Natural language is the most intuitive means for humans to interact with robots, making task planning based on natural language commands a longstanding area of research. Large language models (LLMs) have significantly improved task planning by enhancing understanding of language and common sense. However, current methods still face several challenges: they lack a deep understanding of physical environments, their performance relies heavily on prompt examples, LLMs are oversized and not customized for specific tasks, and the planning costs remain high. To overcome these issues, we introduce the GNN-Transformer Task Planner (GTTP), designed to predict task-level actions by leveraging the semantic environment and incorporating historical state data. The GTTP architecture is scalable through the use of GNN layers, while transformer layers facilitate understanding task progression. In addition, our model uses a text encoder to embed environments, allowing it to be trained on simulated datasets and applied directly in real-world scenarios. We also propose an automated data generation method that includes semantic augmentation, planning verification, and instruction generation via LLM. This method enables the collection of 14k instruction-annotated tasks in the VirtualHome environment with minimal human effort. The model has been validated across diverse scenes containing up to 715 objects, achieving significantly higher success rates compared to baseline models. It has also been successfully deployed on a physical mobile manipulator, demonstrating its practical applicability and effectiveness.

Deep neural network (DNN)-based policy models, such as vision-language-action (VLA) models, excel at automating complex decision-making from multi-modal inputs. However, scaling these models greatly increases computational overhead, complicating deployment in resource-constrained settings like robot manipulation and autonomous driving. To address this, we propose Saliency-Aware Quantized Imitation Learning (SQIL), which combines quantization-aware training with a selective loss-weighting strategy for mission-critical states. By identifying these states via saliency scores and emphasizing them in the training loss, SQIL preserves decision fidelity under low-bit precision. We validate SQIL's generalization capability across extensive simulation benchmarks with environment variations, real-world tasks, and cross-domain tasks (self-driving, physics simulation), consistently recovering full-precision performance. Notably, a 4-bit weight-quantized VLA model for robotic manipulation achieves up to 2.5x speedup and 2.5x energy savings on an edge GPU with minimal accuracy loss. These results underline SQIL's potential for efficiently deploying large IL-based policy models on resource-limited devices.

This paper proposes an adaptive shuttering scheme to overcome the speed dependent distortion in swipe-type fingerprint sensor. Adaptive shuttering is achieved by displacement measurement based on pattern matching for two line images obtained from two rows of pixels. A compact, low-power pattern matching circuit is proposed as well. The proposed adaptive scheme was adopted to optical swipe-type fingerprint sensor to verify. The sensor was fabricated with 90nm CMOS process. The total area of the prototype sensor is only 3200μm×160μm and consumes 3.2mW. Experimental results demonstrate that the prototype chip produces speed-artifact-free image with 40μm×40μm resolution despite of irregular finger motion.

SUMMARY: Mislabeling in the process of next generation sequencing is a frequent problem that can cause an entire genomic analysis to fail, and a regular cohort-level checkup is needed to ensure that it has not occurred. We developed a new, automated tool (BAMixChecker) that accurately detects sample mismatches from a given BAM file cohort with minimal user intervention. BAMixChecker uses a flexible, data-specific set of single-nucleotide polymorphisms and detects orphan (unpaired) and swapped (mispaired) samples based on genotype-concordance score and entropy-based file name analysis. BAMixChecker shows ∼100% accuracy in real WES, RNA-Seq and targeted sequencing data cohorts, even for small panels (<50 genes). BAMixChecker provides an HTML-style report that graphically outlines the sample matching status in tables and heatmaps, with which users can quickly inspect any mismatch events. AVAILABILITY AND IMPLEMENTATION: BAMixChecker is available at https://github.com/heinc1010/BAMixChecker. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Malware using document files as an attack vector has continued to increase and now constitutes a large portion of phishing attacks. To avoid anti-virus detection, malware writers usually implement obfuscation techniques in their source code. Although obfuscation is related to malicious code detection, little research has been conducted on obfuscation with regards to Visual Basic for Applications (VBA) macros. In this paper, we summarize the obfuscation techniques and propose an obfuscated macro code detection method using five machine learning classifiers. To train these classifiers, our proposed method uses 15 discriminant static features, taking into account the characteristics of the VBA macros. We evaluated our approach using a real-world dataset of obfuscated and non-obfuscated VBA macros extracted from Microsoft Office document files. The experimental results demonstrate that our detection approach achieved a F2 score improvement of greater than 23% compared to those of related studies.

Summary: Ion Torrent sequencing is one of the most frequently used platforms in healthcare research and industry. Despite many advantages, platform-specific artifacts complicate efficient separation of true variants from errors, especially in variants with lower allele frequencies (<15%). Here, we developed a multi-step filtering toolbox AIRVF that works on flowgram, raw and mapped reads and called variants to reduce artifact-driven false variant calls. Tests on sequencing data of standard reference material showed up to ∼98% reduction of false variants when combined to conventional public pipelines and ∼48% to the in-house commercial solution, with a minimal loss of sensitivity. Availability and implementation: The program with a detailed manual is available at https://sourceforge.net/projects/airvf/. Contact: [email protected]. Supplementary information: Supplementary data are available at Bioinformatics online.

BACKGROUND: Aberrant mutations in KRAS play a critical role in tumor initiation and progression, and are a negative prognosis factor in lung adenocarcinoma (LUAD). RESULTS: Using genomic analysis for K-Ras isoforms (K-Ras4A and K-Ras4B) and large-scale multi-omics data, we inspected the overall survival (OS) and disease-free survival (DFS) of LUAD patients based on the abundance of transcript variants by analyzing RNA expression and somatic mutation data from The Cancer Genome Atlas (n = 516). The expression of the minor transcript K-Ras4A and its proportion were positively correlated with the presence of KRAS mutations in LUAD. We found that both K-Ras4A abundance measures (expression and proportion) have a strong association with poor OS (p = 0.0149 and p = 3.18E-3, respectively) and DFS (p = 3.03E-4 and p = 0.0237, respectively), but only in patients harboring KRAS mutations. A Cox regression analysis showed significant results in groups with low expression (hazard ratio (HR) = 2.533, 95% confidence interval (CI) = 1.380-4.651, p = 2.72E-3) and low proportion (HR = 2.549, 95% CI = 1.387-4.684, p = 2.58E-3) of K-Ras4A. CONCLUSIONS: Based on the above results, we report the possible use of abundance measures for K-Ras4A for predicting the survival of LUAD patients with KRAS mutations.

The size and power dissipation of an infrared imaging system can be reduced by the use of uncooled microbolometers; but the nonuniformity of the microbolometer makes such imaging systems heavily reliant on complicated calibration techniques, incurring an overhead which is particularly significant in low-cost, compact devices. We therefore propose a shutter-based successive-approximation calibration loop, which avoids the need to implement correction tables in software on an external processor. Prototype imager, consisting of an 80 × 82 pixel infrared focal-plane array and readout circuitry, has been implemented, and the experimental results confirm that our on-chip autocalibration approach compensates effectively for fixed pattern noise caused by the nonuniformity of the microbolometers.

Started in 2006 as a specialized workshop in the field of text mining applied to biomedical informatics, DTMBIO (ACM international workshop on Data and Text Mining in Biomedical Informatics) has been held annually in conjunction with one of the largest data management conferences, CIKM, bringing together researchers working on computer science and bioinformatics area. The purpose of DTMBIO is to foster discussions regarding the state-of-the-art applications of data and text mining on biomedical research problems. DTMBIO 2016 will help scientists navigate emerging trends and opportunities in the evolving area of informatics related techniques and problems in the context of biomedical research.

MOTIVATION: Advances in sequencing technologies have remarkably lowered the detection limit of somatic variants to a low frequency. However, calling mutations at this range is still confounded by many factors including environmental contamination. Vector contamination is a continuously occurring issue and is especially problematic since vector inserts are hardly distinguishable from the sample sequences. Such inserts, which may harbor polymorphisms and engineered functional mutations, can result in calling false variants at corresponding sites. Numerous vector-screening methods have been developed, but none could handle contamination from inserts because they are focusing on vector backbone sequences alone. RESULTS: We developed a novel method-Vecuum-that identifies vector-originated reads and resultant false variants. Since vector inserts are generally constructed from intron-less cDNAs, Vecuum identifies vector-originated reads by inspecting the clipping patterns at exon junctions. False variant calls are further detected based on the biased distribution of mutant alleles to vector-originated reads. Tests on simulated and spike-in experimental data validated that Vecuum could detect 93% of vector contaminants and could remove up to 87% of variant-like false calls with 100% precision. Application to public sequence datasets demonstrated the utility of Vecuum in detecting false variants resulting from various types of external contamination. AVAILABILITY AND IMPLEMENTATION: Java-based implementation of the method is available at http://vecuum.sourceforge.net/ CONTACT: [email protected] information: Supplementary data are available at Bioinformatics online.

MOTIVATION: Finding somatic mutations from massively parallel sequencing data is becoming a standard process in genome-based biomedical studies. There are a number of robust methods developed for detecting somatic single nucleotide variations However, detection of somatic copy number alteration has been substantially less explored and remains vulnerable to frequently raised sampling issues: low frequency in cell population and absence of the matched control samples. RESULTS: We developed a novel computational method SoloDel that accurately classifies low-frequent somatic deletions from germline ones with or without matched control samples. We first constructed a probabilistic, somatic mutation progression model that describes the occurrence and propagation of the event in the cellular lineage of the sample. We then built a Gaussian mixture model to represent the mixed population of somatic and germline deletions. Parameters of the mixture model could be estimated using the expectation-maximization algorithm with the observed distribution of read-depth ratios at the points of discordant-read based initial deletion calls. Combined with conventional structural variation caller, SoloDel greatly increased the accuracy in classifying somatic mutations. Even without control, SoloDel maintained a comparable performance in a wide range of mutated subpopulation size (10-70%). SoloDel could also successfully recall experimentally validated somatic deletions from previously reported neuropsychiatric whole-genome sequencing data. AVAILABILITY AND IMPLEMENTATION: Java-based implementation of the method is available at http://sourceforge.net/projects/solodel/ CONTACT: [email protected] or [email protected] SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Altered metabolism in cancer cells has been viewed as a passive response required for a malignant transformation. However, this view has changed through the recently described metabolic oncogenic factors: mutated isocitrate dehydrogenases (IDH), succinate dehydrogenase (SDH), and fumarate hydratase (FH) that produce oncometabolites that competitively inhibit epigenetic regulation. In this study, we demonstrate in silico predictions of oncometabolites that have the potential to dysregulate epigenetic controls in nine types of cancer by incorporating massive scale genetic mutation information (collected from more than 1,700 cancer genomes), expression profiling data, and deploying Recon 2 to reconstruct context-specific genome-scale metabolic models. Our analysis predicted 15 compounds and 24 substructures of potential oncometabolites that could result from the loss-of-function and gain-of-function mutations of metabolic enzymes, respectively. These results suggest a substantial potential for discovering unidentified oncometabolites in various forms of cancers.

SUMMARY: We propose a targeted re-sequencing simulator Wessim that generates synthetic exome sequencing reads from a given sample genome. Wessim emulates conventional exome capture technologies, including Agilent's SureSelect and NimbleGen's SeqCap, to generate DNA fragments from genomic target regions. The target regions can be either specified by genomic coordinates or inferred from in silico probe hybridization. Coupled with existing next-generation sequencing simulators, Wessim generates a realistic artificial exome sequencing data, which is essential for developing and evaluating exome-targeted variant callers. AVAILABILITY: Source code and the packaged version of Wessim with manuals are available at http://sak042.github.com/Wessim/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

With the remarkable development in inexpensive sequencing technologies and supporting computational tools, we have the promise of medicine being personalized by knowledge of the individual genome. Current technologies provide high throughput, but short reads. Reconstruction of the donor genome is based either on de novo assembly of the (short) reads, or on mapping donor reads to a standard reference. While such techniques demonstrate high success rates for inferring 'simple' genomic segments, they are confounded by segments with complex duplication patterns, including regions of direct medical relevance, like the HLA and the KIR regions.In this work, we address this problem with a method for assessing the quality of a predicted genome sequence for complex regions of the genome. This method combines two natural types of evidence: sequence similarity of the mapped reads to the predicted donor genome, and distribution of reads across the predicted genome. We define a new scoring function for read-to-genome matchings, which penalizes for sequence dissimilarities and deviations from expected read location distribution, and present an efficient algorithm for finding matchings that minimize the penalty. The algorithm is based on a formal problem, first defined in this paper, called Coverage Sensitive many-to-many min-cost bipartite Matching (CSM). This new problem variant generalizes the standard (one-to-one) weighted bipartite matching problem, and can be solved using network flows. The resulting Java-based tool, called SAGE (Scoring function for Assembled GEnomes), is freely available upon request. We demonstrate over simulated data that SAGE can be used to infer correct haplotypes of the highly repetitive KIR region on the Human chromosome 19.

BACKGROUND: Cells coordinate their metabolism, proliferation, and cellular communication according to environmental cues through signal transduction. Because signal transduction has a primary role in cellular processes, many experimental techniques and approaches have emerged to discover the molecular components and dynamics that are dependent on cellular contexts. However, omics approaches based on genome-wide expression analysis data comparing one differing condition (e.g. complex disease patients and normal subjects) did not investigate the dynamics and inter-pathway cross-communication that are dependent on cellular contexts. Therefore, we introduce a new computational omics approach for discovering signal transduction pathways regulated by transcription and transcriptional regulations between pathways in signaling networks that are dependent on cellular contexts, especially focusing on a transcription-mediated mechanism of inter-pathway cross-communication. RESULTS: Applied to dendritic cells treated with lipopolysaccharide, our analysis well depicted how dendritic cells respond to the treatment through transcriptional regulations between signal transduction pathways in dendritic cell maturation and T cell activation. CONCLUSIONS: Our new approach helps to understand the underlying biological phenomenon of expression data (e.g. complex diseases such as cancer) by providing a graphical network which shows transcriptional regulations between signal transduction pathways. The software programs are available upon request.

BACKGROUND: Metastasis is the most dangerous step in cancer progression and causes more than 90% of cancer death. Although many researchers have been working on biological features and characteristics of metastasis, most of its genetic level processes remain uncertain. Some studies succeeded in elucidating metastasis related genes and pathways, followed by predicting prognosis of cancer patients, but there still is a question whether the result genes or pathways contain enough information and noise features have been controlled appropriately. METHODS: We set four tumor type classes composed of various tumor characteristics such as tissue origin, cellular environment, and metastatic ability. We conducted a set of comparisons among the four tumor classes followed by searching for genes that are consistently up or down regulated through the whole comparisons. RESULTS: We identified four sets of genes that are consistently differently expressed in the comparisons, each of which denotes one of four cellular characteristics respectively - liver tissue, colon tissue, liver viability and metastasis characteristics. We found that our candidate genes for tissue specificity are consistent with the TiGER database. And we also found that the metastasis candidate genes from our method were more consistent with the known biological background and independent from other noise features. CONCLUSION: We suggested a new method for identifying metastasis related genes from a large-scale database. The proposed method attempts to minimize the influences from other factors except metastatic ability including tissue originality and tissue viability by confining the result of metastasis unrelated test combinations.

BACKGROUND: As systems biology has begun to draw growing attention, bio-network inference and analysis have become more and more important. Though there have been many efforts for bio-network inference, they are still far from practical applications due to too many false inferences and lack of comprehensible interpretation in the biological viewpoints. In order for applying to real problems, they should provide effective inference, reliable validation, rational elucidation, and sufficient extensibility to incorporate various relevant information sources. RESULTS: We have been developing an information fusion software platform called BioCAD. It is utilizing both of local and global optimization for bio-network inference, text mining techniques for network validation and annotation, and Web services-based workflow techniques. In addition, it includes an effective technique to elucidate network edges by integrating various information sources. This paper presents the architecture of BioCAD and essential modules for bio-network inference and analysis. CONCLUSION: BioCAD provides a convenient infrastructure for network inference and network analysis. It automates series of users' processes by providing data preprocessing tools for various formats of data. It also helps inferring more accurate and reliable bio-networks by providing network inference tools which utilize information from distinct sources. And it can be used to analyze and validate the inferred bio-networks using information fusion tools.

To realize location-based services, it is essential to handle the extreme situation that must cope with a very large volume, at least millions, of moving items. In this paper, we describe a location information system prototype of GALIS, which is a cluster-based scalable distributed computing system architecture which consists of multiple data processors, each dedicated to keeping records relevant to a different geographical zone and a different time zone. The proposed system contains all of the major computing nodes of GALIS architecture and is developed as a middleware on top of commercial main-memory database engines and spatial database engines, for short-term data and long-term data processing, respectively. To show the usefulness of our system, some experimental results showing clear advantages of distributed computing are also explained.

Modeling on-chip inductive effects for interconnects of multi-gigahertz microprocessors remains challenging. SPICE simulation of these effects is very slow because of the large number of mutual inductances. Meanwhile, ignoring the non-linear behavior of drivers in a fast linear circuit simulator results in large errors for the inductive effect. In this paper, a fast and accurate time-domain transient analysis approach is presented, which captures the non-linearity of circuit drivers, the effect of non-ideal ground and de-coupling capacitors in a bus structure. The proposed method models the non-linearity of drivers in conjunction with specific bus geometries. Linearized waveforms at each driver output are incorporated into an interconnect reduced-order simulator for fast transient simulation. In addition, non-ideal ground and de-coupling capacitor models enable accurate signal and ground bounce simulations. Results show that this simulation approach is up-to 68x faster than SPICE while maintaining 95% accuracy.