Explore the vast range of titles available.

A major challenge for effective application of CRISPR systems is to accurately predict the single guide RNA (sgRNA) on-target knockout efficacy and off-target profile, which would facilitate the optimized design of sgRNAs with high sensitivity and specificity. Here we present DeepCRISPR , a comprehensive computational platform to unify sgRNA on-target and off-target site prediction into one framework with deep learning, surpassing available state-of-the-art in silico tools. In addition, DeepCRISPR fully automates the identification of sequence and epigenetic features that may affect sgRNA knockout efficacy in a data-driven manner. DeepCRISPR is available at http://www.deepcrispr.net/ .

The Library of Integrated Network-Based Cellular Signatures (LINCS) project aims to create a network-based understanding of biology by cataloging changes in gene expression and signal transduction that occur when cells are exposed to a variety of perturbations. It is helpful for understanding cell pathways and facilitating drug discovery. Here, we developed a novel approach to infer cell-specific pathways and identify a compound's effects using gene expression and phosphoproteomics data under treatments with different compounds. Gene expression data were employed to infer potential targets of compounds and create a generic pathway map. Binary linear programming (BLP) was then developed to optimize the generic pathway topology based on the mid-stage signaling response of phosphorylation. To demonstrate effectiveness of this approach, we built a generic pathway map for the MCF7 breast cancer cell line and inferred the cell-specific pathways by BLP. The first group of 11 compounds was utilized to optimize the generic pathways, and then 4 compounds were used to identify effects based on the inferred cell-specific pathways. Cross-validation indicated that the cell-specific pathways reliably predicted a compound's effects. Finally, we applied BLP to re-optimize the cell-specific pathways to predict the effects of 4 compounds (trichostatin A, MS-275, staurosporine, and digoxigenin) according to compound-induced topological alterations. Trichostatin A and MS-275 (both HDAC inhibitors) inhibited the downstream pathway of HDAC1 and caused cell growth arrest via activation of p53 and p21; the effects of digoxigenin were totally opposite. Staurosporine blocked the cell cycle via p53 and p21, but also promoted cell growth via activated HDAC1 and its downstream pathway. Our approach was also applied to the PC3 prostate cancer cell line, and the cross-validation analysis showed very good accuracy in predicting effects of 4 compounds. In summary, our computational model can be used to elucidate potential mechanisms of a compound's efficacy.

Background The incidence of multiple primary malignant tumors (MPMTs) is rising due to the development of screening technologies, significant treatment advances and increased aging of the population. For patients with a prior cancer history, identifying the tumor origin of the second malignant lesion has important prognostic and therapeutic implications and still represents a difficult problem in clinical practice. Methods In this study, we evaluated the performance of a 90-gene expression assay and explored its potential diagnostic utility for MPMTs across a broad spectrum of tumor types. Thirty-five MPMT patients from Sir Run Run Shaw Hospital, College of Medicine, Zhejiang University and Fudan University Shanghai Cancer Center were enrolled; 73 MPMT specimens met all quality control criteria and were analyzed by the 90-gene expression assay. Results For each clinical specimen, the tumor type predicted by the 90-gene expression assay was compared with its pathological diagnosis, with an overall accuracy of 93.2% (68 of 73, 95% confidence interval 0.84–0.97). For histopathological subgroup analysis, the 90-gene expression assay achieved an overall accuracy of 95.0% (38 of 40; 95% CI 0.82–0.99) for well-moderately differentiated tumors and 92.0% (23 of 25; 95% CI 0.82–0.99) for poorly or undifferentiated tumors, with no statistically significant difference (p-value > 0.5). For squamous cell carcinoma specimens, the overall accuracy of gene expression assay also reached 87.5% (7 of 8; 95% CI 0.47–0.99) for identifying the tumor origins. Conclusions The 90-gene expression assay provides flexibility and accuracy in identifying the tumor origin of MPMTs. Future incorporation of the 90-gene expression assay in pathological diagnosis will assist oncologists in applying precise treatments, leading to improved care and outcomes for MPMT patients.

Tissue-specificity is important for the function of human body. However, it is still not clear how the functional diversity of different tissues is achieved. Here we construct gene regulatory networks in 13 human tissues by integrating large-scale transcription factor （TF）-gene regulations with gene and protein expression data. By comparing these regulatory networks, we find many tissue-specific regulations that are important for tissue identity. In particular, the tissue-specific TFs are found to regulate more genes than those expressed in multiple tissues, and the processes regulated by these tissue-specific TFs are closely related to tissue functions. Moreover, the regulations that are present in certain tissue are found to be enriched in the tissue associated disease genes, and these networks provide the molecular context of disease genes. Therefore, recognizing tissue- specific regulatory networks can help better understand the molecular mechanisms underlying diseases and identify new disease genes.

Accurate gland segmentation in colorectal cancer histopathology is crucial, but the scarcity of pixel-level annotations limits robust model development. This study aims to develop a highly accurate gland segmentation method that leverages weakly labeled data, specifically image-level labels, to overcome the need for extensive pixel-level annotations. We propose a novel three-stage framework that uniquely combines self-supervised fine-tuning of the DINOv2 vision transformer, attention-based pseudo-label generation, and a boundary-aware loss function. Initially, an off-the-shelf DINOv2 encoder is fine-tuned on a large unlabeled dataset of histopathology images. This fine-tuned encoder is then integrated into a classification network equipped with an attention mechanism, which is trained using image-level labels to generate initial pseudo-labels via attention maps. These maps are refined through blending, thresholding, and Conditional Random Field (CRF) post-processing. Finally, a segmentation network, employing the same fine-tuned encoder and a lightweight decoder, is trained using these refined pseudo-labels and a boundary-aware loss. Ablation studies demonstrated the significant benefit of the fine-tuned encoder and the comprehensive post-processing steps for pseudo-label generation. Further studies confirmed the effectiveness of the boundary-aware loss in improving segmentation accuracy. Our method achieved superior performance on the GlaS dataset compared to several state-of-the-art methods, including both fully supervised and weakly supervised approaches, demonstrating higher F1-score, Object Dice, and lower Object Hausdorff distance. This approach effectively addresses the challenge of limited pixel-level annotations by utilizing more readily available image-level data, offering a promising solution for improved colorectal cancer diagnosis. The proposed framework shows potential for generalization to other histopathology image analysis tasks.

Interaction of myeloma cells with osteoclasts (OC) can enhance tumor cell expansion through activation of complex signaling transduction networks. Both cells reside in the bone marrow, a hypoxic niche. How OC-myeloma interaction in a hypoxic environment affects myeloma cell growth and their response to drug treatment is poorly understood. In this study, we i ) cultured myeloma cells in the presence/absence of OCs under normoxia and hypoxia conditions and did protein profiling analysis using reverse phase protein array; ii ) computationally developed an Integer Linear Programming approach to infer OC-mediated myeloma cell-specific signaling pathways under normoxic and hypoxic conditions. Our modeling analysis indicated that in the presence OCs, (1) cell growth-associated signaling pathways, PI3K/AKT and MEK/ERK, were activated and apoptotic regulatory proteins, BAX and BIM, down-regulated under normoxic condition; (2) β1 Integrin/FAK signaling pathway was activated in myeloma cells under hypoxic condition. Simulation of drug treatment effects by perturbing the inferred cell-specific pathways showed that targeting myeloma cells with the combination of PI3K and integrin inhibitors potentially (1) inhibited cell proliferation by reducing the expression/activation of NF-κB, S6, c-Myc and c-Jun under normoxic condition; (2) blocked myeloma cell migration and invasion by reducing the expression of FAK and PKC under hypoxic condition.

This paper proposes a novel recursive partitioning method based on constrained learning neural networks to find an arbitrary number (less than the order of the polynomial) of (real or complex) roots of arbitrary polynomials. Moreover, this paper also gives a BP network constrained learning algorithm (CLA) used in root-finders based on the constrained relations between the roots and the coefficients of polynomials. At the same time, an adaptive selection method for the parameter δP with the CLA is also given. The experimental results demonstrate that this method can more rapidly and effectively obtain the roots of arbitrary high order polynomials with higher precision than traditional root-finding approaches.

The classification mechanisms of linear feedforward neural network classifiers (FNNC), whose hidden layer performs the Fisher linear transformation of the input patterns, under the supervision of outer-supervised signals are investigated. The “bottleneck” behaviours in linear FNNCs are observed and analyzed. In addition, the structure stabilities of the linear FNNCs are also discussed. It is pointed out that the key point to break through the “bottleneck” behaviours for linear FNNCs is to change linear hidden neurons into nonlinear hidden ones. Finally, the experimental results, taking the parity 3 problem as example, are given.

TP3; The classification mechanisms of linear feed forward neural network classifiers (FNNC), whose hidden layer performs the Fisher lineartrans formation of the input patterns, under the supervision of outer-supervised signals are investigated. The \"bottleneck\" behavioursin linear FNNCs are observed and analyzed. In addition, the structure stabilities of the linear FNNCs are also discussed. It is pointed out that the key point to break through the \"bottleneck\" behaviours forlinear FNNCs is to change linear hidden neurons into nonlinear hiddenones. Finally, the experimental results, taking the parity 3 problem asexample, are given.

described by multiple instances (e.g., image patches) and simultaneously associated with multiple labels. Existing MIML methods are useful in many applications but most of which suffer from relatively low accuracy and training efficiency due to several issues: i) the inter-label correlations(i.e., the probabilistic correlations between the multiple labels corresponding to an object) are neglected; ii) the inter-instance correlations (i.e., the probabilistic correlations of different instances in predicting the object label) cannot be learned directly (or jointly) with other types of correlations due to the missing instance labels; iii) diverse inter-correlations (e.g., inter-label correlations, inter-instance correlations) can only be learned in multiple stages. To resolve these issues, a new single-stage framework called broad multi-instance multi-label learning (BMIML) is proposed. In BMIML, there are three innovative modules: i) an auto-weighted label enhancement learning (AWLEL) based on broad learning system (BLS) is designed, which simultaneously and efficiently captures the inter-label correlations while traditional BLS cannot; ii) A specific MIML neural network called scalable multi-instance probabilistic regression (SMIPR) is constructed to effectively estimate the inter-instance correlations using the object label only, which can provide additional probabilistic information for learning; iii) Finally, an interactive decision optimization (IDO) is designed to combine and optimize the results from AWLEL and SMIPR and form a single-stage framework. Experiments show that BMIML is highly competitive to (or even better than) existing methods in accuracy and much faster than most MIML methods even for large medical image data sets (> 90K images).