Toxicity of Water-Soluble D-g-PNIPAM Polymers in a Complex with Chemotherapy Drugs and Mechanism of Their Action In Vitro.

The application of a biocompatible polymer nanocarrier can provide target delivery to tumor tissues, improved pharmacokinetics, controlled drug release, etc. Therefore, the proposed strategy was to use the water-soluble star-like copolymers with a Dextran core and Poly(N-isopropylacrylamide) grafts (D-g-PNIPAM) for conjugation with the widely used chemotherapy drugs in oncology-Cisplatin (Cis-Pt) and Doxorubicin (Dox). The molecular characteristics of the copolymer were received using size-exclusion chromatography. The physicochemical characterization of the D-g-PNIPAM-Cis-Pt (or Dox) nanosystem was conducted using dynamic light scattering and FTIR spectroscopy. Using traditional biochemical methods, a comparative analysis of the enhancement of the cytotoxic effect of free Cis-Pt and Dox in combination with D-g-PNIPAM copolymers was performed in cancer cells of the Lewis lung carcinoma line, which are both sensitive and resistant to Dox; in addition, the mechanism of their action in vitro was evaluated.

Isothermal amplifications - a comprehensive review on current methods.

The introduction of nucleic acid amplification techniques has revolutionized the field of medical diagnostics in the last decade. The advent of PCR catalyzed the increasing application of DNA, not just for molecular cloning but also for molecular based diagnostics. Since the introduction of PCR, a deeper understanding of molecular mechanisms and enzymes involved in DNA/RNA replication has spurred the development of novel methods devoid of temperature cycling. Isothermal amplification methods have since been introduced utilizing different mechanisms, enzymes, and conditions. The ease with which isothermal amplification methods have allowed nucleic acid amplification to be carried out has had a profound impact on the way molecular diagnostics are being designed after the turn of the millennium. With all the advantages isothermal amplification brings, the issues or complications surrounding each method are heterogeneous making it difficult to identify the best approach for an end-user. This review pays special attention to the various isothermal amplification methods by classifying them based on the mechanistic characteristics which include reaction formats, amplification information, promoter, strand break, and refolding mechanisms. We would also compare the efficiencies and usefulness of each method while highlighting the potential applications and detection methods involved. This review will serve as an overall outlook on the journey and development of isothermal amplification methods as a whole.

Silent Death by Sound: C60 Fullerene Sonodynamic Treatment of Cancer Cells.

The acoustic pressure waves of ultrasound (US) not only penetrate biological tissues deeper than light, but they also generate light emission, termed sonoluminescence. This promoted the idea of its use as an alternative energy source for photosensitizer excitation. Pristine C60 fullerene (C60), an excellent photosensitizer, was explored in the frame of cancer sonodynamic therapy (SDT). For that purpose, we analyzed C60 effects on human cervix carcinoma HeLa cells in combination with a low-intensity US treatment. The time-dependent accumulation of C60 in HeLa cells reached its maximum at 24 h (800 ± 66 ng/106 cells). Half of extranuclear C60 is localized within mitochondria. The efficiency of the C60 nanostructure's sonoexcitation with 1 MHz US was tested with cell-based assays. A significant proapoptotic sonotoxic effect of C60 was found for HeLa cells. C60's ability to induce apoptosis of carcinoma cells after sonoexcitation with US provides a promising novel approach for cancer treatment.

Examination of blood samples using deep learning and mobile microscopy.

BACKGROUND: Microscopic examination of human blood samples is an excellent opportunity to assess general health status and diagnose diseases. Conventional blood tests are performed in medical laboratories by specialized professionals and are time and labor intensive. The development of a point-of-care system based on a mobile microscope and powerful algorithms would be beneficial for providing care directly at the patient's bedside. For this purpose human blood samples were visualized using a low-cost mobile microscope, an ocular camera and a smartphone. Training and optimisation of different deep learning methods for instance segmentation are used to detect and count the different blood cells. The accuracy of the results is assessed using quantitative and qualitative evaluation standards. RESULTS: Instance segmentation models such as Mask R-CNN, Mask Scoring R-CNN, D2Det and YOLACT were trained and optimised for the detection and classification of all blood cell types. These networks were not designed to detect very small objects in large numbers, so extensive modifications were necessary. Thus, segmentation of all blood cell types and their classification was feasible with great accuracy: qualitatively evaluated, mean average precision of 0.57 and mean average recall of 0.61 are achieved for all blood cell types. Quantitatively, 93% of ground truth blood cells can be detected. CONCLUSIONS: Mobile blood testing as a point-of-care system can be performed with diagnostic accuracy using deep learning methods. In the future, this application could enable very fast, cheap, location- and knowledge-independent patient care.

Variant expression signatures of microRNAs and protein related to growth in a crossbreed between two strains of Nile tilapia (Oreochromis niloticus).

Nile tilapia (Oreochromis niloticus) is a species of worldwide importance for aquaculture. A crossbred lineage was developed through introgressive backcross breeding techniques and combines the high growth performance of the Chitralada (CHIT) lwith attractive reddish color of the Red Stirling (REDS) strains. Since the crossbreed has an unknown genetically improved background, the objective of this work was to characterize expression signatures that portray the advantageous phenotype of the crossbreeds. We characterized the microRNA transcriptome by high throughput sequencing (RNA-seq) and the proteome through mass spectrometry (ESI-Q-TOF-MS) and applied bioinformatics for the comparative analysis of such molecular data on the three strains. Crossbreed expressed a distinct set of miRNAs and proteins compared to the parents. They comprised several microRNAs regulate traits of economic interest. Proteomic profiles revealed differences between parental and crossbreed in expression of proteins associated with glycolisis. Distinctive miRNA and protein signatures contribute to the phenotype of crossbreed.

Machine Learning Methods in Predicting Patients with Suspected Myocardial Infarction Based on Short-Time HRV Data.

Diagnosis of cardiovascular diseases is an urgent task because they are the main cause of death for 32% of the world's population. Particularly relevant are automated diagnostics using machine learning methods in the digitalization of healthcare and introduction of personalized medicine in healthcare institutions, including at the individual level when designing smart houses. Therefore, this study aims to analyze short 10-s electrocardiogram measurements taken from 12 leads. In addition, the task is to classify patients with suspected myocardial infarction using machine learning methods. We have developed four models based on the k-nearest neighbor classifier, radial basis function, decision tree, and random forest to do this. An analysis of time parameters showed that the most significant parameters for diagnosing myocardial infraction are SDNN, BPM, and IBI. An experimental investigation was conducted on the data of the open PTB-XL dataset for patients with suspected myocardial infarction. The results showed that, according to the parameters of the short ECG, it is possible to classify patients with a suspected myocardial infraction as sick and healthy with high accuracy. The optimized Random Forest model showed the best performance with an accuracy of 99.63%, and a root mean absolute error is less than 0.004. The proposed novel approach can be used for patients who do not have other indicators of heart attacks.

Ten simple rules on how to write a standard operating procedure.

Research publications and data nowadays should be publicly available on the internet and, theoretically, usable for everyone to develop further research, products, or services. The long-term accessibility of research data is, therefore, fundamental in the economy of the research production process. However, the availability of data is not sufficient by itself, but also their quality must be verifiable. Measures to ensure reuse and reproducibility need to include the entire research life cycle, from the experimental design to the generation of data, quality control, statistical analysis, interpretation, and validation of the results. Hence, high-quality records, particularly for providing a string of documents for the verifiable origin of data, are essential elements that can act as a certificate for potential users (customers). These records also improve the traceability and transparency of data and processes, therefore, improving the reliability of results. Standards for data acquisition, analysis, and documentation have been fostered in the last decade driven by grassroot initiatives of researchers and organizations such as the Research Data Alliance (RDA). Nevertheless, what is still largely missing in the life science academic research are agreed procedures for complex routine research workflows. Here, well-crafted documentation like standard operating procedures (SOPs) offer clear direction and instructions specifically designed to avoid deviations as an absolute necessity for reproducibility. Therefore, this paper provides a standardized workflow that explains step by step how to write an SOP to be used as a starting point for appropriate research documentation.

Quantification of nitroaromatic explosives in contaminated soil using MALDI-TOF mass spectrometry.

Contamination from various sources is a global environmental and health threat, with mining and military activities in particular having spread nitroaromatic compounds, such as 2,4,6-trinitrotoluene and its degradation products and by-products, to the soil. The investigation and monitoring of large contaminated areas requires new detection methods since the established ones are expensive and time-consuming. Hence, we established a matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) method using 1,5-diaminonaphthalene as the matrix substance and an internal standard for quantification. Analyzing standard substances, we found specific signals for radical and fragment ions of different nitrotoluenes and nitrobenzenes with good reproducibility and detection limits down to 0.25 ng/µL. The analysis of soil sample extracts from a former production site showed clear signals for 2,4,6-trinitrotoluene and the primary degradation products aminodinitrotoluenes. Furthermore, quantification gave results comparable to those obtained by conventional liquid chromatography-tandem mass spectrometry analysis. The MALDI-TOF MS method has a comparatively lower reproducibility, with relative standard deviations of 6% to 20% for multiple measurements of standard solutions and soil sample extracts. Nevertheless, a comparison of both methods revealed the advantages of MALDI-TOF MS analysis of explosive-contaminated areas with regard to costs, time, and handling. Finally, our MALDI-TOF MS method fulfills all the needs for high sample throughput and can therefore be a valuable screening tool for explosive-contaminated areas. Graphical abstract.

Re-Emerging foci of visceral leishmaniasis in Armenia - first molecular diagnosis of clinical samples.

Visceral leishmaniasis (VL) was firstly reported in Armenia in 1913. Following a considerable increase of the number of cases until the mid 1950s, the disease disappeared after 1969 and re-emerged in 1999. Scientific literature about VL in Armenia is available only in Russian or Armenian. This paper presents a historical overview about leishmaniasis in Armenia based on this literature as well as an epidemiological update since the re-emergence of the disease. In 1999-2016, 116 indigenous VL cases were recorded mainly in children in 8 of the 11 districts, however, VL is underreported because of lack of trained medical personal and diagnostic facilities. The aim of this work was to apply for the first time molecular diagnosis of VL in Armenia. Out of 25 VL suspected patients, 22 were positive by microscopy and polymerase chain reaction (PCR). Genotyping using internal transcribed spacer 1-PCR-restriction fragment length polymorphism and sequencing identified the causative agent of VL in Armenia as Leishmania infantum. The present work is an important step towards the inclusion of molecular techniques in the current diagnosis of VL in Armenia and the establishment of local molecular diagnostic facilities.

Toxicity of C60 fullerene-cisplatin nanocomplex against Lewis lung carcinoma cells.

Cisplatin (Cis-Pt) is the cytotoxic agent widely used against tumors of various origin, but its therapeutic efficiency is substantially limited by a non-selective effect and high toxicity. Conjugation of Cis-Pt with nanocarriers is thought to be one option to enable drug targeting. The aim of this study was to estimate toxic effects of the nanocomplex formed by noncovalent interaction of C60 fullerene with Cis-Pt against Lewis lung carcinoma (LLC) cells in comparison with free drug. Scanning tunneling microscopy showed that the minimum size of C60-Cis-Pt nanoparticles in aqueous colloid solution was 1.1 nm whereas that of C60 fullerene was 0.72 nm, thus confirming formation of the nanocomplex. The cytotoxic effect of C60-Cis-Pt nanocomplex against LLC cells was shown to be higher with IC50 values 3.3 and 4.5 times lower at 48 h and 72 h, respectively, as compared to the free drug. 12.5 µM Cis-Pt had no effect on LLC cell viability and morphology while C60-Cis-Pt nanocomplex in Cis-Pt-equivalent concentration substantially decreased the cell viability, impaired their shape and adhesion, inhibited migration and induced accumulation in proapoptotic subG1 phase. Apoptosis induced by the C60-Cis-Pt nanocomplex was confirmed by caspase 3/7 activation and externalization of phosphatidylserine on the outer surface of LLC cells with the double Annexin V-FITC/PI staining. We assume that C60 fullerene as a component of the C60-Cis-Pt nanocomplex promoted Cis-Pt entry and intracellular accumulation thus contributing to intensification of the drug's toxic effect against lung cancer cells.

A pilot study on fingerprinting Leishmania species from the Old World using Fourier transform infrared spectroscopy.

Leishmania species are protozoan parasites and the causative agents of leishmaniasis, a vector borne disease that imposes a large health burden on individuals living mainly in tropical and subtropical regions. Different Leishmania species are responsible for the distinct clinical patterns, such as cutaneous, mucocutaneous, and visceral leishmaniasis, with the latter being potentially fatal if left untreated. For this reason, it is important to perform correct species identification and differentiation. Fourier transform infrared spectroscopy (FTIR) is an analytical spectroscopic technique increasingly being used as a potential tool for identification of microorganisms for diagnostic purposes. By employing mid-infrared (MIR) spectral data, it is not only possible to assess the chemical structures but also to achieve differentiation supported by multivariate statistic analysis. This work comprises a pilot study on differentiation of Leishmania species of the Old World (L. major, L. tropica, L. infantum, and L. donovani) as well as hybrids of distinct species by using vibrational spectroscopic fingerprints. Films of intact Leishmania parasites and their deoxyribonucleic acid (DNA) were characterized comparatively with respect to their biochemical nature and MIR spectral patterns. The strains' hyperspectral datasets were multivariately examined by means of variance-based principal components analysis (PCA) and distance-based hierarchical cluster analysis (HCA). With the implementation of MIR spectral datasets we show that a phenotypic differentiation of Leishmania at species and intra-species level is feasible. Thus, FTIR spectroscopy can be further exploited for building up spectral databases of Leishmania parasites in view of high-throughput analysis of clinical specimens. Graphical abstract For Leishmania species discrimination, sample films of intact parasites and their extracted DNA were analyzed by FTIR micro-spectroscopy. Hyperspectral datasets that comprise mid-infrared fingerprints were submitted to multivariate analysis tools such as principal components analysis (PCA) and hierarchical cluster analysis (HCA).

Intact cell mass spectrometry as a rapid and specific tool for the differentiation of toxic effects in cell-based ecotoxicological test systems.

In the last few decades, MALDI-TOF MS has become a useful technique not only in proteomics, but also as a fast and specific tool for whole cell analysis through intact cell mass spectrometry (IC-MS). The present study evaluated IC-MS as a novel tool for the detection of distinct patterns that can be observed after exposure to a certain toxin or concentration by utilizing the eukaryotic fish cell line RTL-W1. Two different viability assays were performed to define the range for IC-MS investigations, each of which employing copper sulfate, acridine, and ß-naphthoflavone (BNF) as model compounds for several classes of environmental toxins. The IC-MS of RTL-W1 cells revealed not only specific spectral patterns for the various toxins, but also that the concentration used had an effect on RTL-W1 profiles. After the exposure with copper sulfate and acridine, the spectra of RTL-W1 showed a significant increase of certain peaks in the higher mass range (m/z >7000), which is probably attributed to the apoptosis of RTL-W1. On the contrary, exposure to BNF showed a distinct change of ion abundances only in the lower mass range (m/z <7000). Furthermore, a set of mass peaks could be identified as a specific biomarker for a single toxin treatment, so IC-MS demonstrates a new method for the distinction of toxic effects in fish cells. Due to fast sample preparation and high throughput, IC-MS offers great potential for ecotoxicological studies to investigate cellular effects of different substances and complex environmental samples.

Screening and genetic characterization of thermo-tolerant Synechocystis sp. PCC6803 strains created by adaptive evolution.

BACKGROUND: Temperature tolerance is an important aspect for commercial scale outdoor cultivation of microalgae and cyanobacteria. While various genes are known to be related to Synechocystis sp. PCC6803's heat shock response, there is very limited published data concerning the specific genes involved in long term thermal tolerance. We have previously used random mutagenesis and adaptive evolution to generate a mixture of strains of Synechocystis sp. PCC6803 with significantly increased thermal tolerance. The genetic modifications leading to the phenotypes of the newly generated strains are the focus of this work. RESULTS: We used a custom screening platform, based on 96-deepwell microplate culturing in an in house designed cultivation chamber integrated in a liquid handling robot for screening and selection; in addition we also used a more conventional system. The increased thermal tolerances of the isolated monoclonal strains were validated in larger bioreactors and their whole genomes sequenced. Comparison of the sequence information to the parental wild type identified various mutations responsible for the enhanced phenotypes. Among the affected genes identified are clpC, pnp, pyk2, sigF, nlpD, pyrR, pilJ and cya1. CONCLUSIONS: The applied methods (random mutagenesis, in vivo selection, screening, validation, whole genome sequencing) were successfully applied to identify various mutations, some of which are very unlikely to have been identified by other approaches. Several of the identified mutations are found in various strains and (due to their distribution) are likely to have occurred independently. This, coupled with the relatively low number of affected genes underscores the significance of these specific mutations to convey thermal tolerance in Synechocystis.

High-throughput cultivation and screening platform for unicellular phototrophs.

BACKGROUND: High-throughput cultivation and screening methods allow a parallel, miniaturized and cost efficient processing of many samples. These methods however, have not been generally established for phototrophic organisms such as microalgae or cyanobacteria. RESULTS: In this work we describe and test high-throughput methods with the model organism Synechocystis sp. PCC6803. The required technical automation for these processes was achieved with a Tecan Freedom Evo 200 pipetting robot. The cultivation was performed in 2.2 ml deepwell microtiter plates within a cultivation chamber outfitted with programmable shaking conditions, variable illumination, variable temperature, and an adjustable CO2 atmosphere. Each microtiter-well within the chamber functions as a separate cultivation vessel with reproducible conditions. The automated measurement of various parameters such as growth, full absorption spectrum, chlorophyll concentration, MALDI-TOF-MS, as well as a novel vitality measurement protocol, have already been established and can be monitored during cultivation. Measurement of growth parameters can be used as inputs for the system to allow for periodic automatic dilutions and therefore a semi-continuous cultivation of hundreds of cultures in parallel. The system also allows the automatic generation of mid and long term backups of cultures to repeat experiments or to retrieve strains of interest. CONCLUSIONS: The presented platform allows for high-throughput cultivation and screening of Synechocystis sp. PCC6803. The platform should be usable for many phototrophic microorganisms as is, and be adaptable for even more. A variety of analyses are already established and the platform is easily expandable both in quality, i.e. with further parameters to screen for additional targets and in quantity, i.e. size or number of processed samples.

PlanktoVision--an automated analysis system for the identification of phytoplankton.

BACKGROUND: Phytoplankton communities are often used as a marker for the determination of fresh water quality. The routine analysis, however, is very time consuming and expensive as it is carried out manually by trained personnel. The goal of this work is to develop a system for an automated analysis. RESULTS: A novel open source system for the automated recognition of phytoplankton by the use of microscopy and image analysis was developed. It integrates the segmentation of the organisms from the background, the calculation of a large range of features, and a neural network for the classification of imaged organisms into different groups of plankton taxa. The analysis of samples containing 10 different taxa showed an average recognition rate of 94.7% and an average error rate of 5.5%. The presented system has a flexible framework which easily allows expanding it to include additional taxa in the future. CONCLUSIONS: The implemented automated microscopy and the new open source image analysis system--PlanktoVision--showed classification results that were comparable or better than existing systems and the exclusion of non-plankton particles could be greatly improved. The software package is published as free software and is available to anyone to help make the analysis of water quality more reproducible and cost effective.

Characterization of genome methylation patterns in the desert locust Schistocerca gregaria.

DNA methylation is a widely conserved epigenetic modification. The analysis of genome-scale DNA methylation patterns in various organisms suggests that major features of animal methylomes are widely conserved. However, based on the variation of DNA methyltransferase genes in invertebrates, it has also been proposed that DNA methylation could provide a molecular mechanism for ecological adaptation. We have now analyzed the methylome of the desert locust, Schistocerca gregaria, which represents an organism with a high degree of phenotypic plasticity. Using genome-scale bisulfite sequencing, we show here that the S. gregaria methylome is characterized by CpG- and exon-specific methylation and thus shares two major features with other animal methylomes. In contrast to other invertebrates, however, overall methylation levels were substantially higher and a significant fraction of transposons was methylated. Additionally, genic sequences were densely methylated in a pronounced bimodal pattern, suggesting a role for DNA methylation in the regulation of locust gene expression. Our results thus uncover a unique pattern of genome methylation in locusts and provide an important foundation for investigating the role of DNA methylation in locust phase polyphenism.

Comparison of Sonodynamic Treatment Set-Ups for Cancer Cells with Organic Sonosensitizers and Nanosonosensitizers.

Cancer sonodynamic therapy (SDT) is the therapeutic strategy of a high-frequency ultrasound (US) combined with a special sonosensitizer that becomes cytotoxic upon US exposure. The growing number of newly discovered sonosensitizers and custom US in vitro treatment solutions push the SDT field into a need for systemic studies and reproducible in vitro experimental set-ups. In the current research, we aimed to compare two of the most used and suitable SDT in vitro set-ups-"sealed well" and "transducer in well"-in one systematic study. We assessed US pressure, intensity, and temperature distribution in wells under US irradiation. Treatment efficacy was evaluated for both set-ups towards cancer cell lines of different origins, treated with two promising sonosensitizer candidates-carbon nanoparticle C60 fullerene (C60) and herbal alkaloid berberine. C60 was found to exhibit higher sonotoxicity toward cancer cells than berberine. The higher efficacy of sonodynamic treatment with a "transducer in well" set-up than a "sealed well" set-up underlined its promising application for SDT in vitro studies. The "transducer in well" set-up is recommended for in vitro US treatment investigations based on its US-field homogeneity and pronounced cellular effects. Moreover, SDT with C60 and berberine could be exploited as a promising combinative approach for cancer treatment.

The combination of omics strategies to evaluate starter and probiotic strains in the Catharina sour Brazilian-style beer.

Catharina sour, the first internationally recognized Brazilian beer, is characterized by fermentation with lactic acid bacteria (LAB), which may have probiotic potential, and the addition of fruit juice. This study aimed to evaluate the use of the starter Streptococcus thermophilus TH-4 (TH-4) and the probiotics Lacticaseibacillus paracasei F19 and 431, associated with Saccharomyces cerevisiae US-05, in the absence (control)/presence of passion fruit or peach juices. Evaluation proceeded during fermentation and storage by enumeration using pour-plate and qPCR; gene expressions of hop resistance; proteome by Liquid Chromatography Tandem Mass Spectrometry (LC-MS/MS); and odor, flavor, and metabolome by Headspace Solid-Phase Microextraction (HS-SPME), coupled with the gas chromatography-mass spectrometry (GC-MS) analysis. We concluded that the strains studied are recommended for applications in sour beers, due to the presence of defense mechanisms like membrane adhesion and H + pump. Furthermore, HS-SPME/GC-MS indicated that the strains may contribute to the beer flavor and odor.

A toolbox of machine learning software to support microbiome analysis.

The human microbiome has become an area of intense research due to its potential impact on human health. However, the analysis and interpretation of this data have proven to be challenging due to its complexity and high dimensionality. Machine learning (ML) algorithms can process vast amounts of data to uncover informative patterns and relationships within the data, even with limited prior knowledge. Therefore, there has been a rapid growth in the development of software specifically designed for the analysis and interpretation of microbiome data using ML techniques. These software incorporate a wide range of ML algorithms for clustering, classification, regression, or feature selection, to identify microbial patterns and relationships within the data and generate predictive models. This rapid development with a constant need for new developments and integration of new features require efforts into compile, catalog and classify these tools to create infrastructures and services with easy, transparent, and trustable standards. Here we review the state-of-the-art for ML tools applied in human microbiome studies, performed as part of the COST Action ML4Microbiome activities. This scoping review focuses on ML based software and framework resources currently available for the analysis of microbiome data in humans. The aim is to support microbiologists and biomedical scientists to go deeper into specialized resources that integrate ML techniques and facilitate future benchmarking to create standards for the analysis of microbiome data. The software resources are organized based on the type of analysis they were developed for and the ML techniques they implement. A description of each software with examples of usage is provided including comments about pitfalls and lacks in the usage of software based on ML methods in relation to microbiome data that need to be considered by developers and users. This review represents an extensive compilation to date, offering valuable insights and guidance for researchers interested in leveraging ML approaches for microbiome analysis.

Advancing microbiome research with machine learning: key findings from the ML4Microbiome COST action.

The rapid development of machine learning (ML) techniques has opened up the data-dense field of microbiome research for novel therapeutic, diagnostic, and prognostic applications targeting a wide range of disorders, which could substantially improve healthcare practices in the era of precision medicine. However, several challenges must be addressed to exploit the benefits of ML in this field fully. In particular, there is a need to establish "gold standard" protocols for conducting ML analysis experiments and improve interactions between microbiome researchers and ML experts. The Machine Learning Techniques in Human Microbiome Studies (ML4Microbiome) COST Action CA18131 is a European network established in 2019 to promote collaboration between discovery-oriented microbiome researchers and data-driven ML experts to optimize and standardize ML approaches for microbiome analysis. This perspective paper presents the key achievements of ML4Microbiome, which include identifying predictive and discriminatory 'omics' features, improving repeatability and comparability, developing automation procedures, and defining priority areas for the novel development of ML methods targeting the microbiome. The insights gained from ML4Microbiome will help to maximize the potential of ML in microbiome research and pave the way for new and improved healthcare practices.