Exploration is a critical challenge in robotics, centered on understanding unknown environments. In this work, we focus on structured indoor environments, which often exhibit predictable, repeating patterns. Conventional frontier-based exploration approaches have difficulty leveraging this predictability, relying on simple heuristics such as ‘closest first’ for exploration. More recent deep learning-based methods predict unknown regions of the map for information gain computation, but these approaches are often sensitive to the predicted map quality or fail to account for sensor coverage. To overcome these issues, our key insight is to jointly reason over what the robot can observe and its uncertainty to calculate probabilistic information gain. We introduce MapEx, a new exploration framework that uses predicted maps to form probabilistic sensor model for information gain estimation. MapEx generates multiple predicted maps based on observed information, and takes into consideration both the computed variances of predicted maps and estimated visible area to estimate the information gain of a given viewpoint. Experiments on the real-world KTH dataset showed on average 12.4% improvement than representative map-prediction based exploration and 25.4% improvement than nearest frontier approach. Website: https://mapex-explorer.github.io/

Open-set semantic mapping is crucial for openworld robots. Current mapping approaches either are limited by the depth range or only map beyond-range entities in constrained settings, where overall they fail to combine within-range and beyond-range observations. Furthermore, these methods make a trade-off between fine-grained semantics and efficiency. We introduce RayFronts, a unified representation that enables both dense and beyond-range efficient semantic mapping. RayFronts encodes task-agnostic openset semantics to both in-range voxels and beyond-range rays encoded at map boundaries, empowering the robot to reduce search volumes significantly and make informed decisions both within & beyond sensory range, while running at 8.84 Hz on an Orin AGX. Benchmarking the within-range semantics shows that RayFronts’s fine-grained image encoding provides 1.34× zero-shot 3D semantic segmentation performance while improving throughput by 16.5×. Traditionally, online mapping performance is entangled with other system components, complicating evaluation. We propose a planner-agnostic evaluation framework that captures the utility for online beyond-range search and exploration, and show RayFronts reduces search volume 2.2× more efficiently than the closest online baselines.

Autonomous exploration in unknown environments requires estimating the information gain of an action to guide planning decisions. While prior approaches often compute information gain at discrete waypoints, pathwise integration offers a more comprehensive estimation but is often computationally challenging or infeasible and prone to overestimation. In this work, we propose the Pathwise Information Gain with Map Prediction for Exploration (PIPE) planner, which integrates cumulative sensor coverage along planned trajectories while leveraging map prediction to mitigate overestimation. To enable efficient pathwise coverage computation, we introduce a method to efficiently calculate the expected observation mask along the planned path, significantly reducing computational overhead. We validate PIPE on real-world floorplan datasets, demonstrating its superior performance over state-of-the-art baselines. Our results highlight the benefits of integrating predictive mapping with pathwise information gain for efficient and informed exploration. Website: pipe-planner.github.io

Interestingness recognition is crucial for decision making in autonomous exploration for mobile robots. Previous methods proposed an unsupervised online learning approach that can adapt to environments and detect interesting scenes quickly, but lack the ability to adapt to human-informed interesting objects. To solve this problem, we introduce a human-interactive framework, AirInteraction, that can detect human-informed objects via few-shot online learning. To reduce the communication bandwidth, we first apply an online unsupervised learning algorithm on the unmanned vehicle for interestingness recognition and then only send the potential interesting scenes to a base-station for human inspection. The human operator is able to draw and provide bounding box annotations for particular interesting objects, which are sent back to the robot to detect similar objects via few-shot learning. Only using few human-labeled examples, the robot can learn novel interesting object categories during the mission and detect interesting scenes that contain the objects. We evaluate our method on various interesting scene recognition datasets. To the best of our knowledge, it is the first human-informed few-shot object detection framework for autonomous exploration.

Autonomous robots frequently need to detect “interesting” scenes to decide on further exploration, or to decide which data to share for cooperation. These scenarios often require fast deployment with little or no training data. Prior work considers “interestingness” based on data from the same distribution. Instead, we propose to develop a method that automatically adapts online to the environment to report interesting scenes quickly. To address this problem, we develop a novel translation-invariant visual memory and design a three-stage architecture for long-term, short-term, and online learning, which enables the system to learn human-like experience, environmental knowledge, and online adaption, respectively. With this system, we achieve an average of 20% higher accuracy than the state-of-the-art unsupervised methods in a subterranean tunnel environment. We show comparable performance to supervised methods for robot exploration scenarios showing the efficacy of our approach. We expect that the presented method will play an important role in the robotic interestingness recognition exploration tasks.

Single-cell (scSeq) and single-nucleus sequencing (snSeq) are powerful tools to investigate cancer genomics at single cell resolution. Multiple studies have recently illuminated intratumoral heterogeneity in glioblastoma, however, the majority focused on molecular complexity of tumor cells, without considering unexplored host cell types that contribute to the microenvironment around tumor. To address the glioblastoma microenvironment composition and potential tumor-host interactions, we performed deep coverage sequencing of freshly resected primary GBM patient tissue without implementing any tumor enrichment strategies. The sequencing resulted in 902 cells and 1186 nuclei, respectively, passing quality control and with low mitochondrial gene percentage. We customized reference transcriptome by listing gene transcript loci as exons to take into account immature RNA, which greatly improved the alignment rate for single-nucleus data. We applied Cell Ranger pipelines (Version 3.0.2) and Seurat package (Version 2.3.1) and discovered 10 clusters in both scSeq and snSeq. Pathway analysis of each cluster signature in scSeq data along with known GBM microenvironment cell signatures revealed glioma tumor population along with surrounding microglia/macrophages, astrocytes, pericytes, oligodendrocytes, T cells and endothelial cells. The analysis of snSeq was able to capture the majority of cell types from patient tissues (tumor and microenvironment cells), but interestingly presented different cell type composition in microenvironment cell types such as microglia/macrophages. Integrating single-cell and single-nucleus transcriptomic data using canonical correlation analysis facilitated a comparison of snSeq and scSeq, contrasting depiction for certain cell types (e.g. NKX6-2 gene in Oligodendrocytes). Differential analysis of pathways between tumor and microenvironment cells unveiled potentially rewired pathways such as double strand break repair pathway. Our results demonstrate the cellular diversity of brain tumor microenvironment and lay a foundation to further investigate the individual tumor and host cell transcriptomes that are influenced not only by their cell identity but also by their interaction with surrounding microenvironment.

Deep Q-Network (DQN) is an algorithm that achieves human-level performance in complex domains like Atari games. One of the important elements of DQN is its use of a target network, which is necessary to stabilize learning. We argue that using a target network is incompatible with online reinforcement learning, and it is possible to achieve faster and more stable learning without a target network when we use Mellowmax, an alternative softmax operator. We derive novel properties of Mellowmax, and empirically show that the combination of DQN and Mellowmax, but without a target network, outperforms DQN with a target network.

EDDY (Evaluation of Differential DependencY) interrogates transcriptomic data to identify differential genetic dependencies within a biological pathway. Through its probabilistic framework with resampling and permutation, aided by the incorporation of annotated gene sets, EDDY demonstrated superior sensitivity to other methods. However, this statistical rigor incurs considerable computational cost, limiting its application to larger datasets. The ample and independent computation coupled with manageable memory footprint positioned EDDY as a strong candidate for graphical processing unit (GPU) implementation. Custom kernels decompose the independence test loop, network construction, network enumeration, and Bayesian network scoring to accelerate the computation. GPU-accelerated EDDY consistently exhibits two orders of magnitude in performance enhancement, allowing the statistical rigor of the EDDY algorithm to be applied to larger datasets.

BACKGROUND: Genomic analysis of drug response can provide unique insights into therapies that can be used to match the "right drug to the right patient." However, the process of discovering such therapeutic insights using genomic data is not straightforward and represents an area of active investigation. EDDY (Evaluation of Differential DependencY), a statistical test to detect differential statistical dependencies, is one method that leverages genomic data to identify differential genetic dependencies. EDDY has been used in conjunction with the Cancer Therapeutics Response Portal (CTRP), a dataset with drug-response measurements for more than 400 small molecules, and RNAseq data of cell lines in the Cancer Cell Line Encyclopedia (CCLE) to find potential drug-mediator pairs. Mediators were identified as genes that showed significant change in genetic statistical dependencies within annotated pathways between drug sensitive and drug non-sensitive cell lines, and the results are presented as a public web-portal (EDDY-CTRP). However, the interpretability of drug-mediator pairs currently hinders further exploration of these potentially valuable results. METHODS: In this study, we address this challenge by constructing evidence networks built with protein and drug interactions from the STITCH and STRING interaction databases. STITCH and STRING are sister databases that catalog known and predicted drug-protein interactions and protein-protein interactions, respectively. Using these two databases, we have developed a method to construct evidence networks to "explain" the relation between a drug and a mediator. RESULTS: We applied this approach to drug-mediator relations discovered in EDDY-CTRP analysis and identified evidence networks for ~70% of drug-mediator pairs where most mediators were not known direct targets for the drug. Constructed evidence networks enable researchers to contextualize the drug-mediator pair with current research and knowledge. Using evidence networks, we were able to improve the interpretability of the EDDY-CTRP results by linking the drugs and mediators with genes associated with both the drug and the mediator. CONCLUSION: We anticipate that these evidence networks will help inform EDDY-CTRP results and enhance the generation of important insights to drug sensitivity that will lead to improved precision medicine applications.

BACKGROUND: Breast cancer is a highly heterogeneous disease with respect to molecular alterations and cellular composition making therapeutic and clinical outcome unpredictable. This diversity creates a significant challenge in developing tumor classifications that are clinically reliable with respect to prognosis prediction. RESULTS: This paper describes an unsupervised context analysis to infer context-specific gene regulatory networks from 1,614 samples obtained from publicly available gene expression data, an extension of a previously published methodology. We use the context-specific gene regulatory networks to classify the tumors into clinically relevant subgroups, and provide candidates for a finer sub-grouping of the previously known intrinsic tumors with a focus on Basal-like tumors. Our analysis of pathway enrichment in the key contexts provides an insight into the biological mechanism underlying the identified subtypes of breast cancer. CONCLUSIONS: The use of context-specific gene regulatory networks to identify biological contexts from heterogenous breast cancer data set was able to identify genomic drivers for subgroups within the previously reported intrinsic subtypes. These subgroups (contexts) uphold the clinical relevant features for the intrinsic subtypes and were associated with increased survival differences compared to the intrinsic subtypes. We believe our computational approach led to the generation of novel rationalized hypotheses to explain mechanisms of disease progression within sub-contexts of breast cancer that could be therapeutically exploited once validated.

Modeling the dynamics of biological processes has recently become an important research topic in computational biology and systems engineering. One of the most important reasons to model a biological process is to enable high-throughput in-silico experiments that attempt to predict or intervene in the process. These experiments can help accelerate the design of therapies through their rapid and inexpensive replication and alteration. While some techniques exist for reasoning with biological processes, few take advantage of the flexible and scalable algorithms popular in AI research. In reasoning about interventions in biological processes, where scalability is crucial for feasible application, we apply AI planning-based search techniques and demonstrate their advantage over existing enumerative methods. We also present a novel formulation of intervention planning that relies on models that characterize and attempt to change the phenotype of a system. We study three biological systems: the yeast cell cycle, a model of the human aging process, and the Wnt5a network governing the metastasis of melanoma in humans. The contribution of our investigation is in demonstrating that: (i) prior approaches, based on dynamic programming, cannot scale as well as heuristic search, and (ii) the newly found scalability enables us to plan previously unknown sequences of interventions that reveal novel and biologically significant responses in the systems which are consistent with biological knowledge in the literature.

MicroRNAs are small non-coding RNAs of 21-25 nucleotides that might impact regulatory mechanisms in cancer. Due to their influence on cell physiology, alteration of miRNA regulation can be implicated in carcinogenesis and disease progression. In general, one miRNA is predicted to regulate several hundred genes, and as a result, miRNA profiling could serve as a better classifier than gene expression profiling.More than 50% of brain metastasis (brain mets) are associated with non-small cell lung cancer (NSCLC). As miRNAs can regulate certain genes, the presence or absence of certain miRNA could lead to oncogene potential for brain mets. In this study, we combine validated miRNA expression values with imaging features to separate NSCLC brain mets from non-brain mets and identify biomarkers that may indicate possibility of brain mets. This research involves comprehensive miRNA expression profiling, validation of miRNA with qRT-PCR, correlation of miRNA with imaging features such as PET/CT and CT scan. Eleven statistically significant miRNA were identified and matched with imaging features to yield a class separation of brain mets and non-brain mets.

Many researchers are investigating the possibility of utilizing global gene expression profile data as a platform to infer gene regulatory networks. However, heavy computational burden and measurement noises render these efforts difficult and approaches based on quantized levels are vigorously investigated as an alternative. Methods based on quantized values require a procedure to convert continuous expression values into discrete ones. Although there have been algorithms to quantize values into multiple discrete states, these algorithms assumed strict state mixtures (SSM,) so that all expression profiles were divided into pre-specified number of states. We propose two novel quantization algorithms (QAs), model-based quantization algorithm and model-free quantization algorithm that generalize SSM algorithms in two major aspects. First, our QAs assume the maximum number of expression states (Es) be arbitrary. Second, expression profiles can exhibit any combinations of Espossible states. In this paper, we compare the performances between SSM algorithms and QAs using simulation studies as well as applications to actual data and show that quantizing gene expression data using adaptive algorithms is an effective way to reduce data complexity without sacrificing much of essential information

MOTIVATION: A number of models have been proposed for genetic regulatory networks. In principle, a network may contain any number of genes, so long as data are available to make inferences about their relationships. Nevertheless, there are two important reasons why the size of a constructed network should be limited. Computationally and mathematically, it is more feasible to model and simulate a network with a small number of genes. In addition, it is more likely that a small set of genes maintains a specific core regulatory mechanism. RESULTS: Subnetworks are constructed in the context of a directed graph by beginning with a seed consisting of one or more genes believed to participate in a viable subnetwork. Functionalities and regulatory relationships among seed genes may be partially known or they may simply be of interest. Given the seed, we iteratively adjoin new genes in a manner that enhances subnetwork autonomy. The algorithm is applied using both the coefficient of determination and the Boolean-function influence among genes, and it is illustrated using a glioma gene-expression dataset. AVAILABILITY: Software for the seed-growing algorithm will be available at the website for Probabilistic Boolean Networks: http://www2.mdanderson.org/app/ilya/PBN/PBN.htm

MOTIVATION: A major problem of pattern classification is estimation of the Bayes error when only small samples are available. One way to estimate the Bayes error is to design a classifier based on some classification rule applied to sample data, estimate the error of the designed classifier, and then use this estimate as an estimate of the Bayes error. Relative to the Bayes error, the expected error of the designed classifier is biased high, and this bias can be severe with small samples. RESULTS: This paper provides a correction for the bias by subtracting a term derived from the representation of the estimation error. It does so for Boolean classifiers, these being defined on binary features. Although the general theory applies to any Boolean classifier, a model is introduced to reduce the number of parameters. A key point is that the expected correction is conservative. Properties of the corrected estimate are studied via simulation. The correction applies to binary predictors because they are mathematically identical to Boolean classifiers. In this context the correction is adapted to the coefficient of determination, which has been used to measure nonlinear multivariate relations between genes and design genetic regulatory networks. An application using gene-expression data from a microarray experiment is provided on the website http://gspsnap.tamu.edu/smallsample/ (user:'smallsample', password:'smallsample)').

MOTIVATION: Our goal is to construct a model for genetic regulatory networks such that the model class: (i) incorporates rule-based dependencies between genes; (ii) allows the systematic study of global network dynamics; (iii) is able to cope with uncertainty, both in the data and the model selection; and (iv) permits the quantification of the relative influence and sensitivity of genes in their interactions with other genes. RESULTS: We introduce Probabilistic Boolean Networks (PBN) that share the appealing rule-based properties of Boolean networks, but are robust in the face of uncertainty. We show how the dynamics of these networks can be studied in the probabilistic context of Markov chains, with standard Boolean networks being special cases. Then, we discuss the relationship between PBNs and Bayesian networks--a family of graphical models that explicitly represent probabilistic relationships between variables. We show how probabilistic dependencies between a gene and its parent genes, constituting the basic building blocks of Bayesian networks, can be obtained from PBNs. Finally, we present methods for quantifying the influence of genes on other genes, within the context of PBNs. Examples illustrating the above concepts are presented throughout the paper.