1
|
Qin X, Hu J, Ma S, Wu M. Estimation of multiple networks with common structures in heterogeneous subgroups. J MULTIVARIATE ANAL 2024; 202:105298. [PMID: 38433779 PMCID: PMC10907012 DOI: 10.1016/j.jmva.2024.105298] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/05/2024]
Abstract
Network estimation has been a critical component of high-dimensional data analysis and can provide an understanding of the underlying complex dependence structures. Among the existing studies, Gaussian graphical models have been highly popular. However, they still have limitations due to the homogeneous distribution assumption and the fact that they are only applicable to small-scale data. For example, cancers have various levels of unknown heterogeneity, and biological networks, which include thousands of molecular components, often differ across subgroups while also sharing some commonalities. In this article, we propose a new joint estimation approach for multiple networks with unknown sample heterogeneity, by decomposing the Gaussian graphical model (GGM) into a collection of sparse regression problems. A reparameterization technique and a composite minimax concave penalty are introduced to effectively accommodate the specific and common information across the networks of multiple subgroups, making the proposed estimator significantly advancing from the existing heterogeneity network analysis based on the regularized likelihood of GGM directly and enjoying scale-invariant, tuning-insensitive, and optimization convexity properties. The proposed analysis can be effectively realized using parallel computing. The estimation and selection consistency properties are rigorously established. The proposed approach allows the theoretical studies to focus on independent network estimation only and has the significant advantage of being both theoretically and computationally applicable to large-scale data. Extensive numerical experiments with simulated data and the TCGA breast cancer data demonstrate the prominent performance of the proposed approach in both subgroup and network identifications.
Collapse
Affiliation(s)
- Xing Qin
- School of Statistics and Information, Shanghai University of International Business and Economics, Shanghai, China
| | - Jianhua Hu
- School of Statistics and Management, Shanghai University of Finance and Economics, Shanghai, China
| | - Shuangge Ma
- Department of Biostatistics, Yale School of Public Health, New Haven, USA
| | - Mengyun Wu
- School of Statistics and Management, Shanghai University of Finance and Economics, Shanghai, China
| |
Collapse
|
2
|
Boychev N, Lee S, Yeung V, Ross AE, Kuang L, Chen L, Dana R, Ciolino JB. Contact lenses as novel tear fluid sampling vehicles for total RNA isolation, precipitation, and amplification. Sci Rep 2024; 14:11727. [PMID: 38778161 PMCID: PMC11111455 DOI: 10.1038/s41598-024-62215-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/08/2024] [Accepted: 05/14/2024] [Indexed: 05/25/2024] Open
Abstract
The tear fluid is a readily accessible, potential source for biomarkers of disease and could be used to monitor the ocular response to contact lens (CL) wear or ophthalmic pathologies treated by therapeutic CLs. However, the tear fluid remains largely unexplored as a biomarker source for RNA-based molecular analyses. Using a rabbit model, this study sought to determine whether RNA could be collected from commercial CLs and whether the duration of CL wear would impact RNA recovery. The results were referenced to standardized strips of filtered paper (e.g., Shirmer Strips) placed in the inferior fornix. By performing total RNA isolation, precipitation, and amplification with commercial kits and RT-PCR methods, CLs were found to have no significant differences in RNA concentration and purity compared to Schirmer Strips. The study also identified genes that could be used to normalize RNA levels between tear samples. Of the potential control genes or housekeeping genes, GAPDH was the most stable. This study, which to our knowledge has never been done before, provides a methodology for the detection of RNA and gene expression changes from tear fluid that could be used to monitor or study eye diseases.
Collapse
Affiliation(s)
- Nikolay Boychev
- Department of Ophthalmology, Schepens Eye Research Institute, Massachusetts Eye and Ear, and Harvard Medical School, Boston, USA.
| | - Seokjoo Lee
- Department of Ophthalmology, Schepens Eye Research Institute, Massachusetts Eye and Ear, and Harvard Medical School, Boston, USA
| | - Vincent Yeung
- Department of Ophthalmology, Schepens Eye Research Institute, Massachusetts Eye and Ear, and Harvard Medical School, Boston, USA
| | - Amy E Ross
- Department of Ophthalmology, Schepens Eye Research Institute, Massachusetts Eye and Ear, and Harvard Medical School, Boston, USA
| | - Liangju Kuang
- Department of Ophthalmology, Schepens Eye Research Institute, Massachusetts Eye and Ear, and Harvard Medical School, Boston, USA
| | - Lin Chen
- Department of Optometry and Visual Science, West China Hospital, Sichuan University, Chengdu, Sichuan, China
- Department of Ophthalmology, Affiliated Hospital of Zunyi Medical University, Zunyi, Guizhou, China
| | - Reza Dana
- Department of Ophthalmology, Schepens Eye Research Institute, Massachusetts Eye and Ear, and Harvard Medical School, Boston, USA
| | - Joseph B Ciolino
- Department of Ophthalmology, Schepens Eye Research Institute, Massachusetts Eye and Ear, and Harvard Medical School, Boston, USA
| |
Collapse
|
3
|
Manzanera Esteve IV, Wang F, Reed JL, Qi HX, Thayer W, Gore JC, Chen LM. Model-based parcellation of diffusion MRI of injured spinal cord predicts hand use impairment and recovery in squirrel monkeys. Behav Brain Res 2024; 459:114808. [PMID: 38081518 PMCID: PMC10865381 DOI: 10.1016/j.bbr.2023.114808] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/26/2023] [Revised: 11/30/2023] [Accepted: 12/07/2023] [Indexed: 12/17/2023]
Abstract
A mathematical model-based parcellation of magnetic resonance diffusion tensor images (DTI) has been developed to quantify progressive changes in three types of tissues - grey (GM), white matter (WM), and damaged spinal cord tissue, along with behavioral assessments over a 6 month period following targeted spinal cord injuries (SCI) in monkeys. Sigmoid Gompertz function based fittings of DTI metrics provide early indicators that correlate with, and predict, recovery of hand grasping behavior. Our three tissue pool model provided unbiased, data-driven segmentation of spinal cord images and identified DTI metrics that can serve as reliable biomarkers of severity of spinal cord injuries and predictors of behavioral outcomes.
Collapse
Affiliation(s)
- Isaac V Manzanera Esteve
- Department of Plastic Surgery, Vanderbilt University Medical Center, Nashville, TN, USA; Vanderbilt University Institute of Imaging Science, Vanderbilt University Medical Center, Nashville, TN, USA.
| | - Feng Wang
- Vanderbilt University Institute of Imaging Science, Vanderbilt University Medical Center, Nashville, TN, USA; Department of Radiology and Radiological Sciences, Vanderbilt University Medical Center, Nashville, TN, USA
| | - Jamie L Reed
- Vanderbilt University Institute of Imaging Science, Vanderbilt University Medical Center, Nashville, TN, USA; Department of Radiology and Radiological Sciences, Vanderbilt University Medical Center, Nashville, TN, USA
| | - Hui Xin Qi
- Department of Psychology, Vanderbilt University, Nashville, TN, USA
| | - Wesley Thayer
- Department of Plastic Surgery, Vanderbilt University Medical Center, Nashville, TN, USA
| | - John C Gore
- Vanderbilt University Institute of Imaging Science, Vanderbilt University Medical Center, Nashville, TN, USA; Department of Radiology and Radiological Sciences, Vanderbilt University Medical Center, Nashville, TN, USA; Department of Biomedical Engineering, Vanderbilt University, Nashville, TN, USA
| | - Li Min Chen
- Vanderbilt University Institute of Imaging Science, Vanderbilt University Medical Center, Nashville, TN, USA; Department of Radiology and Radiological Sciences, Vanderbilt University Medical Center, Nashville, TN, USA
| |
Collapse
|
4
|
Merzbacher C, Oyarzún DA. Applications of artificial intelligence and machine learning in dynamic pathway engineering. Biochem Soc Trans 2023; 51:1871-1879. [PMID: 37656433 PMCID: PMC10657174 DOI: 10.1042/bst20221542] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/24/2023] [Revised: 08/07/2023] [Accepted: 08/21/2023] [Indexed: 09/02/2023]
Abstract
Dynamic pathway engineering aims to build metabolic production systems embedded with intracellular control mechanisms for improved performance. These control systems enable host cells to self-regulate the temporal activity of a production pathway in response to perturbations, using a combination of biosensors and feedback circuits for controlling expression of heterologous enzymes. Pathway design, however, requires assembling together multiple biological parts into suitable circuit architectures, as well as careful calibration of the function of each component. This results in a large design space that is costly to navigate through experimentation alone. Methods from artificial intelligence (AI) and machine learning are gaining increasing attention as tools to accelerate the design cycle, owing to their ability to identify hidden patterns in data and rapidly screen through large collections of designs. In this review, we discuss recent developments in the application of machine learning methods to the design of dynamic pathways and their components. We cover recent successes and offer perspectives for future developments in the field. The integration of AI into metabolic engineering pipelines offers great opportunities to streamline design and discover control systems for improved production of high-value chemicals.
Collapse
Affiliation(s)
| | - Diego A. Oyarzún
- School of Informatics, University of Edinburgh, Edinburgh, U.K
- The Alan Turing Institute, London, U.K
- School of Biological Sciences, University of Edinburgh, Edinburgh, U.K
| |
Collapse
|
5
|
Xia W, Zou J, Qiu X, Chen F, Zhu B, Li C, Deng DL, Li X. Configured quantum reservoir computing for multi-task machine learning. Sci Bull (Beijing) 2023; 68:2321-2329. [PMID: 37679257 DOI: 10.1016/j.scib.2023.08.040] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/07/2023] [Revised: 07/22/2023] [Accepted: 08/16/2023] [Indexed: 09/09/2023]
Abstract
Amidst the rapid advancements in experimental technology, noise-intermediate-scale quantum (NISQ) devices have become increasingly programmable, offering versatile opportunities to leverage quantum computational advantage. Here we explore the intricate dynamics of programmable NISQ devices for quantum reservoir computing. Using a genetic algorithm to configure the quantum reservoir dynamics, we systematically enhance the learning performance. Remarkably, a single configured quantum reservoir can simultaneously learn multiple tasks, including a synthetic oscillatory network of transcriptional regulators, chaotic motifs in gene regulatory networks, and the fractional-order Chua's circuit. Our configured quantum reservoir computing yields highly precise predictions for these learning tasks, outperforming classical reservoir computing. We also test the configured quantum reservoir computing in foreign exchange (FX) market applications and demonstrate its capability to capture the stochastic evolution of the exchange rates with significantly greater accuracy than classical reservoir computing approaches. Through comparison with classical reservoir computing, we highlight the unique role of quantum coherence in the quantum reservoir, which underpins its exceptional learning performance. Our findings suggest the exciting potential of configured quantum reservoir computing for exploiting the quantum computation power of NISQ devices in developing artificial general intelligence.
Collapse
Affiliation(s)
- Wei Xia
- State Key Laboratory of Surface Physics, Key Laboratory of Micro and Nano Photonic Structures (MOE), and Department of Physics, Fudan University, Shanghai 200433, China
| | - Jie Zou
- State Key Laboratory of Surface Physics, Key Laboratory of Micro and Nano Photonic Structures (MOE), and Department of Physics, Fudan University, Shanghai 200433, China
| | - Xingze Qiu
- State Key Laboratory of Surface Physics, Key Laboratory of Micro and Nano Photonic Structures (MOE), and Department of Physics, Fudan University, Shanghai 200433, China; School of Physics Science and Engineering, Tongji University, Shanghai 200092, China
| | - Feng Chen
- Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, Shanghai 200433, China
| | - Bing Zhu
- Hong Kong and Shang Hai Banking Corporation Laboratory, Hong Kong and Shang Hai Banking Corporation Holdings PLC, Guangzhou 511458, China
| | - Chunhe Li
- Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, Shanghai 200433, China; Shanghai Center for Mathematical Sciences and School of Mathematical Sciences, Fudan University, Shanghai 200433, China
| | - Dong-Ling Deng
- Center for Quantum Information, IIIS, Tsinghua University, Beijing 100084, China; Shanghai Qi Zhi Institute, AI Tower, Shanghai 200232, China
| | - Xiaopeng Li
- State Key Laboratory of Surface Physics, Key Laboratory of Micro and Nano Photonic Structures (MOE), and Department of Physics, Fudan University, Shanghai 200433, China; Shanghai Qi Zhi Institute, AI Tower, Shanghai 200232, China; Shanghai Research Center for Quantum Sciences, Shanghai 201315, China.
| |
Collapse
|
6
|
Merzbacher C, Mac Aodha O, Oyarzún DA. Bayesian Optimization for Design of Multiscale Biological Circuits. ACS Synth Biol 2023. [PMID: 37339382 PMCID: PMC10367132 DOI: 10.1021/acssynbio.3c00120] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 06/22/2023]
Abstract
Recent advances in synthetic biology have enabled the construction of molecular circuits that operate across multiple scales of cellular organization, such as gene regulation, signaling pathways, and cellular metabolism. Computational optimization can effectively aid the design process, but current methods are generally unsuited for systems with multiple temporal or concentration scales, as these are slow to simulate due to their numerical stiffness. Here, we present a machine learning method for the efficient optimization of biological circuits across scales. The method relies on Bayesian optimization, a technique commonly used to fine-tune deep neural networks, to learn the shape of a performance landscape and iteratively navigate the design space toward an optimal circuit. This strategy allows the joint optimization of both circuit architecture and parameters, and provides a feasible approach to solve a highly nonconvex optimization problem in a mixed-integer input space. We illustrate the applicability of the method on several gene circuits for controlling biosynthetic pathways with strong nonlinearities, multiple interacting scales, and using various performance objectives. The method efficiently handles large multiscale problems and enables parametric sweeps to assess circuit robustness to perturbations, serving as an efficient in silico screening method prior to experimental implementation.
Collapse
Affiliation(s)
| | - Oisin Mac Aodha
- School of Informatics, University of Edinburgh, Edinburgh EH8 9AB, U.K
- The Alan Turing Institute, London NW1 2DB, U.K
| | - Diego A Oyarzún
- School of Informatics, University of Edinburgh, Edinburgh EH8 9AB, U.K
- The Alan Turing Institute, London NW1 2DB, U.K
- School of Biological Sciences, University of Edinburgh, Edinburgh EH9 3JH, U.K
| |
Collapse
|
7
|
Zhang Y, Yu L, Jing R, Han B, Luo J. Fast and Efficient Design of Deep Neural Networks for Predicting N 7-Methylguanosine Sites Using autoBioSeqpy. ACS OMEGA 2023; 8:19728-19740. [PMID: 37305295 PMCID: PMC10249100 DOI: 10.1021/acsomega.3c01371] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 02/28/2023] [Accepted: 05/10/2023] [Indexed: 06/13/2023]
Abstract
N7-Methylguanosine (m7G) is a crucial post-transcriptional RNA modification that plays a pivotal role in regulating gene expression. Accurately identifying m7G sites is a fundamental step in understanding the biological functions and regulatory mechanisms associated with this modification. While whole-genome sequencing is the gold standard for RNA modification site detection, it is a time-consuming, expensive, and intricate process. Recently, computational approaches, especially deep learning (DL) techniques, have gained popularity in achieving this objective. Convolutional neural networks and recurrent neural networks are examples of DL algorithms that have emerged as versatile tools for modeling biological sequence data. However, developing an efficient network architecture with superior performance remains a challenging task, requiring significant expertise, time, and effort. To address this, we previously introduced a tool called autoBioSeqpy, which streamlines the design and implementation of DL networks for biological sequence classification. In this study, we utilized autoBioSeqpy to develop, train, evaluate, and fine-tune sequence-level DL models for predicting m7G sites. We provided detailed descriptions of these models, along with a step-by-step guide on their execution. The same methodology can be applied to other systems dealing with similar biological questions. The benchmark data and code utilized in this study can be accessed for free at http://github.com/jingry/autoBioSeeqpy/tree/2.0/examples/m7G.
Collapse
Affiliation(s)
- Yonglin Zhang
- Department
of Pharmacy, Affiliated Hospital of North
Sichuan Medical College, Nanchong 637000, China
| | - Lezheng Yu
- School
of Chemistry and Materials Science, Guizhou
Education University, Guiyang 550024, China
| | - Runyu Jing
- School
of Cyber Science and Engineering, Sichuan
University, Chengdu 610017, China
| | - Bin Han
- GCP
Center/Institute of Drug Clinical Trials, Affiliated Hospital of North Sichuan Medical College, Nanchong 637503, China
| | - Jiesi Luo
- Basic
Medical College, Southwest Medical University, Luzhou 646099, Sichuan, China
- Key
Medical
Laboratory of New Drug Discovery and Druggability Evaluation, Luzhou
Key Laboratory of Activity Screening and Druggability Evaluation for
Chinese Materia Medica, Southwest Medical
University, Luzhou 646099, China
| |
Collapse
|
8
|
Teichner R, Shomar A, Barak O, Brenner N, Marom S, Meir R, Eytan D. Identifying regulation with adversarial surrogates. Proc Natl Acad Sci U S A 2023; 120:e2216805120. [PMID: 36920920 PMCID: PMC10041131 DOI: 10.1073/pnas.2216805120] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/10/2022] [Accepted: 02/15/2023] [Indexed: 03/16/2023] Open
Abstract
Homeostasis, the ability to maintain a relatively constant internal environment in the face of perturbations, is a hallmark of biological systems. It is believed that this constancy is achieved through multiple internal regulation and control processes. Given observations of a system, or even a detailed model of one, it is both valuable and extremely challenging to extract the control objectives of the homeostatic mechanisms. In this work, we develop a robust data-driven method to identify these objectives, namely to understand: "what does the system care about?". We propose an algorithm, Identifying Regulation with Adversarial Surrogates (IRAS), that receives an array of temporal measurements of the system and outputs a candidate for the control objective, expressed as a combination of observed variables. IRAS is an iterative algorithm consisting of two competing players. The first player, realized by an artificial deep neural network, aims to minimize a measure of invariance we refer to as the coefficient of regulation. The second player aims to render the task of the first player more difficult by forcing it to extract information about the temporal structure of the data, which is absent from similar "surrogate" data. We test the algorithm on four synthetic and one natural data set, demonstrating excellent empirical results. Interestingly, our approach can also be used to extract conserved quantities, e.g., energy and momentum, in purely physical systems, as we demonstrate empirically.
Collapse
Affiliation(s)
- Ron Teichner
- Viterbi Department of Electrical & Computer Engineering, Technion, Israel Institute of Technology, 32000 Haifa, Israel
- Network Biology Research Lab, Technion, Israel Institute of Technology, 32000 Haifa, Israel
| | - Aseel Shomar
- Network Biology Research Lab, Technion, Israel Institute of Technology, 32000 Haifa, Israel
- Department of Chemical Engineering, Technion, Israel Institute of Technology, 32000 Haifa, Israel
| | - Omri Barak
- Network Biology Research Lab, Technion, Israel Institute of Technology, 32000 Haifa, Israel
- Rappaport Faculty of Medicine, Technion, Israel Institute of Technology, 32000 Haifa, Israel
| | - Naama Brenner
- Network Biology Research Lab, Technion, Israel Institute of Technology, 32000 Haifa, Israel
- Department of Chemical Engineering, Technion, Israel Institute of Technology, 32000 Haifa, Israel
| | - Shimon Marom
- Network Biology Research Lab, Technion, Israel Institute of Technology, 32000 Haifa, Israel
- Rappaport Faculty of Medicine, Technion, Israel Institute of Technology, 32000 Haifa, Israel
| | - Ron Meir
- Viterbi Department of Electrical & Computer Engineering, Technion, Israel Institute of Technology, 32000 Haifa, Israel
- Network Biology Research Lab, Technion, Israel Institute of Technology, 32000 Haifa, Israel
| | - Danny Eytan
- Network Biology Research Lab, Technion, Israel Institute of Technology, 32000 Haifa, Israel
- Rappaport Faculty of Medicine, Technion, Israel Institute of Technology, 32000 Haifa, Israel
| |
Collapse
|
9
|
Xu R, Dai F, Wu H, Jiao R, He F, Ma J. Shaping the scaling characteristics of gap gene expression patterns in Drosophila. Heliyon 2023; 9:e13623. [PMID: 36879745 PMCID: PMC9984453 DOI: 10.1016/j.heliyon.2023.e13623] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/23/2022] [Revised: 01/25/2023] [Accepted: 02/06/2023] [Indexed: 02/11/2023] Open
Abstract
How patterns are formed to scale with tissue size remains an unresolved problem. Here we investigate embryonic patterns of gap gene expression along the anterior-posterior (AP) axis in Drosophila. We use embryos that greatly differ in length and, importantly, possess distinct length-scaling characteristics of the Bicoid (Bcd) gradient. We systematically analyze the dynamic movements of gap gene expression boundaries in relation to both embryo length and Bcd input as a function of time. We document the process through which such dynamic movements drive both an emergence of a global scaling landscape and evolution of boundary-specific scaling characteristics. We show that, despite initial differences in pattern scaling characteristics that mimic those of Bcd in the anterior, such characteristics of final patterns converge. Our study thus partitions the contributions of Bcd input and regulatory dynamics inherent to the AP patterning network in shaping embryonic pattern's scaling characteristics.
Collapse
Affiliation(s)
- Ruoqing Xu
- Women's Hospital, Zhejiang University School of Medicine, Hangzhou, Zhejiang 310058, China
- Institute of Genetics, Zhejiang University School of Medicine, Hangzhou, Zhejiang 310058, China
| | - Fei Dai
- Institute of Biophysics, Chinese Academy of Sciences, Beijing 100101, China
| | - Honggang Wu
- Sino-French Hoffmann Institute, School of Basic Medical Science, Guangzhou Medical University, Guangzhou 510182, China
- Key Laboratory of Interdisciplinary Research, Chinese Academy of Sciences, Beijing 100101, China
| | - Renjie Jiao
- Sino-French Hoffmann Institute, School of Basic Medical Science, Guangzhou Medical University, Guangzhou 510182, China
- Key Laboratory of Interdisciplinary Research, Chinese Academy of Sciences, Beijing 100101, China
| | - Feng He
- Women's Hospital, Zhejiang University School of Medicine, Hangzhou, Zhejiang 310058, China
- Institute of Genetics, Zhejiang University School of Medicine, Hangzhou, Zhejiang 310058, China
- Corresponding author. Women's Hospital, Zhejiang University School of Medicine, Hangzhou, Zhejiang 310058, China.
| | - Jun Ma
- Women's Hospital, Zhejiang University School of Medicine, Hangzhou, Zhejiang 310058, China
- Institute of Genetics, Zhejiang University School of Medicine, Hangzhou, Zhejiang 310058, China
- Joint Institute of Genetics and Genome Medicine between Zhejiang University and University of Toronto, Hangzhou, Zhejiang, China
- Corresponding author. Women's Hospital, Zhejiang University School of Medicine, Hangzhou, Zhejiang 310058, China.
| |
Collapse
|
10
|
Mao G, Zeng R, Peng J, Zuo K, Pang Z, Liu J. Reconstructing gene regulatory networks of biological function using differential equations of multilayer perceptrons. BMC Bioinformatics 2022; 23:503. [PMID: 36434499 PMCID: PMC9700916 DOI: 10.1186/s12859-022-05055-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/16/2022] [Accepted: 11/14/2022] [Indexed: 11/26/2022] Open
Abstract
BACKGROUND Building biological networks with a certain function is a challenge in systems biology. For the functionality of small (less than ten nodes) biological networks, most methods are implemented by exhausting all possible network topological spaces. This exhaustive approach is difficult to scale to large-scale biological networks. And regulatory relationships are complex and often nonlinear or non-monotonic, which makes inference using linear models challenging. RESULTS In this paper, we propose a multi-layer perceptron-based differential equation method, which operates by training a fully connected neural network (NN) to simulate the transcription rate of genes in traditional differential equations. We verify whether the regulatory network constructed by the NN method can continue to achieve the expected biological function by verifying the degree of overlap between the regulatory network discovered by NN and the regulatory network constructed by the Hill function. And we validate our approach by adapting to noise signals, regulator knockout, and constructing large-scale gene regulatory networks using link-knockout techniques. We apply a real dataset (the mesoderm inducer Xenopus Brachyury expression) to construct the core topology of the gene regulatory network and find that Xbra is only strongly expressed at moderate levels of activin signaling. CONCLUSION We have demonstrated from the results that this method has the ability to identify the underlying network topology and functional mechanisms, and can also be applied to larger and more complex gene network topologies.
Collapse
Affiliation(s)
- Guo Mao
- grid.412110.70000 0000 9548 2110Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology, Deya Road, Changsha, 410073 China
| | - Ruigeng Zeng
- grid.412110.70000 0000 9548 2110Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology, Deya Road, Changsha, 410073 China
| | - Jintao Peng
- grid.412110.70000 0000 9548 2110Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology, Deya Road, Changsha, 410073 China
| | - Ke Zuo
- grid.412110.70000 0000 9548 2110Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology, Deya Road, Changsha, 410073 China
| | - Zhengbin Pang
- grid.412110.70000 0000 9548 2110Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology, Deya Road, Changsha, 410073 China
| | - Jie Liu
- grid.412110.70000 0000 9548 2110Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology, Deya Road, Changsha, 410073 China ,grid.412110.70000 0000 9548 2110Laboratory of Software Engineering for Complex System, National University of Defense Technology, Deya Road, Changsha, 410073 China
| |
Collapse
|
11
|
Chen F, Li C. Inferring structural and dynamical properties of gene networks from data with deep learning. NAR Genom Bioinform 2022; 4:lqac068. [PMID: 36110897 PMCID: PMC9469930 DOI: 10.1093/nargab/lqac068] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/18/2022] [Revised: 07/22/2022] [Accepted: 08/24/2022] [Indexed: 11/29/2022] Open
Abstract
The reconstruction of gene regulatory networks (GRNs) from data is vital in systems biology. Although different approaches have been proposed to infer causality from data, some challenges remain, such as how to accurately infer the direction and type of interactions, how to deal with complex network involving multiple feedbacks, as well as how to infer causality between variables from real-world data, especially single cell data. Here, we tackle these problems by deep neural networks (DNNs). The underlying regulatory network for different systems (gene regulations, ecology, diseases, development) can be successfully reconstructed from trained DNN models. We show that DNN is superior to existing approaches including Boolean network, Random Forest and partial cross mapping for network inference. Further, by interrogating the ensemble DNN model trained from single cell data from dynamical system perspective, we are able to unravel complex cell fate dynamics during preimplantation development. We also propose a data-driven approach to quantify the energy landscape for gene regulatory systems, by combining DNN with the partial self-consistent mean field approximation (PSCA) approach. We anticipate the proposed method can be applied to other fields to decipher the underlying dynamical mechanisms of systems from data.
Collapse
Affiliation(s)
- Feng Chen
- Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University , Shanghai 200433, China
- Shanghai Center for Mathematical Sciences, Fudan University , Shanghai 200433, China
| | - Chunhe Li
- Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University , Shanghai 200433, China
- Shanghai Center for Mathematical Sciences, Fudan University , Shanghai 200433, China
- School of Mathematical Sciences, Fudan University , Shanghai 200433, China
| |
Collapse
|
12
|
Moškon M, Mraz M. Programmable evolution of computing circuits in cellular populations. Neural Comput Appl 2022. [DOI: 10.1007/s00521-022-07532-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/17/2022]
|
13
|
Barbier I, Kusumawardhani H, Schaerli Y. Engineering synthetic spatial patterns in microbial populations and communities. Curr Opin Microbiol 2022; 67:102149. [DOI: 10.1016/j.mib.2022.102149] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/28/2022] [Revised: 03/08/2022] [Accepted: 03/16/2022] [Indexed: 02/03/2023]
|