Abhinav Achreja, Tao Yu, Anjali Mittal, Srinadh Choppara, Olamide Animasahun, Minal Nenwani, Fulei Wuchu, Noah Meurs, Aradhana Mohan, Jin Heon Jeon, Itisam Sarangi, Anusha Jayaraman, Sarah Owen, Reva Kulkarni, Michele Cusato, Frank Weinberg, Hye Kyong Kweon, Chitra Subramanian, Max S Wicha, Sofia D Merajver, Sunitha Nagrath, Kathleen R Cho, Analisa DiFeo, Xiongbin Lu, Deepak Nagrath <<<

Recurrent loss-of-function deletions cause frequent inactivation of tumour suppressor genes but often also involve the collateral deletion of essential genes in chromosomal proximity, engendering dependence on paralogues that maintain similar function. Although these paralogues are attractive anticancer targets, no methodology exists to uncover such collateral lethal genes. Here we report a framework for collateral lethal gene identification via metabolic fluxes, CLIM, and use it to reveal MTHFD2 as a collateral lethal gene in UQCR11-deleted ovarian tumours. We show that MTHFD2 has a non-canonical oxidative function to provide mitochondrial NAD, and demonstrate the regulation of systemic metabolic activity by the paralogue metabolic pathway maintaining metabolic flux compensation. This UQCR11-MTHFD2 collateral lethality is confirmed in vivo, with MTHFD2 inhibition leading to complete remission of UQCR11-deleted ovarian tumours. Using CLIM's machine learning and genome-scale metabolic flux analysis, we elucidate the broad efficacy of targeting MTHFD2 despite distinct cancer genetic profiles co-occurring with UQCR11 deletion and irrespective of stromal compositions of tumours. <<<

Species of the Enterobacter cloacae complex are widely encountered in nature, but they can act as pathogens. The biochemical and molecular studies on E. cloacae have shown genomic heterogeneity, comprising six species: Enterobacter cloacae, Enterobacter asburiae, Enterobacter hormaechei, Enterobacter kobei, Enterobacter ludwigii and Enterobacter nimipressuralis, E. cloacae and E. hormaechei are the most frequently isolated in human clinical specimens. Phenotypic identification of all species belonging to this taxon is usually difficult and not always reliable; therefore, molecular methods are often used. Although the E. cloacae complex strains are among the most common Enterobacter spp. causing nosocomial bloodstream infections in the last decade, little is known about their virulence-associated properties. By contrast, much has been published on the antibiotic-resistance features of these microorganisms. In fact, they are capable of overproducing AmpC β-lactamases by derepression of a chromosomal gene or by the acquisition of a transferable ampC gene on plasmids conferring the antibiotic resistance. Many other resistance determinants that are able to render ineffective almost all antibiotic families have been recently acquired. Most studies on antimicrobial susceptibility are focused on E. cloacae, E. hormaechei and E. asburiae; these studies reported small variations between the species, and the only significant differences had no discriminating features. <<<

Ferroptosis is a form of regulated cell death driven by the accumulation of lipid hydroperoxides. Regulation of ferroptosis might be beneficial to cancer treatment. Non-coding RNAs (ncRNAs) are a class of RNA transcripts that generally cannot encode proteins and have been demonstrated to play critical roles in regulating ferroptosis. Herein, we developed ncFO, the ncRNA-ferroptosis association database, to document the manually curated and predicted ncRNAs that are associated with ferroptosis. Collectively, ncFO contains 90 experimentally verified entries, including 46 microRNAs (miRNAs), 21 long non-coding RNAs (lncRNAs), and 17 circular RNAs (circRNAs). In addition, ncFO also incorporates two online prediction tools based on the regulation and co-expression of ncRNA and ferroptosis genes. Using default parameters, we obtained 3260 predicted entries, including 598 miRNAs and 178 lncRNAs, by regulation, as well as 2,592,661 predicted entries, including 967 miRNAs and 9632 lncRNAs, by ncRNA-ferroptosis gene co-expression in more than 8000 samples across 20 cancer types. The detailed information of each entry includes ncRNA name, disease, species, tissue, target, regulation, publication time, and PubMed identifier. ncFO also provides survival analysis and differential expression analysis for ncRNAs. In summary, ncFO offers a user-friendly platform to search and predict ferroptosis-associated ncRNAs, which might facilitate research on ferroptosis and discover potential targets for cancer treatment. ncFO can be accessed at http://www.jianglab.cn/ncFO/. <<<

Erin Rooney Riggs, Erica F Andersen, Athena M Cherry, Sibel Kantarci, Hutton Kearney, Ankita Patel, Gordana Raca, Deborah I Ritter, Sarah T South, Erik C Thorland, Daniel Pineda-Alvarez, Swaroop Aradhya, Christa Lese Martin <<<

PURPOSE: Copy-number analysis to detect disease-causing losses and gains across the genome is recommended for the evaluation of individuals with neurodevelopmental disorders and/or multiple congenital anomalies, as well as for fetuses with ultrasound abnormalities. In the decade that this analysis has been in widespread clinical use, tremendous strides have been made in understanding the effects of copy-number variants (CNVs) in both affected individuals and the general population. However, continued broad implementation of array and next-generation sequencing-based technologies will expand the types of CNVs encountered in the clinical setting, as well as our understanding of their impact on human health.METHODS: To assist clinical laboratories in the classification and reporting of CNVs, irrespective of the technology used to identify them, the American College of Medical Genetics and Genomics has developed the following professional standards in collaboration with the National Institutes of Health (NIH)-funded Clinical Genome Resource (ClinGen) project.RESULTS: This update introduces a quantitative, evidence-based scoring framework; encourages the implementation of the five-tier classification system widely used in sequence variant classification; and recommends "uncoupling" the evidence-based classification of a variant from its potential implications for a particular individual.CONCLUSION: These professional standards will guide the evaluation of constitutional CNVs and encourage consistency and transparency across clinical laboratories. <<<

Less than 5 years ago the CRISPR/Cas nuclease was first introduced into eukaryotes, shortly becoming the most efficient and widely used tool for genome engineering. For plants, efforts were centred on obtaining heritable changes in most transformable crop species by inducing mutations into open reading frames of interest, via non-homologous end joining. Now it is important to take the next steps and further develop the technology to reach its full potential. For breeding, besides using DNA-free editing and avoiding off target effects, it will be desirable to apply the system for the mutation of regulatory elements and for more complex genome rearrangements. Targeting enzymatic activities, like transcriptional regulators or DNA modifying enzymes, will be important for plant biology in the future. <<<

Historically, the primary focus of cancer research has been molecular and clinical studies of a few essential pathways and genes. Recent years have seen the rapid accumulation of large-scale cancer omics data catalysed by breakthroughs in high-throughput technologies. This fast data growth has given rise to an evolving concept of 'big data' in cancer, whose analysis demands large computational resources and can potentially bring novel insights into essential questions. Indeed, the combination of big data, bioinformatics and artificial intelligence has led to notable advances in our basic understanding of cancer biology and to translational advancements. Further advances will require a concerted effort among data scientists, clinicians, biologists and policymakers. Here, we review the current state of the art and future challenges for harnessing big data to advance cancer research and treatment. <<<

BACKGROUND: Insertion sequences (ISs) are mobile repeat sequences and most of them can copy themselves to new host genome locations, leading to genome plasticity and gene regulation in prokaryotes. In this study, we present functional and evolutionary relationships between IS and neighboring genes in a large-scale comparative genomic analysis.RESULTS: IS families were located in all prokaryotic phyla, with preferential occurrence of IS3, IS4, IS481, and IS5 families in Alpha-, Beta-, and Gammaproteobacteria, Actinobacteria and Firmicutes as well as in eukaryote host-associated organisms and autotrophic opportunistic pathogens. We defined the concept of the IS-Gene couple (IG), which allowed to highlight the functional and regulatory impacts of an IS on the closest gene. Genes involved in transcriptional regulation and transport activities were found overrepresented in IG. In particular, major facilitator superfamily (MFS) transporters, ATP-binding proteins and transposases raised as favorite neighboring gene functions of IS hotspots. Then, evolutionary conserved IS-Gene sets across taxonomic lineages enabled the classification of IS-gene couples into phylum, class-to-genus, and species syntenic IS-Gene couples. The IS5, IS21, IS4, IS607, IS91, ISL3 and IS200 families displayed two to four times more ISs in the phylum and/or class-to-genus syntenic IGs compared to other IS families. This indicates that those families were probably inserted earlier than others and then subjected to horizontal transfer, transposition and deletion events over time. In phylum syntenic IG category, Betaproteobacteria, Crenarchaeota, Calditrichae, Planctomycetes, Acidithiobacillia and Cyanobacteria phyla act as IS reservoirs for other phyla, and neighboring gene functions are mostly related to transcriptional regulators. Comparison of IS occurrences with predicted regulatory motifs led to ~ 26.5% of motif-containing ISs with 2 motifs per IS in average. These results, concomitantly with short IS-Gene distances, suggest that those ISs would interfere with the expression of neighboring genes and thus form strong candidates for an adaptive pairing.CONCLUSIONS: All together, our large-scale study provide new insights into the IS genetic context and strongly suggest their regulatory roles. <<<

Artificial intelligence (AI) models based on deep learning now represent the state of the art for making functional predictions in genomics research. However, the underlying basis on which predictive models make such predictions is often unknown. For genomics researchers, this missing explanatory information would frequently be of greater value than the predictions themselves, as it can enable new insights into genetic processes. We review progress in the emerging area of explainable AI (xAI), a field with the potential to empower life science researchers to gain mechanistic insights into complex deep learning models. We discuss and categorize approaches for model interpretation, including an intuitive understanding of how each approach works and their underlying assumptions and limitations in the context of typical high-throughput biological datasets. <<<

Speech enhancement is a critical component of many user-oriented audio applications, yet current systems still suffer from distorted and unnatural outputs. While generative models have shown strong potential in speech synthesis, they are still lagging behind in speech enhancement. This work leverages recent advances in diffusion probabilistic models, and proposes a novel speech enhancement algorithm that incorporates characteristics of the observed noisy speech signal into the diffusion and reverse processes. More specifically, we propose a generalized formulation of the diffusion probabilistic model named conditional diffusion probabilistic model that, in its reverse process, can adapt to non-Gaussian real noises in the estimated speech signal. In our experiments, we demonstrate strong performance of the proposed approach compared to representative generative models, and investigate the generalization capability of our models to other datasets with noise characteristics unseen during training. <<<

It has been suggested that beige fat thermogenesis is tightly controlled by epigenetic regulators that sense environmental cues such as temperature. Here, we report that subcutaneous adipose expression of the DNA demethylase TET1 is suppressed by cold and other stimulators of beige adipocyte thermogenesis. TET1 acts as an autonomous repressor of key thermogenic genes, including Ucp1 and Ppargc1a, in beige adipocytes. Adipose-selective Tet1 knockout mice generated by using Fabp4-Cre improves cold tolerance and increases energy expenditure and protects against diet-induced obesity and insulin resistance. Moreover, the suppressive role of TET1 in the thermogenic gene regulation of beige adipocytes is largely DNA demethylase-independent. Rather, TET1 coordinates with HDAC1 to mediate the epigenetic changes to suppress thermogenic gene transcription. Taken together, TET1 is a potent beige-selective epigenetic breaker of the thermogenic gene program. Our findings may lead to a therapeutic strategy to increase energy expenditure in obesity and related metabolic disorders. <<<

An effective backbone network is important to deep learning-based Deformable Medical Image Registration (DMIR), because it extracts and matches the features between two images to discover the mutual correspondence for fine registration. However, the existing deep networks focus on single image situation and are limited in registration task which is performed on paired images. Therefore, we advance a novel backbone network, XMorpher, for the effective corresponding feature representation in DMIR. 1) It proposes a novel full transformer architecture including dual parallel feature extraction networks which exchange information through cross attention, thus discovering multi-level semantic correspondence while extracting respective features gradually for final effective registration. 2) It advances the Cross Attention Transformer (CAT) blocks to establish the attention mechanism between images which is able to find the correspondence automatically and prompts the features to fuse efficiently in the network. 3) It constrains the attention computation between base windows and searching windows with different sizes, and thus focuses on the local transformation of deformable registration and enhances the computing efficiency at the same time. Without any bells and whistles, our XMorpher gives Voxelmorph 2.8% improvement on DSC, demonstrating its effective representation of the features from the paired images in DMIR. We believe that our XMorpher has great application potential in more paired medical images. Our XMorpher is open on https://github.com/Solemoon/XMorpher <<<

Mary L Stackpole, Weihua Zeng, Shuo Li, Chun-Chi Liu, Yonggang Zhou, Shanshan He, Angela Yeh, Ziye Wang, Fengzhu Sun, Qingjiao Li, Zuyang Yuan, Asli Yildirim, Pin-Jung Chen, Paul Winograd, Benjamin Tran, Yi-Te Lee, Paul Shize Li, Zorawar Noor, Megumi Yokomizo, Preeti Ahuja, Yazhen Zhu, Hsian-Rong Tseng, James S Tomlinson, Edward Garon, Samuel French, Clara E Magyar, Sarah Dry, Clara Lajonchere, Daniel Geschwind, Gina Choi, Sammy Saab, Frank Alber, Wing Hung Wong, Steven M Dubinett, Denise R Aberle, Vatche Agopian, Steven-Huy B Han, Xiaohui Ni, Wenyuan Li, Xianghong Jasmine Zhou <<<

Early cancer detection by cell-free DNA faces multiple challenges: low fraction of tumor cell-free DNA, molecular heterogeneity of cancer, and sample sizes that are not sufficient to reflect diverse patient populations. Here, we develop a cancer detection approach to address these challenges. It consists of an assay, cfMethyl-Seq, for cost-effective sequencing of the cell-free DNA methylome (with > 12-fold enrichment over whole genome bisulfite sequencing in CpG islands), and a computational method to extract methylation information and diagnose patients. Applying our approach to 408 colon, liver, lung, and stomach cancer patients and controls, at 97.9% specificity we achieve 80.7% and 74.5% sensitivity in detecting all-stage and early-stage cancer, and 89.1% and 85.0% accuracy for locating tissue-of-origin of all-stage and early-stage cancer, respectively. Our approach cost-effectively retains methylome profiles of cancer abnormalities, allowing us to learn new features and expand to other cancer types as training cohorts grow. <<<

Deep neural networks excel at finding hierarchical representations that solve complex tasks over large datasets. How can we humans understand these learned representations? In this work, we present network dissection, an analytic framework to systematically identify the semantics of individual hidden units within image classification and image generation networks. First, we analyze a convolutional neural network (CNN) trained on scene classification and discover units that match a diverse set of object concepts. We find evidence that the network has learned many object classes that play crucial roles in classifying scene classes. Second, we use a similar analytic method to analyze a generative adversarial network (GAN) model trained to generate scenes. By analyzing changes made when small sets of units are activated or deactivated, we find that objects can be added and removed from the output scenes while adapting to the context. Finally, we apply our analytic framework to understanding adversarial attacks and to semantic image editing. <<<

The correct use of model evaluation, model selection, and algorithm selection techniques is vital in academic machine learning research as well as in many industrial settings. This article reviews different techniques that can be used for each of these three subtasks and discusses the main advantages and disadvantages of each technique with references to theoretical and empirical studies. Further, recommendations are given to encourage best yet feasible practices in research and applications of machine learning. Common methods such as the holdout method for model evaluation and selection are covered, which are not recommended when working with small datasets. Different flavors of the bootstrap technique are introduced for estimating the uncertainty of performance estimates, as an alternative to confidence intervals via normal approximation if bootstrapping is computationally feasible. Common cross-validation techniques such as leave-one-out cross-validation and k-fold cross-validation are reviewed, the bias-variance trade-off for choosing k is discussed, and practical tips for the optimal choice of k are given based on empirical evidence. Different statistical tests for algorithm comparisons are presented, and strategies for dealing with multiple comparisons such as omnibus tests and multiple-comparison corrections are discussed. Finally, alternative methods for algorithm selection, such as the combined F-test 5x2 cross-validation and nested cross-validation, are recommended for comparing machine learning algorithms when datasets are small. <<<

This document aims to be a self-contained, mathematically precise overview of transformer architectures and algorithms (*not* results). It covers what transformers are, how they are trained, what they are used for, their key architectural components, and a preview of the most prominent models. The reader is assumed to be familiar with basic ML terminology and simpler neural network architectures such as MLPs. <<<

Discovering causal structure among a set of variables is a fundamental problem in many empirical sciences. Traditional score-based casual discovery methods rely on various local heuristics to search for a Directed Acyclic Graph (DAG) according to a predefined score function. While these methods, e.g., greedy equivalence search, may have attractive results with infinite samples and certain model assumptions, they are usually less satisfactory in practice due to finite data and possible violation of assumptions. Motivated by recent advances in neural combinatorial optimization, we propose to use Reinforcement Learning (RL) to search for the DAG with the best scoring. Our encoder-decoder model takes observable data as input and generates graph adjacency matrices that are used to compute rewards. The reward incorporates both the predefined score function and two penalty terms for enforcing acyclicity. In contrast with typical RL applications where the goal is to learn a policy, we use RL as a search strategy and our final output would be the graph, among all graphs generated during training, that achieves the best reward. We conduct experiments on both synthetic and real datasets, and show that the proposed approach not only has an improved search ability but also allows a flexible score function under the acyclicity constraint. <<<

The highest accuracy object detectors to date are based on a two-stage approach popularized by R-CNN, where a classifier is applied to a sparse set of candidate object locations. In contrast, one-stage detectors that are applied over a regular, dense sampling of possible object locations have the potential to be faster and simpler, but have trailed the accuracy of two-stage detectors thus far. In this paper, we investigate why this is the case. We discover that the extreme foreground-background class imbalance encountered during training of dense detectors is the central cause. We propose to address this class imbalance by reshaping the standard cross entropy loss such that it down-weights the loss assigned to well-classified examples. Our novel Focal Loss focuses training on a sparse set of hard examples and prevents the vast number of easy negatives from overwhelming the detector during training. To evaluate the effectiveness of our loss, we design and train a simple dense detector we call RetinaNet. Our results show that when trained with the focal loss, RetinaNet is able to match the speed of previous one-stage detectors while surpassing the accuracy of all existing state-of-the-art two-stage detectors. Code is at: this https URL. <<<

Genome instability and aberrant alterations of transcriptional programs both play important roles in cancer. Single-cell RNA sequencing (scRNA-seq) has the potential to investigate both genetic and nongenetic sources of tumor heterogeneity in a single assay. Here we present a computational method, Numbat, that integrates haplotype information obtained from population-based phasing with allele and expression signals to enhance detection of copy number variations from scRNA-seq. Numbat exploits the evolutionary relationships between subclones to iteratively infer single-cell copy number profiles and tumor clonal phylogeny. Analysis of 22 tumor samples, including multiple myeloma, gastric, breast and thyroid cancers, shows that Numbat can reconstruct the tumor copy number profile and precisely identify malignant cells in the tumor microenvironment. We identify genetic subpopulations with transcriptional signatures relevant to tumor progression and therapy resistance. Numbat requires neither sample-matched DNA data nor a priori genotyping, and is applicable to a wide range of experimental settings and cancer types. <<<

Identification of alleles that improve crop production and lead to higher-yielding varieties are needed for food security. Here we show that the quantitative trait locus WFP (WEALTHY FARMER'S PANICLE) encodes OsSPL14 (SQUAMOSA PROMOTER BINDING PROTEIN-LIKE 14, also known as IPA1). Higher expression of OsSPL14 in the reproductive stage promotes panicle branching and higher grain yield in rice. OsSPL14 controls shoot branching in the vegetative stage and is affected by microRNA excision. We also demonstrate the feasibility of using the OsSLP14(WFP) allele to increase rice crop yield. Introduction of the high-yielding OsSPL14(WFP) allele into the standard rice variety Nipponbare resulted in increased rice production. <<<