulation data, we emphasize the capability of the VAE architecture to concurrently maximize the timescale of the latent space while inferring a reduced coordinate, which assists in finding slow processes as according to the variational approach to conformational dynamics. We additionally provide evidence that the VDE framework (Hernandez et al., 2017), which uses this autocorrelation loss along with a time-lagged reconstruction loss, obtains a variationally optimized latent coordinate in comparison with related loss functions. We thus recommend leveraging the autocorrelation of the latent space while training neural network models of biomolecular simulation data to better represent slow processes.
قيم البحث
اقرأ أيضاً
Often the analysis of time-dependent chemical and biophysical systems produces high-dimensional time-series data for which it can be difficult to interpret which individual features are most salient. While recent work from our group and others has de
monstrated the utility of time-lagged co-variate models to study such systems, linearity assumptions can limit the compression of inherently nonlinear dynamics into just a few characteristic components. Recent work in the field of deep learning has led to the development of variational autoencoders (VAE), which are able to compress complex datasets into simpler manifolds. We present the use of a time-lagged VAE, or variational dynamics encoder (VDE), to reduce complex, nonlinear processes to a single embedding with high fidelity to the underlying dynamics. We demonstrate how the VDE is able to capture nontrivial dynamics in a variety of examples, including Brownian dynamics and atomistic protein folding. Additionally, we demonstrate a method for analyzing the VDE model, inspired by saliency mapping, to determine what features are selected by the VDE model to describe dynamics. The VDE presents an important step in applying techniques from deep learning to more accurately model and interpret complex biophysics.
Native electrospray ionization/ion mobility-mass spectrometry (ESI/IM-MS) allows an accurate determination of low-resolution structural features of proteins. Yet, the presence of proton dynamics, observed already by us for DNA in the gas phase, and i
ts impact on protein structural determinants, have not been investigated so far. Here, we address this issue by a multi-step simulation strategy on a pharmacologically relevant peptide, the N-terminal residues of amyloid-beta peptide (Abeta(1-16)). Our calculations reproduce the experimental maximum charge state from ESI-MS and are also in fair agreement with collision cross section (CCS) data measured here by ESI/IM-MS. Although the main structural features are preserved, subtle conformational changes do take place in the first ~0.1 ms of dynamics. In addition, intramolecular proton dynamics processes occur on the ps-timescale in the gas phase as emerging from quantum mechanics/molecular mechanics (QM/MM) simulations at the B3LYP level of theory. We conclude that proton transfer phenomena do occur frequently during fly time in ESI-MS experiments (typically on the ms timescale). However, the structural changes associated with the process do not significantly affect the structural determinants.
Reinforcement learning (RL) can enable task-oriented dialogue systems to steer the conversation towards successful task completion. In an end-to-end setting, a response can be constructed in a word-level sequential decision making process with the en
tire system vocabulary as action space. Policies trained in such a fashion do not require expert-defined action spaces, but they have to deal with large action spaces and long trajectories, making RL impractical. Using the latent space of a variational model as action space alleviates this problem. However, current approaches use an uninformed prior for training and optimize the latent distribution solely on the context. It is therefore unclear whether the latent representation truly encodes the characteristics of different actions. In this paper, we explore three ways of leveraging an auxiliary task to shape the latent variable distribution: via pre-training, to obtain an informed prior, and via multitask learning. We choose response auto-encoding as the auxiliary task, as this captures the generative factors of dialogue responses while requiring low computational cost and neither additional data nor labels. Our approach yields a more action-characterized latent representations which support end-to-end dialogue policy optimization and achieves state-of-the-art success rates. These results warrant a more wide-spread use of RL in end-to-end dialogue models.
An information source generates independent and identically distributed status update messages from an observed random phenomenon which takes $n$ distinct values based on a given pmf. These update packets are encoded at the transmitter node to be sen
t to a receiver node which wants to track the observed random variable with as little age as possible. The transmitter node implements a selective $k$ encoding policy such that rather than encoding all possible $n$ realizations, the transmitter node encodes the most probable $k$ realizations. We consider three different policies regarding the remaining $n-k$ less probable realizations: $highest$ $k$ $selective$ $encoding$ which disregards whenever a realization from the remaining $n-k$ values occurs; $randomized$ $selective$ $encoding$ which encodes and sends the remaining $n-k$ realizations with a certain probability to further inform the receiver node at the expense of longer codewords for the selected $k$ realizations; and $highest$ $k$ $selective$ $encoding$ $with$ $an$ $empty$ $symbol$ which sends a designated empty symbol when one of the remaining $n-k$ realizations occurs. For all of these three encoding schemes, we find the average age and determine the age-optimal real codeword lengths, including the codeword length for the empty symbol in the case of the latter scheme, such that the average age at the receiver node is minimized. Through numerical evaluations for arbitrary pmfs, we show that these selective encoding policies result in a lower average age than encoding every realization, and find the corresponding age-optimal $k$ values.
Understanding E3 ligase and target substrate interactions are important for cell biology and therapeutic development. However, experimental identification of E3 target relationships is not an easy task due to the labor-intensive nature of the experim
ents. In this article, a sequence-based E3-target prediction model is proposed for the first time. The proposed framework utilizes composition of k-spaced amino acid pairs (CKSAAP) to learn the relationship between E3 ligases and their target protein. A class separable latent space encoding scheme is also devised that provides a compressed representation of feature space. A thorough ablation study is performed to identify an optimal gap size for CKSAAP and the number of latent variables that can represent the E3-target relationship successfully. The proposed scheme is evaluated on an independent dataset for a variety of standard quantitative measures. In particular, it achieves an average accuracy of $70.63%$ on an independent dataset. The source code and datasets used in the study are available at the authors GitHub page (https://github.com/psychemistz/E3targetPred).
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
