Search for: All records

Properties of molecules are indicative of their functions and thus are useful in many applications. With the advances of deep-learning methods, computational approaches for predicting molecular properties are gaining increasing momentum. However, there lacks customized and advanced methods and comprehensive tools for this task currently.

Here, we develop a suite of comprehensive machine-learning methods and tools spanning different computational models, molecular representations and loss functions for molecular property prediction and drug discovery. Specifically, we represent molecules as both graphs and sequences. Built on these representations, we develop novel deep models for learning from molecular graphs and sequences. In order to learn effectively from highly imbalanced datasets, we develop advanced loss functions that optimize areas under precision–recall curves (PRCs) and receiver operating characteristic (ROC) curves. Altogether, our work not only serves as a comprehensive tool, but also contributes toward developing novel and advanced graph and sequence-learning methodologies. Results on both online and offline antibiotics discovery and molecular property prediction tasks show that our methods achieve consistent improvements over prior methods. In particular, our methods achieve #1 ranking in terms of both ROC-AUC (area under curve) and PRC-AUC on the AI Cures open challenge for drug discovery related to COVID-19.

Our source code is released as part of the MoleculeX library (https://github.com/divelab/MoleculeX) under AdvProp.

Supplementary data are available at Bioinformatics online.

 

High‐speed video records of a single‐stroke positive cloud‐to‐ground (+CG) flash were used to examine the evolution of eight needles developing more or less radially from the +CG channel. All these eight needles occurred during the later return‐stroke stage and the following continuing current stage. Six needles, after their initial extension from the lateral surface of the parent channel core, elongated via bidirectional recoil events, which are responsible for flickering, and two of them evolved into negative stepped leaders. For the latter two, the mean extension speed decreased from 5.3 × 10⁶to 3.4 × 10⁵and then to 1.3 × 10⁵ m/s during the initial, recoil‐event, and stepping stages, respectively. The initial needle extension ranged from 70 to 320 m (N = 8), extension via recoil events from 50 to 210 m (N = 6), and extension via stepping from 810 to 1,870 m (N = 2). Compared with needles developing from leader channels, the different behavior of needle flickering, the longer length, the faster extension speed, and the higher flickering rate observed in this work may be attributed to a considerably higher current (rate of charge supply) during the return‐stroke and early continuing‐current stages of +CG flashes.

 

Public goods are often either over-consumed in the absence of regulatory mechanisms, or remain completely unused, as in the Covid-19 pandemic, where social distance constraints are enforced to limit the number of people who can share public spaces. In this work, we plug this gap through market based mechanisms designed to efficiently allocate capacity constrained public goods. To design these mechanisms, we leverage the theory of Fisher markets, wherein each agent in the economy is endowed with an artificial currency budget that they can spend to avail public goods. While Fisher markets provide a strong methodological backbone to model resource allocation problems, their applicability is limited to settings involving two types of constraints - budgets of individual buyers and capacities of goods. Thus, we introduce a modified Fisher market, where each individual may have additional physical constraints, characterize its solution properties and establish the existence of a market equilibrium. Furthermore, to account for additional constraints we introduce a social convex optimization problem where we perturb the budgets of agents such that the KKT conditions of the perturbed social problem establishes equilibrium prices. Finally, to compute the budget perturbations we present a fixed point scheme and illustrate convergence guarantees through numerical experiments. Thus, our mechanism, both theoretically and computationally, overcomes a fundamental limitation of classical Fisher markets, which only consider capacity and budget constraints. 

Climate warming is known to impact ecosystem composition and functioning. However, it remains largely unclear how soil microbial communities respond to long-term, moderate warming. In this study, we used Illumina sequencing and microarrays (GeoChip 5.0) to analyze taxonomic and functional gene compositions of the soil microbial community after 14 years of warming (at 0.8–1.0 °C for 10 years and then 1.5–2.0 °C for 4 years) in a Californian grassland. Long-term warming had no detectable effect on the taxonomic composition of soil bacterial community, nor on any plant or abiotic soil variables. In contrast, functional gene compositions differed between warming and control for bacterial, archaeal, and fungal communities. Functional genes associated with labile carbon (C) degradation increased in relative abundance in the warming treatment, whereas those associated with recalcitrant C degradation decreased. A number of functional genes associated with nitrogen (N) cycling (e.g., denitrifying genes encoding nitrate-, nitrite-, and nitrous oxidereductases) decreased, whereasnifHgene encoding nitrogenase increased in the warming treatment. These results suggest that microbial functional potentials are more sensitive to long-term moderate warming than the taxonomic composition of microbial community.