Spatial omics technologies, generating high-throughput and multimodal data, have necessitated the development of advanced data integration methods to facilitate comprehensive biological and clinical treatment discoveries. Based on the cross-attention concept, we developed an AI learning based toolchain called StereoMM, a graph based fusion model that can incorporate omics data such as gene expression, histological images, and spatial location. StereoMM uses an attention module for omics data interaction and a graph autoencoder to integrate spatial positions and omics data in a self-supervised manner. Applying StereoMM across various cancer types and platforms has demonstrated its robust capability. StereoMM outperforms competitors in identifying spatial regions reflecting tumour progression and shows promise in classifying colorectal cancer patients into deficient mismatch repair and proficient mismatch repair groups. The comprehensive inter-modal integration and efficiency of StereoMM enable researchers to construct spatial views of integrated multimodal features efficiently, advancing thorough tissue and patient characterization.

MOTIVATION: scATAC-seq has enabled chromatin accessibility landscape profiling at the single-cell level, providing opportunities for determining cell-type-specific regulation codes. However, high dimension, extreme sparsity, and large scale of scATAC-seq data have posed great challenges to cell-type identification. Thus, there has been a growing interest in leveraging the well-annotated scRNA-seq data to help annotate scATAC-seq data. However, substantial computational obstacles remain to transfer information from scRNA-seq to scATAC-seq, especially for their heterogeneous features. RESULTS: We propose a new transfer learning method, scNCL, which utilizes prior knowledge and contrastive learning to tackle the problem of heterogeneous features. Briefly, scNCL transforms scATAC-seq features into gene activity matrix based on prior knowledge. Since feature transformation can cause information loss, scNCL introduces neighborhood contrastive learning to preserve the neighborhood structure of scATAC-seq cells in raw feature space. To learn transferable latent features, scNCL uses a feature projection loss and an alignment loss to harmonize embeddings between scRNA-seq and scATAC-seq. Experiments on various datasets demonstrated that scNCL not only realizes accurate and robust label transfer for common types, but also achieves reliable detection of novel types. scNCL is also computationally efficient and scalable to million-scale datasets. Moreover, we prove scNCL can help refine cell-type annotations in existing scATAC-seq atlases. AVAILABILITY AND IMPLEMENTATION: The source code and data used in this paper can be found in https://github.com/CSUBioGroup/scNCL-release.

MOTIVATION: Graphs or networks are widely utilized to model the interactions between different entities (e.g. proteins, drugs, etc.) for biomedical applications. Predicting potential interactions/links in biomedical networks is important for understanding the pathological mechanisms of various complex human diseases, as well as screening compound targets for drug discovery. Graph neural networks (GNNs) have been utilized for link prediction in various biomedical networks, which rely on the node features extracted from different data sources, e.g. sequence, structure and network data. However, it is challenging to effectively integrate these data sources and automatically extract features for different link prediction tasks. RESULTS: In this article, we propose a novel Pre-Training Graph Neural Networks-based framework named PT-GNN to integrate different data sources for link prediction in biomedical networks. First, we design expressive deep learning methods [e.g. convolutional neural network and graph convolutional network (GCN)] to learn features for individual nodes from sequence and structure data. Second, we further propose a GCN-based encoder to effectively refine the node features by modelling the dependencies among nodes in the network. Third, the node features are pre-trained based on graph reconstruction tasks. The pre-trained features can be used for model initialization in downstream tasks. Extensive experiments have been conducted on two critical link prediction tasks, i.e. synthetic lethality (SL) prediction and drug-target interaction (DTI) prediction. Experimental results demonstrate PT-GNN outperforms the state-of-the-art methods for SL prediction and DTI prediction. In addition, the pre-trained features benefit improving the performance and reduce the training time of existing models. AVAILABILITY AND IMPLEMENTATION: Python codes and dataset are available at: https://github.com/longyahui/PT-GNN. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Flow cytometry (FCM) is widely used in both clinical and basic research to characterize cell phenotypes and functions. The latest FCM instruments analyze up to 20 markers of individual cells, producing high-dimensional data. This requires the use of the latest clustering and dimensionality reduction techniques to automatically segregate cell sub-populations in an unbiased manner. However, automated analyses may lead to false discoveries due to inter-sample differences in quality and properties. RESULTS: We present an R package, flowAI, containing two methods to clean FCM files from unwanted events: (i) an automatic method that adopts algorithms for the detection of anomalies and (ii) an interactive method with a graphical user interface implemented into an R shiny application. The general approach behind the two methods consists of three key steps to check and remove suspected anomalies that derive from (i) abrupt changes in the flow rate, (ii) instability of signal acquisition and (iii) outliers in the lower limit and margin events in the upper limit of the dynamic range. For each file analyzed our software generates a summary of the quality assessment from the aforementioned steps. The software presented is an intuitive solution seeking to improve the results not only of manual but also and in particular of automatic analysis on FCM data. AVAILABILITY AND IMPLEMENTATION: R source code available through Bioconductor: http://bioconductor.org/packages/flowAI/ CONTACTS: [email protected] or [email protected] SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Single-cell mass cytometry significantly increases the dimensionality of cytometry analysis as compared to fluorescence flow cytometry, providing unprecedented resolution of cellular diversity in tissues. However, analysis and interpretation of these high-dimensional data poses a significant technical challenge. Here, we present cytofkit, a new Bioconductor package, which integrates both state-of-the-art bioinformatics methods and in-house novel algorithms to offer a comprehensive toolset for mass cytometry data analysis. Cytofkit provides functions for data pre-processing, data visualization through linear or non-linear dimensionality reduction, automatic identification of cell subsets, and inference of the relatedness between cell subsets. This pipeline also provides a graphical user interface (GUI) for ease of use, as well as a shiny application (APP) for interactive visualization of cell subpopulations and progression profiles of key markers. Applied to a CD14-CD19- PBMCs dataset, cytofkit accurately identified different subsets of lymphocytes; applied to a human CD4+ T cell dataset, cytofkit uncovered multiple subtypes of TFH cells spanning blood and tonsils. Cytofkit is implemented in R, licensed under the Artistic license 2.0, and freely available from the Bioconductor website, https://bioconductor.org/packages/cytofkit/. Cytofkit is also applicable for flow cytometry data analysis.

Conventional recurrent neural networks (RNNs) have difficulties in learning long-term dependencies. To tackle this problem, we propose an architecture called segmented-memory recurrent neural network (SMRNN). A symbolic sequence is broken into segments and then presented as inputs to the SMRNN one symbol per cycle. The SMRNN uses separate internal states to store symbol-level context, as well as segment-level context. The symbol-level context is updated for each symbol presented for input. The segment-level context is updated after each segment. The SMRNN is trained using an extended real-time recurrent learning algorithm. We test the performance of SMRNN on the information latching problem, the "two-sequence problem" and the problem of protein secondary structure (PSS) prediction. Our implementation results indicate that SMRNN performs better on long-term dependency problems than conventional RNNs. Besides, we also theoretically analyze how the segmented memory of SMRNN helps learning long-term temporal dependencies and study the impact of the segment length.

Protein secondary structure (PSS) prediction is an important topic in bioinformatics. Our study on a large set of non-homologous proteins shows that long-range interactions commonly exist and negatively affect PSS prediction. Besides, we also reveal strong correlations between secondary structure (SS) elements. In order to take into account the long-range interactions and SS-SS correlations, we propose a novel prediction system based on cascaded bidirectional recurrent neural network (BRNN). We compare the cascaded BRNN against another two BRNN architectures, namely the original BRNN architecture used for speech recognition as well as Pollastri's BRNN that was proposed for PSS prediction. Our cascaded BRNN achieves an overall three state accuracy Q3 of 74.38\%, and reaches a high Segment OVerlap (SOV) of 66.0455. It outperforms the original BRNN and Pollastri's BRNN in both Q3 and SOV. Specifically, it improves the SOV score by 4-6%.

In this paper, we propose a hybrid RNN/HMM system for protein secondary structure prediction, where each secondary structure segment is approximated by a second-order recurrent neural network embedded in the state of a segmental hidden Markov model. We evaluate the hybrid system on the RS126 and CB396 sets and obtain promising results.