Autoencoder Model for Translating Omics Signatures

The development of effective therapeutics and vaccines for human diseases requires a systematic understanding of human biology. While animal and in vitro culture models have successfully elucidated the molecular mechanisms of diseases in many studies, they yet fail to adequately recapitulate human biology as evidenced by the predominant likelihood of failure in clinical trials. To address this broadly important problem, we developed AutoTransOP, a neural network autoencoder framework to map omics profiles from designated species or cellular contexts into a global latent space, from which germane information can be mapped between different contexts. This approach performs as well or better than extant machine learning methods and can identify animal/culture-specific molecular features predictive of other contexts, without requiring homology matching. For an especially challenging test case, we successfully apply our framework to a set of inter-species vaccine serology studies, where no 1-1 mapping between human and non-human primate features exists.

[1]  P. Ellinor,et al.  Transfer learning enables predictions in network biology , 2023, Nature.

[2]  Fabian J Theis,et al.  Predicting cellular responses to complex perturbations in high‐throughput screens , 2023, Molecular systems biology.

[3]  S. Hediyeh-zadeh,et al.  Biologically informed deep learning to query gene programs in single-cell atlases , 2023, Nature Cell Biology.

[4]  M. Wysocka,et al.  A systematic review of biologically-informed deep learning models for cancer: fundamental trends for encoding and interpreting oncology data , 2022, BMC Bioinformatics.

[5]  G. Alevizos,et al.  DeepSNEM: Deep Signaling Network Embeddings for compound mechanism of action identification , 2022, bioRxiv.

[6]  Anand V. Sastry,et al.  Optimal dimensionality selection for independent component analysis of transcriptomic data , 2021, BMC Bioinformatics.

[7]  D. Lauffenburger,et al.  Computational Interspecies Translation Between Alzheimer’s Disease Mouse Models and Human Subjects Identifies Innate Immune Complement, TYROBP, and TAM Receptor Agonist Signatures, Distinct From Influences of Aging , 2021, Frontiers in Neuroscience.

[8]  Anand V. Sastry,et al.  Mining all publicly available expression data to compute dynamic microbial transcriptional regulatory networks , 2021, bioRxiv.

[9]  Shijie C. Zheng,et al.  recount3: summaries and queries for large-scale RNA-seq expression and splicing , 2021, Genome Biology.

[10]  Ramzan Umarov,et al.  DeepCellState: An autoencoder-based framework for predicting cell type specific transcriptional states induced by drug treatment , 2020, bioRxiv.

[11]  Marco Piñón,et al.  I Overview , 2020, The Diaries and Letters of Lord Woolton 1940-1945.

[12]  Bilal Alsallakh,et al.  Captum: A unified and generic model interpretability library for PyTorch , 2020, ArXiv.

[13]  Paige N. Vega,et al.  An interspecies translation model implicates integrin signaling in infliximab-resistant inflammatory bowel disease , 2020, Science Signaling.

[14]  Fabian J. Theis,et al.  Alveolar regeneration through a Krt8+ transitional stem cell state that persists in human lung fibrosis , 2020, Nature Communications.

[15]  Shafiq R. Joty,et al.  Unsupervised Word Translation with Adversarial Autoencoder , 2020, CL.

[16]  Ron Edgar,et al.  NCBI gene expression and hybridization array data repository , 2020 .

[17]  D. Lauffenburger,et al.  Translating preclinical models to humans , 2020, Science.

[18]  Peter Sinčák,et al.  A Review of Activation Function for Artificial Neural Network , 2020, 2020 IEEE 18th World Symposium on Applied Machine Intelligence and Informatics (SAMI).

[19]  Natalia Gimelshein,et al.  PyTorch: An Imperative Style, High-Performance Deep Learning Library , 2019, NeurIPS.

[20]  Saeid Nahavandi,et al.  Deep learning for deepfakes creation and detection: A survey , 2019, Comput. Vis. Image Underst..

[21]  Jonathan A. Kropski,et al.  Single-cell RNA-sequencing reveals profibrotic roles of distinct epithelial and mesenchymal lineages in pulmonary fibrosis , 2019, bioRxiv.

[22]  C. Ponting,et al.  Resolving the fibrotic niche of human liver cirrhosis at single cell level , 2019, Nature.

[23]  Samantha Dale Strasser,et al.  Proteogenomic Network Analysis of Context-Specific KRAS Signaling in Mouse-to-Human Cross-Species Translation. , 2019, Cell systems.

[24]  Mohammad Lotfollahi,et al.  scGen predicts single-cell perturbation responses , 2019, Nature Methods.

[25]  Fabian J Theis,et al.  Single-cell RNA-seq denoising using a deep count autoencoder , 2019, Nature Communications.

[26]  Douglas A Lauffenburger,et al.  Computational translation of genomic responses from experimental model systems to humans , 2019, PLoS Comput. Biol..

[27]  Bernhard Schölkopf,et al.  Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations , 2018, ICML.

[28]  A. Butte,et al.  Reference-based analysis of lung single-cell sequencing reveals a transitional profibrotic macrophage , 2018, Nature Immunology.

[29]  Michael I. Jordan,et al.  Deep Generative Modeling for Single-cell Transcriptomics , 2018, Nature Methods.

[30]  R. Tibshirani,et al.  Found In Translation: a machine learning model for mouse-to-human inference , 2018, Nature Methods.

[31]  Marta R. Costa-jussà,et al.  (Self-Attentive) Autoencoder-based Universal Language Representation for Machine Translation , 2018, ArXiv.

[32]  Jin Gu,et al.  VASC: Dimension Reduction and Visualization of Single-cell RNA-seq Data by Deep Variational Autoencoder , 2018, Genom. Proteom. Bioinform..

[33]  R. Devon Hjelm,et al.  Learning deep representations by mutual information estimation and maximization , 2018, ICLR.

[34]  Galit Alter,et al.  Evaluation of a mosaic HIV-1 vaccine in a multicentre, randomised, double-blind, placebo-controlled, phase 1/2a clinical trial (APPROACH) and in rhesus monkeys (NHP 13-19) , 2018, The Lancet.

[35]  J. Sáez-Rodríguez,et al.  Benchmark and integration of resources for the estimation of human transcription factor activities , 2018, bioRxiv.

[36]  Aaron C. Courville,et al.  MINE: Mutual Information Neural Estimation , 2018, ArXiv.

[37]  Aaron C. Courville,et al.  Mutual Information Neural Estimation , 2018, ICML.

[38]  Xinghua Shi,et al.  A deep auto-encoder model for gene expression prediction , 2017, BMC Genomics.

[39]  Marc Hafner,et al.  Common and cell-type specific responses to anti-cancer drugs revealed by high throughput transcript profiling , 2017, Nature Communications.

[40]  Kathleen M Jagodnik,et al.  Massive mining of publicly available RNA-seq data from human and mouse , 2017, Nature Communications.

[41]  Casey S. Greene,et al.  Extracting a Biologically Relevant Latent Space from Cancer Transcriptomes with Variational Autoencoders , 2017, bioRxiv.

[42]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[43]  Anne E Carpenter,et al.  Opportunities and obstacles for deep learning in biology and medicine , 2017, bioRxiv.

[44]  Angela N. Brooks,et al.  A Next Generation Connectivity Map: L1000 Platform and the First 1,000,000 Profiles , 2017, Cell.

[45]  Ankur Taly,et al.  Axiomatic Attribution for Deep Networks , 2017, ICML.

[46]  Yoshihiro Yamanishi,et al.  Elucidating the modes of action for bioactive compounds in a cell-specific manner by large-scale chemically-induced transcriptomics , 2017, Scientific Reports.

[47]  Mariano J. Alvarez,et al.  Network-based inference of protein activity helps functionalize the genetic landscape of cancer , 2016, Nature Genetics.

[48]  C. Greene,et al.  ADAGE-Based Integration of Publicly Available Pseudomonas aeruginosa Gene Expression Data with Denoising Autoencoders Illuminates Microbe-Host Interactions , 2016, mSystems.

[49]  Xinghua Lu,et al.  Learning a hierarchical representation of the yeast transcriptomic machinery using an autoencoder model , 2016, BMC Bioinformatics.

[50]  Jerome H. Kim,et al.  Dissecting Polyclonal Vaccine-Induced Humoral Immunity against HIV Using Systems Serology , 2015, Cell.

[51]  J. Seok,et al.  Evidence-Based Translation for the Genomic Responses of Murine Models for the Study of Human Immunity , 2015, PloS one.

[52]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[53]  Erhan Bilal,et al.  Understanding the limits of animal models as predictors of human biology: lessons learned from the sbv IMPROVER Species Translation Challenge , 2014, Bioinform..

[54]  Theodore Sakellaropoulos,et al.  The species translation challenge—A systems biology perspective on human and rat bronchial epithelial cells , 2014, Scientific Data.

[55]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[56]  M. Ghert,et al.  Lost in translation: animal models and clinical trials in cancer treatment. , 2014, American journal of translational research.

[57]  Adam A. Margolin,et al.  The Cancer Cell Line Encyclopedia enables predictive modeling of anticancer drug sensitivity , 2012, Nature.

[58]  Marc Robinson-Rechavi,et al.  When orthologs diverge between human and mouse , 2011, Briefings Bioinform..

[59]  R. Tagliaferri,et al.  Discovery of drug mode of action and drug repositioning from transcriptional responses , 2010, Proceedings of the National Academy of Sciences.

[60]  S. Sawilowsky.  New Effect Size Rules of Thumb , 2009 .

[61]  Jacob Cohen.  Statistical Power Analysis for the Behavioral Sciences , 1969, The SAGE Encyclopedia of Research Design.

[62]  Achim Zeileis,et al.  Diagnostic Checking in Regression Relationships , 2015 .

[63]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[64]  Alex E. Lash,et al.  Gene Expression Omnibus: NCBI gene expression and hybridization array data repository , 2002, Nucleic Acids Res..

[65]  J. Charles,et al.  A Sino-German λ 6 cm polarization survey of the Galactic plane I . Survey strategy and results for the first survey region , 2006 .