Toolkit Items

Spatial transcriptomics is a transcriptomic assay method identified in the supplied review as a recent methodological advance. In that evidence, it is presented as part of a broader technology set that enables easier and more accurate visualization of cell behavior and qualitative and quantitative analysis of cell-cell interactions.

BROAD is a computational protein design method that combines Rosetta-based structure modeling, machine learning, and integer linear programming to improve design search beyond Rosetta sampling alone. It was demonstrated in antibody design to increase the predicted HIV neutralization breadth of VRC23 across a panel of 180 divergent viral strains.

Optical mapping, using fluorescent probes and high-speed cameras, offers detailed insights into cardiac activity and arrhythmias by analysing electrical signals, calcium dynamics, and metabolism.

The Bayesian optimization framework is a computational method built from high-throughput Lustro measurements to guide control of blue light-sensitive optogenetic systems. It uses data-driven learning, uncertainty quantification, and experimental design to identify light induction conditions for multiplexed regulation in Saccharomyces cerevisiae.

Lustro is a high-throughput optogenetics platform for studying and controlling blue light-sensitive optogenetic systems. In the cited 2023 work, it was combined with machine learning to achieve multiplexed control of split transcription factor responses in Saccharomyces cerevisiae.

RAMalgo (reproducible automated multimodal algometry) improves the standardization, comprehensiveness, and throughput of preclinical pain testing.

Reflectance of red light is used to measure paw withdrawal with millisecond precision.

The merging of optogenetics and optical mapping techniques for 'all-optical' electrophysiology marks a significant step forward. This combination allows for the contactless actuation and sensing of cardiac electrophysiology, offering unprecedented spatial-temporal resolution and control.

The Vivid (VVD) LOV domain is a photosensitive allosteric light, oxygen, voltage domain from a fungal circadian clock photoreceptor. It responds to blue-light-driven covalent bond formation with a large N-terminal conformational change, and its atomistic allosteric mechanism has been analyzed computationally.

We developed a computational pipeline and applied it to analyzing 3D point clouds of SMLM localizations (event lists) of the caveolar coat protein, caveolin-1 (Cav1).

AI-assisted sgRNA design, and machine-learning approaches for predicting off-target effects further enhance the safety, stratification, and monitoring of CRISPR therapeutics

The paper discusses how AI and ML tools, including deep learning, predictive analytics, and computer vision, are being applied to accelerate method optimization, enhance robustness evaluation, predict method performance, and strengthen data integrity throughout the analytical procedure lifecycle.

Computational modelling and machine learning are emerging as pivotal tools in enhancing optical techniques, offering new avenues for analysing complex data and optimizing therapeutic strategies.

Data-driven AAV engineering, integrating machine learning and high-throughput screening, has significantly accelerated the development of next-generation vectors.

machine-learning approaches for predicting off-target effects further enhance the safety, stratification, and monitoring of CRISPR therapeutics

The entire process was automated using machine learning.

Here, we developed the web server implementation of the PICNIC (Proteins Involved in CoNdensates In Cells) machine learning algorithm. PICNIC uses sequence- and structure-based features derived from AlphaFold2 models to predict if a protein is involved in biomolecular condensates.

In case of well-studied proteins with available annotations, the user can further benefit from an extended model, PICNIC-GO, which includes additional features based on Gene Ontology terms.

We present ProDomino, a machine learning pipeline to rationalize domain recombination, trained on a semisynthetic protein sequence dataset derived from naturally occurring intradomain insertion events.

Using this gene signature, support vector machine models accurately identified GM, achieving an area under the curve of 99.6% (99.0-99.9%) and an accuracy of 98.6% (98.2-98.9%).

we developed SyMetrics, a framework that integrates predictors of splicing, RNA stability, evolutionary conservation, codon usage, synonymous variation effects, sequence properties, and allele frequency

The web research summary states that the anchor paper describes TSCS (Transcript SNVs Classifier relying on complementary sequencings), a machine-learning framework that integrates short-read MGI RNA-seq with long-read PacBio RNA-seq to improve transcript SNV discovery and to distinguish genomic transcript SNVs from RNA-editing-derived transcript SNVs.