Biology subjects

Hiranuma, N.

Publications and source records attributed to Hiranuma, N..

4 recordsLinked to original sources

bioRxiv2018

DeepProfile: Deep learning of patient molecular profiles for precision medicine in acute myeloid leukemia

We present the DeepProfile framework, which learns a variational autoencoder (VAE) network from thousands of publicly available gene expression samples and uses this network to encode a low-dimensional representation (LDR) to predict complex disease phenotypes. To our knowledge, DeepProfile is the first attempt to use deep learning to extract a feature representation from a vast quantity of unlabeled (i.e, lacking phenotype information) expression samples that are not incorporated into the prediction problem. We use Deep-Profile to predict acute myeloid leukemia patients in vitro responses to 160 chemotherapy drugs. We show that, when compared to the original features (i.e., expression levels) and LDRs from two commonly used dimensionality reduction methods, DeepProfile: (1) better predicts complex phenotypes, (2) better captures known functional gene groups, and (3) better reconstructs the input data. We show that DeepProfile is generalizable to other diseases and phenotypes by using it to predict ovarian cancer patients tumor invasion patterns and breast cancer patients disease subtypes.

bioinformatics↗

bioRxiv2018

AIControl: Replacing matched control experiments with machine learning improves ChIP-seq peak identification

ChIP-seq is a technique to determine binding locations of transcription factors, which remains a central challenge in molecular biology. Current practice is to use a \"control\" dataset to remove background signals from a immunoprecipitation (IP) target dataset. We introduce the AlControl framework, which eliminates the need to obtain a control dataset and instead identifies binding peaks by estimating the distributions of background signals from many publicly available control ChIP-seq datasets. We thereby avoid the cost of running control experiments while simultaneously increasing the accuracy of binding location identification. Specifically, AIControl can (1) estimate background signals at fine resolution, (2) systematically weigh the most appropriate control datasets in a data-driven way, (3) capture sources of potential biases that may be missed by one control dataset, and (4) remove the need for costly and time-consuming control experiments. We applied AIControl to 410 IP datasets in the ENCODE ChIP-seq database, using 440 control datasets from 107 cell types to impute background signal. Without using matched control datasets, AIControl identified peaks that were more enriched for putative binding sites than those identified by other popular peak callers that used a matched control dataset. We also demonstrated that our framework identifies binding sites that recover documented protein interactions more accurately.

bioinformatics↗

bioRxiv2017

DeepATAC: A deep-learning method to predict regulatory factor binding activity from ATAC-seq signals

Determining the binding locations of regulatory factors, such as transcription factors and histone modifications, is essential to both basic biology research and many clinical applications. Obtaining such genome-wide location maps directly is often invasive and resource-intensive, so it is common to impute binding locations from DNA sequence or measures of chromatin accessibility. We introduce DeepATAC, a deep-learning approach for imputing binding locations that uses both DNA sequence and chromatin accessibility as measured by ATAC-seq. DeepATAC significantly outperforms current approaches such as FIMO motif predictions overlapped with ATAC-seq peaks, and models based only on DNA sequence, such as DeepSEA. Visualizing the input importances for the DeepATAC model reveals DNA sequence motifs and ATAC-seq signal patterns that are important for predicting binding events. The Keras implementation and analysis pipelines of DeepATAC are available at https://github.com/hiranumn/deepatac.

bioinformatics↗

bioRxiv2016

Cis-Compound Mutations are Prevalent in Triple Negative Breast Cancer and Can Drive Tumor Progression

About 16% of breast cancers fall into a clinically aggressive category designated triple negative (TNBC) due to a lack of ERBB2, estrogen receptor and progesterone receptor expression1-3. The mutational spectrum of TNBC has been characterized as part of The Cancer Genome Atlas (TCGA)4; however, snapshots of primary tumors cannot reveal the mechanisms by which TNBCs progress and spread. To address this limitation we initiated the Intensive Trial of OMics in Cancer (ITOMIC)-001, in which patients with metastatic TNBC undergo multiple biopsies over space and time5. Whole exome sequencing (WES) of 67 samples from 11 patients identified 426 genes containing multiple distinct single nucleotide variants (SNVs) within the same sample, instances we term Multiple SNVs affecting the Same Gene and Sample (MSSGS). We find that >90% of MSSGS result from cis-compound mutations (in which both SNVs affect the same allele), that MSSGS comprised of SNVs affecting adjacent nucleotides arise from single mutational events, and that most other MSSGS result from the sequential acquisition of SNVs. Some MSSGS drive cancer progression, as exemplified by a TNBC driven by FGFR2(S252W;Y375C). MSSGS are more prevalent in TNBC than other breast cancer subtypes and occur at higher-than-expected frequencies across TNBC samples within TCGA. MSSGS may denote genes that play as yet unrecognized roles in cancer progression.

clinical trials↗