There is an avalanche of biomedical data generation and a parallel expansion in computational capabilities to analyze and make sense of these data. Starting with genome sequencing and widely employed deep sequencing technologies, these trends have now taken hold in all omics disciplines and increasingly call for multi-omics integration as well as data interpretation by artificial intelligence technologies. Here, we focus on mass spectrometry (MS)-based proteomics and describe how machine learning and, in particular, deep learning now predicts experimental peptide measurements from amino acid sequences alone. This will dramatically improve the quality and reliability of analytical workflows because experimental results should agree with predictions in a multi-dimensional data landscape. Machine learning has also become central to biomarker discovery from proteomics data, which now starts to outperform existing best-in-class assays. Finally, we discuss model transparency and explainability and data privacy that are required to deploy MS-based biomarkers in clinical settings.

Author information: (1)Charité Universitätsmedizin Berlin, Department of Biochemistry, 10117 Berlin, Germany; The Francis Crick Institute, Molecular Biology of Metabolism Laboratory, London NW11AT, UK; The University of Cambridge, Department of Biochemistry and Cambridge Centre for Proteomics, Cambridge CB21GA, UK. (2)Charité Universitätsmedizin Berlin, Department of Infectious Diseases and Respiratory Medicine, 10117 Berlin, Germany. (3)Charité Universitätsmedizin Berlin, Department of Biochemistry, 10117 Berlin, Germany. (4)University College London, Department of Mathematics, London WC1E 6BT, UK; University College London, Department of Women's Cancer, EGA Institute for Women'S Health, London WC1E 6BT, UK. (5)National Phenome Centre and Imperial Clinical Phenotyping Centre, Department of Metabolism, Digestion and Reproduction, Imperial College London, London SW72AZ, UK; Lobachevsky University, Department of Applied Mathematics, Nizhny Novgorod 603105, Russia; Imperial College London, Section of Bioanalytical Chemistry, Division of Systems Medicine, Department of Metabolism, Digestion and Reproduction, London SW7 2AZ, UK. (6)The Francis Crick Institute, Molecular Biology of Metabolism Laboratory, London NW11AT, UK. (7)Lobachevsky University, Department of Applied Mathematics, Nizhny Novgorod 603105, Russia; University of Hertfordshire, School of Physics, Astronomy and Mathematics, Hatfield AL10 9AB, UK; Sechenov First Moscow State Medical University, Department of Paediatrics and Paediatric Infectious Diseases, Moscow 119435, Russia. (8)Charité Universitätsmedizin Berlin, Department of Biochemistry, 10117 Berlin, Germany; The Francis Crick Institute, Molecular Biology of Metabolism Laboratory, London NW11AT, UK. (9)Medical University Innsbruck, Division of Intensive Care and Emergency Medicine, Department of Internal Medicine, 6020 Innsbruck, Austria. (10)Medical University of Innsbruck, Department of Internal Medicine II, 6020 Innsbruck, Austria. (11)Medical University of Innsbruck, Institute of Human Genetics, 6020 Innsbruck, Austria. (12)Medical University of Innsbruck, Christian Doppler Laboratory for Iron and Phosphate Biology, Department of Internal Medicine I, 6020 Innsbruck, Austria. (13)Charité Universitätsmedizin Berlin, Department of Infectious Diseases and Respiratory Medicine, 10117 Berlin, Germany; Berlin Institute of Health, 10178 Berlin, Germany. (14)Charité Universitätsmedizin Berlin, Medical Department of Hematology, Oncology & Tumor Immunology, Virchow Campus & Molekulares Krebsforschungszentrum, 13353 Berlin, Germany; Berlin Institute of Health, 10178 Berlin, Germany. (15)Charité Universitätsmedizin Berlin, Department of Nephrology and Internal Intensive Care Medicine, 10117 Berlin, Germany. (16)The Francis Crick Institute, Molecular Biology of Metabolism Laboratory, London NW11AT, UK; Chalmers Tekniska Högskola, Department of Biology and Biological Engineering, SE-412 96 Gothenburg, Sweden. (17)University of Edinburgh, Centre for Genomic and Experimental Medicine, Institute of Genetics and Cancer, Edinburgh EH4 2XU, UK; University of Edinburgh, Usher Institute, Edinburgh EH16 4UX, UK. (18)University of Edinburgh, MRC Human Genetics Unit, Institute of Genetics and Cancer, Edinburgh EH4 2XU, UK. (19)University of Edinburgh, Centre for Genomic and Experimental Medicine, Institute of Genetics and Cancer, Edinburgh EH4 2XU, UK. (20)University College London, Department of Women's Cancer, EGA Institute for Women'S Health, London WC1E 6BT, UK. (21)University College London, Department of Mathematics, London WC1E 6BT, UK; University College London, Department of Women's Cancer, EGA Institute for Women'S Health, London WC1E 6BT, UK; Lobachevsky University, Laboratory of Systems Medicine of Healthy Ageing, Nizhny Novgorod 603105, Russia. (22)Charité Universitätsmedizin Berlin, Department of Infectious Diseases and Respiratory Medicine, 10117 Berlin, Germany; German Centre for Lung Research, 35392 Gießen, Germany. (23)Bernhard Nocht Institute for Tropical Medicine, Department of Tropical Medicine, and University Medical Center Hamburg-Eppendorf, Department of Medicine, 20359 Hamburg, Germany. (24)The University of Cambridge, Department of Biochemistry and Cambridge Centre for Proteomics, Cambridge CB21GA, UK. (25)Charité - Universitätsmedizin Berlin, Core Facility - High-Throughput Mass Spectrometry, 10117 Berlin, Germany. (26)Charité Universitätsmedizin Berlin, Department of Biochemistry, 10117 Berlin, Germany; The Francis Crick Institute, Molecular Biology of Metabolism Laboratory, London NW11AT, UK. Electronic address: markus.ralser@charite.de. (27)Charité Universitätsmedizin Berlin, Department of Infectious Diseases and Respiratory Medicine, 10117 Berlin, Germany; Bernhard Nocht Institute for Tropical Medicine, Department of Tropical Medicine, and University Medical Center Hamburg-Eppendorf, Department of Medicine, 20359 Hamburg, Germany.

Viruses are traditionally thought to be under selective pressure to maintain compact genomes and thus depend on host cell translational machinery for reproduction. However, some viruses encode abundant tRNA and other translation-related genes, potentially optimizing for codon usage differences between phage and host. Here, we systematically interrogate selective advantages that carrying 18 tRNAs may convey to a T4-like Vibriophage. Host DNA and RNA degrade upon infection, including host tRNAs, which are replaced by those of the phage. These tRNAs are expressed at levels slightly better adapted to phage codon usage, especially that of late genes. The phage is unlikely to randomly acquire as diverse an array of tRNAs as observed (p = 0.0017). Together, our results support that the main driver behind phage tRNA acquisition is pressure to sustain translation as host machinery degrades, a process resulting in a dynamically adapted codon usage strategy during the course of infection.

Cells do not exist in isolation; they continuously act within and react to their environment. And this environment is not static; it continuously adapts and responds to cells. Here, we investigate how vascular structure and function impact emergent cell population behavior using an agent-based model (ABM). Our ABM enables researchers to "mix and match" cell agents, subcellular modules, and microenvironment components ranging from simple nutrient sources to complex, realistic vascular architectures that accurately capture hemodynamics. We use this ABM to highlight the bilateral relationship between cells and nearby vasculature, demonstrate the effect of vascular structure on environmental heterogeneity, and emphasize the non-linear, non-intuitive relationship between vascular function and the behavior of cell populations over time. Our ABM is well suited to characterizing in vitro and in vivo studies, with applications from basic science to translational synthetic biology and medicine. The model is freely available at https://github.com/bagherilab/ARCADE. A record of this paper's transparent peer review process is included in the supplemental information.

The recent advent of CRISPR and other molecular tools enabled the reconstruction of cell lineages based on induced DNA mutations and promises to solve the ones of more complex organisms. To date, no lineage reconstruction algorithms have been rigorously examined for their performance and robustness across dataset types and number of cells. To benchmark such methods, we decided to organize a DREAM challenge using in vitro experimental intMEMOIR recordings and in silico data for a C. elegans lineage tree of about 1,000 cells and a Mus musculus tree of 10,000 cells. Some of the 22 approaches submitted had excellent performance, but structural features of the trees prevented optimal reconstructions. Using smaller sub-trees as training sets proved to be a good approach for tuning algorithms to reconstruct larger trees. The simulation and reconstruction methods here generated delineate a potential way forward for solving larger cell lineage trees such as in mouse.

Author information: (1)Biomedical Engineering, Oregon Health and Science University, Portland, OR 97239, USA. (2)Biomolecular Engineering and UC Santa Cruz Genome Institute, University of California, Santa Cruz, Santa Cruz, CA, USA. (3)Sage Bionetworks, Seattle, WA, USA. (4)The Genome Institute, Washington University School of Medicine, 4444 Forest Park Avenue, St. Louis, MO 63110, USA. (5)Computational Biology, Ontario Institute for Cancer Research, Toronto, Canada. (6)Division of Applied Bioinformatics, German Cancer Research Center (DKFZ) and Faculty of Biosciences, Heidelberg University, Heidelberg, Germany. (7)Broad Institute of MIT and Harvard, Cambridge, MA 02142, USA. (8)Icahn School of Medicine at Mount Sinai, Department of Genetics and Genomic Sciences, One Gustave Levy Place, New York, NY 1498, USA. (9)Icahn School of Medicine at Mount Sinai, Department of Genetics and Genomic Sciences, One Gustave Levy Place, New York, NY 1498, USA; IBM T.J. Watson Research Center, 1101 Kitchawan Road, Route 134, Yorktown Heights, NY 10598, USA. (10)Computational Biology, Ontario Institute for Cancer Research, Toronto, Canada; Departments of Medical Biophysics and Pharmacology & Toxicology, University of Toronto, Toronto, Canada; Departments of Human Genetics and Urology, University of California, Los Angeles, Los Angeles, CA, USA. (11)Biomedical Engineering, Oregon Health and Science University, Portland, OR 97239, USA. Electronic address: ellrott@ohsu.edu.