FLAN: feature-wise latent additive neural models for biological applications.

MOTIVATION: Interpretability has become a necessary feature for machine learning models deployed in critical scenarios, e.g. legal system, healthcare. In these situations, algorithmic decisions may have (potentially negative) long-lasting effects on the end-user affected by the decision. While deep learning models achieve impressive results, they often function as a black-box. Inspired by linear models, we propose a novel class of structurally constrained deep neural networks, which we call FLAN (Feature-wise Latent Additive Networks). Crucially, FLANs process each input feature separately, computing for each of them a representation in a common latent space. These feature-wise latent representations are then simply summed, and the aggregated representation is used for the prediction. These feature-wise representations allow a user to estimate the effect of each individual feature independently from the others, similarly to the way linear models are interpreted. RESULTS: We demonstrate FLAN on a series of benchmark datasets in different biological domains. Our experiments show that FLAN achieves good performances even in complex datasets (e.g. TCR-epitope binding prediction), despite the structural constraint we imposed. On the other hand, this constraint enables us to interpret FLAN by deciphering its decision process, as well as obtaining biological insights (e.g. by identifying the marker genes of different cell populations). In supplementary experiments, we show similar performances also on non-biological datasets. CODE AND DATA AVAILABILITY: Code and example data are available at https://github.com/phineasng/flan_bio.

PCfun: a hybrid computational framework for systematic characterization of protein complex function.

In molecular biology, it is a general assumption that the ensemble of expressed molecules, their activities and interactions determine biological function, cellular states and phenotypes. Stable protein complexes-or macromolecular machines-are, in turn, the key functional entities mediating and modulating most biological processes. Although identifying protein complexes and their subunit composition can now be done inexpensively and at scale, determining their function remains challenging and labor intensive. This study describes Protein Complex Function predictor (PCfun), the first computational framework for the systematic annotation of protein complex functions using Gene Ontology (GO) terms. PCfun is built upon a word embedding using natural language processing techniques based on 1 million open access PubMed Central articles. Specifically, PCfun leverages two approaches for accurately identifying protein complex function, including: (i) an unsupervised approach that obtains the nearest neighbor (NN) GO term word vectors for a protein complex query vector and (ii) a supervised approach using Random Forest (RF) models trained specifically for recovering the GO terms of protein complex queries described in the CORUM protein complex database. PCfun consolidates both approaches by performing a hypergeometric statistical test to enrich the top NN GO terms within the child terms of the GO terms predicted by the RF models. The documentation and implementation of the PCfun package are available at https://github.com/sharmavaruns/PCfun. We anticipate that PCfun will serve as a useful tool and novel paradigm for the large-scale characterization of protein complex function.

DECODE: a computational pipeline to discover T cell receptor binding rules.

MOTIVATION: Understanding the mechanisms underlying T cell receptor (TCR) binding is of fundamental importance to understanding adaptive immune responses. A better understanding of the biochemical rules governing TCR binding can be used, e.g. to guide the design of more powerful and safer T cell-based therapies. Advances in repertoire sequencing technologies have made available millions of TCR sequences. Data abundance has, in turn, fueled the development of many computational models to predict the binding properties of TCRs from their sequences. Unfortunately, while many of these works have made great strides toward predicting TCR specificity using machine learning, the black-box nature of these models has resulted in a limited understanding of the rules that govern the binding of a TCR and an epitope. RESULTS: We present an easy-to-use and customizable computational pipeline, DECODE, to extract the binding rules from any black-box model designed to predict the TCR-epitope binding. DECODE offers a range of analytical and visualization tools to guide the user in the extraction of such rules. We demonstrate our pipeline on a recently published TCR-binding prediction model, TITAN, and show how to use the provided metrics to assess the quality of the computed rules. In conclusion, DECODE can lead to a better understanding of the sequence motifs that underlie TCR binding. Our pipeline can facilitate the investigation of current immunotherapeutic challenges, such as cross-reactive events due to off-target TCR binding. AVAILABILITY AND IMPLEMENTATION: Code is available publicly at https://github.com/phineasng/DECODE. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

COSIFER: a Python package for the consensus inference of molecular interaction networks.

SUMMARY: The advent of high-throughput technologies has provided researchers with measurements of thousands of molecular entities and enable the investigation of the internal regulatory apparatus of the cell. However, network inference from high-throughput data is far from being a solved problem. While a plethora of different inference methods have been proposed, they often lead to non-overlapping predictions, and many of them lack user-friendly implementations to enable their broad utilization. Here, we present Consensus Interaction Network Inference Service (COSIFER), a package and a companion web-based platform to infer molecular networks from expression data using state-of-the-art consensus approaches. COSIFER includes a selection of state-of-the-art methodologies for network inference and different consensus strategies to integrate the predictions of individual methods and generate robust networks. AVAILABILITY AND IMPLEMENTATION: COSIFER Python source code is available at https://github.com/PhosphorylatedRabbits/cosifer. The web service is accessible at https://ibm.biz/cosifer-aas. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

The number of titrated microRNA species dictates ceRNA regulation.

microRNAs (miRNAs) play key roles in cancer, but their propensity to couple their targets as competing endogenous RNAs (ceRNAs) has only recently emerged. Multiple models have studied ceRNA regulation, but these models did not account for the effects of co-regulation by miRNAs with many targets. We modeled ceRNA and simulated its effects using established parameters for miRNA/mRNA interaction kinetics while accounting for co-regulation by multiple miRNAs with many targets. Our simulations suggested that co-regulation by many miRNA species is more likely to produce physiologically relevant context-independent couplings. To test this, we studied the overlap of inferred ceRNA networks from four tumor contexts-our proposed pan-cancer ceRNA interactome (PCI). PCI was composed of interactions between genes that were co-regulated by nearly three-times as many miRNAs as other inferred ceRNA interactions. Evidence from expression-profiling datasets suggested that PCI interactions are predictive of gene expression in 12 independent tumor- and non-tumor contexts. Biochemical assays confirmed ceRNA couplings for two PCI subnetworks, including oncogenes CCND1, HIF1A and HMGA2, and tumor suppressors PTEN, RB1 and TP53. Our results suggest that PCI is enriched for context-independent interactions that are coupled by many miRNA species and are more likely to be context independent.

High-throughput validation of ceRNA regulatory networks.

BACKGROUND: MicroRNAs (miRNAs) play multiple roles in tumor biology. Interestingly, reports from multiple groups suggest that miRNA targets may be coupled through competitive stoichiometric sequestration. Specifically, computational models predicted and experimental assays confirmed that miRNA activity is dependent on miRNA target abundance, and consequently, changes in the abundance of some miRNA targets lead to changes to the regulation and abundance of their other targets. The resulting indirect regulatory influence between miRNA targets resembles competition and has been dubbed competitive endogenous RNA (ceRNA). Recent studies have questioned the physiological relevance of ceRNA interactions, our ability to accurately predict these interactions, and the number of genes that are impacted by ceRNA interactions in specific cellular contexts. RESULTS: To address these concerns, we reverse engineered ceRNA networks (ceRNETs) in breast and prostate adenocarcinomas using context-specific TCGA profiles, and tested whether ceRNA interactions can predict the effects of RNAi-mediated gene silencing perturbations in PC3 and MCF7 cells._ENREF_22 Our results, based on tests of thousands of inferred ceRNA interactions that are predicted to alter hundreds of cancer genes in each of the two tumor contexts, confirmed statistically significant effects for half of the predicted targets. CONCLUSIONS: Our results suggest that the expression of a significant fraction of cancer genes may be regulated by ceRNA interactions in each of the two tumor contexts.

Quantitative modeling of the terminal differentiation of B cells and mechanisms of lymphomagenesis.

Mature B-cell exit from germinal centers is controlled by a transcriptional regulatory module that integrates antigen and T-cell signals and, ultimately, leads to terminal differentiation into memory B cells or plasma cells. Despite a compact structure, the module dynamics are highly complex because of the presence of several feedback loops and self-regulatory interactions, and understanding its dysregulation, frequently associated with lymphomagenesis, requires robust dynamical modeling techniques. We present a quantitative kinetic model of three key gene regulators, BCL6, IRF4, and BLIMP, and use gene expression profile data from mature human B cells to determine appropriate model parameters. The model predicts the existence of two different hysteresis cycles that direct B cells through an irreversible transition toward a differentiated cellular state. By synthetically perturbing the interactions in this network, we can elucidate known mechanisms of lymphomagenesis and suggest candidate tumorigenic alterations, indicating that the model is a valuable quantitative tool to simulate B-cell exit from the germinal center under a variety of physiological and pathological conditions.

Therapeutic aphaeresis: experience in Puerto Rico.

The Puerto Rico (PR) Region of the American Red Cross (ARC) evaluated the therapeutic aphaeresis program and we conducted 1609 procedures in 30 months between 2011 and 2013. The primary objective of the present review was to demonstrate our data and compare it to the reviewed medical evidence regarding the adequacy of applying therapeutic aphaeresis (TA) for chosen indications based on data in the literature. It was concluded that our service is very active and appropriate, and the number of TA's done varies and it's not steady year-by-year. The indications are the same as most common indicators across the World and the adverse reactions are too. We are the only ones doing apheresis in the pediatric population of PR. No deaths have been reported from our procedures. We understand that clinicians do not have enough knowledge about TA and tend to apply TA's in many cases as a last resort treatment for many diseases. Education at medical faculties and of hospital staff (nurses and medical technologists) about TA is very important. There is a need for symposia about this topic to the medical and general community.

Stochastic modeling of a gene regulatory network driving B cell development in germinal centers.

Germinal centers (GCs) are the key histological structures of the adaptive immune system, responsible for the development and selection of B cells producing high-affinity antibodies against antigens. Due to their level of complexity, unexpected malfunctioning may lead to a range of pathologies, including various malignant formations. One promising way to improve the understanding of malignant transformation is to study the underlying gene regulatory networks (GRNs) associated with cell development and differentiation. Evaluation and inference of the GRN structure from gene expression data is a challenging task in systems biology: recent achievements in single-cell (SC) transcriptomics allow the generation of SC gene expression data, which can be used to sharpen the knowledge on GRN structure. In order to understand whether a particular network of three key gene regulators (BCL6, IRF4, BLIMP1), influenced by two external stimuli signals (surface receptors BCR and CD40), is able to describe GC B cell differentiation, we used a stochastic model to fit SC transcriptomic data from a human lymphoid organ dataset. The model is defined mathematically as a piecewise-deterministic Markov process. We showed that after parameter tuning, the model qualitatively recapitulates mRNA distributions corresponding to GC and plasmablast stages of B cell differentiation. Thus, the model can assist in validating the GRN structure and, in the future, could lead to better understanding of the different types of dysfunction of the regulatory mechanisms.

Gene Network Analyses Identify Co-regulated Transcription Factors and BACH1 as a Key Driver in Rheumatoid Arthritis Fibroblast-like Synoviocytes.

RNA-sequencing and differential gene expression studies have significantly advanced our understanding of pathogenic pathways underlying Rheumatoid Arthritis (RA). Yet, little is known about cell-specific regulatory networks and their contributions to disease. In this study, we focused on fibroblast-like synoviocytes (FLS), a cell type central to disease pathogenesis and joint damage in RA. We used a strategy that computed sample-specific gene regulatory networks (GRNs) to compare network properties between RA and osteoarthritis FLS. We identified 28 transcription factors (TFs) as key regulators central to the signatures of RA FLS. Six of these TFs are new and have not been previously implicated in RA, and included BACH1, HLX, and TGIF1. Several of these TFs were found to be co-regulated, and BACH1 emerged as the most significant TF and regulator. The main BACH1 targets included those implicated in fatty acid metabolism and ferroptosis. The discovery of BACH1 was validated in experiments with RA FLS. Knockdown of BACH1 in RA FLS significantly affected the gene expression signatures, reduced cell adhesion and mobility, interfered with the formation of thick actin fibers, and prevented the polarized formation of lamellipodia, all required for the RA destructive behavior of FLS. This is the first time that BACH1 is shown to have a central role in the regulation of FLS phenotypes, and gene expression signatures, as well as in ferroptosis and fatty acid metabolism. These new discoveries have the potential to become new targets for treatments aimed at selectively targeting the RA FLS.

Input output robustness in simple bacterial signaling systems.

Biological signaling systems produce an output, such as the level of a phosphorylated protein, in response to defined input signals. The output level as a function of the input level is called the system's input-output relation. One may ask whether this input-output relation is sensitive to changes in the concentrations of the system's components, such as proteins and ATP. Because component concentrations often vary from cell to cell, it might be expected that the input-output relation will likewise vary. If this is the case, different cells exposed to the same input signal will display different outputs. Such variability can be deleterious in systems where survival depends on accurate match of output to input. Here we suggest a mechanism that can provide input-output robustness, that is, an input-output relation that does not depend on variations in the concentrations of any of the system's components. The mechanism is based on certain bacterial signaling systems. It explains how specific molecular details can work together to provide robustness. Moreover, it suggests an approach that can help identify a wide family of nonequilibrium mechanisms that potentially have robust input-output relations.

FPGA Accelerated Analysis of Boolean Gene Regulatory Networks.

Boolean models are a powerful abstraction for qualitative modeling of gene regulatory networks. With the recent availability of advanced high-throughput technologies, Boolean models have increasingly grown in size and complexity, posing a challenge for existing software simulation tools that have not scaled at the same speed. Field Programmable Gate Arrays (FPGAs) are powerful reconfigurable integrated circuits that can offer massive performance improvements. Due to their highly parallel nature, FPGAs are well suited to simulate complex molecular networks. We present here a new simulation framework for Boolean models, which first converts the model to Verilog, a standardized hardware description language, and then connects it to an execution core that runs on an FPGA coherently attached to a POWER8 processor. We report an order of magnitude speedup over a multi-threaded software simulation tool running on the same processor on a selection of Boolean models. Analysis on a T-cell large granular lymphocyte leukemia (T-LGL) demonstrates that our framework achieves consistent performance improvements resulting in new biological insights. In addition, we show that our solution allows to perform attractor detection at an unprecedented speed, exhibiting a speedup ranging from one to three orders of magnitude compared to alternative software solutions.

Inferring clonal composition from multiple tumor biopsies.

Knowledge about the clonal evolution of a tumor can help to interpret the function of its genetic alterations by identifying initiating events and events that contribute to the selective advantage of proliferative, metastatic, and drug-resistant subclones. Clonal evolution can be reconstructed from estimates of the relative abundance (frequency) of subclone-specific alterations in tumor biopsies, which, in turn, inform on its composition. However, estimating these frequencies is complicated by the high genetic instability that characterizes many cancers. Models for genetic instability suggest that copy number alterations (CNAs) can influence mutation-frequency estimates and thus impede efforts to reconstruct tumor phylogenies. Our analysis suggested that accurate mutation frequency estimates require accounting for CNAs-a challenging endeavour using the genetic profile of a single tumor biopsy. Instead, we propose an optimization algorithm, Chimæra, to account for the effects of CNAs using profiles of multiple biopsies per tumor. Analyses of simulated data and tumor profiles suggested that Chimæra estimates are consistently more accurate than those of previously proposed methods and resulted in improved phylogeny reconstructions and subclone characterizations. Our analyses inferred recurrent initiating mutations in hepatocellular carcinomas, resolved the clonal composition of Wilms' tumors, and characterized the acquisition of mutations in drug-resistant prostate cancers.

Multiscale Modeling of Germinal Center Recapitulates the Temporal Transition From Memory B Cells to Plasma Cells Differentiation as Regulated by Antigen Affinity-Based Tfh Cell Help.

Germinal centers play a key role in the adaptive immune system since they are able to produce memory B cells and plasma cells that produce high affinity antibodies for an effective immune protection. The mechanisms underlying cell-fate decisions are not well understood but asymmetric division of antigen, B-cell receptor affinity, interactions between B-cells and T follicular helper cells (triggering CD40 signaling), and regulatory interactions of transcription factors have all been proposed to play a role. In addition, a temporal switch from memory B-cell to plasma cell differentiation during the germinal center reaction has been shown. To investigate if antigen affinity-based Tfh cell help recapitulates the temporal switch we implemented a multiscale model that integrates cellular interactions with a core gene regulatory network comprising BCL6, IRF4, and BLIMP1. Using this model we show that affinity-based CD40 signaling in combination with asymmetric division of B-cells result in switch from memory B-cell to plasma cell generation during the course of the germinal center reaction. We also show that cell fate division is unlikely to be (solely) based on asymmetric division of Ag but that BLIMP1 is a more important factor. Altogether, our model enables to test the influence of molecular modulations of the CD40 signaling pathway on the production of germinal center output cells.

Convergent network effects along the axis of gene expression during prostate cancer progression.

BACKGROUND: Tumor-specific genomic aberrations are routinely determined by high-throughput genomic measurements. It remains unclear how complex genome alterations affect molecular networks through changing protein levels and consequently biochemical states of tumor tissues. RESULTS: Here, we investigate the propagation of genomic effects along the axis of gene expression during prostate cancer progression. We quantify genomic, transcriptomic, and proteomic alterations based on 105 prostate samples, consisting of benign prostatic hyperplasia regions and malignant tumors, from 39 prostate cancer patients. Our analysis reveals the convergent effects of distinct copy number alterations impacting on common downstream proteins, which are important for establishing the tumor phenotype. We devise a network-based approach that integrates perturbations across different molecular layers, which identifies a sub-network consisting of nine genes whose joint activity positively correlates with increasingly aggressive tumor phenotypes and is predictive of recurrence-free survival. Further, our data reveal a wide spectrum of intra-patient network effects, ranging from similar to very distinct alterations on different molecular layers. CONCLUSIONS: This study uncovers molecular networks with considerable convergent alterations across tumor sites and patients. It also exposes a diversity of network effects: we could not identify a single sub-network that is perturbed in all high-grade tumor regions.

Transient transcriptional responses to stress are generated by opposing effects of mRNA production and degradation.

The state of the transcriptome reflects a balance between mRNA production and degradation. Yet how these two regulatory arms interact in shaping the kinetics of the transcriptome in response to environmental changes is not known. We subjected yeast to two stresses, one that induces a fast and transient response, and another that triggers a slow enduring response. We then used microarrays following transcriptional arrest to measure genome-wide decay profiles under each condition. We found condition-specific changes in mRNA decay rates and coordination between mRNA production and degradation. In the transient response, most induced genes were surprisingly destabilized, whereas repressed genes were somewhat stabilized, exhibiting counteraction between production and degradation. This strategy can reconcile high steady-state level with short response time among induced genes. In contrast, the stress that induces the slow response displays the more expected behavior, whereby most induced genes are stabilized, and repressed genes are destabilized. Our results show genome-wide interplay between mRNA production and degradation, and that alternative modes of such interplay determine the kinetics of the transcriptome in response to stress.

Network-based Biased Tree Ensembles (NetBiTE) for Drug Sensitivity Prediction and Drug Sensitivity Biomarker Identification in Cancer.

We present the Network-based Biased Tree Ensembles (NetBiTE) method for drug sensitivity prediction and drug sensitivity biomarker identification in cancer using a combination of prior knowledge and gene expression data. Our devised method consists of a biased tree ensemble that is built according to a probabilistic bias weight distribution. The bias weight distribution is obtained from the assignment of high weights to the drug targets and propagating the assigned weights over a protein-protein interaction network such as STRING. The propagation of weights, defines neighborhoods of influence around the drug targets and as such simulates the spread of perturbations within the cell, following drug administration. Using a synthetic dataset, we showcase how application of biased tree ensembles (BiTE) results in significant accuracy gains at a much lower computational cost compared to the unbiased random forests (RF) algorithm. We then apply NetBiTE to the Genomics of Drug Sensitivity in Cancer (GDSC) dataset and demonstrate that NetBiTE outperforms RF in predicting IC50 drug sensitivity, only for drugs that target membrane receptor pathways (MRPs): RTK, EGFR and IGFR signaling pathways. We propose based on the NetBiTE results, that for drugs that inhibit MRPs, the expression of target genes prior to drug administration is a biomarker for IC50 drug sensitivity following drug administration. We further verify and reinforce this proposition through control studies on, PI3K/MTOR signaling pathway inhibitors, a drug category that does not target MRPs, and through assignment of dummy targets to MRP inhibiting drugs and investigating the variation in NetBiTE accuracy.

CellCycleTRACER accounts for cell cycle and volume in mass cytometry data.

Recent studies have shown that cell cycle and cell volume are confounding factors when studying biological phenomena in single cells. Here we present a combined experimental and computational method, CellCycleTRACER, to account for these factors in mass cytometry data. CellCycleTRACER is applied to mass cytometry data collected on three different cell types during a TNFα stimulation time-course. CellCycleTRACER reveals signaling relationships and cell heterogeneity that were otherwise masked.

Depletion of FOXM1 via MET Targeting Underlies Establishment of a DNA Damage-Induced Senescence Program in Gastric Cancer.

PURPOSE: Deregulated signaling via the MET receptor tyrosine kinase is abundant in gastric tumors, with up to 80% of cases displaying aberrant MET expression. A growing body of evidence suggests MET as a potential target for tumor radiosensitization. EXPERIMENTAL DESIGN: Cellular proliferation and DNA damage-induced senescence were studied in a panel of MET-overexpressing human gastric cancer cell lines as well as in xenograft models after MET inhibition and/or ionizing radiation. Pathways activation and protein expression were assessed by immunoblotting and immunohistochemistry. Tumor tissue microarrays (91 gastric cancer patients) were generated and copy number alteration (178 patients) and gene expression (373 patients) data available at The Cancer Genome Atlas were analyzed to assess the coalterations of MET and FOXM1. RESULTS: MET targeting administered before ionizing radiation instigates DNA damage-induced senescence (∼80%, P < 0.001) rather than cell death. MET inhibition-associated senescence is linked to the blockade of MAPK pathway, correlates with downregulation of FOXM1, and can be abrogated (11.8% vs. 95.3%, P < 0.001) by ectopic expression of FOXM1 in the corresponding gastric tumor cells. Cells with ectopic FOXM1 expression demonstrate considerable (∼20%, P < 0.001) growth advantage despite MET targeting, suggesting a novel clinically relevant resistance mechanism to MET inhibition as the copresence of both MET and FOXM1 protein (33%) and mRNA (30%) overexpression as well as gene amplification (24,7%) are common in patients with gastric cancer. CONCLUSIONS: FOXM1, a negative regulator of senescence, has been identified as a key downstream effector and potential clinical biomarker that mediates MET signaling following infliction of DNA damage in gastric tumors. Clin Cancer Res; 22(21); 5322-36. ©2016 AACR.