Machine learning-based approach for automated classification of cell and extracellular matrix using nanomechanical properties.

Fibrosis characterized by excess accumulation of extracellular matrix (ECM) due to complex cell-ECM interactions plays a pivotal role in pathogenesis. Herein, we employ the pancreatic ductal adenocarcinoma (PDAC) model to investigate dynamic alterations in nanomechanical attributes arising from the cell-ECM interactions to study the fibrosis paradigm. Several segregated studies performed on cellular and ECM components fail to recapitulate their complex collaboration. We utilized collagen and fibronectin, the two most abundant PDAC ECM components, and studied their nanomechanical attributes. We demonstrate alteration in morphology and nanomechanical attributes of collagen with varying thicknesses of collagen gel. Furthermore, by mixing collagen and fibronectin in various stoichiometry, their nanomechanical attributes were observed to vary. To demonstrate the dynamicity and complexity of cell-ECM, we utilized Panc-1 and AsPC-1 cells with or without collagen. We observed that Panc-1 and AsPC-1 cells interact differently with collagen and vice versa, evident from their alteration in nanomechanical properties. Further, using nanomechanics data, we demonstrate that ML-based techniques were able to classify between ECM as well as cell, and cell subtypes in the presence/absence of collagen with higher accuracy. This work demonstrates a promising avenue to explore other ECM components facilitating deeper insights into tumor microenvironment and fibrosis paradigm.

Multi-Agent Deep Reinforcement Learning for Multi-Robot Applications: A Survey.

Deep reinforcement learning has produced many success stories in recent years. Some example fields in which these successes have taken place include mathematics, games, health care, and robotics. In this paper, we are especially interested in multi-agent deep reinforcement learning, where multiple agents present in the environment not only learn from their own experiences but also from each other and its applications in multi-robot systems. In many real-world scenarios, one robot might not be enough to complete the given task on its own, and, therefore, we might need to deploy multiple robots who work together towards a common global objective of finishing the task. Although multi-agent deep reinforcement learning and its applications in multi-robot systems are of tremendous significance from theoretical and applied standpoints, the latest survey in this domain dates to 2004 albeit for traditional learning applications as deep reinforcement learning was not invented. We classify the reviewed papers in our survey primarily based on their multi-robot applications. Our survey also discusses a few challenges that the current research in this domain faces and provides a potential list of future applications involving multi-robot systems that can benefit from advances in multi-agent deep reinforcement learning.

Gatekeeper Tyrosine Phosphorylation of SYMRK Is Essential for Synchronizing the Epidermal and Cortical Responses in Root Nodule Symbiosis.

Symbiosis receptor kinase (SYMRK) is indispensable for activation of root nodule symbiosis (RNS) at both epidermal and cortical levels and is functionally conserved in legumes. Previously, we reported SYMRK to be phosphorylated on "gatekeeper" Tyr both in vitro as well as in planta. Since gatekeeper phosphorylation was not necessary for activity, the significance remained elusive. Herein, we show that substituting gatekeeper with nonphosphorylatable residues like Phe or Ala significantly affected autophosphorylation on selected targets on activation segment/αEF and ß3-αC loop of SYMRK. In addition, the same gatekeeper mutants failed to restore proper symbiotic features in a symrk null mutant where rhizobial invasion of the epidermis and nodule organogenesis was unaffected but rhizobia remain restricted to the epidermis in infection threads migrating parallel to the longitudinal axis of the root, resulting in extensive infection patches at the nodule apex. Thus, gatekeeper phosphorylation is critical for synchronizing epidermal/cortical responses in RNS.

Intracellular catalytic domain of symbiosis receptor kinase hyperactivates spontaneous nodulation in absence of rhizobia.

Symbiosis Receptor Kinase (SYMRK), a member of the Nod factor signaling pathway, is indispensible for both nodule organogenesis and intracellular colonization of symbionts in rhizobia-legume symbiosis. Here, we show that the intracellular kinase domain of a SYMRK (SYMRK-kd) but not its inactive or full-length version leads to hyperactivation of the nodule organogenic program in Medicago truncatula TR25 (symrk knockout mutant) in the absence of rhizobia. Spontaneous nodulation in TR25/SYMRK-kd was 6-fold higher than rhizobia-induced nodulation in TR25/SYMRK roots. The merged clusters of spontaneous nodules indicated that TR25 roots in the presence of SYMRK-kd have overcome the control over both nodule numbers and their spatial position. In the presence of rhizobia, SYMRK-kd could rescue the epidermal infection processes in TR25, but colonization of symbionts in the nodule interior was significantly compromised. In summary, ligand-independent deregulated activation of SYMRK hyperactivates nodule organogenesis in the absence of rhizobia, but its ectodomain is required for proper symbiont colonization.

Autophosphorylation of gatekeeper tyrosine by symbiosis receptor kinase.

Plant receptor-like kinases (RLKs) share their evolutionary origin with animal interleukin-1 receptor-associated kinase (IRAK)/Pelle family of soluble kinases and are distinguished by having tyrosine as 'gatekeeper'. This position is adjacent to the hinge region and is hidden in a hydrophobic pocket of the catalytic cleft of protein kinases and is therefore least probable to be a target for any modification. This communication illustrates the accessibility of the gatekeeper site (Y670) towards both autophosphorylation and dephosphorylation in the recombinant cytoplasmic domain of symbiosis receptor kinase from Arachis hypogaea (AhSYMRK). Autophosphorylation on gatekeeper tyrosine was detected prior to extraction but never under in vitro conditions. We hypothesize gatekeeper phosphorylation to be associated with synthesis/maturation of AhSYMRK and this phenomenon may be prevalent among RLKs.