Struct2Graph: a graph attention network for structure based predictions of protein-protein interactions.

BACKGROUND: Development of new methods for analysis of protein-protein interactions (PPIs) at molecular and nanometer scales gives insights into intracellular signaling pathways and will improve understanding of protein functions, as well as other nanoscale structures of biological and abiological origins. Recent advances in computational tools, particularly the ones involving modern deep learning algorithms, have been shown to complement experimental approaches for describing and rationalizing PPIs. However, most of the existing works on PPI predictions use protein-sequence information, and thus have difficulties in accounting for the three-dimensional organization of the protein chains. RESULTS: In this study, we address this problem and describe a PPI analysis based on a graph attention network, named Struct2Graph, for identifying PPIs directly from the structural data of folded protein globules. Our method is capable of predicting the PPI with an accuracy of 98.89% on the balanced set consisting of an equal number of positive and negative pairs. On the unbalanced set with the ratio of 1:10 between positive and negative pairs, Struct2Graph achieves a fivefold cross validation average accuracy of 99.42%. Moreover, Struct2Graph can potentially identify residues that likely contribute to the formation of the protein-protein complex. The identification of important residues is tested for two different interaction types: (a) Proteins with multiple ligands competing for the same binding area, (b) Dynamic protein-protein adhesion interaction. Struct2Graph identifies interacting residues with 30% sensitivity, 89% specificity, and 87% accuracy. CONCLUSIONS: In this manuscript, we address the problem of prediction of PPIs using a first of its kind, 3D-structure-based graph attention network (code available at https://github.com/baranwa2/Struct2Graph ). Furthermore, the novel mutual attention mechanism provides insights into likely interaction sites through its unsupervised knowledge selection process. This study demonstrates that a relatively low-dimensional feature embedding learned from graph structures of individual proteins outperforms other modern machine learning classifiers based on global protein features. In addition, through the analysis of single amino acid variations, the attention mechanism shows preference for disease-causing residue variations over benign polymorphisms, demonstrating that it is not limited to interface residues.

Recurrent neural networks enable design of multifunctional synthetic human gut microbiome dynamics.

Predicting the dynamics and functions of microbiomes constructed from the bottom-up is a key challenge in exploiting them to our benefit. Current models based on ecological theory fail to capture complex community behaviors due to higher order interactions, do not scale well with increasing complexity and in considering multiple functions. We develop and apply a long short-term memory (LSTM) framework to advance our understanding of community assembly and health-relevant metabolite production using a synthetic human gut community. A mainstay of recurrent neural networks, the LSTM learns a high dimensional data-driven non-linear dynamical system model. We show that the LSTM model can outperform the widely used generalized Lotka-Volterra model based on ecological theory. We build methods to decipher microbe-microbe and microbe-metabolite interactions from an otherwise black-box model. These methods highlight that Actinobacteria, Firmicutes and Proteobacteria are significant drivers of metabolite production whereas Bacteroides shape community dynamics. We use the LSTM model to navigate a large multidimensional functional landscape to design communities with unique health-relevant metabolite profiles and temporal behaviors. In sum, the accuracy of the LSTM model can be exploited for experimental planning and to guide the design of synthetic microbiomes with target dynamic functions.

CGAT: Cell Graph ATtention Network for Grading of Pancreatic Disease Histology Images.

Early detection of Pancreatic Ductal Adenocarcinoma (PDAC), one of the most aggressive malignancies of the pancreas, is crucial to avoid metastatic spread to other body regions. Detection of pancreatic cancer is typically carried out by assessing the distribution and arrangement of tumor and immune cells in histology images. This is further complicated due to morphological similarities with chronic pancreatitis (CP), and the co-occurrence of precursor lesions in the same tissue. Most of the current automated methods for grading pancreatic cancers rely on extensive feature engineering involving accurate identification of cell features or utilising single number spatially informed indices for grading purposes. Moreover, sophisticated methods involving black-box approaches, such as neural networks, do not offer insights into the model's ability to accurately identify the correct disease grade. In this paper, we develop a novel cell-graph based Cell-Graph Attention (CGAT) network for the precise classification of pancreatic cancer and its precursors from multiplexed immunofluorescence histology images into the six different types of pancreatic diseases. The issue of class imbalance is addressed through bootstrapping multiple CGAT-nets, while the self-attention mechanism facilitates visualization of cell-cell features that are likely responsible for the predictive capabilities of the model. It is also shown that the model significantly outperforms the decision tree classifiers built using spatially informed metric, such as the Morisita-Horn (MH) indices.

A deep learning architecture for metabolic pathway prediction.

MOTIVATION: Understanding the mechanisms and structural mappings between molecules and pathway classes are critical for design of reaction predictors for synthesizing new molecules. This article studies the problem of prediction of classes of metabolic pathways (series of chemical reactions occurring within a cell) in which a given biochemical compound participates. We apply a hybrid machine learning approach consisting of graph convolutional networks used to extract molecular shape features as input to a random forest classifier. In contrast to previously applied machine learning methods for this problem, our framework automatically extracts relevant shape features directly from input SMILES representations, which are atom-bond specifications of chemical structures composing the molecules. RESULTS: Our method is capable of correctly predicting the respective metabolic pathway class of 95.16% of tested compounds, whereas competing methods only achieve an accuracy of 84.92% or less. Furthermore, our framework extends to the task of classification of compounds having mixed membership in multiple pathway classes. Our prediction accuracy for this multi-label task is 97.61%. We analyze the relative importance of various global physicochemical features to the pathway class prediction problem and show that simple linear/logistic regression models can predict the values of these global features from the shape features extracted using our framework. AVAILABILITY AND IMPLEMENTATION: https://github.com/baranwa2/MetabolicPathwayPrediction. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Robust atomic force microscopy using multiple sensors.

Atomic force microscopy typically relies on high-resolution high-bandwidth cantilever deflection measurements based control for imaging and estimating sample topography and properties. More precisely, in amplitude-modulation atomic force microscopy (AM-AFM), the control effort that regulates deflection amplitude is used as an estimate of sample topography; similarly, contact-mode AFM uses regulation of deflection signal to generate sample topography. In this article, a control design scheme based on an additional feedback mechanism that uses vertical z-piezo motion sensor, which augments the deflection based control scheme, is proposed and evaluated. The proposed scheme exploits the fact that the piezo motion sensor, though inferior to the cantilever deflection signal in terms of resolution and bandwidth, provides information on piezo actuator dynamics that is not easily retrievable from the deflection signal. The augmented design results in significant improvements in imaging bandwidth and robustness, especially in AM-AFM, where the complicated underlying nonlinear dynamics inhibits estimating piezo motions from deflection signals. In AM-AFM experiments, the two-sensor based design demonstrates a substantial improvement in robustness to modeling uncertainties by practically eliminating the peak in the sensitivity plot without affecting the closed-loop bandwidth when compared to a design that does not use the piezo-position sensor based feedback. The contact-mode imaging results, which use proportional-integral controllers for cantilever-deflection regulation, demonstrate improvements in bandwidth and robustness to modeling uncertainties, respectively, by over 30% and 20%. The piezo-sensor based feedback is developed using H∞ control framework.

Fast and robust control of nanopositioning systems: Performance limits enabled by field programmable analog arrays.

This paper aims at control design and its implementation for robust high-bandwidth precision (nanoscale) positioning systems. Even though modern model-based control theoretic designs for robust broadband high-resolution positioning have enabled orders of magnitude improvement in performance over existing model independent designs, their scope is severely limited by the inefficacies of digital implementation of the control designs. High-order control laws that result from model-based designs typically have to be approximated with reduced-order systems to facilitate digital implementation. Digital systems, even those that have very high sampling frequencies, provide low effective control bandwidth when implementing high-order systems. In this context, field programmable analog arrays (FPAAs) provide a good alternative to the use of digital-logic based processors since they enable very high implementation speeds, moreover with cheaper resources. The superior flexibility of digital systems in terms of the implementable mathematical and logical functions does not give significant edge over FPAAs when implementing linear dynamic control laws. In this paper, we pose the control design objectives for positioning systems in different configurations as optimal control problems and demonstrate significant improvements in performance when the resulting control laws are applied using FPAAs as opposed to their digital counterparts. An improvement of over 200% in positioning bandwidth is achieved over an earlier digital signal processor (DSP) based implementation for the same system and same control design, even when for the DSP-based system, the sampling frequency is about 100 times the desired positioning bandwidth.