Predicting spatially resolved gene expression via tissue morphology using adaptive spatial GNNs.

MOTIVATION: Spatial transcriptomics technologies, which generate a spatial map of gene activity, can deepen the understanding of tissue architecture and its molecular underpinnings in health and disease. However, the high cost makes these technologies difficult to use in practice. Histological images co-registered with targeted tissues are more affordable and routinely generated in many research and clinical studies. Hence, predicting spatial gene expression from the morphological clues embedded in tissue histological images provides a scalable alternative approach to decoding tissue complexity. RESULTS: Here, we present a graph neural network based framework to predict the spatial expression of highly expressed genes from tissue histological images. Extensive experiments on two separate breast cancer data cohorts demonstrate that our method improves the prediction performance compared to the state-of-the-art, and that our model can be used to better delineate spatial domains of biological interest. AVAILABILITY AND IMPLEMENTATION: https://github.com/song0309/asGNN/.

Impeller: a path-based heterogeneous graph learning method for spatial transcriptomic data imputation.

MOTIVATION: Recent advances in spatial transcriptomics allow spatially resolved gene expression measurements with cellular or even sub-cellular resolution, directly characterizing the complex spatiotemporal gene expression landscape and cell-to-cell interactions in their native microenvironments. Due to technology limitations, most spatial transcriptomic technologies still yield incomplete expression measurements with excessive missing values. Therefore, gene imputation is critical to filling in missing data, enhancing resolution, and improving overall interpretability. However, existing methods either require additional matched single-cell RNA-seq data, which is rarely available, or ignore spatial proximity or expression similarity information. RESULTS: To address these issues, we introduce Impeller, a path-based heterogeneous graph learning method for spatial transcriptomic data imputation. Impeller has two unique characteristics distinct from existing approaches. First, it builds a heterogeneous graph with two types of edges representing spatial proximity and expression similarity. Therefore, Impeller can simultaneously model smooth gene expression changes across spatial dimensions and capture similar gene expression signatures of faraway cells from the same type. Moreover, Impeller incorporates both short- and long-range cell-to-cell interactions (e.g. via paracrine and endocrine) by stacking multiple GNN layers. We use a learnable path operator in Impeller to avoid the over-smoothing issue of the traditional Laplacian matrices. Extensive experiments on diverse datasets from three popular platforms and two species demonstrate the superiority of Impeller over various state-of-the-art imputation methods. AVAILABILITY AND IMPLEMENTATION: The code and preprocessed data used in this study are available at https://github.com/aicb-ZhangLabs/Impeller and https://zenodo.org/records/11212604.

Binding peptide generation for MHC Class I proteins with deep reinforcement learning.

MOTIVATION: MHC Class I protein plays an important role in immunotherapy by presenting immunogenic peptides to anti-tumor immune cells. The repertoires of peptides for various MHC Class I proteins are distinct, which can be reflected by their diverse binding motifs. To characterize binding motifs for MHC Class I proteins, in vitro experiments have been conducted to screen peptides with high binding affinities to hundreds of given MHC Class I proteins. However, considering tens of thousands of known MHC Class I proteins, conducting in vitro experiments for extensive MHC proteins is infeasible, and thus a more efficient and scalable way to characterize binding motifs is needed. RESULTS: We presented a de novo generation framework, coined PepPPO, to characterize binding motif for any given MHC Class I proteins via generating repertoires of peptides presented by them. PepPPO leverages a reinforcement learning agent with a mutation policy to mutate random input peptides into positive presented ones. Using PepPPO, we characterized binding motifs for around 10 000 known human MHC Class I proteins with and without experimental data. These computed motifs demonstrated high similarities with those derived from experimental data. In addition, we found that the motifs could be used for the rapid screening of neoantigens at a much lower time cost than previous deep-learning methods. AVAILABILITY AND IMPLEMENTATION: The software can be found in https://github.com/minrq/pMHC. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Attentive Variational Information Bottleneck for TCR-peptide interaction prediction.

MOTIVATION: We present a multi-sequence generalization of Variational Information Bottleneck and call the resulting model Attentive Variational Information Bottleneck (AVIB). Our AVIB model leverages multi-head self-attention to implicitly approximate a posterior distribution over latent encodings conditioned on multiple input sequences. We apply AVIB to a fundamental immuno-oncology problem: predicting the interactions between T-cell receptors (TCRs) and peptides. RESULTS: Experimental results on various datasets show that AVIB significantly outperforms state-of-the-art methods for TCR-peptide interaction prediction. Additionally, we show that the latent posterior distribution learned by AVIB is particularly effective for the unsupervised detection of out-of-distribution amino acid sequences. AVAILABILITY AND IMPLEMENTATION: The code and the data used for this study are publicly available at: https://github.com/nec-research/vibtcr. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Turtling: a time-aware neural topic model on NIH grant data.

Motivation: Recent initiatives for federal grant transparency allow direct knowledge extraction from large volumes of grant texts, serving as a powerful alternative to traditional surveys. However, its computational modeling is challenging as grants are usually multifaceted with constantly evolving topics. Results: We propose Turtling, a time-aware neural topic model with three unique characteristics. First, Turtling employs pretrained biomedical word embedding to extract research topics. Second, it leverages a probabilistic time-series model to allow smooth and coherent topic evolution. Lastly, Turtling leverages additional topic diversity loss and funding institute classification loss to improve topic quality and facilitate funding institute prediction. We apply Turtling on publicly available NIH grant text and show that it significantly outperforms other methods on topic quality metrics. We also demonstrate that Turtling can provide insights into research topic evolution by detecting topic trends across decades. In summary, Turtling may be a valuable tool for grant text analysis. Availability and implementation: Turtling is freely available as an open-source software at https://github.com/aicb-ZhangLabs/Turtling.

On TCR binding predictors failing to generalize to unseen peptides.

Several recent studies investigate TCR-peptide/-pMHC binding prediction using machine learning or deep learning approaches. Many of these methods achieve impressive results on test sets, which include peptide sequences that are also included in the training set. In this work, we investigate how state-of-the-art deep learning models for TCR-peptide/-pMHC binding prediction generalize to unseen peptides. We create a dataset including positive samples from IEDB, VDJdb, McPAS-TCR, and the MIRA set, as well as negative samples from both randomization and 10X Genomics assays. We name this collection of samples TChard. We propose the hard split, a simple heuristic for training/test split, which ensures that test samples exclusively present peptides that do not belong to the training set. We investigate the effect of different training/test splitting techniques on the models' test performance, as well as the effect of training and testing the models using mismatched negative samples generated randomly, in addition to the negative samples derived from assays. Our results show that modern deep learning methods fail to generalize to unseen peptides. We provide an explanation why this happens and verify our hypothesis on the TChard dataset. We then conclude that robust prediction of TCR recognition is still far for being solved.

DECODE: a Deep-learning framework for Condensing enhancers and refining boundaries with large-scale functional assays.

MOTIVATION: Mapping distal regulatory elements, such as enhancers, is a cornerstone for elucidating how genetic variations may influence diseases. Previous enhancer-prediction methods have used either unsupervised approaches or supervised methods with limited training data. Moreover, past approaches have implemented enhancer discovery as a binary classification problem without accurate boundary detection, producing low-resolution annotations with superfluous regions and reducing the statistical power for downstream analyses (e.g. causal variant mapping and functional validations). Here, we addressed these challenges via a two-step model called Deep-learning framework for Condensing enhancers and refining boundaries with large-scale functional assays (DECODE). First, we employed direct enhancer-activity readouts from novel functional characterization assays, such as STARR-seq, to train a deep neural network for accurate cell-type-specific enhancer prediction. Second, to improve the annotation resolution, we implemented a weakly supervised object detection framework for enhancer localization with precise boundary detection (to a 10 bp resolution) using Gradient-weighted Class Activation Mapping. RESULTS: Our DECODE binary classifier outperformed a state-of-the-art enhancer prediction method by 24% in transgenic mouse validation. Furthermore, the object detection framework can condense enhancer annotations to only 13% of their original size, and these compact annotations have significantly higher conservation scores and genome-wide association study variant enrichments than the original predictions. Overall, DECODE is an effective tool for enhancer classification and precise localization. AVAILABILITY AND IMPLEMENTATION: DECODE source code and pre-processing scripts are available at decode.gersteinlab.org. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Ranking-Based Convolutional Neural Network Models for Peptide-MHC Class I Binding Prediction.

T-cell receptors can recognize foreign peptides bound to major histocompatibility complex (MHC) class-I proteins, and thus trigger the adaptive immune response. Therefore, identifying peptides that can bind to MHC class-I molecules plays a vital role in the design of peptide vaccines. Many computational methods, for example, the state-of-the-art allele-specific method MHCflurry , have been developed to predict the binding affinities between peptides and MHC molecules. In this manuscript, we develop two allele-specific Convolutional Neural Network-based methods named ConvM and SpConvM to tackle the binding prediction problem. Specifically, we formulate the problem as to optimize the rankings of peptide-MHC bindings via ranking-based learning objectives. Such optimization is more robust and tolerant to the measurement inaccuracy of binding affinities, and therefore enables more accurate prioritization of binding peptides. In addition, we develop a new position encoding method in ConvM and SpConvM to better identify the most important amino acids for the binding events. We conduct a comprehensive set of experiments using the latest Immune Epitope Database (IEDB) datasets. Our experimental results demonstrate that our models significantly outperform the state-of-the-art methods including MHCflurry with an average percentage improvement of 6.70% on AUC and 17.10% on ROC5 across 128 alleles.

A Deep Generative Model for Molecule Optimization via One Fragment Modification.

Molecule optimization is a critical step in drug development to improve desired properties of drug candidates through chemical modification. We developed a novel deep generative model Modof over molecular graphs for molecule optimization. Modof modifies a given molecule through the prediction of a single site of disconnection at the molecule and the removal and/or addition of fragments at that site. A pipeline of multiple, identical Modof models is implemented into Modof-pipe to modify an input molecule at multiple disconnection sites. Here we show that Modof-pipe is able to retain major molecular scaffolds, allow controls over intermediate optimization steps and better constrain molecule similarities. Modof-pipe outperforms the state-of-the-art methods on benchmark datasets: without molecular similarity constraints, Modof-pipe achieves 81.2% improvement in octanol-water partition coefficient penalized by synthetic accessibility and ring size; and 51.2%, 25.6% and 9.2% improvement if the optimized molecules are at least 0.2, 0.4 and 0.6 similar to those before optimization, respectively. Modof-pipe is further enhanced into Modof-pipe m to allow modifying one molecule to multiple optimized ones. Modof-pipe m achieves additional performance improvement as at least 17.8% better than Modof-pipe.

Model-based autoencoders for imputing discrete single-cell RNA-seq data.

Deep neural networks have been widely applied for missing data imputation. However, most existing studies have been focused on imputing continuous data, while discrete data imputation is under-explored. Discrete data is common in real world, especially in research areas of bioinformatics, genetics, and biochemistry. In particular, large amounts of recent genomic data are discrete count data generated from single-cell RNA sequencing (scRNA-seq) technology. Most scRNA-seq studies produce a discrete matrix with prevailing 'false' zero count observations (missing values). To make downstream analyses more effective, imputation, which recovers the missing values, is often conducted as the first step in pre-processing scRNA-seq data. In this paper, we propose a novel Zero-Inflated Negative Binomial (ZINB) model-based autoencoder for imputing discrete scRNA-seq data. The novelties of our method are twofold. First, in addition to optimizing the ZINB likelihood, we propose to explicitly model the dropout events that cause missing values by using the Gumbel-Softmax distribution. Second, the zero-inflated reconstruction is further optimized with respect to the raw count matrix. Extensive experiments on simulation datasets demonstrate that the zero-inflated reconstruction significantly improves imputation accuracy. Real data experiments show that the proposed imputation can enhance separating different cell types and improve the accuracy of differential expression analysis.

High-order neural networks and kernel methods for peptide-MHC binding prediction.

MOTIVATION: Effective computational methods for peptide-protein binding prediction can greatly help clinical peptide vaccine search and design. However, previous computational methods fail to capture key nonlinear high-order dependencies between different amino acid positions. As a result, they often produce low-quality rankings of strong binding peptides. To solve this problem, we propose nonlinear high-order machine learning methods including high-order neural networks (HONNs) with possible deep extensions and high-order kernel support vector machines to predict major histocompatibility complex-peptide binding. RESULTS: The proposed high-order methods improve quality of binding predictions over other prediction methods. With the proposed methods, a significant gain of up to 25-40% is observed on the benchmark and reference peptide datasets and tasks. In addition, for the first time, our experiments show that pre-training with high-order semi-restricted Boltzmann machines significantly improves the performance of feed-forward HONNs. Moreover, our experiments show that the proposed shallow HONN outperform the popular pre-trained deep neural network on most tasks, which demonstrates the effectiveness of modelling high-order feature interactions for predicting major histocompatibility complex-peptide binding. AVAILABILITY AND IMPLEMENTATION: There is no associated distributable software. CONTACT: renqiang@nec-labs.com or mark.gerstein@yale.edu SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

An integrated approach to blood-based cancer diagnosis and biomarker discovery.

Disrupted or abnormal biological processes responsible for cancers often quantitatively manifest as disrupted additive and multiplicative interactions of gene/protein expressions correlating with cancer progression. However, the examination of all possible combinatorial interactions between gene features in most case-control studies with limited training data is computationally infeasible. In this paper, we propose a practically feasible data integration approach, QUIRE (QUadratic Interactions among infoRmative fEatures), to identify discriminative complex interactions among informative gene features for cancer diagnosis and biomarker discovery directly based on patient blood samples. QUIRE works in two stages, where it first identifies functionally relevant gene groups for the disease with the help of gene functional annotations and available physical protein interactions, then it explores the combinatorial relationships among the genes from the selected informative groups. Based on our private experimentally generated data from patient blood samples using a novel SOMAmer (Slow Off-rate Modified Aptamer) technology, we apply QUIRE to cancer diagnosis and biomarker discovery for Renal Cell Carcinoma (RCC) and Ovarian Cancer (OVC). To further demonstrate the general applicability of our approach, we also apply QUIRE to a publicly available Colorectal Cancer (CRC) dataset that can be used to prioritize our SOMAmer design. Our experimental results show that QUIRE identifies gene-gene interactions that can better identify the different cancer stages of samples, as compared to other state-of-the-art feature selection methods. A literature survey shows that many of the interactions identified by QUIRE play important roles in the development of cancer.