Abstract Motivation Single-cell sequencing technologies allow researchers to study cell-cell variation within a cell population. Variations between cells are driven by the underlying biological network, particularly gene regulatory networks (GRNs). GRNs rewire as cells evolve, and different cells can have different GRNs. However, while single-cell RNA-sequencing (scRNA-seq) and single-cell multi-omics data have been used to reconstruct GRNs, the output GRNs are rarely cell-specific, but rather, most existing methods infer population-level or cell-type-level GRNs. Results We propose CeSpGRN (Cell-Specific Gene Regulatory Network inference), a method that infers cell-specific GRNs from scRNA-seq, paired scRNA-seq and scATAC-seq, or spatial transcriptomic data. In particular, existing methods that use matching scRNA-seq and scATAC-seq data incorporate population-level region information in GRN inference, whereas CeSpGRN utilizes single-cell resolution region information. CeSpGRN infers cell-specific GRNs using a kernel-weighted Gaussian Copula Graphical Model, and incorporates multi-omic or spatial location information when constructing the objective function. We tested CeSpGRN on both simulated and real datasets, and the results show that CeSpGRN has a superior performance compared to baseline methods in reconstructing GRNs and detecting regulatory interactions that differ between cells. CeSpGRN uncovered regulatory interactions that rewire during biological processes on real datasets. Availability and implementation CeSpGRN is a Python package available at https://github.com/PeterZZQ/CeSpGRN.

MOTIVATION: Gene regulatory networks (GRNs) in a cell provide the tight feedback needed to synchronize cell actions. However, genes in a cell also take input from, and provide signals to other neighboring cells. These cell-cell interactions (CCIs) and the GRNs deeply influence each other. Many computational methods have been developed for GRN inference in cells. More recently, methods were proposed to infer CCIs using single cell gene expression data with or without cell spatial location information. However, in reality, the two processes do not exist in isolation and are subject to spatial constraints. Despite this rationale, no methods currently exist to infer GRNs and CCIs using the same model. RESULTS: We propose CLARIFY, a tool that takes GRNs as input, uses them and spatially resolved gene expression data to infer CCIs, while simultaneously outputting refined cell-specific GRNs. CLARIFY uses a novel multi-level graph autoencoder, which mimics cellular networks at a higher level and cell-specific GRNs at a deeper level. We applied CLARIFY to two real spatial transcriptomic datasets, one using seqFISH and the other using MERFISH, and also tested on simulated datasets from scMultiSim. We compared the quality of predicted GRNs and CCIs with state-of-the-art baseline methods that inferred either only GRNs or only CCIs. The results show that CLARIFY consistently outperforms the baseline in terms of commonly used evaluation metrics. Our results point to the importance of co-inference of CCIs and GRNs and to the use of layered graph neural networks as an inference tool for biological networks. AVAILABILITY AND IMPLEMENTATION: The source code and data is available at https://github.com/MihirBafna/CLARIFY.

MOTIVATION: The study of the evolutionary history of biological networks enables deep functional understanding of various bio-molecular processes. Network growth models, such as the Duplication-Mutation with Complementarity (DMC) model, provide a principled approach to characterizing the evolution of protein-protein interactions (PPIs) based on duplication and divergence. Current methods for model-based ancestral network reconstruction primarily use greedy heuristics and yield sub-optimal solutions. RESULTS: We present a new Integer Linear Programming (ILP) solution for maximum likelihood reconstruction of ancestral PPI networks using the DMC model. We prove the correctness of our solution that is designed to find the optimal solution. It can also use efficient heuristics from general-purpose ILP solvers to obtain multiple optimal and near-optimal solutions that may be useful in many applications. Experiments on synthetic data show that our ILP obtains solutions with higher likelihood than those from previous methods, and is robust to noise and model mismatch. We evaluate our algorithm on two real PPI networks, with proteins from the families of bZIP transcription factors and the Commander complex. On both the networks, solutions from our ILP have higher likelihood and are in better agreement with independent biological evidence from other studies. AVAILABILITY AND IMPLEMENTATION: A Python implementation is available at https://bitbucket.org/cdal/network-reconstruction. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

The experimental determination of transcriptional regulatory networks in the laboratory remains difficult and timeconsuming, while computational methods to infer these networks provide only modest accuracy. The latter can be attributed partly to the limitations of a single-organism approach. Computational biology has long used comparative and evolutionary approaches to extend the reach and accuracy of its analyses. In this paper, we describe ProPhyC, a probabilistic phylogenetic model and associated inference algorithms, designed to improve the inference of regulatory networks for a family of organisms by using known evolutionary relationships among these organisms. ProPhyC can be used with various network evolutionary models and any existing inference method. Extensive experimental results on both biological and synthetic data confirm that our model (through its associated refinement algorithms) yields substantial improvement in the quality of inferred networks over all current methods. We also compare ProPhyC with a transfer learning approach we design. This approach also uses phylogenetic relationships while inferring regulatory networks for a family of organisms. Using similar input information but designed in a very different framework, this transfer learning approach does not perform better than ProPhyC, which indicates that ProPhyC makes good use of the evolutionary information.