%{search_type} search results

• Cover; Copyright; Table of Contents; Preface; Conventions Used in This Book; Using Code Examples; O'Reilly Online Learning; How to Contact Us; Acknowledgments;
• Chapter 1. Why Life Science?; Why Deep Learning?; Contemporary Life Science Is About Data; What Will You Learn?;
• Chapter 2. Introduction to Deep Learning; Linear Models; Multilayer Perceptrons; Training Models; Validation; Regularization; Hyperparameter Optimization; Other Types of Models; Convolutional Neural Networks; Recurrent Neural Networks; Further Reading;
• Chapter 3. Machine Learning with DeepChem; DeepChem Datasets

• Training a Model to Predict Toxicity of MoleculesCase Study: Training an MNIST Model; The MNIST Digit Recognition Dataset; A Convolutional Architecture for MNIST; Conclusion;
• Chapter 4. Machine Learning for Molecules; What Is a Molecule?; What Are Molecular Bonds?; Molecular Graphs; Molecular Conformations; Chirality of Molecules; Featurizing a Molecule; SMILES Strings and RDKit; Extended-Connectivity Fingerprints; Molecular Descriptors; Graph Convolutions; Training a Model to Predict Solubility; MoleculeNet; SMARTS Strings; Conclusion;
• Chapter 5. Biophysical Machine Learning

• Protein StructuresProtein Sequences; A Short Primer on Protein Binding; Biophysical Featurizations; Grid Featurization; Atomic Featurization; The PDBBind Case Study; PDBBind Dataset; Featurizing the PDBBind Dataset; Conclusion;
• Chapter 6. Deep Learning for Genomics; DNA, RNA, and Proteins; And Now for the Real World; Transcription Factor Binding; A Convolutional Model for TF Binding; Chromatin Accessibility; RNA Interference; Conclusion;
• Chapter 7. Machine Learning for Microscopy; A Brief Introduction to Microscopy; Modern Optical Microscopy; The Diffraction Limit

• Electron and Atomic Force MicroscopySuper-Resolution Microscopy; Deep Learning and the Diffraction Limit?; Preparing Biological Samples for Microscopy; Staining; Sample Fixation; Sectioning Samples; Fluorescence Microscopy; Sample Preparation Artifacts; Deep Learning Applications; Cell Counting; Cell Segmentation; Computational Assays; Conclusion;
• Chapter 8. Deep Learning for Medicine; Computer-Aided Diagnostics; Probabilistic Diagnoses with Bayesian Networks; Electronic Health Record Data; The Dangers of Large Patient EHR Databases?; Deep Radiology; X-Ray Scans and CT Scans; Histology

• MRI ScansLearning Models as Therapeutics; Diabetic Retinopathy; Conclusion; Ethical Considerations; Job Losses; Summary;
• Chapter 9. Generative Models; Variational Autoencoders; Generative Adversarial Networks; Applications of Generative Models in the Life Sciences; Generating New Ideas for Lead Compounds; Protein Design; A Tool for Scientific Discovery; The Future of Generative Modeling; Working with Generative Models; Analyzing the Generative Model's Output; Conclusion;
• Chapter 10. Interpretation of Deep Models; Explaining Predictions; Optimizing Inputs; Predicting Uncertainty

Deep learning has already achieved remarkable results in many fields. Now it's making waves throughout the sciences broadly and the life sciences in particular. This practical book teaches developers and scientists how to use deep learning for genomics, chemistry, biophysics, microscopy, medical analysis, and other fields. Ideal for practicing developers and scientists ready to apply their skills to scientific applications such as biology, genetics, and drug discovery, this book introduces several deep network primitives. You'll follow a case study on the problem of designing new therapeutics that ties together physics, chemistry, biology, and medicine-an example that represents one of science's greatest challenges. Learn the basics of performing machine learning on molecular data Understand why deep learning is a powerful tool for genetics and genomics Apply deep learning to understand biophysical systems Get a brief introduction to machine learning with DeepChem Use deep learning to analyze microscopic images Analyze medical scans using deep learning techniques Learn about variational autoencoders and generative adversarial networks Interpret what your model is doing and how it's working.
(source: Nielsen Book Data)

• An overview and practical guide to building Markov state models
• Markov model theory
• Estimation and Validation of Markov models
• Uncertainty estimation
• Analysis of Markov models
• Transition Path Theory
• Understanding Protein Folding using Markov state models
• Understanding Molecular Recognition by Kinetic Network Models Constructed from Molecular Dynamics Simulations
• Markov State and Diffusive Stochastic Models in Electron Spin Resonance
• Software for building Markov state models.

The aim of this book volume is to explain the importance of Markov state models to molecular simulation, how they work, and how they can be applied to a range of problems. The Markov state model (MSM) approach aims to address two key challenges of molecular simulation: 1) How to reach long timescales using short simulations of detailed molecular models 2) How to systematically gain insight from the resulting sea of data MSMs do this by providing a compact representation of the vast conformational space available to biomolecules by decomposing it into states sets of rapidly interconverting conformations and the rates of transitioning between states.This kinetic definition allows one to easily vary the temporal and spatial resolution of an MSM from high-resolution models capable of quantitative agreement with (or prediction of) experiment to low-resolution models that facilitate understanding. Additionally, MSMs facilitate the calculation of quantities that are difficult to obtain from more direct MD analyses, such as the ensemble of transition pathways. This book introduces the mathematical foundations of Markov models, how they can be used to analyze simulations and drive efficient simulations, and some of the insights these models have yielded in a variety of applications of molecular simulation.

Structured non-coding RNAs play key roles in fundamental cellular processes, but determining their three-dimensional structure remains challenging. In this dissertation, I investigate the feasibility of accurate and consistent de novo modeling of RNA 3D structures at atomic resolution under the Rosetta molecular modeling framework. In the first part, I present a novel RNA structure prediction method called Stepwise Assembly. This method deterministically enumerates a low-energy subspace of the RNA's available conformations through recursively constructing well-packed atomic-detail models in small steps. Stepwise Assembly is shown to systematically outperform existing Monte Carlo and knowledge-based methods for RNA 3D structure prediction. In the second part, I then demonstrate how Rosetta RNA de novo modeling can be combined with non-exchangeable 1H NMR chemical shift data to produce high-resolution RNA structures, without the use of other NMR measurements. The resulting method is rigorously validated on 23 RNA motifs, including 11 blind tests obtained from five leading labs in the RNA NMR community.

Fifteen years ago, the advent of modern high-throughput sequencing revolutionized computational genetics with a flood of data. Today, high-throughput biochemical assays promise to make biochemistry the next data-rich domain for machine learning. However, existing computational methods, built for small analyses of about 1,000 molecules, do not scale to emerging multi-million molecule datasets. For many algorithms, pairwise similarity comparisons between molecules are a critical bottleneck, presenting a 1,000x-1,000,000x scaling barrier. In this dissertation, I describe the design of SIML and PAPER, our GPU implementations of 2D and 3D chemical similarities, as well as SCISSORS, our metric embedding algorithm. On a model problem of interest, combining these techniques allows up to 274,000x speedup in time and up to 2.8 million-fold reduction in space while retaining excellent accuracy. I further discuss how these high-speed techniques have allowed insight into chemical shape similarity and the behavior of machine learning kernel methods in the presence of noise.

The advent of atomistic molecular dynamics simulations held the promise of a complete understanding of biomolecular dynamics. However, this goal has remained elusive, as increased computational power has brought with it larger systems to simulate and an overwhelming number of observables to analyze. In this work, I describe how recent advancements in Markov state modeling have helped overcome this dimensionality problem and enabled the characterization of complex phenomena, such as the folding-upon-binding processes of intrinsically disordered peptides. But is it possible to produce even more insightful models? To this end, I present a method that exploits Markov state models to infer statistically causal drivers of protein dynamics. Finally, I discuss a neural network alternative to Markov models, which yields physically interpretable insights and has the potential to replace expensive atomistic simulations.

Understanding the molecular bases of human health could greatly augment our ability to prevent and treat diseases. For example, a deeper understanding of protein folding would serve as a reference point for understanding, preventing, and reversing protein misfolding in diseases like Alzheimer's. Unfortunately, the small size and tremendous flexibility of proteins and other biomolecules make it difficult to simultaneously monitor their thermodynamics and kinetics with sufficient chemical detail. Atomistic Molecular Dynamics (MD) simulations can provide a solution to this problem in some cases; however, they are often too short to capture biologically relevant timescales with sufficient statistical accuracy. We have developed a number of methods to address these limitations. In particular, our work on Markov State Models (MSMs) now makes it possible to map out the conformational space of biomolecules by combining many short simulations into a single statistical model. Here we describe our use of MSMs to better understand protein and RNA folding. We chose to focus on these folding problems because of their relevance to misfolding diseases and the fact that any method capable of describing such drastic conformational changes should also be applicable to less dramatic but equally important structural rearrangements like allostery. One of the key insights from our folding simulations is that protein native states are kinetic hubs. That is, the unfolded ensemble is not one rapidly mixing set of conformations. Instead, there are many non-native states that can each interconvert more rapidly with the native state than with one another. In addition to these general observations, we also demonstrate how MSMs can be used to make predictions about the structural and kinetic properties of specific systems. Finally, we explain how MSMs and other enhanced sampling algorithms can be used to drive efficient sampling.

DNA gyrase is an essential bacterial molecular motor that uses ATP hydrolysis to drive the directional introduction of DNA supercoils. The enzyme employs a duplex strand passage mechanism that requires coordinating the opening and closing of three protein "gates": the N-gate, DNA-gate, and Exit-gate. The N-gate is formed by the dimerization of ATPase domains and acts as a nucleotide-dependent clamp that captures DNA for subsequent strand passage. Dynamic measurements of N-gate conformational changes are necessary to understand how gyrase harnesses chemical energy to direct changes in DNA topology. Here, we report real-time single molecule measurements of E. coli gyrase N-gate conformational dynamics under varying DNA and nucleotide conditions. We identify a landscape of distinct conformational intermediates whose populations can be shifted upon DNA and nucleotide binding. The N-gate is primarily open in the absence of DNA and nucleotide, but transiently samples closed conformations. The non-hydrolyzable ATP analog AMPPNP, but not ADP, induces stable N-gate dimerization, where FRET values are consistent with a closed conformation seen in crystal structures based on in silico modeling of dye positions. In the presence of DNA, the enzyme samples a distinct high FRET conformation of the N-gate that is consistent with an intermediate conformation previously described in studies of B. subtilis gyrase. Our measurements support a loose-coupling model in which N-gate conformations are highly dynamic and depend on both DNA and nucleotide binding. Substrate-induced N-gate conformational changes appear to be conserved across divergent bacterial species and could extend to other enzymes in the Gyrase-Hsp90-MutL (GHL) ATPase family. This work sets the stage for detailed structural modeling and for multimodal measurements that directly correlate protein and DNA dynamics in this complex molecular machine.

Despite over half a century of study, many interesting questions concerning protein folding remain. I detail the gaps in our theoretical understanding of folding, describe how new theories and experiments could fill those gaps, and discuss my own attempts to understand one of biology's most amazing phenomena. Specifically, I discuss how master equations can be used to understand folding kinetics, how we can understand the surprising simplicity of folding kinetics, and how a experiments determining the rate-length law of folding could contribute to our ability to falsify theoretical arguments. I conclude with five stimulating questions that if answered would further our understanding of folding significantly.

Binuclear non-heme iron enzymes are pervasive in nature and catalyze a variety of biologically important reactions, including reactions relevant to the biosynthesis of DNA, fatty acid metabolism, the protection of pathogens from oxidative stress, cell signaling, iron storage, and many others. Elucidating the structures of their diiron active sites and the contributions of these structures to reactivity can provide molecular level insight into catalysis. The near IR circular dichroism (CD), magnetic circular dichroism (MCD), and variable temperature variable field (VTVH) MCD spectroscopies form a powerful methodology that allows for detailed structural understanding of the diiron active sites in these enzymes. Presented are studies that focus on myo-inositol oxygenase, an enzyme with significance to human health, and de novo designed diiron proteins that model native enzymes.

Femtosecond x-ray scattering techniques are used to directly visualize ultrafast strains and changes in atomic-scale structure in nanoscale CdSe and CdS spheres and rods. We construct a tomographic view of photo-induced lattice displacements and nanoscale shape changes by measuring multiple lattice reflections. Large amplitude tensile strains at the percent level are observed, associated with a rapid expansion followed by contraction along the nanocrystal radial direction. These morphological changes occur simultaneously with the first steps in the melting transition on hundreds of femtosecond time-scales. This work represents the first direct, real-time probe of the dynamics of these strains in few-nanometer scale particles, with bulk thermodynamic elastic constants remaining sufficient to describe their response despite the extreme excitation conditions.

We are in the midst of a machine learning revolution. From self-driving cars to clinical diagnostics, machine learning promises to change the way we live our lives and make decisions. Applied to drug discovery, machine learning enables us to build upon existing experimental data and more effectively explore the vastness of chemical space for new therapeutics. In particular, virtual screening allows us to evaluate many more compounds and biological targets than we can test experimentally, helping to identify starting points for further development. In this dissertation, I present several applications of machine learning to drug discovery. Much of the work presented here focuses on multitask neural networks---variants of the models that have transformed computer vision and beaten some of the world's best Go players. Applications of these models to ligand-based virtual screening demonstrate improvements over standard machine learning methods such as random forest and logistic regression. I also describe neural network models built on simple encodings of the molecular graph, moving beyond traditional fingerprint-based screening methods to a richer and more flexible input representation.

Conformational transitions are a key phenomenon in biological processes; proteins and nucleic acids require structural malleability that not only enables them to adopt specific three-dimensional structures that impart activity, but also accommodates conformational transitions that enhance their functions and allow them to communicate with their surrounding environment. Protein conformational transitions have been extensively studied for a large number of systems, but RNA conformational transitions are less well understood. In this dissertation, I have studied conformational transitions in RNA occurring at the levels of both secondary and tertiary structure. A thiamine pyrophosphate and an adenine riboswitch have been used to follow the folding of RNA from an ensemble of partially structured heterogeneous conformers in the ligand-free state to fully folded native states in the ligand-bound state. Small angle X-ray scattering and two-dimensional chemical footprinting have been used as the primary experimental techniques to query the conformational transitions occurring in these two RNA systems. Being solution techniques, these methods are particularly suitable for probing heterogeneous ensembles of RNA structures that exist at thermodynamic equilibrium in variable salt and ligand concentrations. The results provide detailed characterization of partially folded RNA structures and the conformational transitions that mediate their conversion to natively folded forms.

Lattice models of proteins have been extensively used to study protein thermodynamics, folding dynamics and evolution. Our study considers two different hydrophobic-polar (HP) models on the two-dimensional square lattice: the purely HP model and a model where a compactness-favoring term is added. We exhaustively enumerate all the possible structures in our models and perform the study of their corresponding folds, HP arrangements in space and shapes. The two models considered differ greatly in their numbers of structures, folds, arrangements, and shapes. Despite their differences both lattice models have distinctive protein-like features: (1) Shapes are compact in both models, especially when a compactness-favoring energy term is added. (2) The residue composition is independent of the chain length and is very close to 50% hydrophobic in both models, as we observe in real proteins. (3) Comparative modeling works well in both models, particularly in the more compact one. The fact that our models show protein-like features suggests that lattice models incorporate the fundamental physical principles of proteins. Our work supports the use of lattice models to study questions about proteins that require exactness and extensive calculations, such as protein design and evolution, which are often too complex and computationally demanding to be addressed with more detailed models.

Nucleic acids--DNA and RNA--are critical to life, involved in the storage and decoding of genetic information in the cell as well as the regulation and catalysis of specific biological processes. The function of a nucleic acid molecule is determined in large part by the structure it adopts, which in turn depends on its sequence. The mechanisms of sequence-directed nucleic acid folding remain incompletely understood, particularly for large RNA molecules. The work presented in this thesis uses single-molecule optical-trapping techniques to study nucleic acid folding, where reversible folding is induced and measured in individual molecules through the application of force. In Chapter 2 we demonstrate direct measurement of the full folding energy landscapes of DNA hairpins, which comprise a model system for studying nucleic acid secondary structure, and show how such landscapes are sensitive to sequence. In Chapter 3 we study the electrostatics of DNA hairpin folding by measuring trends in folding energies under different ionic conditions and comparing these trends with those predicted by Poisson-Boltzmann theory. Finally, in Chapter 4 we examine folding of the TPP riboswitch aptamer, an RNA molecule with complex secondary structure that also adopts tertiary structure upon binding a small-molecule ligand. We measured the folding energy landscape of the aptamer and perturbations of this landscape resulting from mutations and ligand binding, and propose a kinetic model to describe the coupling between aptamer folding and ligand binding. Taken together, the results presented here demonstrate the usefulness of the energy landscape framework for characterizing nucleic acid folding in conjunction with single-molecule measurements.

The discovery by Cech and coworkers that structured RNA molecules could catalyze specific reactions has revolutionized our understanding of RNA's role and place in the biological machinery of life. The notion of understanding RNA folding from a biophysical perspective means understanding the formation of RNA structure in terms of the basic physical forces at play. This thesis describes the the use of electrostatic and coarse grain simulations and associated experiments to investigate different features of RNA folding. Chapter 1 gives an brief introduction to RNA folding, the primary physical forces that influence its formation, and a review of recent advances in our understanding of structure formation in RNA. Chapters 2 and 3 comprise the next section of the thesis and detail advances in our understanding of electrostatic effects around nucleic acids, a topic of great importance in RNA folding. Specifically, chapter 2 presents the development of a size-modified Poisson-Boltzmann theory to help account for the effects of ionic size while chapter 3 presents a critical assessment of the Poisson-Boltzmann description of electrostatic relaxation in tethered duplex model systems. Chapter 4 highlights a general theoretical framework for understanding the combined effects of electrostatics and junction topology on RNA folding stability and specificity. The last section focuses on the use of coarse grained simulation to understand the role of junction topology in shaping the allowed conformational space of the Transactivation Response (TAR) element from the genome of the Human Immunodeficiency Virus (HIV). Though the last section is not, strictly speaking, a study of RNA folding, understanding RNA conformational motion is of critical importance to the question of structure acquisition in RNAs.