Modeling vegetation greenness and its climate sensitivity with deep‐learning technology

Climate sensitivity of vegetation has long been explored using statistical or process‐based models. However, great uncertainties still remain due to the methodologies’ deficiency in capturing the complex interactions between climate and vegetation. Here, we developed global gridded climate–vegetation models based on long short‐term memory (LSTM) network, which is a powerful deep‐learning algorithm for long‐time series modeling, to achieve accurate vegetation monitoring and investigate the complex relationship between climate and vegetation. We selected the normalized difference vegetation index (NDVI) that represents vegetation greenness as model outputs. The climate data (monthly temperature and precipitation) were used as inputs. We trained the networks with data from 1982 to 2003, and the data from 2004 to 2015 were used to validate the models. Error analysis and sensitivity analysis were performed to assess the model errors and investigate the sensitivity of global vegetation to climate change. Results show that models based on deep learning are very effective in simulating and predicting the vegetation greenness dynamics. For models training, the root mean square error (RMSE) is <0.01. Model validation also assure the accuracy of our models. Furthermore, sensitivity analysis of models revealed a spatial pattern of global vegetation to climate, which provides us a new way to investigate the climate sensitivity of vegetation. Our study suggests that it is a good way to integrate deep‐learning method to monitor the vegetation change under global change. In the future, we can explore more complex climatic and ecological systems with deep learning and coupling with certain physical process to better understand the nature.     

Social networks based on frequency of roost cohabitation do not reflect association rates of Myotis lucifugus within their roosts

Bats are a group of mammals well known for forming dynamic social groups. Studies of bat social structures are often based upon the frequency at which bats occupy the same roosts because observing bats directly is not always possible. However, it is not always clear how closely bats occupying the same roost associate with each other, obscuring whether associations result from social relationships or factors such as shared preferences for roosts. Our goal was to determine if bats cohabitating buildings were also found together inside roosts by using anti‐collision technology for PIT tags, which enables simultaneous detection of multiple tags. We PIT‐tagged 293 female little brown myotis (Myotis lucifugus) and installed antennas within two buildings used as maternity roosts in Yellowstone National Park. Antennas were positioned at roost entryways to generate cohabitation networks and along regions of attic ceilings in each building to generate intraroost networks based on proximity of bats to each other. We found that intraroost and cohabitation networks of buildings were significantly correlated, with the same bats tending to be linked in both networks, but that bats cohabitating the same building often roosted apart, leading to differing assessments of social structure. Cohabitation rates implied that bats associate with a greater number of their roost‐mates than was supported by observations within the roost. This caused social networks built upon roost cohabitation rates to be denser, smaller in diameter, and contain nodes with higher average degree centrality. These results show that roost cohabitation does not reflect preference for roost‐mates in little brown myotis, as is often inferred from similar studies, and that social network analyses based on cohabitation may provide misleading results.     

Lipid-dependent sequential allosteric activation of heat-sensing TRPV1 channels by anchor-stereoselective “hot” vanilloid compounds and analogs

Both a silent resident phosphatidylinositol lipid and a “hot” vanilloid agonist capsaicin or resiniferatoxin have been shown to share the same inter-subunit binding pocket between a voltage sensor like domain and a pore domain in TRPV1. However, how the vanilloid competes off the resident lipid for allosteric TRPV1 activation is unknown. Here, the in silico research suggested that anchor-stereoselective sequential cooperativity between an initial recessive transient silent weak ligand binding site and a subsequent dominant steady-state strong ligand binding site in the vanilloid pocket may facilitate the lipid release for allosteric activation of TRPV1 by vanilloids or analogs upon non-covalent interactions. Thus, the resident lipid may play a critical role in allosteric activation of TRPV1 by vanilloid compounds and analogs.     

Comparative proteomic analysis of cysteine oxidation in colorectal cancer patients

Oxidative stress promotes damage to cellular proteins, lipids, membranes and DNA, and plays a key role in the development of cancer. Reactive oxygen species disrupt redox homeostasis and promote tumor formation by initiating aberrant activation of signaling pathways that lead to tumorigenesis. We used shotgun proteomics to identify proteins containing oxidation-sensitive cysteines in tissue specimens from colorectal cancer patients. We then compared the patterns of cysteine oxidation in the membrane fractions between the tumor and non-tumor tissues. Using nano-UPLC-MS^E proteomics, we identified 31 proteins containing 37 oxidation-sensitive cysteines. These proteins were observed with IAM-binding cysteines in non-tumoral region more than tumoral region of CRC patients. Then using the Ingenuity pathway program, we evaluated the cellular canonical networks connecting those proteins. Within the networks, proteins with multiple connections were related with organ morphology, cellular metabolism, and various disorders. We have thus identified networks of proteins whose redox status is altered by oxidative stress, perhaps leading to changes in cellular functionality that promotes tumorigenesis.     

A gait index may underestimate changes of gait: a comparison of the Movement Deviation Profile and the Gait Deviation Index

The ability of the Movement Deviation Profile (MDP) and Gait Deviation Index (GDI) to detect gait changes was compared in a child with cerebral palsy who underwent game training. Conventional gait analysis showed that sagittal plane angles became mirrored about normality after training. Despite considerable gait changes, the GDI showed minimal change, while the MDP detected a difference equal to a shift between 10-9 on the Functional Assessment Questionnaire scale. Responses of the GDI and MDP were examined during a synthetic transition of the patient's curves from before intervention to a state mirrored about normality. The GDI showed a symmetric response on the two opposite sides of normality but the neural network based MDP gave an asymmetric response reflecting faithfully the unequal biomechanical consequences of joint angle changes. In conclusion, the MDP can detect altered gait even if the changes are missed by the GDI.     

Inertial motion capture in conjunction with an artificial neural network can differentiate the gait patterns of hemiparetic stroke patients compared with able-bodied counterparts

Clinical gait analysis has proven to reduce uncertainties in selecting the appropriate quantity and type of treatment for patients with neuromuscular disorders. However, gait analysis as a clinical tool is under-utilised due to the limitations and cost of acquiring and managing data. To overcome these obstacles, inertial motion capture (IMC) recently emerged to counter the limitations attributed to other methods. This paper investigates the use of IMC for training and testing a back-propagation artificial neural network (ANN) for the purpose of distinguishing between hemiparetic stroke and able-bodied ambulation. Routine gait analysis was performed on 30 able-bodied control subjects and 28 hemiparetic stroke patients using an IMC system. An ANN was optimised to classify the two groups, achieving a repeatable network accuracy of 99.4%. It is concluded that an IMC system and appropriate computer methods may be useful for the planning and monitoring of gait rehabilitation therapy of stroke victims.     

Accounting for robustness in modeling signal transduction responses

Abstract

A classical question in systems biology is to find a Boolean model which is able to predict the observed responses of a signaling network. It has been previously shown that such models can be tailored based on experimental data. While fitting a minimum-size network to the experimentally observed data is a natural assumption, it can potentially result in a network which is not so robust against the noises in the training dataset. Indeed, it is widely accepted now that biological systems are generally evolved to be very robust. Therefore, in the present work, we extended the classical formulation of Boolean network construction in order to put weight on the robustness of the created network. We show that our method results generally in more relevant networks. Consequently, considering robustness as a design principle of biological networks can result in more realistic models.