Biology subjects

Altman, R. B.

Publications and source records attributed to Altman, R. B..

40 records · Page 3Linked to original sources

bioRxiv2019

Classifying Non-Small Cell Lung Cancer Histopathology Types and Transcriptomic Subtypes using Convolutional Neural Networks

Non-small cell lung cancer is a leading cause of cancer death worldwide, and histopathological evaluation plays the primary role in its diagnosis. However, the morphological patterns associated with the molecular subtypes have not been systematically studied. To bridge this gap, we developed a quantitative histopathology analytic framework to identify the gene expression subtypes of non-small cell lung cancer objectively. We processed whole-slide histopathology images of lung adenocarcinoma (n=427) and lung squamous cell carcinoma patients (n=457) in The Cancer Genome Atlas. To establish neural networks for quantitative image analyses, we first build convolutional neural network models to identify tumor regions from adjacent dense benign tissues (areas under the receiver operating characteristic curves (AUC) > 0.935) and recapitulated expert pathologists diagnosis (AUC > 0.88), with the results validated in an independent cohort (n=125; AUC > 0.85). We further demonstrated that quantitative histopathology morphology features identified the major transcriptomic subtypes of both adenocarcinoma and squamous cell carcinoma (P < 0.01). Our study is the first to classify the transcriptomic subtypes of non-small cell lung cancer using fully-automated machine learning methods. Our approach does not rely on prior pathology knowledge and can discover novel clinically-relevant histopathology patterns objectively. The developed procedure is generalizable to other tumor types or diseases.

pathology↗

bioRxiv2018

Graph Convolutional Neural Networks for Predicting Drug-Target Interactions

Accurate determination of target-ligand interactions is crucial in the drug discovery process. In this paper, we propose a two-staged graph-convolutional (Graph-CNN) framework for predicting protein-ligand interactions. We first describe an unsupervised graph-autoencoder to learn fixed-size representations of protein pockets. Two Graph-CNNs are then trained to automatically extract features from pocket graphs and 2D molecular graphs, respectively. We demonstrate that graph-autoencoders can learn meaningful fixed-size representation for protein pockets of varying sizes and the Graph-CNN framework can effectively capture protein-ligand binding interactions without relying on target-ligand co-complexes. Across several metrics, Graph-CNNs achieved better or comparable performance to 3DCNN ligand-scoring, AutoDock Vina, RF-Score, and NNScore on common virtual screening benchmark datasets. Visualization of key pocket residues and ligand atoms contributing to the classification decisions confirms that our networks recognize meaningful interactions between pockets and ligands.\n\nAvailability and ImplementationContact: rbaltman@stanford.edu\n\nSupplementary information:

bioinformatics↗

bioRxiv2018

Standardized biogeographic grouping system for annotating populations in pharmacogenetic research

The varying frequencies of pharmacogenetic alleles between populations have important implications for the impact of these alleles in different populations. Current population grouping methods to communicate these patterns are insufficient as they are inconsistent and fail to reflect the global distribution of genetic variability. To facilitate and standardize the reporting of variability in pharmacogenetic allele frequencies, we present seven geographically-defined groups: American, Central/South Asian, East Asian, European, Near Eastern, Oceanian, and Sub-Saharan African, and two admixed groups: African American/Afro-Caribbean and Latino. These nine groups are defined by global autosomal genetic structure and based on data from large-scale sequencing initiatives. We recognize that broadly grouping global populations is an oversimplification of human diversity and does not capture complex social and cultural identity. However, these groups meet a key need in pharmacogenetics research by enabling consistent communication of the scale of variability in global allele frequencies and are now used by PharmGKB.

genetics↗

bioRxiv2018

ERASE: a novel surface reconditioning strategy for single-molecule experiments

While surface-based single-molecule experiments have revolutionized our understanding of biology and biomolecules, the workflow in preparing for such experiments, especially surface cleaning and functionalization remains labor-intensive and time-consuming. Even worse, meticulously assembled flow channels can be used only once for most experiments. A reusable surface would thus dramatically increase productivity and efficiency of single-molecule experiments. In this paper, we report a novel surface reconditioning strategy termed ERASE (Epitaxial Removal Aided by Strand Exchange) that allows a single flow cell to be used for vast repetition of single-molecule experiments. In this method, biomolecules immobilized to the surface through a nucleic acid duplex are liberated when a competing DNA strand disrupts the duplex via toehold-mediated strand displacement. We demonstrate the wide-range applicability of this method with various common surface preparation techniques, fluorescent dyes, and biomolecules including the bacterial ribosome. Beyond time and cost savings, we also show ERASE can assort molecules based on a nucleic acid barcode sequence, thus allowing experiments on different molecules in parallel. Our method increases the utility of prepared surfaces and is a significant improvement to the current single-use paradigm.

biophysics↗