Ecological and evolutionary consequences of selective interspecific information use

Recent work has shown that animals frequently use social information from individuals of their own species as well as from other species; however, the ecological and evolutionary consequences of this social information use remain poorly understood. Additionally, information users may be selective in their social information use, deciding from whom and how to use information, but this has been overlooked in an interspecific context. In particular, the intentional decision to reject a behaviour observed via social information has received less attention, although recent work has indicated its presence in various taxa. Based on existing literature, we explore in which circumstances selective interspecific information use may lead to different ecological and coevolutionary outcomes between two species, such as explaining observed co-occurrences of putative competitors. The initial ecological differences and the balance between the costs of competition and the benefits of social information use potentially determine whether selection may lead to trait divergence, convergence or coevolutionary arms race between two species. We propose that selective social information use, including adoption and rejection of behaviours, may have far-reaching fitness consequences, potentially leading to community-level eco-evolutionary outcomes. We argue that these consequences of selective interspecific information use may be much more widespread than has thus far been considered.     

Estimating tree-based dynamic treatment regimes using observational data with restricted treatment sequences

A dynamic treatment regime (DTR) is a sequence of decision rules that provide guidance on how to treat individuals based on their static and time-varying status. Existing observational data are often used to generate hypotheses about effective DTRs. A common challenge with observational data, however, is the need for analysts to consider “restrictions” on the treatment sequences. Such restrictions may be necessary for settings where (1) one or more treatment sequences that were offered to individuals when the data were collected are no longer considered viable in practice, (2) specific treatment sequences are no longer available, or (3) the scientific focus of the analysis concerns a specific type of treatment sequences (eg, “stepped-up” treatments). To address this challenge, we propose a restricted tree–based reinforcement learning (RT-RL) method that searches for an interpretable DTR with the maximum expected outcome, given a (set of) user-specified restriction(s), which specifies treatment options (at each stage) that ought not to be considered as part of the estimated tree-based DTR. In simulations, we evaluate the performance of RT-RL versus the standard approach of ignoring the partial data for individuals not following the (set of) restriction(s). The method is illustrated using an observational data set to estimate a two-stage stepped-up DTR for guiding the level of care placement for adolescents with substance use disorder.     

Role of plant volatiles in host location by the specialist parasitoidMicroplitis croceipes cresson (Braconidae: Hymenoptera)

A study was conducted to determine the primary source of volatile cues within the plant-host complex used by hostseeking freeflying female Microplitis cro-ceipesCresson in flight tunnel bioassays. In single-source and two-choice tests, using wasps given an oviposition experience on either cotton (Gossypium hirsutum)or cowpea (Vigna unguiculata)seedlings damaged by corn earworm (CEW; Helicoverpa zeaBoddie), the damaged seedlings were significantly more attractive than the CEW frass, which was in turn more attractive than the larvae themselves. In a series of two-choice wind-tunnel tests, the discriminatory ability of the wasps was examined, following various oviposition experiences. Significantly more wasps flew to plants with old damage than to plants with fresh damage, regardless of whether they had experience on fresh or old damage. In a comparison of plant species, wasps with only one experience on either hostdamaged cotton or host-damaged cowpea were unable to distinguish between them, and showed no preference for either plant, whereas wasps with multiple experiences on a particular plant preferentially flew to that plant in the choice test. In comparing hosts with nonhosts, wasps successfully learned to distinguish CEW from beet armyworm (BAW; Spodoptera exigua)on cotton but were unable to distinguish CEW from either BAW or cabbage looper (Trichoplusia ni)on cowpea. The results show the important role played by plant volatiles in the location of hosts by M. croceipesand indicate the wasps limitations in discriminating among the various odors. The ecological advantages and disadvantages of this behavior are discussed.     

Differences in preference for species-specific female calls between acoustically experienced and acoustically naive maleRibautodelphax planthoppers (Homoptera: Delphacidae)

Males of the planthopper Ribautodelphax imitanswere exposed to playbacks of either conspecific or heterospecific (R. imitantoides)female calls during their development from egg to adult, and thereafter these, as well as naive males,were offered a two- way choice between these calls. Males of all treatments approached the conspecific call significantly more often. However, males primed by the conspecific call chose the heterospecific call almost four times less often than did males primed by heterospecific calls or naive males, thus showing that the preference for conspecific calls can be partly learned. Males primed by heterospecific calls performed very similarly to completely naive males, suggesting that the signal recognition mechanism is much less sensitive to heterospecific calls than to conspecific calls. Males with experience of the conspecific female call tended to take more time to reach the call source in the trials than both other types of males. The evolutionary implications of these findings are discussed.     

CryoRes: Local Resolution Estimation of Cryo-EM Density Maps by Deep Learning

Recent progress in cryo-EM research has ignited a revolution in biological macromolecule structure determination. Resolution is an essential parameter for quality assessment of a cryo-EM density map, and it is known that resolution varies in different regions of a map. Currently available methods for local resolution estimation require manual adjustment of parameters and in some cases necessitate acquisition or de novo generation of so-called “half maps”. Here, we developed CryoRes, a deep-learning algorithm to estimate local resolution directly from a single final cryo-EM density map, specifically by learning resolution-aware patterns of density map voxels through supervised training on a large dataset comprising 1,174 experimental cryo-EM density maps. CryoRes significantly outperforms all of the state-of-the-art competing resolution estimation methods, achieving an average RMSE of 2.26 Å for local resolution estimation relative to the currently most reliable FSC-based method blocres, yet requiring only the single final map as input. Further, CryoRes is able to generate a molecular mask for each map, with accuracy 12.12% higher than the masks generated by ResMap. CryoRes is ultra-fast, fully automatic, parameter-free, applicable to cryo-EM subtomogram data, and freely available at https://cryores.zhanglab.net.     

Individual risk prediction: Comparing random forests with Cox proportional-hazards model by a simulation study

With big data becoming widely available in healthcare, machine learning algorithms such as random forest (RF) that ignores time-to-event information and random survival forest (RSF) that handles right-censored data are used for individual risk prediction alternatively to the Cox proportional hazards (Cox-PH) model. We aimed to systematically compare RF and RSF with Cox-PH. RSF with three split criteria [log-rank (RSF-LR), log-rank score (RSF-LRS), maximally selected rank statistics (RSF-MSR)]; RF, Cox-PH, and Cox-PH with splines (Cox-S) were evaluated through a simulation study based on real data. One hundred eighty scenarios were investigated assuming different associations between the predictors and the outcome (linear/linear and interactions/nonlinear/nonlinear and interactions), training sample sizes (500/1000/5000), censoring rates (50%/75%/93%), hazard functions (increasing/decreasing/constant), and number of predictors (seven, 15 including noise variables). Methods' performance was evaluated with time-dependent area under curve and integrated Brier score. In all scenarios, RF had the worst performance. In scenarios with a low number of events (⩽70), Cox-PH was at least noninferior to RSF, whereas under linearity assumption it outperformed RSF. Under the presence of interactions, RSF performed better than Cox-PH as the number of events increased whereas Cox-S reached at least similar performance with RSF under nonlinear effects. RSF-LRS performed slightly worse than RSF-LR and RSF-MSR when including noise variables and interaction effects. When applied to real data, models incorporating survival time performed better. Although RSF algorithms are a promising alternative to conventional Cox-PH as data complexity increases, they require a higher number of events for training. In time-to-event analysis, algorithms that consider survival time should be used.     

Automatic Detection of Severely and Mildly Infected COVID-19 Patients with Supervised Machine Learning Models

ObjectivesWhen the prognosis of COVID-19 disease can be detected early, the intense-pressure and loss of workforce in health-services can be partially reduced. The primary-purpose of this article is to determine the feature-dataset consisting of the routine-blood-values (RBV) and demographic-data that affect the prognosis of COVID-19. Second, by applying the feature-dataset to the supervised machine-learning (ML) models, it is to identify severely and mildly infected COVID-19 patients at the time of admission.Material and methodsThe sample of this study consists of severely (n = 192) and mildly (n = 4010) infected-patients hospitalized with the diagnosis of COVID-19 between March-September, 2021. The RBV-data measured at the time of admission and age-gender characteristics of these patients were analyzed retrospectively. For the selection of the features, the minimum-redundancy-maximum-relevance (MRMR) method, principal-components-analysis and forward-multiple-logistics-regression analyzes were used. The features set were statistically compared between mild and severe infected-patients. Then, the performances of various supervised-ML-models were compared in identifying severely and mildly infected-patients using the feature set.ResultsIn this study, 28 RBV-parameters and age-variable were found as the feature-dataset. The effect of features on the prognosis of the disease has been clinically proven. The ML-models with the highest overall-accuracy in identifying patient-groups were found respectively, as follows: local-weighted-learning (LWL)-97.86%, K-star (K*)-96.31%, Naive-Bayes (NB)-95.36% and k-nearest-neighbor (KNN)-94.05%. Also, the most successful models with the highest area-under-the-receiver-operating-characteristic-curve (AUC) values in identifying patient groups were found respectively, as follows: LWL-0.95%, K*-0.91%, NB-0.85% and KNN-0.75%.ConclusionThe findings in this article have significant a motivation for the healthcare professionals to detect at admission severely and mildly infected COVID-19 patients.     

A transformer architecture for retention time prediction in liquid chromatography mass spectrometry-based proteomics

Accurate retention time (RT) prediction is important for spectral library-based analysis in data-independent acquisition mass spectrometry-based proteomics. The deep learning approach has demonstrated superior performance over traditional machine learning methods for this purpose. The transformer architecture is a recent development in deep learning that delivers state-of-the-art performance in many fields such as natural language processing, computer vision, and biology. We assess the performance of the transformer architecture for RT prediction using datasets from five deep learning models Prosit, DeepDIA, AutoRT, DeepPhospho, and AlphaPeptDeep. The experimental results on holdout datasets and independent datasets exhibit state-of-the-art performance of the transformer architecture. The software and evaluation datasets are publicly available for future development in the field.     

Role of a telencephalic nucleus in the delayed song learning of socially isolated zebra finches

Male zebra finches normally learn their song from adult models during a restricted period of juvenile development. If song models are not available then, juveniles develop an isolate song which can be modified in adulthood. In this report we investigate the features of juvenile experience that underly the timing of song learning. Juvenile males raised in soundproof chambers or in visual isolation from conspecifics developed stable isolate song. However, whereas visual isolate song notes were similar to those of colony-reared males, soundproof chamber isolates included many phonologically abnormal notes in their songs. Despite having stable isolate songs, both groups copied new notes from tutors presented to them in adulthood (2.7 notes per bird for soundproof chamber isolates, 4.4 notes per bird for visual isolates). Old notes were often modified or eliminated. We infer that social interactions with live tutors are normally important for closing the sensitive period for song learning. Lesions of a forebrain nucleus (IMAN) had previously been shown to disrupt juvenile song learning, but not maintenance of adult song for up to 5 weeks after surgery. In this study, colony-reared adult males given bilateral lesions of IMAN retained all their song notes for up to 4–7.5 months after lesioning. However, similar lesions blocked all song note acquisition in adulthood by both visual and soundproof chamber isolates. Other work has shown that intact hearing is necessary for the maintenance of adult zebra finch song. We infer that auditory pathways used for song maintenance and acquisition differ: IMAN is necessary for auditorily guided song acquisition—whether by juveniles or adults—but not for adult auditorily guided song maintenance. © 1993 John Wiley & Sons, Inc.