Characterization Of Landscape Research Articles

Francisco de Holanda e os descaminhos de seus textos (séculos XVIII, XIX e XX)

This review aims to gather scattered information about the paths of some texts by Francisco de Holanda. As it would only be edited and published from the end of the 19th century, that is, more than three centuries after the production of the texts, the routes taken by Holanda’s manuscripts seem to aid in understanding the uniqueness of some of his propositions, while also contributing to the characterization of the Iberian intellectual landscape. In our view, the turbulent transmission of his texts provides an important piece of data for the comparison of the issues surrounding his production. In summary, the trajectory of the autographs is traced from their production in the 16th century, their rediscovery in the late 18th century, until their actual edition in the period between the late 19th and early 20th centuries.

Characterization of metabolite landscape discrimination four Bovis calculus sources by untargeted metabolomics combined with chemometric

Bovis calculus has been used as a traditional Chinese medicine for more than 2000 years. Due to Natural Bovis calculus (NBC) is expensive and rare. To meet the clinical needs, three kinds of Bovis calculus substitutes, namely Bovis calculus sativus (BCS), Bovis calculus artifactus (BCA), and Bovis calculus culture (BCC) were approved to be used. To illustrate the characterization of metabolite landscape of the Bovis calculus sources, untargeted metabolomics by UHPLC-HRMS was carried out on four sources of Bovis calculus. The results showed that a total of 12,643 features were observed in Bovis calculus samples. The four Bovis calculus sources could be clearly discriminated based on 6262 significant difference features according to PCA and PLS-DA. NBC and BCA samples showed different metabolites characterization. BCS and BCC samples showed similarity with each other. The quality of BCC was affected by producers. Heat map analysis results showed that identified 43 chemical compounds can be used as marker to classified Bovis calucus sources. These compounds mainly affected bile acid biosynthesis, betaine metabolism, and taurine and hypotaurine metabolism. As we know, this is the first comprehensive comparison of the metabolite difference among NBC, BCS, BCC and BCA based on untargeted metabolomics combined with chemometric. The results illustrated that the material basis of the four Bovis calculus source was not consistent, it correlated with the producing process. BCS and BCC may be used to replace each other. It provides a theoretical basis for its clinical application.

Comprehensive Characterization of the Genetic Landscape of African Swine Fever Virus: Insights into Infection Dynamics, Immunomodulation, Virulence and Genes with Unknown Function.

African Swine Fever (ASF) is a lethal contagious hemorrhagic viral disease affecting the swine population. The causative agent is African Swine Fever Virus (ASFV). There is no treatment or commercial vaccine available at present. This virus poses a significant threat to the global swine industry and economy, with 100% mortality rate in acute cases. ASFV transmission occurs through both direct and indirect contact, with control measures limited to early detection, isolation, and culling of infected pigs. ASFV exhibits a complex genomic structure and encodes for more than 50 structural and 100 non-structural proteins and has 150 to 167 open reading frames (ORFs). While many of the proteins are non-essential for viral replication, they play crucial roles in mediating with the host to ensure longevity and transmission of virus in the host. The dynamic nature of ASFV research necessitates constant updates, with ongoing exploration of various genes and their functions, vaccine development, and other ASF-related domains. This comprehensive review aims to elucidate the structural and functional roles of both newly discovered and previously recorded genes involved in distinct stages of ASFV infection and immunomodulation. Additionally, the review discusses the virulence genes and genes with unknown functions, and proposes future interventions.

Environmental and anthropogenic factors mediating the functional connectivity of the mesquite lizard along the eastern Trans-Mexican Volcanic Belt.

Functional connectivity, the extent to which a landscape facilitates or impedes the dispersal of individuals across the landscape, is a key factor for the survival of species. Anthropogenic activities, such as urbanization, agriculture and roads, negatively impact functional connectivity of most species, particularly low-vagility species like lizards. Here, we examine how a landscape modified by anthropogenic activities affects the functional connectivity, at both broad and fine scales, of a widely distributed generalist lizard Sceloporus grammicus in the eastern Trans-Mexican Volcanic Belt, Mexico. We estimated for the first time the species' genetic structure, gene flow and functional connectivity in agricultural and forest zones using genomic data, a comprehensive landscape characterization and novel methods including gravity models. Our results showed not only marked genetic differentiation across the study region but also that functional connectivity is maintained for tens of kilometres despite S. grammicus low vagility. Specifically, we found that substrate and air temperature facilitated connectivity over broad and fine scales, respectively, while agricultural cover, relative humidity and slope were important for connectivity and gene flow. Contrastingly, forest cover and roads favoured (broad-scale) and limited (fine-scale) connectivity, likely associated with movement facilitated by small forest patches and with thermoregulation. Altogether, these results support that S. grammicus alternates its thermoregulatory behaviour depending on the distance travelled and the habitat environmental conditions, and that it can disperse through relatively modified landscapes, mainly using agricultural zones. The information obtained is crucial to understanding the response of lizards to current anthropogenic pressures and their potential to adapt.

Molecular characterization of the salivary adenoid cystic carcinoma immune landscape by anatomic subsites

Adenoid cystic carcinoma (AdCC) is a slow-growing salivary gland malignancy that relapses frequently. AdCCs of the submandibular gland exhibit unique differences in prognosis and treatment response to adjuvant radiotherapy compared to other sites, yet the role of tumor anatomic subsite on gene expression and tumor immune microenvironment (TIME) composition remains unclear. We used 87 samples, including 48 samples (27 AdCC and 21 normal salivary gland tissue samples) from 4 publicly available AdCC RNA sequencing datasets, a validation set of 33 minor gland AdCCs, and 39 samples from an in-house cohort (30 AdCC and 9 normal salivary gland samples). RNA sequencing data were used for single sample gene set enrichment analysis and TIME deconvolution. Quantitative PCR and multiplex immunofluorescence were performed on the in-house cohort. Wilcoxon rank-sum, nonparametric equality-of-medians tests and linear regression models were used to evaluate tumor subsite differences. AdCCs of different anatomic subsites including parotid, submandibular, sublingual, and minor salivary glands differed with respect to expression of several key tumorigenic pathways. Among the three major salivary glands, the reactive oxygen species (ROS)/nuclear factor erythroid 2-related factor 2 (NRF2) pathway signature was significantly underexpressed in AdCC of submandibular compared to parotid and sublingual glands while this association was not observed among normal glands. Additionally, the NRF2 pathway, whose expression was associated with favorable overall survival, was overexpressed in AdCCs of parotid gland compared to minor and submandibular glands. The TIME deconvolution identified differences in CD4+ T cell populations between AdCC of major and minor glands and natural killer (NK) cells among AdCC of minor, submandibular, and parotid glands while plasma cells were enriched in normal submandibular glands compared to other normal gland controls. Our data reveal key molecular differences in AdCC of different anatomic subsites. The ROS and NRF2 pathways are underexpressed in submandibular and minor AdCCs compared to parotid gland AdCCs, and NRF2 pathway expression is associated with favorable overall survival. The CD4+ T, NK, and plasma cell populations also vary by tumor subsites, suggesting that the observed submandibular AdCC tumor-intrinsic pathway differences may be responsible for influencing the TIME composition and survival differences.

Multi-omics and single cell characterization of cancer immunosenescence landscape

Cellular senescence (CS) is closely related to tumor progression. However, the studies about CS genes across human cancers have not explored the relationship between cancer senescence signature and telomere length. Additionally, single-cell analyses have not revealed the evolutionary trends of malignant cells and immune cells at the CS level. We defined a CS-associated signature, called “senescence signature”, and found that patients with higher senescence signature had worse prognosis. Higher senescence signature was related to older age, higher genomic instability, longer telomeres, increased lymphocytic infiltration, higher pro-tumor immune infiltrates (Treg cells and MDSCs), and could predict responses to immune checkpoint inhibitor therapy. Single-cell analysis further reveals malignant cells and immune cells share a consistent evolutionary trend at the CS level. MAPK signaling pathway and apoptotic processes may play a key role in CS, and senescence signature may effectively predict sensitivity of MEK1/2 inhibitors, ERK1/2 inhibitors and BCL-2 family inhibitors. We also developed a new CS prediction model of cancer survival and established a portal website to apply this model (https://bio-pub.shinyapps.io/cs_nomo/).

TransCell: In Silico Characterization of Genomic Landscape and Cellular Responses by Deep Transfer Learning.

Gene expression profiling of new or modified cell lines becomes routine today; however, obtaining comprehensive molecular characterization and cellular responses for a variety of cell lines, including those derived from underrepresented groups, is not trivial when resources are minimal. Using gene expression to predict other measurements has been actively explored; however, systematic investigation of its predictive power in various measurements has not been well studied. Here, we evaluated commonly used machine learning methods and presented TransCell, a two-step deep transfer learning framework that utilized the knowledge derived from pan-cancer tumor samples to predict molecular features and responses. Among these models, TransCell had the best performance in predicting metabolite, gene effect score (or genetic dependency), and drug sensitivity, and had comparable performance in predicting mutation, copy number variation, and protein expression. Notably, TransCell improved the performance by over 50% in drug sensitivity prediction and achieved a correlation of 0.7 in gene effect score prediction. Furthermore, predicted drug sensitivities revealed potential repurposing candidates for new 100 pediatric cancer cell lines, and predicted gene effect scores reflected BRAF resistance in melanoma cell lines. Together, we investigated the predictive power of gene expression in six molecular measurement types and developed a web portal (http://apps.octad.org/transcell/) that enables the prediction of 352,000 genomic and cellular response features solely from gene expression profiles.

The making of the Chinese urban landscape: Exploring a framework for analysis

Despite sociopolitical changes, urban landscape heritage has traditionally been valued in Chinese society. However, in the past two to three decades, intensifying pressures for urban redevelopment have created major challenges to urban landscape management. While the management of urban landscape change has focused on landscape-based conservation techniques, urban landscape characterization and assessment, and urban landscape planning, its theoretical and practical foundations remain to be clarified. In connection with the epistemological orientations of landscape in both China and the outside world, this article proposes a new conceptual framework comprising a triad of structural-correlative, morphogenetic-generative, and integrated perspectives for the study and management of urban landscape heritage in China.

Oxidative stress-related genes score predicts prognosis and immune cell infiltration landscape characterization in breast cancer

BackgroundThe tumor microenvironment (TME) typically experiences oxidative stress (OS), marked by a high level of reactive oxygen species (ROS) that can impact tumor advancement and prognosis by modulating the behavior of tumor cells and various immune cells. Oxidative stress-related genes (OSRG) encompass a range of genes involved in ROS pathways, and their specific roles in breast cancer (BC) necessitate further investigation. MethodsUnivariate Cox analysis was performed on genes linked to the OS pathway in the Gene Set Enrichment Analysis (GSEA) database, leading to the identification of 29 significant OSRG in BC. OSRG was divided into three distinct clusters according to the expression and the OSRG score based on the differentially expressed genes (DEGs) was further calculated by principal component analysis (PCA). The correlation between OSRG score and BC clinical features, mutation characteristics, immune checkpoints and immune cell infiltration was analyzed. Establish a multiariable Cox regression model to predict OSRG score effects on clinical characteristics. ResultsSignificant differences were observed in survival analysis, enriched pathways, and immune infiltration among the three OSRG clusters based on 29 genes. Gene clusters were identified through the final selected 395 DEGs, revealing three distinct OSRG expression patterns. An OSRG score model was constructed using DEGs, demonstrating a significant association between high OSRG score and poor prognosis. Significantly, immune checkpoint-related genes exhibited a notable upregulation in the high OSRG score cohort. Additionally, a positive correlation was observed between the OSRG score and tumor mutation burden (TMB) in BC. The OSRG score holds potential implications for clinical immunotherapy in BC patients, and a nomogram was constructed with robust predictive capability for evaluating patient prognosis. ConclusionsThis study elucidated the features of OSRG within BC TME and their possible prognostic significance, offering valuable insights for the development of more targeted immunotherapy approaches for individuals with BC.

Machine Learning Derived Collective Variables for the Study of Protein Homodimerization in Membrane.

The accurate calculation of equilibrium constants for protein-protein association is of fundamental importance to quantitative biology and remains an outstanding challenge for computational biophysics. Traditionally, equilibrium constants have been computed from one-dimensional free energy surfaces derived from sampling along a single collective variable. Importantly, recent advances in enhanced sampling methodology have facilitated the characterization of multidimensional free energy landscapes, often exposing multiple thermodynamically important minima missed by more restrictive sampling methods. A key to the effectiveness of this multidimensional sampling approach is the identification of collective variables that effectively define the configurational space of dissociated and associated states. Here we present the application of two machine learning methods for the unbiased determination of collective variables for enhanced sampling and analysis of protein-protein association. Our results both validate prior work, based on intuition derived collective variables, and demonstrate the effectiveness of the machine learning methods for the identification of collective variables for association reactions in complex biomolecular systems.

MDB-10. DIVERGENT MEDULLOBLASTOMA CHROMATIN STATES DISCLOSE KDM2B AS A NOVEL ONCOGENIC DEPENDENCY

Abstract BACKGROUND Medulloblastoma (MB) is a highly malignant childhood cerebellar tumor comprising a collection of molecularly and clinically distinct entities. Group 3 and Group 4-MB subgroups originate from overlapping progenitor pools of the developing rhombic lip when neuronal differentiation hierarchies are subverted through somatic alterations. Mutations suspected to deregulate the activity of chromatin-modifying genes are pervasive in Group 3 and Group 4-MB. However, the molecular consequences of these alterations remain largely undefined. METHODS We characterized the chromatin landscape of fifty-two primary MBs using chromatin immunoprecipitation followed by sequencing (ChIP-seq) for six histone modifications and performed multi-modal integration with sample-matched somatic lesions, genome-wide DNA methylation, and transcriptomic profiles. RESULTS Analysis of differential chromatin states across MB subgroups using a Hidden Markov Model revealed a significant enrichment of the bivalent enhancer state (EnhBiv; marked by coincident H3K4me1 and H3K27me3) in Group 4-MB which localized to promoters of neurodevelopmental genes and transcription factors. To functionally dissect the pathogenetic significance of the enriched EnhBiv state in Group 4-MB, we sought to identify key regulators that confer this state. Integrative bioinformatics coupled with CUT&RUN analysis revealed significant enrichment of KDM2B, a histone lysine demethylase overexpressed in Group 4-MB, in gene promoters marked by the EnhBiv state. CRISPR gene targeting or targeted protein degradation of KDM2B selectively suppressed growth of Group 3 and Group 4-MB models in vitro and in vivo. Mechanistically, inhibition of KDM2B disrupted chromatin bivalency by blocking PRC2 complex recruitment and reducing H3K27me3 deposition, profoundly derepressing PRC2 targets involved in neuronal differentiation. CONCLUSIONS Our comprehensive characterization of the MB chromatin landscape in a large cohort of primary tumors provides unprecedented insights into the epigenetic basis of MB subgroups, implicating novel mechanisms of tumorigenesis, and nominating KDM2B as a selective dependency in Group 3/4-MB that should be prioritized as an attractive therapeutic target.

Confinement energy landscape classification reveals membrane receptor nano-organization mechanisms

The cell membrane organization has an essential functional role through the control of membrane receptor confinement in micro- or nanodomains. Several mechanisms have been proposed to account for these properties, although some features have remained controversial, notably the nature, size, and stability of cholesterol- and sphingolipid-rich domains or lipid rafts. Here, we probed the effective energy landscape acting on single-nanoparticle-labeled membrane receptors confined in raft nanodomains— epidermal growth factor receptor (EGFR), Clostridium perfringens ε-toxin receptor (CPεTR), and Clostridium septicum α-toxin receptor (CSαTR)—and compared it with hop-diffusing transferrin receptors. By establishing a new analysis pipeline combining Bayesian inference, decision trees, and clustering approaches, we systematically classified single-protein trajectories according to the type of effective confining energy landscape. This revealed the existence of only two distinct organization modalities: confinement in a quadratic energy landscape for EGFR, CPεTR, and CSαTR (A), and free diffusion in confinement domains resulting from the steric hindrance due to F-actin barriers for transferrin receptor (B).The further characterization of effective confinement energy landscapes by Bayesian inference revealed the role of interactions with the domain environment in cholesterol- and sphingolipid-rich domains with (EGFR) or without (CPεTR and CSαTR) interactions with F-actin to regulate the confinement energy depth. These two distinct mechanisms result in the same organization type (A). We revealed that the apparent domain sizes for these receptor trajectories resulted from Brownian exploration of the energy landscape in a steady-state-like regime at a common effective temperature, independently of the underlying molecular mechanisms. These results highlight that confinement domains may be adequately described as interaction hotspots rather than rafts with abrupt domain boundaries. Altogether, these results support a new model for functional receptor confinement in membrane nanodomains and pave the way to the constitution of an atlas of membrane protein organization.

GPU‐Accelerated Urban Flood Modeling Using a Nonuniform Structured Grid and a Super Grid Scale River Channel

AbstractNew remote sensing technologies, and the meter‐scale geospatial data they create, now allow for detailed urban landscape characterization, thereby advancing grid‐based hydrodynamic models. However, using a uniform fine grid over urban catchments generally result in dense grids and can lead to prohibitive computational costs. Moreover, an inability to see below the water surface and measure river bathymetry in most terrain remote sensing can severely impact local‐scale river hydraulics calculations given the significant volume of water conveyed by the channel. This paper introduces a super grid channel model which allow river channels with any width above that of the grid resolution to be simulated in 1D manner. As an extension of a previous subgrid model, this integration facilitates a seamless transition between subgrid and super grid channels, accommodating situations where channel width may surpass or fall below the grid resolution. The key contribution is the integration of the novel 1D channel representation with a nonuniform structured 2D floodplain hydrodynamic model and then coding this for application on GPU. Compared with the previous pure 2D nonuniform structured approaches, the new model presents an efficient compromise for riverine urban flooding where we are less concerned about fine‐scale details of in‐channel flow. Three tests reveal that the proposed model maintains accuracy but with significantly reduced computational cost. By leveraging GPU architectures, a ∼10× speedup compared to CPU computations is achieved, and a typical 6‐day urban flooding problem (domain size 1.42 km2) at 1 m resolution can be achieved within 10 hr on a single 8 GB GPU.

Effect of global shrinkage parameter of horseshoe prior in compressed sensing

This study investigates the effect of the global shrinkage parameter τ of a horseshoe prior, one of the global–local shrinkage priors, on linear regression in sparse signal processing. Statistical mechanics methods are employed to examine the accuracy of signal estimation. The phase diagram of the success and failure of signal recovery in noiseless compressed sensing with varying τ is discussed from the viewpoint of dynamic characterization of approximate message passing (AMP) as a solving algorithm and static characterization of the free-energy landscape. It is found that there exists a parameter region where the AMP algorithm can hardly recover the true signal, even though the true signal is locally stable. The analysis of the free-energy landscape also provides important insight into the optimal choice of τ.

Gut microbial genomes with paired isolates from China illustrate probiotic and cardiometabolic effects

The gut microbiome displays genetic differences among populations, and characterization of the genomic landscape of the gut microbiome in China remains limited. Here, we present the Chinese Gut Microbial Reference (CGMR) set, comprising 101,060 high-quality metagenomic assembled genomes (MAGs) of 3,707 nonredundant species from 3,234 fecal samples across primarily rural Chinese locations, 1,376 live isolates mainly from lactic acid bacteria, and 987 novel species relative to worldwide databases. We observed region-specific coexisting MAGs and MAGs with probiotic and cardiometabolic functionalities. Preliminary mouse experiments suggest a probiotic effect of two Faecalibacillus intestinalis isolates in alleviating constipation, cardiometabolic influences of three Bacteroides fragilis_A isolates in obesity, and isolates from the genera Parabacteroides and Lactobacillus in host lipid metabolism. Our study expands the current microbial genomes with paired isolates and demonstrates potential host effects, contributing to the mechanistic understanding of host-microbe interactions.

Shifts in the functional capacity and metabolite composition of the gut microbiome during recovery from enteric infection.

While enteric pathogens have been widely studied for their roles in causing foodborne infection, their impacts on the gut microbial community have yet to be fully characterized. Previous work has identified notable changes in the gut microbiome related to pathogen invasion, both taxonomically and genetically. Characterization of the metabolic landscape during and after enteric infection, however, has not been explored. Consequently, we investigated the metabolome of paired stools recovered from 60 patients (cases) during and after recovery from enteric bacterial infections (follow-ups). Shotgun metagenomics was applied to predict functional microbial pathways combined with untargeted metametabolomics classified by Liquid Chromatography Mass Spectrometry. Notably, cases had a greater overall metabolic capacity with significantly higher pathway richness and evenness relative to the follow-ups (p<0.05). Metabolic pathways related to central carbon metabolism, amino acid metabolism, and lipid and fatty acid biosynthesis were more highly represented in cases and distinct signatures for menaquinone production were detected. By contrast, the follow-up samples had a more diverse metabolic landscape with enhanced richness of polar metabolites (p<0.0001) and significantly greater richness, evenness, and overall diversity of nonpolar metabolites (p<0.0001). Although many metabolites could not be annotated with existing databases, a marked increase in certain clusters of metabolites was observed in the follow-up samples when compared to the case samples and vice versa. These findings suggest the importance of key metabolites in gut health and recovery and enhance understanding of metabolic fluctuations during enteric infections.

Integrated Approach of Historical Landscape Characterisation Techniques and Remote Sensing for the Definition of Predictive Models and Scenario Analysis in the Planning of Archaeological Areas

This study explores the synergistic integration of remote sensing (RS) and Historical Landscape Characterisation (HLC) methodology as an innovative, multi-scalar and holistic approach to enhance archaeological planning. The goal is to maximize the effectiveness of the investigations, optimizing data collection and improving the contextual understanding of the sites. In fact, these methodologies can significantly contribute to the documentation, conservation, planning and valorisation of archaeological areas. By integrating RS data with features detected by HLC, a complete picture is obtained that facilitates a deeper understanding of the landscape and historical dynamics. This article will explain the combined approach of RS and HLC, presenting some methodologies key to improving the precision and effectiveness of archaeological planning. This integration facilitates the sustainable preservation of archaeological resources and contributes to the conscious management of cultural heritage in the context of contemporary development. The paper demonstrates, through a case study, how the application of the two methodologies (RS and HLC) in an integrated form can provide an exhaustive interpretation of the territory in which the archaeological area is located, which can represent an exhaustive knowledge base on which to set up effective processes for the strategic territorial planning of archaeological areas.

Landscaping characterization of the campus at the UEMG Ituiutaba, Minas Gerais, Brazil

The purpose of this work was to characterize the landscape of the campus at the University of the Minas Gerais State (in portuguese, Universidade do Estado de Minas Gerais - UEMG), located at Ituiutaba. As for such, the local plants were identified ranging from herbaceous to shrub type, due to them being the most commonly employed to perform alterations for landscape purposes. Subsequently, some areas of the campus were photographed to create a landscape characterization of the scenery in regard to its landscape's composition and vegetation. 102 species of herbaceous, subshrub, and shrub plants were found belonging to 39 families; 38.23% being native and the other 61.77% being non-native (cultivated, naturalized, and exotic). In regard to the landscape’s composition in loco, the principles of message, equilibrium, scale, dominance, harmony, and climax were contemplated. Furthermore, in regard to the guiding principles for the selection of vegetable species, it was observed that aesthetic, functional and temporal attributes were incorporated in all the analyzed areas. In conclusion, the landscape’s composition of the campus at the UEMG Ituiutaba fulfills its aesthetic, functional and ecological roles, however it’s worth highlighting that the adequate handling can be the defining factor in assuring the continuity of these functions.

Mutation characteristics and molecular evolution of ovarian metastasis from gastric cancer and potential biomarkers for paclitaxel treatment

Ovarian metastasis is one of the major causes of treatment failure in patients with gastric cancer (GC). However, the genomic characteristics of ovarian metastasis in GC remain poorly understood. In this study, we enroll 74 GC patients with ovarian metastasis, with 64 having matched primary and metastatic samples. Here, we show a characterization of the mutation landscape of this disease, alongside an investigation into the molecular heterogeneity and pathway mutation enrichments between synchronous and metachronous metastasis. We classify patients into distinct clonal evolution patterns based on the distribution of mutations in paired samples. Notably, the parallel evolution group exhibits the most favorable prognosis. Additionally, by analyzing the differential response to chemotherapy, we identify potential biomarkers, including SALL4, CCDC105, and CLDN18, for predicting the efficacy of paclitaxel treatment. Furthermore, we validate that CLDN18 fusion mutations improve tumor response to paclitaxel treatment in GC with ovarian metastasis in vitro and vivo.

Genotype sampling for deep-learning assisted experimental mapping of a combinatorially complete fitness landscape.

Experimental characterization of fitness landscapes, which map genotypes onto fitness, is important for both evolutionary biology and protein engineering. It faces a fundamental obstacle in the astronomical number of genotypes whose fitness needs to be measured for any one protein. Deep learning may help to predict the fitness of many genotypes from a smaller neural network training sample of genotypes with experimentally measured fitness. Here I use a recently published experimentally mapped fitness landscape of more than 260 000 protein genotypes to ask how such sampling is best performed. I show that multilayer perceptrons, recurrent neural networks, convolutional networks, and transformers, can explain more than 90% of fitness variance in the data. In addition, 90% of this performance is reached with a training sample comprising merely ≈103 sequences. Generalization to unseen test data is best when training data is sampled randomly and uniformly, or sampled to minimize the number of synonymous sequences. In contrast, sampling to maximize sequence diversity or codon usage bias reduces performance substantially. These observations hold for more than one network architecture. Simple sampling strategies may perform best when training deep learning neural networks to map fitness landscapes from experimental data. The fitness landscape data analyzed here is publicly available as described previously (Papkou et al. 2023). All code used to analyze this landscape is publicly available at https://github.com/andreas-wagner-uzh/fitness_landscape_sampling.