Characterization of protein complexes, i.e. sets of proteins assembling into a single larger physical entity, is important, as such assemblies play many essential roles in cells such as gene regulation. From networks of protein-protein interactions, potential protein complexes can be identified computationally through the application of community detection methods, which flag groups of entities interacting with each other in certain patterns. Most community detection algorithms tend to be unsupervised and assume that communities are dense network subgraphs, which is not always true, as protein complexes can exhibit diverse network topologies. The few existing supervised machine learning methods are serial and can potentially be improved in terms of accuracy and scalability by using better-suited machine learning models and parallel algorithms. Here, we present Super.Complex, a distributed, supervised AutoML-based pipeline for overlapping community detection in weighted networks. We also propose three new evaluation measures for the outstanding issue of comparing sets of learned and known communities satisfactorily. Super.Complex learns a community fitness function from known communities using an AutoML method and applies this fitness function to detect new communities. A heuristic local search algorithm finds maximally scoring communities, and a parallel implementation can be run on a computer cluster for scaling to large networks. On a yeast protein-interaction network, Super.Complex outperforms 6 other supervised and 4 unsupervised methods. Application of Super.Complex to a human protein-interaction network with ~8k nodes and ~60k edges yields 1,028 protein complexes, with 234 complexes linked to SARS-CoV-2, the COVID-19 virus, with 111 uncharacterized proteins present in 103 learned complexes. Super.Complex is generalizable with the ability to improve results by incorporating domain-specific features. Learned community characteristics can also be transferred from existing applications to detect communities in a new application with no known communities. Code and interactive visualizations of learned human protein complexes are freely available at: https://sites.google.com/view/supercomplex/super-complex-v3-0.

Reactive oxygen species (ROS) are primary effectors of cytotoxicity induced by many anti-cancer drugs. Rhythms in the pseudo-steady-state (PSS) levels of particular intracellular ROS in cancer cells and their relevance to drug effectiveness are unknown thus far. We report that the PSS levels of intracellular superoxide (SOX), an important ROS, exhibit an inherent rhythm in HCT116 colon cancer cells, which is entrained (reset) by the SOX inducer, menadione (MD). This reset was dependent on the expression of p53, and it doubled the sensitivity of the cells to MD. The period of oscillation was found to have a linear correlation with MD concentration, given by the equation, T, in h = 23.52 − 1.05 [MD concentration in µM]. Further, we developed a mathematical model to better understand the molecular mechanisms involved in rhythm reset. Biologically meaningful parameters were obtained through parameter estimation techniques; the model can predict experimental profiles of SOX, establish qualitative relations between interacting species in the system and serves as an important tool to understand the profiles of various species. The model was also able to successfully predict the rhythm reset in MD treated hepatoma cell line, HepG2.

IntroductionThe integrity of the intestinal epithelium is crucial for human health and is harmed in autism spectrum disorder (ASD). An aberrant gut microbial composition resulting in gut-derived metabolic toxins was found to damage the intestinal epithelium, jeopardizing tissue integrity. These toxins further reach the brain via the gut-brain axis, disrupting the normal function of the brain. A mechanistic understanding of metabolic disturbances in the brain and gut is essential to design effective therapeutics and early intervention to block disease progression. Herein, we present a novel computational framework integrating constraint based tissue specific metabolic (CBM) model and whole-body physiological pharmacokinetics (PBPK) modeling for ASD. Furthermore, the role of gut microbiota, diet, and oxidative stress is analyzed in ASD.MethodsA representative gut model capturing host-bacteria and bacteria-bacteria interaction was developed using CBM techniques and patient data. Simultaneously, a PBPK model of toxin metabolism was assembled, incorporating multi-scale metabolic information. Furthermore, dynamic flux balance analysis was performed to integrate CBM and PBPK. The effectiveness of a probiotic and dietary intervention to improve autism symptoms was tested on the integrated model.ResultsThe model accurately highlighted critical metabolic pathways of the gut and brain that are associated with ASD. These include central carbon, nucleotide, and vitamin metabolism in the host gut, and mitochondrial energy and amino acid metabolisms in the brain. The proposed dietary intervention revealed that a high-fiber diet is more effective than a western diet in reducing toxins produced inside the gut. The addition of probiotic bacteria Lactobacillus acidophilus, Bifidobacterium longum longum, Akkermansia muciniphila, and Prevotella ruminicola to the diet restores gut microbiota balance, thereby lowering oxidative stress in the gut and brain.ConclusionThe proposed computational framework is novel in its applicability, as demonstrated by the determination of the whole-body distribution of ROS toxins and metabolic association in ASD. In addition, it emphasized the potential for developing novel therapeutic strategies to alleviate autism symptoms. Notably, the presented integrated model validates the importance of combining PBPK modeling with COBRA -specific tissue details for understanding disease pathogenesis.

Background Proteins often assemble into higher-order complexes to perform their biological functions. Such protein–protein interactions (PPI) are often experimentally measured for pairs of proteins and summarized in a weighted PPI network, to which community detection algorithms can be applied to define the various higher-order protein complexes. Current methods include unsupervised and supervised approaches, often assuming that protein complexes manifest only as dense subgraphs. Utilizing supervised approaches, the focus is not on how to find them in a network, but only on learning which subgraphs correspond to complexes, currently solved using heuristics. However, learning to walk trajectories on a network to identify protein complexes leads naturally to a reinforcement learning (RL) approach, a strategy not extensively explored for community detection. Here, we develop and evaluate a reinforcement learning pipeline for community detection on weighted protein–protein interaction networks to detect new protein complexes. The algorithm is trained to calculate the value of different subgraphs encountered while walking on the network to reconstruct known complexes. A distributed prediction algorithm then scales the RL pipeline to search for novel protein complexes on large PPI networks. Results The reinforcement learning pipeline is applied to a human PPI network consisting of 8k proteins and 60k PPI, which results in 1,157 protein complexes. The method demonstrated competitive accuracy with improved speed compared to previous algorithms. We highlight protein complexes such as C4orf19, C18orf21, and KIAA1522 which are currently minimally characterized. Additionally, the results suggest TMC04 be a putative additional subunit of the KICSTOR complex and confirm the involvement of C15orf41 in a higher-order complex with HIRA, CDAN1, ASF1A, and by 3D structural modeling. Conclusions Reinforcement learning offers several distinct advantages for community detection, including scalability and knowledge of the walk trajectories defining those communities. Applied to currently available human protein interaction networks, this method had comparable accuracy with other algorithms and notable savings in computational time, and in turn, led to clear predictions of protein function and interactions for several uncharacterized human proteins.

Many, if not most, proteins assemble into higher-order complexes to perform their biological functions. Such protein-protein interactions (PPI) are often experimentally measured for pairs of proteins and summarized in a weighted PPI network, to which community detection algorithms can be applied to define the various higher-order protein complexes. Current methods, which include both unsupervised and supervised approaches, often assume that protein complexes manifest only as dense subgraphs, and in the case of supervised approaches, focus only on learning which subgraphs correspond to complexes, not how to find them in a network, a task that is currently solved using heuristics. However, learning to walk trajectories on a network with the goal of finding protein complexes lends itself naturally to a reinforcement learning (RL) approach, a strategy that has not been extensively explored for community detection. Here, we evaluated the use of a reinforcement learning pipeline for community detection in weighted protein-protein interaction networks to detect new protein complexes. Using known complexes, the algorithm is trained to calculate the value of different possible subgraph densities in the process of walking on the network to find a protein complex. Then, a distributed prediction algorithm scales the RL pipeline to search for protein complexes on large PPI networks. The reinforcement learning pipeline applied to a human PPI network consisting of 8k proteins and 60k PPI results in 1,157 protein complexes and shows competitive accuracy with improved speed when compared to previous algorithms. We highlight protein complexes harboring minimally characterized proteins including C4orf19, C18orf21, and KIAA1522, suggest TMC04 to be a putative additional subunit of the KICSTOR complex, and confirm the participation of C15orf41 in a higher-order complex with CDAN1, ASF1A, and HIRA by 3D structural modeling. Reinforcement learning offers several distinct advantages for community detection, including scalability and knowledge of the walk trajectories defining those communities.