arXiv Computer Science @arxiv_cs@qoto.org

Figuring out small molecule binding sites in target proteins, in the resolution of either pocket or residue, is critical in many virtual and real drug-discovery scenarios. Since it is not always easy to find such binding sites based on domain knowledge or traditional methods, different deep learning methods that predict binding sites out of protein structures have been developed in recent years. Here we present a new such deep learning algorithm, that significantly outperformed all state-of-the-art baselines in terms of the both resolutions$\unicode{x2013}$pocket and residue. This good performance was also demonstrated in a case study involving the protein human serum albumin and its binding sites. Our algorithm included new ideas both in the model architecture and in the training method. For the model architecture, it incorporated SE(3)-invariant geometric self-attention layers that operate on top of residue-level CNN outputs. This residue-level processing of the model allowed a transfer learning between the two resolutions, which turned out to significantly improve the binding pocket prediction. Moreover, we developed novel augmentation method based on protein homology, which prevented our model from over-fitting. Overall, we believe that our contribution to the literature is twofold. First, we provided a new computational method for binding site prediction that is relevant to real-world applications, as shown by the good performance on different benchmarks and case study. Second, the novel ideas in our method$\unicode{x2013}$the model architecture, transfer learning and the homology augmentation$\unicode{x2013}$would serve as useful components in future works.

Large language models (LLMs) have recently taken the world by storm. They can generate coherent text, hold meaningful conversations, and be taught concepts and basic sets of instructions - such as the steps of an algorithm. In this context, we are interested in exploring the application of LLMs to graph drawing algorithms by performing experiments on ChatGPT. These algorithms are used to improve the readability of graph visualizations. The probabilistic nature of LLMs presents challenges to implementing algorithms correctly, but we believe that LLMs' ability to learn from vast amounts of data and apply complex operations may lead to interesting graph drawing results. For example, we could enable users with limited coding backgrounds to use simple natural language to create effective graph visualizations. Natural language specification would make data visualization more accessible and user-friendly for a wider range of users. Exploring LLMs' capabilities for graph drawing can also help us better understand how to formulate complex algorithms for LLMs; a type of knowledge that could transfer to other areas of computer science. Overall, our goal is to shed light on the exciting possibilities of using LLMs for graph drawing while providing a balanced assessment of the challenges and opportunities they present. A free copy of this paper with all supplemental materials required to reproduce our results is available on https://osf.io/n5rxd/?view_only=f09cbc2621f44074810b7d843f1e12f9

Wireless Sensor Networks (WSNs) have become increasingly valuable in various civil/military applications like industrial process control, civil engineering applications such as buildings structural strength monitoring, environmental monitoring, border intrusion, IoT (Internet of Things), and healthcare. However, the sensed data generated by WSNs is often noisy and unreliable, making it a challenge to detect and diagnose anomalies. Machine learning (ML) techniques have been widely used to address this problem by detecting and identifying unusual patterns in the sensed data. This survey paper provides an overview of the state of the art applications of ML techniques for data anomaly detection in WSN domains. We first introduce the characteristics of WSNs and the challenges of anomaly detection in WSNs. Then, we review various ML techniques such as supervised, unsupervised, and semi-supervised learning that have been applied to WSN data anomaly detection. We also compare different ML-based approaches and their performance evaluation metrics. Finally, we discuss open research challenges and future directions for applying ML techniques in WSNs sensed data anomaly detection.

Intelligent reflecting surface (IRS) has recently received much attention from the research community due to its potential to achieve high spectral and power efficiency cost-effectively. In addition to traditional cellular networks, the use of IRS in vehicular networks is also considered. Prior works on IRS-aided vehicle-to-everything communications focus on deploying reflection surfaces on the facades of buildings along the road for sidelink performance enhancement. This paper goes beyond the state of the art by presenting a novel paradigm coined Intelligent Reflecting Vehicle Surface (IRVS). It embeds a massive number of reflection elements on vehicles' surfaces to aid moving vehicular networks in military and emergency communications. We propose an alternative optimization method to optimize jointly active beamforming at the base station and passive reflection across multiple randomly-distributed vehicle surfaces. Performance evaluation in terms of sum spectral efficiency under continuous, discrete, and random phase shifts is conducted. Numerical results reveal that IRVS can substantially improve the capacity of a moving vehicular network.

Intelligent reflecting surface (IRS) is envisioned to become a key technology for the upcoming six-generation (6G) wireless system due to its potential of reaping high performance in a power-efficient and cost-efficient way. With its disruptive capability and hardware constraint, the integration of IRS imposes some fundamental particularities on the coordination of multi-user signal transmission. Consequently, the conventional orthogonal and non-orthogonal multiple-access schemes are hard to directly apply because of the joint optimization of active beamforming at the base station and passive reflection at the IRS. Relying on an alternating optimization method, we develop novel schemes for efficient multiple access in IRS-aided multi-user multi-antenna systems in this paper. Achievable performance in terms of the sum spectral efficiency is theoretically analyzed. A comprehensive comparison of different schemes and configurations is conducted through Monte-Carlo simulations to clarify which scheme is favorable for this emerging 6G paradigm.

In recent years, compact and efficient scene understanding representations have gained popularity in increasing situational awareness and autonomy of robotic systems. In this work, we illustrate the concept of a panoptic edge segmentation and propose PENet, a novel detection network called that combines semantic edge detection and instance-level perception into a compact panoptic edge representation. This is obtained through a joint network by multi-task learning that concurrently predicts semantic edges, instance centers and offset flow map without bounding box predictions exploiting the cross-task correlations among the tasks. The proposed approach allows extending semantic edge detection to panoptic edge detection which encapsulates both category-aware and instance-aware segmentation. We validate the proposed panoptic edge segmentation method and demonstrate its effectiveness on the real-world Cityscapes dataset.

We present IMPACT, a flexible toolchain for nonlinear model predictive control (NMPC) specification with automatic code generation capabilities. The toolchain reduces the engineering complexity of NMPC implementations by providing the user with an easy-to-use application programming interface, and with the flexibility of using multiple state-of-the-art tools and numerical optimization solvers for rapid prototyping of NMPC solutions. IMPACT is written in Python, users can call it from Python and MATLAB, and the generated NMPC solvers can be directly executed from C, Python, MATLAB and Simulink. An application example is presented involving problem specification and deployment on embedded hardware using Simulink, showing the effectiveness and applicability of IMPACT for NMPC-based solutions.

Model-based Reinforcement Learning (RL) integrates learning and planning and has received increasing attention in recent years. However, learning the model can incur a significant cost (in terms of sample complexity), due to the need to obtain a sufficient number of samples for each state-action pair. In this paper, we investigate the benefits of leveraging structural information about the system in terms of reducing sample complexity. Specifically, we consider the setting where the transition probability matrix is a known function of a number of structural parameters, whose values are initially unknown. We then consider the problem of estimating those parameters based on the interactions with the environment. We characterize the difference between the Q estimates and the optimal Q value as a function of the number of samples. Our analysis shows that there can be a significant saving in sample complexity by leveraging structural information about the model. We illustrate the findings by considering several problems including controlling a queuing system with heterogeneous servers, and seeking an optimal path in a stochastic windy gridworld.

We study the spread of multi-competitive viruses over a (possibly) time-varying network of individuals accounting for the presence of shared infrastructure networks that further enables transmission of the virus. We establish a sufficient condition for exponentially fast eradication of a virus for: 1) time-invariant graphs, 2) time-varying graphs with symmetric interactions between individuals and homogeneous virus spread across the network (same healing and infection rate for all individuals), and 3) directed and slowly varying graphs with heterogeneous virus spread (not necessarily same healing and infection rates for all individuals) across the network. Numerical examples illustrate our theoretical results and indicate that, for the time-varying case, violation of the aforementioned sufficient conditions could lead to the persistence of a virus.

Image-to-image reconstruction problems with free or inexpensive metadata in the form of class labels appear often in biological and medical image domains. Existing text-guided or style-transfer image-to-image approaches do not translate to datasets where additional information is provided as discrete classes. We introduce and implement a model which combines image-to-image and class-guided denoising diffusion probabilistic models. We train our model on a real-world dataset of microscopy images used for drug discovery, with and without incorporating metadata labels. By exploring the properties of image-to-image diffusion with relevant labels, we show that class-guided image-to-image diffusion can improve the meaningful content of the reconstructed images and outperform the unguided model in useful downstream tasks.

Until recently, conventional biochemical staining had the undisputed status as well-established benchmark for most biomedical problems related to clinical diagnostics, fundamental research and biotechnology. Despite this role as gold-standard, staining protocols face several challenges, such as a need for extensive, manual processing of samples, substantial time delays, altered tissue homeostasis, limited choice of contrast agents for a given sample, 2D imaging instead of 3D tomography and many more. Label-free optical technologies, on the other hand, do not rely on exogenous and artificial markers, by exploiting intrinsic optical contrast mechanisms, where the specificity is typically less obvious to the human observer. Over the past few years, digital staining has emerged as a promising concept to use modern deep learning for the translation from optical contrast to established biochemical contrast of actual stainings. In this review article, we provide an in-depth analysis of the current state-of-the-art in this field, suggest methods of good practice, identify pitfalls and challenges and postulate promising advances towards potential future implementations and applications.

Performance optimization is an increasingly challenging but often repetitive task. While each platform has its quirks, the underlying code transformations rely on data movement and computational characteristics that recur across applications. This paper proposes to leverage those similarities by constructing an embedding space for subprograms. The continuous space captures both static and dynamic properties of loop nests via symbolic code analysis and performance profiling, respectively. Performance embeddings enable direct knowledge transfer of performance tuning between applications, which can result from autotuning or tailored improvements. We demonstrate this transfer tuning approach on case studies in deep neural networks, dense and sparse linear algebra compositions, and numerical weather prediction stencils. Transfer tuning reduces the search complexity by up to four orders of magnitude and outperforms the MKL library in sparse-dense matrix multiplication. The results exhibit clear correspondences between program characteristics and optimizations, outperforming prior specialized state-of-the-art approaches and generalizing beyond their capabilities.

This work outlines a fast, high-precision time-domain solver for scalar, electromagnetic and gravitational perturbations on hyperboloidal foliations of Kerr space-times. Time-domain Teukolsky equation solvers have typically used explicit methods, which numerically violate Noether symmetries and are Courant-limited. These restrictions can limit the performance of explicit schemes when simulating long-time extreme mass ratio inspirals, expected to appear in LISA band for 2-5 years. We thus explore symmetric (exponential, Padé or Hermite) integrators, which are unconditionally stable and known to preserve certain Noether symmetries and phase-space volume. For linear hyperbolic equations, these implicit integrators can be cast in explicit form, making them well-suited for long-time evolution of black hole perturbations. The 1+1 modal Teukolsky equation is discretized in space using polynomial collocation methods and reduced to a linear system of ordinary differential equations, coupled via mode-coupling arrays and discretized (matrix) differential operators. We use a matricization technique to cast the mode-coupled system in a form amenable to a method-of-lines framework, which simplifies numerical implementation and enables efficient parallelization on CPU and GPU architectures. We test our numerical code by studying late-time tails of Kerr spacetime perturbations in the sub-extremal and extremal cases.

Unsupervised spectral unmixing consists of representing each observed pixel as a combination of several pure materials called endmembers with their corresponding abundance fractions. Beyond the linear assumption, various nonlinear unmixing models have been proposed, with the associated optimization problems solved either by traditional optimization algorithms or deep learning techniques. Current deep learning-based nonlinear unmixing focuses on the models in additive, bilinear-based formulations. By interpreting the reflection process using the discrete Markov chain, the multilinear mixing model (MLM) successfully accounts for the up to infinite-order interactions between endmembers. However, to simulate the physics process of MLM by neural networks explicitly is a challenging problem that has not been approached by far. In this article, we propose a novel autoencoder-based network for unsupervised unmixing based on MLM. Benefitting from an elaborate network design, the relationships among all the model parameters {\em i.e.}, endmembers, abundances, and transition probability parameters are explicitly modeled. There are two modes: MLM-1DAE considers only pixel-wise spectral information, and MLM-3DAE exploits the spectral-spatial correlations within input patches. Experiments on both the synthetic and real datasets demonstrate the effectiveness of the proposed method as it achieves competitive performance to the classic solutions of MLM.

Sangiorgi's normal form bisimilarity is call-by-name, identifies all the call-by-name meaningless terms, and rests on open terms in its definition. The literature contains a normal form bisimilarity for the call-by-value $λ$-calculus, Lassen's enf bisimilarity, which validates all of Moggi's monadic laws. The starting point of this work is the observation that enf bisimilarity is not the call-by-value equivalent of Sangiorgi's, because it does not identify the call-by-value meaningless terms. The issue has to do with open terms. We then develop a new call-by-value normal form bisimilarity, deemed net bisimilarity, by exploiting an existing formalism for dealing with open terms in call-by-value. It turns out that enf and net bisimilarities are incomparable, as net bisimilarity identifies meaningless terms but it does not validate Moggi's laws. Moreover, there is no easy way to merge them. To better understand the situation, we provide a detailed analysis of the rich range of possible call-by-value normal form bisimilarities, relating them to Ehrhard's call-by-value relational semantics.

Moiré engineering in atomically thin van der Waals heterostructures creates artificial quantum materials with designer properties. We solve the many-body problem of interacting electrons confined to a moiré superlattice potential minimum (the moiré atom) using a 2D fermionic neural network. We show that strong Coulomb interactions in combination with the anisotropic moiré potential lead to striking ``Wigner molecule" charge density distributions observable with scanning tunneling microscopy.

The determinant lower bound of Lovasz, Spencer, and Vesztergombi [European Journal of Combinatorics, 1986] is a powerful general way to prove lower bounds on the hereditary discrepancy of a set system. In their paper, Lovasz, Spencer, and Vesztergombi asked if hereditary discrepancy can also be bounded from above by a function of the hereditary discrepancy. This was answered in the negative by Hoffman, and the largest known multiplicative gap between the two quantities for a set system of $m$ substes of a universe of size $n$ is on the order of $\max\{\log n, \sqrt{\log m}\}$. On the other hand, building on work of Matoušek [Proceedings of the AMS, 2013], recently Jiang and Reis [SOSA, 2022] showed that this gap is always bounded up to constants by $\sqrt{\log(m)\log(n)}$. This is tight when $m$ is polynomial in $n$, but leaves open what happens for large $m$. We show that the bound of Jiang and Reis is tight for nearly the entire range of $m$. Our proof relies on a technique of amplifying discrepancy via taking Kronecker products, and on discrepancy lower bounds for a set system derived from the discrete Haar basis.

Neural-network quantum molecular dynamics (NNQMD) simulations based on machine learning are revolutionizing atomistic simulations of materials by providing quantum-mechanical accuracy but orders-of-magnitude faster, illustrated by ACM Gordon Bell prize (2020) and finalist (2021). State-of-the-art (SOTA) NNQMD model founded on group theory featuring rotational equivariance and local descriptors has provided much higher accuracy and speed than those models, thus named Allegro (meaning fast). On massively parallel supercomputers, however, it suffers a fidelity-scaling problem, where growing number of unphysical predictions of interatomic forces prohibits simulations involving larger numbers of atoms for longer times. Here, we solve this problem by combining the Allegro model with sharpness aware minimization (SAM) for enhancing the robustness of model through improved smoothness of the loss landscape. The resulting Allegro-Legato (meaning fast and "smooth") model was shown to elongate the time-to-failure $t_\textrm{failure}$, without sacrificing computational speed or accuracy. Specifically, Allegro-Legato exhibits much weaker dependence of timei-to-failure on the problem size, $t_{\textrm{failure}} \propto N^{-0.14}$ ($N$ is the number of atoms) compared to the SOTA Allegro model $\left(t_{\textrm{failure}} \propto N^{-0.29}\right)$, i.e., systematically delayed time-to-failure, thus allowing much larger and longer NNQMD simulations without failure. The model also exhibits excellent computational scalability and GPU acceleration on the Polaris supercomputer at Argonne Leadership Computing Facility. Such scalable, accurate, fast and robust NNQMD models will likely find broad applications in NNQMD simulations on emerging exaflop/s computers, with a specific example of accounting for nuclear quantum effects in the dynamics of ammonia.

In this paper, we address the discrete-time dynamic average consensus (DAC) of a multi-agent system in the presence of adversarial attacks. The adversarial attack is considered to be of Byzantine type, which compromises the computation capabilities of the agent and sends arbitrary false data to its neighbours. We assume a few of the agents cannot be compromised by adversaries, which we term trusted agents. We first formally define resilient DAC in the presence of Byzantine adversaries. Then we propose our novel Resilient Dynamic Average Consensus (ResDAC) algorithm that ensures the trusted and ordinary agents achieve resilient DAC in the presence of adversarial agents. The only requirements are that of the trusted agents forming a connected dominating set and the first-order differences of the reference signals being bounded. We do not impose any restriction on the tolerable number of adversarial agents that can be present in the network. We also do not restrict the reference signals to be bounded. Finally, we provide numerical simulations to illustrate the effectiveness of the proposed ResDAC algorithm.