Find all our latest news, insights, and events

Like many other branches of bioinformatics, that of biomolecular modeling is evolving at an unprecedented pace by the hand of Artificial Intelligence. At Nexco we are committed to staying at the forefront of these advancements. So, we took the time to peek into CASP16’s first outputs (presentations, abstracts book, videos, preprints, rankings, models, etc.; all freely available online) to review the state of the art of biomolecular structure prediction as of early 2025.

Sequencing by Expansion (SBX) is a new nanopore-based sequencing technology that converts DNA into a highly measurable surrogate called an Xpandomer to boost the signal-to-noise ratio when sequencing. This innovative technology achieves sequencing speeds superior to older techniques and could expand NGS applications in healthcare, where fast turnaround times are essential.

Seeing is believing, but regular images aren’t enough in modern biology. In order to achieve our finest understanding of the mechanisms of life as well as the origins of disease — and ultimately how to treat them — we need to understand how the molecules arising from the (epi)genome distribute. The spatially resolved concentrations of RNA transcripts, proteins, metabolites and other molecules that define a cell’s state, function and fate, can be measured through dedicated Spatial -Omics techniques that are bringing about a revolution in biology and medicine. Among them, the rapidly emerging spatial proteomics technologies enable exploration of the complex protein landscapes of cells and tissues, to inform on their current and future states at higher resolution than ever before and possibly with richer information than alternatives such as spatial transcriptomics.

As we have covered already a few times because these techniques are at the core of Nexco’s expertise and most requested activities, single-cell RNA sequencing (scRNA-seq) and Spatial Transcriptomics (ST) stand as revolutionary tools in biology and medicine. This is so because they allow the exploration of cellular states at high resolution, providing unique descriptors essential to advance fundamental research in biology and to track disease-related markers for diagnosis.

As we have showcased in our blog throughout 2024, the year has been a whirlwind for artificial intelligence, not just for the technology behind the latest AI models themselves and their multiple applications, in our case focusing on those to biological sciences, but also for AI markets and businesses. With rapid advancements, shifting markets, and adapting business strategies, it is crystal-clear that the AI landscape is growing and maturing in many ways, some unexpected.

Throughout 2024 we at Nexco have undergone remarkable growth and achievements, following from close and participating at the frontiers of computational biotechnology, and including you too in our vision. We will keep pushing the boundaries of bioinformatics, harnessing the power of artificial intelligence (AI) and cutting-edge technologies to accelerate research and drive innovation in the life sciences. This dedication to advancement is clearly reflected in our blog posts from the past year, showcasing our commitment to staying ahead in all these rapidly evolving fields that affect fundamental biology, applied biotechnology, and the pharma.

In recent years, and especially after being the star component of various vaccines against Covid-19, RNA has emerged as a major player in therapeutic interventions. This includes not only messenger RNA (mRNA) as the information code to produce therapeutic proteins inside the body, as with mRNA Covid-19 vaccines, but also as the target of small molecules that alter their function and stability, most often by inhibiting their translation.

A recent study published in NPG’s Communications Biology has illuminated the spatial organization of muscle fibers within murine tibialis anterior muscles in three dimensions, by integrating spatially resolved multi-omics. The structural organization unveiled in the study is certainly quite intricate, but makes full functional sense: it turns out that the proportions of different myofiber subtypes, as dictated by their gene expression patterns and also evident in metabolic profiles, differ along the length of the muscle, optimizing the arrangement of the metabolic pathways that produce ATP.

Large Language Models, a special kind of “Artificial Neural Network” trained to “understand” and “reason” on natural text, computer code, and in the languages of biology, are transforming bioinformatics. Read on this primer to learn the basics about LLMs in all the forms useful to your research and to know how we at Nexco are using them to innovate bioinformatics tools and services, including the adaptation of LLMs to your specific needs with privacy and customizability in mind.

Computational protein design is advancing at a fast pace after the cascade of developments in deep learning applied to molecular systems triggered by Deepmind’s release of its AlphaFold 2 model back in 2020. Yet, a significant challenge remains: the existing AI models are quite limited in their ability to incorporate non-protein elements into the design process, limiting their versatility. A recent study from our neighbors at EPFL introduces a method that addresses this limitation head-on: the Context-aware Amino acid Recovery from Backbone Atoms and heteroatoms, CARBonAra. Read on as we present this new tool in the context of existing alternatives and of related work, discussing along the way the field of computational protein design, its applications and challenges, and the still important role of human expert intervention, all of which we offer at Nexco.

Microbiome analysis is the investigation of the vast communities of microbes that live and interact with each other in particular environments. Researchers perform microbiome analysis with metagenomics, which includes sequencing-based approaches such as 16S rRNA sequencing and shotgun metagenome sequencing.

As we cover every month here in our blog, bioinformatics is evolving blazingly fast, in particular in the last years with advancements in artificial intelligence (AI). Every few months, a new tool, resource or database revolutionizes some aspect of the field; and among tools, AI constantly brings new ways to better process and analyze data (as we covered for example when we touched on the latest foundational models for biology) as well as new ways to make better predictions (as exemplified by AlphaFold 3). Today we will touch on large language models (LLMs) trained on human-readable data such as human-written text and source code, just like what powers the infamous ChatGPT, and their several applications to biology — now and in the near future.

Imagine an AI system with so much “knowledge” about biology, that it can seamlessly integrate and analyze vast amounts of genomic, transcriptomic, proteomic, and other -omics data, even mixed together by being “aware” of the relationships between them. Such a system could be used for robust, cross-domain applications in bioinformatics: predicting the effects of genetic mutations, designing novel therapeutic interventions, and uncovering hidden biology.

When looking at molecular structures, and especially when trying to explore their conformations and interactions interactively, computer systems based in flat screens and keyboard-mouse combinations are extremely limiting. Such interfaces feel unintuitive given the poor coupling of 2D inputs and outputs to the actually 3D nature of molecular structure. They are also clunky to use due to the abundance of menus and commands. They offer virtually no way for multiple users to collaborate concurrently other than by sharing video feed of the screen. Even a single user is limited in that s/he can act on the systems at single points.

Through bioinformatics, where data processing and analysis techniques are in continuous evolution as the experimental methods to explore the -omics advance, groundbreaking innovations continue to redefine our understanding of the biological world. New methodologies continuously push the boundaries of what is possible in data analysis, as we have covered in recent articles presenting, for example, a new tool for simple and powerful integration of single-cell RNA data from heterogeneous sources, some new methods to accelerate proteomics analyses, and our own end-to-end solution for Omics analysis, ONex.

You know at Nexco we are always on the lookout for groundbreaking innovations in bioinformatics, in order to keep you informed and ourselves updated with the latest technologies that can help you in your projects in the best possible way. Today, we are thrilled to share the latest leap forward in structural biology: AlphaFold 3 [1]. Read on to know more about this model, its implications, its limitations, and also to see it in action with what we pose is the basis for the future of drug discovery.

We are thrilled to share the exciting highlights from our recent participation at the Swiss Biotech Day 2024 in Basel, in our home country Switzerland! Our founders and CEOs were fully immersed in engaging discussions, forging valuable connections, and exploring exciting opportunities with representatives from numerous companies across the life sciences industry.

Transposable elements, or so-called “jumping genes,” are highly repetitive sequences contributing to around half of the human genome. This vast ocean of transposable elements has countless roles in human development, health, and disease , with an ever-increasing number of discoveries being made thanks to the affordability of omics technologies used to investigate their diverse biological functions.

Long-read sequencing has transformed genomics, transcriptomics, and epigenomics by illuminating the dark side of the genome previously missed with short-read sequencing approaches. Highly repetitive regions like telomeres, centromeres, and transposable elements, alongside clinically relevant genetic variants or structural variations, are no longer cryptic and unreadable but can now be sequenced with unparalleled accuracy and efficiency (1).

In a groundbreaking effort to what we can summarize as “have a computer understand the entirety of the central dogma of molecular biology and everything that arises from it”, a complex group of researchers have developed a new foundational multimodal model, Evo, that can parse and processes protein, DNA, and RNA sequences all at once, akin to how a multimodal AI model or an artificial general intelligence (AGI) can handle say text, video, and audio.

Welcome to the dark side of the genome ─ transposable elements. These repetitive sequences comprise around half of the human genome (1), and their intricate control contributes to countless aspects of healthy human physiology and development, from immune regulation to brain function (2).

The integration of single-cell transcriptomics data coming from different experiments and individuals is at the core of data analysis, but critical and challenging due to the presence of technical variability or “batch effects”. Variations stemming from differences in sample processing and experimental protocols often impede comparative analyses and can lead to overcorrection when applying standard batch effect correction methods, resulting in the loss of true biological variability. A new method just published in Nature Communications offers an elegant and powerful solution: by leveraging prior knowledge in the form of cell type annotations to preserve the biological variance within the data, STACAS v2 ensures that critical distinctions between cell types and individuals are not lost during the integration process. The new method outperforms more complex methods, either supervised or unsupervised, and strikes a remarkable balance between mitigating batch effects and preserving the genuine biological variability within the data, even when faced with incomplete or imprecise cell type annotations. And we at Nexco can use this new tool in your projects involving data from heterogenous sources.

In a recent blog post (“Large Language Models like ChatGPT Begin to Permeate Bioinformatics”) we delved into the integration of ChatGPT-like AI models into bioinformatics pipelines, unveiling new possibilities for text mining, ontology, and other applications in computational biology. In this new post we embark on a broader exploration about how language models are becoming instrumental across diverse domains of research and development in biology by the private and public sectors.

As Next Generation Sequencing (NGS) technologies have advanced, we’ve seen a dramatic reduction in costs and a corresponding surge in data volume. What once cost millions of dollars to sequence a complete human genome can now be done for less than $1,000. This remarkable shift has made sequencing more accessible to a wider range of laboratories, paving the way for precision medicine.

Proteins, the molecular workhorses of life, have found extensive applications across industries due to their remarkable catalytic and recognition capabilities. However, the gap between the natural functions of proteins and the demands of industrial processes often necessitates engineering interventions to enhance traits such as stability, efficiency, and substrate spectrum. At Nexco’s protein engineering and structural biology workflows we not only utilize modern AI tools but also apply decades of hands-on human expertise in protein design, engineering, computational modeling, and experimental characterization. Thus we are at the forefront of mastering protein design and engineering through all possible means.

In a huge collaborative effort, researchers from the BRAIN Initiative Cell Census Network (BICCN) have combined single-cell and spatial transcriptomics to catalog the type and location of cells present across all parts of the mouse brain in unprecedented detail. As reported in a series of articles published in Nature on 13th December 2023, the resulting high-resolution atlas reveals the hidden depths of cellular and regional diversity and spatial cell-cell interactions between distinct brain regions alongside novel cell-type marker combinations (1–3). However, these discoveries were only possible thanks to integrating data from different cutting-edge single-cell and spatial transcriptomic technologies, where each method elegantly complimented the other to harness the maximum amount of spatial and transcriptomic information possible. So, in the third installment of our spatial transcriptomic series, we explore how the integration of multimodal data types in this ambitious project was fundamental to the whole mouse brain atlas and how it creates opportunities for the future.

Understanding interactions between proteins and small molecules is crucial for advancing fundamental biology and drug discovery. While experimentation is of course reliable but very slow and expensive, computational methods are cheap but face challenges in accuracy, prompting a shift towards AI-driven solutions. Here we present three cutting-edge models that break barriers in protein-ligand complex prediction, inspired by novel technologies that fuel AlphaFold 2 and similar software for protein structure prediction. Read on to learn how these models work, how they perform, their pros and cons compared to traditional software, the challenges ahead, and how we at Nexco see them reshaping computational drug design and discovery, holding promise for accelerated pharma research.

The gradual integration of Large Language Models (LLMs) like ChatGPT into biology is starting to happen, opening up new ways to do text mining, ontology, and bioinformatics. Given the potential of this technology to reshape the way researchers approach data analysis and knowledge extraction, we at Nexco are closely monitoring its evolution and its concrete applications. Let’s explore together recent works that apply LLMs to problems in biology, discussing their collective impact and their transformative potential.

Analyzing high-dimensional spatial transcriptomic data appropriately and efficiently is an absolute must for any spatial transcriptomic experiment to produce accurate, robust, and biologically meaningful results. But, for many researchers, spatial transcriptomic data analysis remains challenging due to the sheer scale and complexity of data generated, not to mention the vast number of analysis options available. So, in the second installment of our spatial transcriptomic series, we provide some key considerations to help you get to grips with that all-important data analysis.

Proteomics, the science of studying proteins and their regulation, modifications and functions, generates huge amounts of data. Therefore, software tools for efficient data management, browsing and search are crucial for scientific discovery in this field of biology. Building on an algorithm developed by Facebook, Spectroscape is set to revolutionize the exploration and analysis of proteomic data by allowing for real-time query and visualization of spectral archives and providing researchers with a valuable resource for error correction and novel discoveries. We at Nexco can set up Spectroscape with your private datasets off the web, for you to profit from all its capabilities.

In recent years, scientists have been delving into the virtual world like never before. Leaving aside the hype associated to the idea of a “Metaverse”, the fact is that virtual reality (VR) technology, once seen as a faddish gaming gadget with clunky graphics and cumbersome to use as it required headsets wired to computers and external cameras, has evolved into a powerful, low-entry-barrier tool for researchers in various scientific fields. At Nexco we recognize the potential of VR to transform the way scientists communicate concepts and ideas in the sciences. This is why through collaboration with its creators we have mastered the use of MolecularWebXR, a free tool aimed at revolutionizing discussions in chemistry and biology inside VR, and all web. MolecularWebXR works much like your favorite tool for videoconferencing but with an immersive feel where people can see and talk to others, grab and move objects and point at them with their hands, all facilitating very natural discussion, education and training.

If DeepMind kind of “cracked” the problem of protein structure determination with its AlphaFold program, what is the next frontier in molecular modeling of proteins and biological systems? Here we have summarized the key takeaways from CASP15, the latest edition of the Critical Assessment of Structure Prediction competition from which AlphaFold 2 came out.

This article marks the beginning of a series covering Spatial Transcriptomics, a field rapidly growing thanks to the advent of Next Generation Sequencing. In this initial segment, we will start with a brief overview of the Spatial Transcriptomics landscape, highlighting its historical backdrop and the array of techniques that have emerged.

Writing in Nature Methods, researchers delve into the critical task of preprocessing single-cell RNA-sequencing (scRNA-seq) data before analysis. And they find that the simplest method is in practice the best.

When in 2021 Deepmind made available to the scientific community its star AI model for protein structure prediction, CASP-winning AlphaFold 2, it didn’t stop there. Rather, it allied with the European Institute of Bioinformatics to create the biggest-ever database of confident protein structure models in an attempt to chart the whole “protein universe”. The AlphaFold Protein Structure Database (AFDB) was then born, which as of today contains models for over 200 million proteins. Browsing, managing and understanding structural models at this scale presents many challenges, that these new tools tackle thus allowing scientists to more easily get the flesh out of the huge, rich structural dataset.

Deepmind, the AI giant from Google’s holding, strikes back. Its new tool, AlphaMissense, harnesses the power of AlphaFold, the cutting-edge protein structure prediction AI, to predict the pathogenicity of missense mutations in proteins -presumably better than any other tool out there and with its predictions for the whole human proteome already available online. This new tool addresses a critical need in genomics and holds tremendous potential for the future of clinical diagnostics and precision medicine.