Integrative multi-omics characterization of hepatocellular carcinoma in Hispanic patients.

Background: The incidence and mortality rates of hepatocellular carcinoma (HCC) among Hispanics in the United States are much higher than those of non-Hispanic whites. We conducted comprehensive multi-omics analyses to understand molecular alterations in HCC among Hispanic patients. Methods: Paired tumor and adjacent non-tumor samples were collected from 31 Hispanic HCC in South Texas (STX-Hispanic) for genomic, transcriptomic, proteomic, and metabolomic profiling. Additionally, serum lipids were profiled in 40 Hispanic and non-Hispanic patients with or without clinically diagnosed HCC. Results: Exome sequencing revealed high mutation frequencies of AXIN2 and CTNNB1 in STX Hispanic HCCs, suggesting a predominant activation of the Wnt/ß-catenin pathway. The TERT promoter mutation frequency was also remarkably high in the Hispanic cohort. Cell cycles and liver functions were identified as positively- and negatively-enriched, respectively, with gene set enrichment analysis. Gene sets representing specific liver metabolic pathways were associated with dysregulation of corresponding metabolites. Negative enrichment of liver adipogenesis and lipid metabolism corroborated with a significant reduction in most lipids in the serum samples of HCC patients. Two HCC subtypes from our Hispanic cohort were identified and validated with the TCGA liver cancer cohort. The subtype with better overall survival showed higher activity of immune and angiogenesis signatures, and lower activity of liver function-related gene signatures. It also had higher levels of immune checkpoint and immune exhaustion markers. Conclusions: Our study revealed some specific molecular features of Hispanic HCC and potential biomarkers for therapeutic management of HCC and provides a unique resource for studying Hispanic HCC.

A Metastatic Cancer Expression Generator (MetGen): A Generative Contrastive Learning Framework for Metastatic Cancer Generation.

Despite significant advances in tumor biology and clinical therapeutics, metastasis remains the primary cause of cancer-related deaths. While RNA-seq technology has been used extensively to study metastatic cancer characteristics, challenges persist in acquiring adequate transcriptomic data. To overcome this challenge, we propose MetGen, a generative contrastive learning tool based on a deep learning model. MetGen generates synthetic metastatic cancer expression profiles using primary cancer and normal tissue expression data. Our results demonstrate that MetGen generates comparable samples to actual metastatic cancer samples, and the cancer and tissue classification yields performance rates of 99.8 ± 0.2% and 95.0 ± 2.3%, respectively. A benchmark analysis suggests that the proposed model outperforms traditional generative models such as the variational autoencoder. In metastatic subtype classification, our generated samples show 97.6% predicting power compared to true metastatic samples. Additionally, we demonstrate MetGen's interpretability using metastatic prostate cancer and metastatic breast cancer. MetGen has learned highly relevant signatures in cancer, tissue, and tumor microenvironments, such as immune responses and the metastasis process, which can potentially foster a more comprehensive understanding of metastatic cancer biology. The development of MetGen represents a significant step toward the study of metastatic cancer biology by providing a generative model that identifies candidate therapeutic targets for the treatment of metastatic cancer.

Predicting drug response through tumor deconvolution by cancer cell lines.

Large-scale cancer drug sensitivity data have become available for a collection of cancer cell lines, but only limited drug response data from patients are available. Bridging the gap in pharmacogenomics knowledge between in vitro and in vivo datasets remains challenging. In this study, we trained a deep learning model, Scaden-CA, for deconvoluting tumor data into proportions of cancer-type-specific cell lines. Then, we developed a drug response prediction method using the deconvoluted proportions and the drug sensitivity data from cell lines. The Scaden-CA model showed excellent performance in terms of concordance correlation coefficients (>0.9 for model testing) and the correctly deconvoluted rate (>70% across most cancers) for model validation using Cancer Cell Line Encyclopedia (CCLE) bulk RNA data. We applied the model to tumors in The Cancer Genome Atlas (TCGA) dataset and examined associations between predicted cell viability and mutation status or gene expression levels to understand underlying mechanisms of potential value for drug repurposing.

Clinical and biomarker results from a phase II trial of combined cabozantinib and durvalumab in patients with chemotherapy-refractory colorectal cancer (CRC): CAMILLA CRC cohort.

CAMILLA is a basket trial (NCT03539822) evaluating cabozantinib plus the ICI durvalumab in chemorefractory gastrointestinal cancer. Herein, are the phase II colorectal cohort results. 29 patients were evaluable. 100% had confirmed pMMR/MSS tumors. Primary endpoint was met with ORR of 27.6% (95% CI 12.7-47.2%). Secondary endpoints of 4-month PFS rate was 44.83% (95% CI 26.5-64.3%); and median OS was 9.1 months (95% CI 5.8-20.2). Grade≥3 TRAE occurred in 39%. In post-hoc analysis of patients with RAS wild type tumors, ORR was 50% and median PFS and OS were 6.3 and 21.5 months respectively. Exploratory spatial transcriptomic profiling of pretreatment tumors showed upregulation of VEGF and MET signaling, increased extracellular matrix activity and preexisting anti-tumor immune responses coexisting with immune suppressive features like T cell migration barriers in responders versus non-responders. Cabozantinib plus durvalumab demonstrated anti-tumor activity, manageable toxicity, and have led to the activation of the phase III STELLAR-303 trial.

reguloGPT: Harnessing GPT for Knowledge Graph Construction of Molecular Regulatory Pathways.

Motivation: Molecular Regulatory Pathways (MRPs) are crucial for understanding biological functions. Knowledge Graphs (KGs) have become vital in organizing and analyzing MRPs, providing structured representations of complex biological interactions. Current tools for mining KGs from biomedical literature are inadequate in capturing complex, hierarchical relationships and contextual information about MRPs. Large Language Models (LLMs) like GPT-4 offer a promising solution, with advanced capabilities to decipher the intricate nuances of language. However, their potential for end-to-end KG construction, particularly for MRPs, remains largely unexplored. Results: We present reguloGPT, a novel GPT-4 based in-context learning prompt, designed for the end-to-end joint name entity recognition, N-ary relationship extraction, and context predictions from a sentence that describes regulatory interactions with MRPs. Our reguloGPT approach introduces a context-aware relational graph that effectively embodies the hierarchical structure of MRPs and resolves semantic inconsistencies by embedding context directly within relational edges. We created a benchmark dataset including 400 annotated PubMed titles on N6-methyladenosine (m6A) regulations. Rigorous evaluation of reguloGPT on the benchmark dataset demonstrated marked improvement over existing algorithms. We further developed a novel G-Eval scheme, leveraging GPT-4 for annotation-free performance evaluation and demonstrated its agreement with traditional annotation-based evaluations. Utilizing reguloGPT predictions on m6A-related titles, we constructed the m6A-KG and demonstrated its utility in elucidating m6A's regulatory mechanisms in cancer phenotypes across various cancers. These results underscore reguloGPT's transformative potential for extracting biological knowledge from the literature. Availability and implementation: The source code of reguloGPT, the m6A title and benchmark datasets, and m6A-KG are available at: https://github.com/Huang-AI4Medicine-Lab/reguloGPT.

shinyDeepDR: A user-friendly R Shiny app for predicting anti-cancer drug response using deep learning.

Advancing precision oncology requires accurate prediction of treatment response and accessible prediction models. To this end, we present shinyDeepDR, a user-friendly implementation of our innovative deep learning model, DeepDR, for predicting anti-cancer drug sensitivity. The web tool makes DeepDR more accessible to researchers without extensive programming experience. Using shinyDeepDR, users can upload mutation and/or gene expression data from a cancer sample (cell line or tumor) and perform two main functions: "Find Drug," which predicts the sample's response to 265 approved and investigational anti-cancer compounds, and "Find Sample," which searches for cell lines in the Cancer Cell Line Encyclopedia (CCLE) and tumors in The Cancer Genome Atlas (TCGA) with genomics profiles similar to those of the query sample to study potential effective treatments. shinyDeepDR provides an interactive interface to interpret prediction results and to investigate individual compounds. In conclusion, shinyDeepDR is an intuitive and free-to-use web tool for in silico anti-cancer drug screening.

Systems approach for congruence and selection of cancer models towards precision medicine.

Cancer models are instrumental as a substitute for human studies and to expedite basic, translational, and clinical cancer research. For a given cancer type, a wide selection of models, such as cell lines, patient-derived xenografts, organoids and genetically modified murine models, are often available to researchers. However, how to quantify their congruence to human tumors and to select the most appropriate cancer model is a largely unsolved issue. Here, we present Congruence Analysis and Selection of CAncer Models (CASCAM), a statistical and machine learning framework for authenticating and selecting the most representative cancer models in a pathway-specific manner using transcriptomic data. CASCAM provides harmonization between human tumor and cancer model omics data, systematic congruence quantification, and pathway-based topological visualization to determine the most appropriate cancer model selection. The systems approach is presented using invasive lobular breast carcinoma (ILC) subtype and suggesting CAMA1 followed by UACC3133 as the most representative cell lines for ILC research. Two additional case studies for triple negative breast cancer (TNBC) and patient-derived xenograft/organoid (PDX/PDO) are further investigated. CASCAM is generalizable to any cancer subtype and will authenticate cancer models for faithful non-human preclinical research towards precision medicine.

Molecular and immune signatures, and pathological trajectories of fatal COVID-19 lungs defined by in situ spatial single-cell transcriptome analysis.

Despite intensive studies during the last 3 years, the pathology and underlying molecular mechanism of coronavirus disease 2019 (COVID-19) remain poorly defined. In this study, we investigated the spatial single-cell molecular and cellular features of postmortem COVID-19 lung tissues using in situ sequencing (ISS). We detected 10 414 863 transcripts of 221 genes in whole-slide tissues and segmented them into 1 719 459 cells that were mapped to 18 major parenchymal and immune cell types, all of which were infected by SARS-CoV-2. Compared with the non-COVID-19 control, COVID-19 lungs exhibited reduced alveolar cells (ACs) and increased innate and adaptive immune cells. We also identified 19 differentially expressed genes in both infected and uninfected cells across the tissues, which reflected the altered cellular compositions. Spatial analysis of local infection rates revealed regions with high infection rates that were correlated with high cell densities (HIHD). The HIHD regions expressed high levels of SARS-CoV-2 entry-related factors including ACE2, FURIN, TMPRSS2 and NRP1, and co-localized with organizing pneumonia (OP) and lymphocytic and immune infiltration, which exhibited increased ACs and fibroblasts but decreased vascular endothelial cells and epithelial cells, mirroring the tissue damage and wound healing processes. Sparse nonnegative matrix factorization (SNMF) analysis of niche features identified seven signatures that captured structure and immune niches in COVID-19 tissues. Trajectory inference based on immune niche signatures defined two pathological routes. Trajectory A primarily progressed with increased NK cells and granulocytes, likely reflecting the complication of microbial infections. Trajectory B was marked by increased HIHD and OP, possibly accounting for the increased immune infiltration. The OP regions were marked by high numbers of fibroblasts expressing extremely high levels of COL1A1 and COL1A2. Examination of single-cell RNA-seq data (scRNA-seq) from COVID-19 lung tissues and idiopathic pulmonary fibrosis (IPF) identified similar cell populations consisting mainly of myofibroblasts. Immunofluorescence staining revealed the activation of IL6-STAT3 and TGF-ß-SMAD2/3 pathways in these cells, likely mediating the upregulation of COL1A1 and COL1A2 and excessive fibrosis in the lung tissues. Together, this study provides a spatial single-cell atlas of cellular and molecular signatures of fatal COVID-19 lungs, which reveals the complex spatial cellular heterogeneity, organization, and interactions that characterized the COVID-19 lung pathology.

DepLink: an R Shiny app to systematically link genetic and pharmacologic dependencies of cancer.

Motivation: Large-scale genetic and pharmacologic dependency maps are generated to reveal genetic vulnerabilities and drug sensitivities of cancer. However, user-friendly software is needed to systematically link such maps. Results: Here, we present DepLink, a web server to identify genetic and pharmacologic perturbations that induce similar effects on cell viability or molecular changes. DepLink integrates heterogeneous datasets of genome-wide CRISPR loss-of-function screens, high-throughput pharmacologic screens and gene expression signatures of perturbations. The datasets are systematically connected by four complementary modules tailored for different query scenarios. It allows users to search for potential inhibitors that target a gene (Module 1) or multiple genes (Module 2), mechanisms of action of a known drug (Module 3) and drugs with similar biochemical features to an investigational compound (Module 4). We performed a validation analysis to confirm the capability of our tool to link the effects of drug treatments to knockouts of the drug's annotated target genes. By querying with a demonstrating example of CDK6, the tool identified well-studied inhibitor drugs, novel synergistic gene and drug partners and insights into an investigational drug. In summary, DepLink enables easy navigation, visualization and linkage of rapidly evolving cancer dependency maps. Availability and implementation: The DepLink web server, demonstrating examples and detailed user manual are available at https://shiny.crc.pitt.edu/deplink/. Supplementary information: Supplementary data are available at Bioinformatics Advances online.

Transformer for Gene Expression Modeling (T-GEM): An Interpretable Deep Learning Model for Gene Expression-Based Phenotype Predictions.

Deep learning has been applied in precision oncology to address a variety of gene expression-based phenotype predictions. However, gene expression data's unique characteristics challenge the computer vision-inspired design of popular Deep Learning (DL) models such as Convolutional Neural Network (CNN) and ask for the need to develop interpretable DL models tailored for transcriptomics study. To address the current challenges in developing an interpretable DL model for modeling gene expression data, we propose a novel interpretable deep learning architecture called T-GEM, or Transformer for Gene Expression Modeling. We provided the detailed T-GEM model for modeling gene-gene interactions and demonstrated its utility for gene expression-based predictions of cancer-related phenotypes, including cancer type prediction and immune cell type classification. We carefully analyzed the learning mechanism of T-GEM and showed that the first layer has broader attention while higher layers focus more on phenotype-related genes. We also showed that T-GEM's self-attention could capture important biological functions associated with the predicted phenotypes. We further devised a method to extract the regulatory network that T-GEM learns by exploiting the attributions of self-attention weights for classifications and showed that the network hub genes were likely markers for the predicted phenotypes.

Development and characterization of a mass cytometry panel for detecting the effect of acute doxorubicin exposure on murine cardiac nonmyocytes.

Childhood cancer survivors (CCSs) face lifelong side effects related to their treatment with chemotherapy. Anthracycline agents, such as doxorubicin (DOX), are important in the treatment of childhood cancers but are associated with cardiotoxicity. Cardiac toxicities represent a significant source of chronic disability that cancer survivors face; despite this, the chronic cardiotoxicity phenotype and how it relates to acute toxicity remains poorly defined. To address this critical knowledge gap, we studied the acute effect of DOX on murine cardiac nonmyocytes in vivo. Determination of the acute cellular effects of DOX on nonmyocytes, a cell pool with finite replicative capacity, provides a basis for understanding the pathogenesis of the chronic heart disease that CCSs face. To investigate the acute cellular effects of DOX, we present single-cell RNA sequencing (scRNAseq) data from homeostatic cardiac nonmyocytes and compare it with preexisting datasets, as well as a novel CyTOF datasets. SCANPY, a python-based single-cell analysis, was used to assess the heterogeneity of cells detected in scRNAseq and CyTOF. To further assist in CyTOF data annotation, joint analyses of scRNAseq and CyTOF data using an artificial neural network known as sparse autoencoder for clustering, imputation, and embedding (SAUCIE) are performed. Lastly, the panel is tested on a mouse model of acute DOX exposure at two time points (24 and 72 h) after the last dose of doxorubicin and examined with joint clustering. In sum, we report the first ever CyTOF study of cardiac nonmyocytes and characterize the effect of acute DOX exposure with scRNAseq and CyTOF.NEW & NOTEWORTHY We describe the first mass cytometry studies of murine cardiac nonmyocytes. The mass cytometry panel is compared with single-cell RNA sequencing data. Homeostatic cardiac nonmyocytes are characterized by mass cytometry to identify and quantify four major cell populations: endothelial cells, fibroblasts, leukocytes, and pericytes. The single-cell acute nonmyocyte response to doxorubicin is studied at 24 and 72 h after doxorubicin exposure given daily for 5 days at a dose of 4 mg/kg/day.

Deep learning tackles single-cell analysis-a survey of deep learning for scRNA-seq analysis.

Since its selection as the method of the year in 2013, single-cell technologies have become mature enough to provide answers to complex research questions. With the growth of single-cell profiling technologies, there has also been a significant increase in data collected from single-cell profilings, resulting in computational challenges to process these massive and complicated datasets. To address these challenges, deep learning (DL) is positioned as a competitive alternative for single-cell analyses besides the traditional machine learning approaches. Here, we survey a total of 25 DL algorithms and their applicability for a specific step in the single cell RNA-seq processing pipeline. Specifically, we establish a unified mathematical representation of variational autoencoder, autoencoder, generative adversarial network and supervised DL models, compare the training strategies and loss functions for these models, and relate the loss functions of these models to specific objectives of the data processing step. Such a presentation will allow readers to choose suitable algorithms for their particular objective at each step in the pipeline. We envision that this survey will serve as an important information portal for learning the application of DL for scRNA-seq analysis and inspire innovative uses of DL to address a broader range of new challenges in emerging multi-omics and spatial single-cell sequencing.

Predicting and characterizing a cancer dependency map of tumors with deep learning.

Genome-wide loss-of-function screens have revealed genes essential for cancer cell proliferation, called cancer dependencies. It remains challenging to link cancer dependencies to the molecular compositions of cancer cells or to unscreened cell lines and further to tumors. Here, we present DeepDEP, a deep learning model that predicts cancer dependencies using integrative genomic profiles. It uses a unique unsupervised pretraining that captures unlabeled tumor genomic representations to improve the learning of cancer dependencies. We demonstrated DeepDEP's improvement over conventional machine learning methods and validated the performance with three independent datasets. By systematic model interpretations, we extended the current dependency maps with functional characterizations of dependencies and a proof-of-concept in silico assay of synthetic essentiality. We applied DeepDEP to pan-cancer tumor genomics and built the first pan-cancer synthetic dependency map of 8000 tumors with clinical relevance. In summary, DeepDEP is a novel tool for investigating cancer dependency with rapidly growing genomic resources.

CancerSiamese: one-shot learning for predicting primary and metastatic tumor types unseen during model training.

BACKGROUND: The state-of-the-art deep learning based cancer type prediction can only predict cancer types whose samples are available during the training where the sample size is commonly large. In this paper, we consider how to utilize the existing training samples to predict cancer types unseen during the training. We hypothesize the existence of a set of type-agnostic expression representations that define the similarity/dissimilarity between samples of the same/different types and propose a novel one-shot learning model called CancerSiamese to learn this common representation. CancerSiamese accepts a pair of query and support samples (gene expression profiles) and learns the representation of similar or dissimilar cancer types through two parallel convolutional neural networks joined by a similarity function. RESULTS: We trained CancerSiamese for cancer type prediction for primary and metastatic tumors using samples from the Cancer Genome Atlas (TCGA) and MET500. Network transfer learning was utilized to facilitate the training of the CancerSiamese models. CancerSiamese was tested for different N-way predictions and yielded an average accuracy improvement of 8% and 4% over the benchmark 1-Nearest Neighbor (1-NN) classifier for primary and metastatic tumors, respectively. Moreover, we applied the guided gradient saliency map and feature selection to CancerSiamese to examine 100 and 200 top marker-gene candidates for the prediction of primary and metastatic cancers, respectively. Functional analysis of these marker genes revealed several cancer related functions between primary and metastatic tumors. CONCLUSION: This work demonstrated, for the first time, the feasibility of predicting unseen cancer types whose samples are limited. Thus, it could inspire new and ingenious applications of one-shot and few-shot learning solutions for improving cancer diagnosis, prognostic, and our understanding of cancer.

Androgen deprivation-induced elevated nuclear SIRT1 promotes prostate tumor cell survival by reactivation of AR signaling.

The NAD+-dependent deacetylase, Sirtuin 1 (SIRT1) is involved in prostate cancer pathogenesis. However, the actual contribution is unclear as some reports propose a protective role while others suggest it is harmful. We provide evidence for a contextual role for SIRT1 in prostate cancer. Our data show that (i) mice orthotopically implanted with SIRT1-silenced LNCaP cells produced smaller tumors; (ii) SIRT1 suppression mimicked AR inhibitory effects in hormone responsive LNCaP cells; and (iii) caused significant reduction in gene signatures associated with E2F and MYC targets in AR-null PC-3 and E2F and mTORC1 signaling in castrate-resistant ARv7 positive 22Rv1 cells. Our findings further show increased nuclear SIRT1 (nSIRT1) protein under androgen-depleted relative to androgen-replete conditions in prostate cancer cell lines. Silencing SIRT1 resulted in decreased recruitment of AR to PSA enhancer selectively under androgen-deprivation conditions. Prostate cancer outcome data show that patients with higher levels of nSIRT1 progress to advanced disease relative to patients with low nSIRT1 levels. Collectively, we demonstrate that lowering SIRT1 levels potentially provides new avenues to effectively prevent prostate cancer recurrence.

Prediction and interpretation of cancer survival using graph convolution neural networks.

The survival rate of cancer has increased significantly during the past two decades for breast, prostate, testicular, and colon cancer, while the brain and pancreatic cancers have a much lower median survival rate that has not improved much over the last forty years. This has imposed the challenge of finding gene markers for early cancer detection and treatment strategies. Different methods including regression-based Cox-PH, artificial neural networks, and recently deep learning algorithms have been proposed to predict the survival rate for cancers. We established in this work a novel graph convolution neural network (GCNN) approach called Surv_GCNN to predict the survival rate for 13 different cancer types using the TCGA dataset. For each cancer type, 6 Surv_GCNN models with graphs generated by correlation analysis, GeneMania database, and correlation + GeneMania were trained with and without clinical data to predict the risk score (RS). The performance of the 6 Surv_GCNN models was compared with two other existing models, Cox-PH and Cox-nnet. The results showed that Cox-PH has the worst performance among 8 tested models across the 13 cancer types while Surv_GCNN models with clinical data reported the best overall performance, outperforming other competing models in 7 out of 13 cancer types including BLCA, BRCA, COAD, LUSC, SARC, STAD, and UCEC. A novel network-based interpretation of Surv_GCNN was also proposed to identify potential gene markers for breast cancer. The signatures learned by the nodes in the hidden layer of Surv_GCNN were identified and were linked to potential gene markers by network modularization. The identified gene markers for breast cancer have been compared to a total of 213 gene markers from three widely cited lists for breast cancer survival analysis. About 57% of gene markers obtained by Surv_GCNN with correlation + GeneMania graph either overlap or directly interact with the 213 genes, confirming the effectiveness of the identified markers by Surv_GCNN.

Predicting sites of epitranscriptome modifications using unsupervised representation learning based on generative adversarial networks.

Epitranscriptome is an exciting area that studies different types of modifications in transcripts and the prediction of such modification sites from the transcript sequence is of significant interest. However, the scarcity of positive sites for most modifications imposes critical challenges for training robust algorithms. To circumvent this problem, we propose MR-GAN, a generative adversarial network (GAN) based model, which is trained in an unsupervised fashion on the entire pre-mRNA sequences to learn a low dimensional embedding of transcriptomic sequences. MR-GAN was then applied to extract embeddings of the sequences in a training dataset we created for eight epitranscriptome modifications, including m6A, m1A, m1G, m2G, m5C, m5U, 2'-O-Me, Pseudouridine (Ψ) and Dihydrouridine (D), of which the positive samples are very limited. Prediction models were trained based on the embeddings extracted by MR-GAN. We compared the prediction performance with the one-hot encoding of the training sequences and SRAMP, a state-of-the-art m6A site prediction algorithm and demonstrated that the learned embeddings outperform one-hot encoding by a significant margin for up to 15% improvement. Using MR-GAN, we also investigated the sequence motifs for each modification type and uncovered known motifs as well as new motifs not possible with sequences directly. The results demonstrated that transcriptome features extracted using unsupervised learning could lead to high precision for predicting multiple types of epitranscriptome modifications, even when the data size is small and extremely imbalanced.

GDF6-CD99 Signaling Regulates Src and Ewing Sarcoma Growth.

We report here that the autocrine signaling mediated by growth and differentiation factor 6 (GDF6), a member of the bone morphogenetic protein (BMP) family of cytokines, maintains Ewing sarcoma growth by preventing Src hyperactivation. Surprisingly, Ewing sarcoma depends on the prodomain, not the BMP domain, of GDF6. We demonstrate that the GDF6 prodomain is a ligand for CD99, a transmembrane protein that has been widely used as a marker of Ewing sarcoma. The binding of the GDF6 prodomain to the CD99 extracellular domain results in recruitment of CSK (C-terminal Src kinase) to the YQKKK motif in the intracellular domain of CD99, inhibiting Src activity. GDF6 silencing causes hyperactivation of Src and p21-dependent growth arrest. We demonstrate that two GDF6 prodomain mutants linked to Klippel-Feil syndrome are hyperactive in CD99-Src signaling. These results reveal a cytokine signaling pathway that regulates the CSK-Src axis and cancer cell proliferation and suggest the gain-of-function activity for disease-causing GDF6 mutants.

Knock-out of Hopx disrupts stemness and quiescence of hematopoietic stem cells in mice.

HOPX is a stem cell marker in hair follicles and intestines. It was shown critical for primitive hematopoiesis. We previously showed an association between higher HOPX expression and clinical characteristics related to stemness and quiescence of leukemic cells in acute myeloid leukemia (AML) patients. To further explore its physiologic functions in hematopoietic system, we generated a mouse model with hematopoietic cell-specific knockout of Hopx (Hopx-/-). In young Hopx-/- mice, the hematopoietic stem cells (HSC) showed decreased reconstitution ability after serial transplantation. Further transcriptomic study revealed decreased HSC signatures in long-term HSCs from the Hopx-/- mice. At 18 months of age, half of the Hopx-/- mice developed cytopenia and splenomegaly. Bone marrow (BM) from the sick mice showed myeloid hyperplasia with predominant mature neutrophils, and decreased progenitor cells and lymphocytes. These phenotypes suggested critical functions of Hopx in maintaining HSC quiescence. Transcriptomic study of the Hopx-/- marrow cells showed significant downregulation of the Cxcl12-Cxcr4 axis, which is critical for maintenance of HSC quiescence. We next examined the role of Hopx in AML by using the MN1 overexpression murine leukemia model. Mice transplanted with MN1-overexpressed Hopx-/- BM cells developed AML with more aggressive phenotypes compared with those transplanted with MN1-overexpressed Hopx-wild cells. Hopx-/- MN1-overexpressed leukemia cells showed higher proliferation rate and downregulation of Cxcl12 and Cxcr4. Furthermore, in human AML, BM plasma CXCL12 levels were lower in patients with lower HOPX expression. In conclusion, our study highlights the roles of Hopx in maintenance of quiescence of the hematopoietic stem cells through CXCL12 pathway in vivo and provides implication of this protein in normal and malignant hematopoiesis.

Convolutional neural network models for cancer type prediction based on gene expression.

BACKGROUND: Precise prediction of cancer types is vital for cancer diagnosis and therapy. Through a predictive model, important cancer marker genes can be inferred. Several studies have attempted to build machine learning models for this task however none has taken into consideration the effects of tissue of origin that can potentially bias the identification of cancer markers. RESULTS: In this paper, we introduced several Convolutional Neural Network (CNN) models that take unstructured gene expression inputs to classify tumor and non-tumor samples into their designated cancer types or as normal. Based on different designs of gene embeddings and convolution schemes, we implemented three CNN models: 1D-CNN, 2D-Vanilla-CNN, and 2D-Hybrid-CNN. The models were trained and tested on gene expression profiles from combined 10,340 samples of 33 cancer types and 713 matched normal tissues of The Cancer Genome Atlas (TCGA). Our models achieved excellent prediction accuracies (93.9-95.0%) among 34 classes (33 cancers and normal). Furthermore, we interpreted one of the models, 1D-CNN model, with a guided saliency technique and identified a total of 2090 cancer markers (108 per class on average). The concordance of differential expression of these markers between the cancer type they represent and others is confirmed. In breast cancer, for instance, our model identified well-known markers, such as GATA3 and ESR1. Finally, we extended the 1D-CNN model for the prediction of breast cancer subtypes and achieved an average accuracy of 88.42% among 5 subtypes. The codes can be found at https://github.com/chenlabgccri/CancerTypePrediction. CONCLUSIONS: Here we present novel CNN designs for accurate and simultaneous cancer/normal and cancer types prediction based on gene expression profiles, and unique model interpretation scheme to elucidate biologically relevance of cancer marker genes after eliminating the effects of tissue-of-origin. The proposed model has light hyperparameters to be trained and thus can be easily adapted to facilitate cancer diagnosis in the future.