DeepFrag: a deep convolutional neural network for fragment-based lead optimization.

Machine learning has been increasingly applied to the field of computer-aided drug discovery in recent years, leading to notable advances in binding-affinity prediction, virtual screening, and QSAR. Surprisingly, it is less often applied to lead optimization, the process of identifying chemical fragments that might be added to a known ligand to improve its binding affinity. We here describe a deep convolutional neural network that predicts appropriate fragments given the structure of a receptor/ligand complex. In an independent benchmark of known ligands with missing (deleted) fragments, our DeepFrag model selected the known (correct) fragment from a set over 6500 about 58% of the time. Even when the known/correct fragment was not selected, the top fragment was often chemically similar and may well represent a valid substitution. We release our trained DeepFrag model and associated software under the terms of the Apache License, Version 2.0.

DeepFrag: An Open-Source Browser App for Deep-Learning Lead Optimization.

Lead optimization, a critical step in early stage drug discovery, involves making chemical modifications to a small-molecule ligand to improve properties such as binding affinity. We recently developed DeepFrag, a deep-learning model capable of recommending such modifications. Though a powerful hypothesis-generating tool, DeepFrag is currently implemented in Python and so requires a certain degree of computational expertise. To encourage broader adoption, we have created the DeepFrag browser app, which provides a user-friendly graphical user interface that runs the DeepFrag model in users' web browsers. The browser app does not require users to upload their molecular structures to a third-party server, nor does it require the separate installation of any third-party software. We are hopeful that the app will be a useful tool for both researchers and students. It can be accessed free of charge, without registration, at http://durrantlab.com/deepfrag. The source code is also available at http://git.durrantlab.com/jdurrant/deepfrag-app, released under the terms of the open-source Apache License, Version 2.0.

Gypsum-DL: an open-source program for preparing small-molecule libraries for structure-based virtual screening.

Computational techniques such as structure-based virtual screening require carefully prepared 3D models of potential small-molecule ligands. Though powerful, existing commercial programs for virtual-library preparation have restrictive and/or expensive licenses. Freely available alternatives, though often effective, do not fully account for all possible ionization, tautomeric, and ring-conformational variants. We here present Gypsum-DL, a free, robust open-source program that addresses these challenges. As input, Gypsum-DL accepts virtual compound libraries in SMILES or flat SDF formats. For each molecule in the virtual library, it enumerates appropriate ionization, tautomeric, chiral, cis/trans isomeric, and ring-conformational forms. As output, Gypsum-DL produces an SDF file containing each molecular form, with 3D coordinates assigned. To demonstrate its utility, we processed 1558 molecules taken from the NCI Diversity Set VI and 56,608 molecules taken from a Distributed Drug Discovery (D3) combinatorial virtual library. We also used 4463 high-quality protein-ligand complexes from the PDBBind database to show that Gypsum-DL processing can improve virtual-screening pose prediction. Gypsum-DL is available free of charge under the terms of the Apache License, Version 2.0.

Iron Sequestration in Microbiota Biofilms As A Novel Strategy for Treating Inflammatory Bowel Disease.

Significant alterations of intestinal microbiota and anemia are hallmarks of inflammatory bowel disease (IBD). It is widely accepted that iron is a key nutrient for pathogenic bacteria, but little is known about its impact on microbiota associated with IBD. We used a model device to grow human mucosa-associated microbiota in its physiological anaerobic biofilm phenotype. Compared to microbiota from healthy donors, microbiota from IBD patients generate biofilms ex vivo that were larger in size and cell numbers, contained higher intracellular iron concentrations, and exhibited heightened virulence in a model of human intestinal epithelia in vitro and in the nematode Caenorhabditis elegans. We also describe an unexpected iron-scavenging property for an experimental hydrogen sulfide-releasing derivative of mesalamine. The findings demonstrate that this new drug reduces the virulence of IBD microbiota biofilms through a direct reduction of microbial iron intake and without affecting bacteria survival or species composition within the microbiota. Metabolomic analyses indicate that this drug reduces the intake of purine nucleosides (guanosine), increases the secretion of metabolite markers of purine catabolism (urate and hypoxanthine), and reduces the secretion of uracil (a pyrimidine nucleobase) in complex multispecies human biofilms. These findings demonstrate a new pathogenic mechanism for dysbiotic microbiota in IBD and characterize a novel mode of action for a class of mesalamine derivatives. Together, these observations pave the way towards a new therapeutic strategy for treatment of patients with IBD.

Modeling Host-Microbiome Interactions in Caenorhabditis elegans.

The microbiome influences host processes including nutritional availability, development, immunity, and behavioral responses. Caenorhabditis elegans is a powerful model to study molecular mechanisms of host-microbial interactions. Recent efforts have been made to profile the natural microbiome of C. elegans, laying a foundation for mechanistic studies of host-microbiome interactions in this genetically tractable model system. Studies using single-species microbes, multi-microbial systems, and humanized worm-microbiome interaction studies reveal metabolic and microbial-microbial interactions relevant in higher organisms. This article discusses recent developments in modeling the effects of host-microbiome interactions in C. elegans.

Adding user-friendliness and ease of implementation to continuous speech recognition technology with speech macros: case studies.

Continuous Speech Recognition Technology implementation is expensive, and the failure of leading companies in this niche can hamper usefulness. C-SRT, if deployed and used with speech macros, experiences vastly improved implementations and drastically reduces medical transcription costs.A speech macro is a short phrase that is automatically translated into a block of text or a graphic display. A more powerful form of speech macro can bring up predefined templates and insert spoken text into the proper position automatically, based on its interpretation. Cases from the author's consulting experiences and from medical journals emphasize the need for speech macros from a cost-benefit standpoint. A prototype program is introduced that facilitates the process of creating macros. The need for macro management software is reconciled with current research on speech recognition and technology adoption. A planned experiment is discussed.