SUMMARY: Currently available and frequently used tools for annotating antibiotic resistance genes (ARGs) in genomes and metagenomes provide results using inconsistent nomenclature. This makes the comparison of different ARG annotation outputs challenging. The comparability of ARG annotation outputs can be improved by mapping gene names and their categories to a common controlled vocabulary such as the Antibiotic Resistance Ontology (ARO). We developed argNorm, a command line tool and Python library, to normalize all detected genes across six ARG annotation tools (eight databases) to the ARO. argNorm also adds information to the outputs using the same ARG categorization so that they are comparable across tools. AVAILABILITY AND IMPLEMENTATION: argNorm is available as an open-source tool at: https://github.com/BigDataBiology/argNorm. It can also be downloaded as a PyPI package and is available on Bioconda and as an nf-core module.

Research software has become essential in science, including in the life sciences [1,2].Most of this software is designed and built by research groups funded by short-term research grants.The coding is performed by trainees who move on to other jobs once the project is completed.This can result in dead software tools, whereby a tool described in a manuscript no longer works after publication [3,4].Commercial software uses sales to pay for long-term maintenance and support.In addition to the financial costs, commercial software often lags behind the capabilities of academic software-a natural consequence of the fact that new ideas are often explored first in academia-and commercial software may not be open source, which poses a barrier for some researchers as it can hinder reproducibility.It is noteworthy, though, that, in the field of machine learning, it is not uncommon for commercial entities to release high-quality tools, including AlphaFold2 [5,6], as well as libraries such as PyTorch [7], which then are incorporated by academic research labs into their computational biology projects.During my training and now, as a group leader, I have created several open source research software tools.My group publicly commits to maintaining these for a minimum of 5 years after the publication of the associated manuscript.In practice, several of our projects have been maintained for longer given that they continue to be used.Ideally, software should be maintained for as long as it is being actively used.We also provide some basic support to users, in the form of addressing their queries.In this perspective, I will first define exactly what is meant by maintenance and when we are committing to it, then describe how we make it possible, and finally end with a call for the community and institutions to be explicit about what users can expect from each piece of research software.Maintaining software is different from extending it.Although the exact boundary between the 2 activities is not always clear cut; maintenance, to me, means that the software should perform as described in the manuscript.This means fixing any bugs that are reported.This may mean that changes are necessary, for example, to accommodate new versions of dependencies which break backwards compatibility (a common cause of software collapse [3]).If the software is provided as a service (e.g., as a web server), concerns related to security and privacy may lead to required updates and even lower-level network functionality may need to be updated to keep the service operational.All of the practices I will describe make it easier to extend the code to perform beyond what is described in the manuscript, but we do not commit to this.

MOTIVATION: Metagenomic binning methods to reconstruct metagenome-assembled genomes (MAGs) from environmental samples have been widely used in large-scale metagenomic studies. The recently proposed semi-supervised binning method, SemiBin, achieved state-of-the-art binning results in several environments. However, this required annotating contigs, a computationally costly and potentially biased process. RESULTS: We propose SemiBin2, which uses self-supervised learning to learn feature embeddings from the contigs. In simulated and real datasets, we show that self-supervised learning achieves better results than the semi-supervised learning used in SemiBin1 and that SemiBin2 outperforms other state-of-the-art binners. Compared to SemiBin1, SemiBin2 can reconstruct 8.3-21.5% more high-quality bins and requires only 25% of the running time and 11% of peak memory usage in real short-read sequencing samples. To extend SemiBin2 to long-read data, we also propose ensemble-based DBSCAN clustering algorithm, resulting in 13.1-26.3% more high-quality genomes than the second best binner for long-read data. AVAILABILITY AND IMPLEMENTATION: SemiBin2 is available as open source software at https://github.com/BigDataBiology/SemiBin/ and the analysis scripts used in the study can be found at https://github.com/BigDataBiology/SemiBin2_benchmark.

Microbial community classification enables identification of putative type and source of the microbial community, thus facilitating a better understanding of how the taxonomic and functional structure were developed and maintained. However, previous classification models required a trade-off between speed and accuracy, and faced difficulties to be customized for a variety of contexts, especially less studied contexts. Here, we introduced EXPERT based on transfer learning that enabled the classification model to be adaptable in multiple contexts, with both high efficiency and accuracy. More importantly, we demonstrated that transfer learning can facilitate microbial community classification in diverse contexts, such as classification of microbial communities for multiple diseases with limited number of samples, as well as prediction of the changes in gut microbiome across successive stages of colorectal cancer. Broadly, EXPERT enables accurate and context-aware customized microbial community classification, and potentiates novel microbial knowledge discovery.

UNLABELLED: MOCAT2 is a software pipeline for metagenomic sequence assembly and gene prediction with novel features for taxonomic and functional abundance profiling. The automated generation and efficient annotation of non-redundant reference catalogs by propagating pre-computed assignments from 18 databases covering various functional categories allows for fast and comprehensive functional characterization of metagenomes. AVAILABILITY AND IMPLEMENTATION: MOCAT2 is implemented in Perl 5 and Python 2.7, designed for 64-bit UNIX systems and offers support for high-performance computer usage via LSF, PBS or SGE queuing systems; source code is freely available under the GPL3 license at http://mocat.embl.de CONTACT: : [email protected] SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Neutrophil extracellular traps (NETs) are believed to be essential in controlling several bacterial pathogens. Quantification of NETs in vitro is an important tool in studies aiming to clarify the biological and chemical factors contributing to NET production, stabilization and degradation. This estimation can be performed on the basis of fluorescent microscopy images using appropriate labelings. In this context, it is desirable to automate the analysis to eliminate both the tedious process of manual annotation and possible operator-specific biases. RESULTS: We propose a framework for the automated determination of NET content, based on visually annotated images which are used to train a supervised machine-learning method. We derive several methods in this framework. The best results are obtained by combining these into a single prediction. The overall Q(2) of the combined method is 93%. By having two experts label part of the image set, we were able to compare the performance of the algorithms to the human interoperator variability. We find that the two operators exhibited a very high correlation on their overall assessment of the NET coverage area in the images (R(2) is 97%), although there were consistent differences in labeling at pixel level (Q(2), which unlike R(2) does not correct for additive and multiplicative biases, was only 89%). AVAILABILITY AND IMPLEMENTATION: Open source software (under the MIT license) is available at https://github.com/luispedro/Coelho2015_NetsDetermination for both reproducibility and application to new data.

MOTIVATION: Evaluation of previous systems for automated determination of subcellular location from microscope images has been done using datasets in which each location class consisted of multiple images of the same representative protein. Here, we frame a more challenging and useful problem where previously unseen proteins are to be classified. RESULTS: Using CD-tagging, we generated two new image datasets for evaluation of this problem, which contain several different proteins for each location class. Evaluation of previous methods on these new datasets showed that it is much harder to train a classifier that generalizes across different proteins than one that simply recognizes a protein it was trained on. We therefore developed and evaluated additional approaches, incorporating novel modifications of local features techniques. These extended the notion of local features to exploit both the protein image and any reference markers that were imaged in parallel. With these, we obtained a large accuracy improvement in our new datasets over existing methods. Additionally, these features help achieve classification improvements for other previously studied datasets. AVAILABILITY: The datasets are available for download at http://murphylab.web.cmu.edu/data/. The software was written in Python and C++ and is available under an open-source license at http://murphylab.web.cmu.edu/software/. The code is split into a library, which can be easily reused for other data and a small driver script for reproducing all results presented here. A step-by-step tutorial on applying the methods to new datasets is also available at that address. CONTACT: [email protected] SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Proteins exhibit complex subcellular distributions, which may include localizing in more than one organelle and varying in location depending on the cell physiology. Estimating the amount of protein distributed in each subcellular location is essential for quantitative understanding and modeling of protein dynamics and how they affect cell behaviors. We have previously described automated methods using fluorescent microscope images to determine the fractions of protein fluorescence in various subcellular locations when the basic locations in which a protein can be present are known. As this set of basic locations may be unknown (especially for studies on a proteome-wide scale), we here describe unsupervised methods to identify the fundamental patterns from images of mixed patterns and estimate the fractional composition of them. METHODS: We developed two approaches to the problem, both based on identifying types of objects present in images and representing patterns by frequencies of those object types. One is a basis pursuit method (which is based on a linear mixture model), and the other is based on latent Dirichlet allocation (LDA). For testing both approaches, we used images previously acquired for testing supervised unmixing methods. These images were of cells labeled with various combinations of two organelle-specific probes that had the same fluorescent properties to simulate mixed patterns of subcellular location. RESULTS: We achieved 0.80 and 0.91 correlation between estimated and underlying fractions of the two probes (fundamental patterns) with basis pursuit and LDA approaches, respectively, indicating that our methods can unmix the complex subcellular distribution with reasonably high accuracy. AVAILABILITY: http://murphylab.web.cmu.edu/software.

We propose an adaptive multiresolution (MR) approach to the classification of fingerprint images. The system adds MR decomposition in front of a generic classifier consisting of feature computation and classification in each MR subspace, yielding local decisions, which are then combined into a global decision using a weighting algorithm. In our previous work on classification of protein subcellular location images, we showed that the space-frequency localized information in the MR subspaces adds significantly to the discriminative power of the system. Here, we go one step farther; We develop a new weighting method which allows for the discriminative power of each subband to be expressed and examined within each class. This, in turn, allows us to evaluate the importance of the information contained within a specific subband. Moreover, we develop a pruning procedure to eliminate the subbands that do not contain useful information. This leads to potential identification of the appropriate MR decomposition both on a per class basis and for a given dataset. With this new approach, we make the system adaptive, flexible as well as more accurate and efficient.