Aro: a machine learning approach to identifying single molecules and estimating classification error in fluorescence microscopy images

Diversification of small RNA pathways underlies germline RNA interference incompetence in wild Caenorhabditis elegans strains

The discovery that experimental delivery of dsRNA can induce gene silencing at target genes revolutionized genetics research, by both uncovering essential biological processes and creating new tools for developmental geneticists. However, the efficacy of exogenous RNA interference (RNAi) varies dramatically within the Caenorhabditis elegans natural population, raising questions about our understanding of RNAi in the lab relative to its activity and significance in nature. Here, we investigate why some wild strains fail to mount a robust RNAi response to germline targets. We observe diversity in mechanism: in some strains, the response is stochastic, either on or off among individuals, while in others, the response is consistent but delayed. Increased activity of the Argonaute PPW-1, which is required for germline RNAi in the laboratory strain N2, rescues the response in some strains but dampens it further in others. Among wild strains, genes known to mediate RNAi exhibited very high expression variation relative to other genes in the genome as well as allelic divergence and strain-specific instances of pseudogenization at the sequence level. Our results demonstrate functional diversification in the small RNA pathways in C. elegans and suggest that RNAi processes are evolving rapidly and dynamically in nature.

Single-molecule FISH in C. elegans embryos reveals early embryonic expression dynamics of par-2 , lgl-1 and chin-1 and possible differences between hyper-diverged strains

Wild C. elegans strains harbor natural variation in developmental pathways, but investigating these differences requires precise and well-powered phenotyping methods. Here we employ a microfluidics platform for single-molecule FISH to simultaneously visualize the transcripts of three genes in embryos of two distinct strains. We capture transcripts at high resolution by developmental stage in over one hundred embryos of each strain and observe wide-scale conservation of expression, but subtle differences in par-2 and chin-1 abundance and rate of change. As both genes reside in a genomic interval of hyper-divergence, these results may reflect consequences of pathway evolution over long timescales.

Decoding Optical Data with Machine Learning

Optical spectroscopy and imaging techniques play important roles in many fields such as disease diagnosis, biological study, information technology, optical science, and materials science. Over the past decade, machine learning (ML) has proved promising in decoding complex data, enabling rapid and accurate analysis of optical spectra and images. This review aims to shed light on various ML algorithms for optical data analysis with a focus on their applications in a wide range of fields. The goal of this work is to sketch the validity of ML-based optical data decoding. The review concludes with an outlook on unaddressed problems and opportunities in this emerging subject that interfaces optics, data science and ML.

Direct Kinetic Fingerprinting for High-Accuracy Single-Molecule Counting of Diverse Disease Biomarkers

Methods for detecting and quantifying disease biomarkers in biofluids with high specificity and sensitivity play a pivotal role in enabling clinical diagnostics, including point-of-care tests. The most widely used molecular biomarkers include proteins, nucleic acids, hormones, metabolites, and other small molecules. While numerous methods have been developed for analyzing biomarkers, most techniques are challenging to implement for clinical use due to insufficient analytical performance, high cost, and/or other practical shortcomings. For instance, the detection of cell-free nucleic acid (cfNA) biomarkers by digital PCR and next-generation sequencing (NGS) requires time-consuming nucleic acid extraction steps, often introduces enzymatic amplification bias, and can be costly when high specificity is required. While several amplification-free methods for detecting cfNAs have been reported, these techniques generally suffer from low specificity and sensitivity. Meanwhile, the quantification of protein biomarkers is generally performed using immunoassays such as enzyme-linked immunosorbent assay (ELISA); the analytical performance of these methods is often limited by the availability of antibodies with high affinity and specificity as well as the significant nonspecific binding of antibodies to assay surfaces. To address the drawbacks of existing biomarker detection methods and establish a universal diagnostics platform capable of detecting different types of analytes, we have developed an amplification-free approach, named single-molecule recognition through equilibrium Poisson sampling (SiMREPS), for the detection of diverse biomarkers with arbitrarily high specificity and single-molecule sensitivity. SiMREPS utilizes the transient, reversible binding of fluorescent detection probes to immobilized target molecules to generate kinetic fingerprints that are detected by single-molecule fluorescence microscopy. The analysis of these kinetic fingerprints enables nearly perfect discrimination between specific binding to target molecules and any nonspecific binding. Early proof-of-concept studies demonstrated the in vitro detection of miRNAs with a limit of detection (LOD) of approximately 1 fM and >500-fold selectivity for single-nucleotide polymorphisms. The SiMREPS approach was subsequently expanded to the detection of rare mutant DNA alleles from biofluids at mutant allele fractions of as low as 1 in 1 million, corresponding to a specificity of >99.99999%. Recently, SiMREPS was generalized to protein quantification using dynamically binding antibody probes, permitting LODs in the low-femtomolar to attomolar range. Finally, SiMREPS has been demonstrated to be suitable for the in situ detection of miRNAs in cultured cells, the quantification of small-molecule toxins and drugs, and the monitoring of telomerase activity at the single-molecule level. In this Account, we discuss the principles of SiMREPS for the highly specific and sensitive detection of molecular analytes, including considerations for assay design. We discuss the generality of SiMREPS for the detection of very disparate analytes and provide an overview of data processing methods, including the expansion of the dynamic range using super-resolution analysis and the improvement of performance using deep learning algorithms. Finally, we describe current challenges, opportunities, and future directions for the SiMREPS approach.

Automatic classification and segmentation of single-molecule fluorescence time traces with deep learning

Traces from single-molecule fluorescence microscopy (SMFM) experiments exhibit photophysical artifacts that typically necessitate human expert screening, which is time-consuming and introduces potential for user-dependent expectation bias. Here, we use deep learning to develop a rapid, automatic SMFM trace selector, termed AutoSiM, that improves the sensitivity and specificity of an assay for a DNA point mutation based on single-molecule recognition through equilibrium Poisson sampling (SiMREPS). The improved performance of AutoSiM is based on accepting both more true positives and fewer false positives than the conventional approach of hidden Markov modeling (HMM) followed by hard thresholding. As a second application, the selector is used for automated screening of single-molecule Förster resonance energy transfer (smFRET) data to identify high-quality traces for further analysis, and achieves ~90% concordance with manual selection while requiring less processing time. Finally, we show that AutoSiM can be adapted readily to novel datasets, requiring only modest Transfer Learning.

DeepFRET, a software for rapid and automated single-molecule FRET data classification using deep learning

Single-molecule Förster Resonance energy transfer (smFRET) is an adaptable method for studying the structure and dynamics of biomolecules. The development of high throughput methodologies and the growth of commercial instrumentation have outpaced the development of rapid, standardized, and automated methodologies to objectively analyze the wealth of produced data. Here we present DeepFRET, an automated, open-source standalone solution based on deep learning, where the only crucial human intervention in transiting from raw microscope images to histograms of biomolecule behavior, is a user-adjustable quality threshold. Integrating standard features of smFRET analysis, DeepFRET consequently outputs the common kinetic information metrics. Its classification accuracy on ground truth data reached >95% outperforming human operators and commonly used threshold, only requiring ~1% of the time. Its precise and rapid operation on real data demonstrates DeepFRET's capacity to objectively quantify biomolecular dynamics and the potential to contribute to benchmarking smFRET for dynamic structural biology.

Single-molecule techniques in biophysics: a review of the progress in methods and applications

Single-molecule biophysics has transformed our understanding of biology, but also of the physics of life. More exotic than simple soft matter, biomatter lives far from thermal equilibrium, covering multiple lengths from the nanoscale of single molecules to up to several orders of magnitude higher in cells, tissues and organisms. Biomolecules are often characterized by underlying instability: multiple metastable free energy states exist, separated by levels of just a few multiples of the thermal energy scale k _B T, where k _B is the Boltzmann constant and T absolute temperature, implying complex inter-conversion kinetics in the relatively hot, wet environment of active biological matter. A key benefit of single-molecule biophysics techniques is their ability to probe heterogeneity of free energy states across a molecular population, too challenging in general for conventional ensemble average approaches. Parallel developments in experimental and computational techniques have catalysed the birth of multiplexed, correlative techniques to tackle previously intractable biological questions. Experimentally, progress has been driven by improvements in sensitivity and speed of detectors, and the stability and efficiency of light sources, probes and microfluidics. We discuss the motivation and requirements for these recent experiments, including the underpinning mathematics. These methods are broadly divided into tools which detect molecules and those which manipulate them. For the former we discuss the progress of super-resolution microscopy, transformative for addressing many longstanding questions in the life sciences, and for the latter we include progress in 'force spectroscopy' techniques that mechanically perturb molecules. We also consider in silico progress of single-molecule computational physics, and how simulation and experimentation may be drawn together to give a more complete understanding. Increasingly, combinatorial techniques are now used, including correlative atomic force microscopy and fluorescence imaging, to probe questions closer to native physiological behaviour. We identify the trade-offs, limitations and applications of these techniques, and discuss exciting new directions.

Yeast silencing factor Sir4 and a subset of nucleoporins form a complex distinct from nuclear pore complexes

Lapetina et al. identify a protein interaction network involved in the association of chromatin with the nuclear envelope. This network includes a telomere tether, a silencing factor, a SUMO E3 ligase, and an array of nucleoporins that together form a complex distinct from nuclear pore complexes.

Interactions occurring at the nuclear envelope (NE)–chromatin interface influence both NE structure and chromatin organization. Insights into the functions of NE–chromatin interactions have come from the study of yeast subtelomeric chromatin and its association with the NE, including the identification of various proteins necessary for tethering subtelomeric chromatin to the NE and the silencing of resident genes. Here we show that four of these proteins—the silencing factor Sir4, NE-associated Esc1, the SUMO E3 ligase Siz2, and the nuclear pore complex (NPC) protein Nup170—physically and functionally interact with one another and a subset of NPC components (nucleoporins or Nups). Importantly, this group of Nups is largely restricted to members of the inner and outer NPC rings, but it lacks numerous others including cytoplasmically and nucleoplasmically positioned Nups. We propose that this Sir4-associated Nup complex is distinct from holo-NPCs and that it plays a role in subtelomeric chromatin organization and NE tethering.

The parameter sensitivity of random forests

Background

The Random Forest (RF) algorithm for supervised machine learning is an ensemble learning method widely used in science and many other fields. Its popularity has been increasing, but relatively few studies address the parameter selection process: a critical step in model fitting. Due to numerous assertions regarding the performance reliability of the default parameters, many RF models are fit using these values. However there has not yet been a thorough examination of the parameter-sensitivity of RFs in computational genomic studies. We address this gap here.

Results

We examined the effects of parameter selection on classification performance using the RF machine learning algorithm on two biological datasets with distinct p/n ratios: sequencing summary statistics (low p/n) and microarray-derived data (high p/n). Here, p, refers to the number of variables and, n, the number of samples. Our findings demonstrate that parameterization is highly correlated with prediction accuracy and variable importance measures (VIMs). Further, we demonstrate that different parameters are critical in tuning different datasets, and that parameter-optimization significantly enhances upon the default parameters.

Conclusions

Parameter performance demonstrated wide variability on both low and high p/n data. Therefore, there is significant benefit to be gained by model tuning RFs away from their default parameter settings.

Electronic supplementary material

The online version of this article (doi:10.1186/s12859-016-1228-x) contains supplementary material, which is available to authorized users.

Mutagenesis of GATA motifs controlling the endoderm regulator elt-2 reveals distinct dominant and secondary cis-regulatory elements

Cis-regulatory elements (CREs) are crucial links in developmental gene regulatory networks, but in many cases, it can be difficult to discern whether similar CREs are functionally equivalent. We found that despite similar conservation and binding capability to upstream activators, different GATA cis-regulatory motifs within the promoter of the C. elegans endoderm regulator elt-2 play distinctive roles in activating and modulating gene expression throughout development. We fused wild-type and mutant versions of the elt-2 promoter to a gfp reporter and inserted these constructs as single copies into the C. elegans genome. We then counted early embryonic gfp transcripts using single-molecule RNA FISH (smFISH) and quantified gut GFP fluorescence. We determined that a single primary dominant GATA motif located 527bp upstream of the elt-2 start codon was necessary for both embryonic activation and later maintenance of transcription, while nearby secondary GATA motifs played largely subtle roles in modulating postembryonic levels of elt-2. Mutation of the primary activating site increased low-level spatiotemporally ectopic stochastic transcription, indicating that this site acts repressively in non-endoderm cells. Our results reveal that CREs with similar GATA factor binding affinities in close proximity can play very divergent context-dependent roles in regulating the expression of a developmentally critical gene in vivo.

MED GATA factors promote robust development of the C. elegans endoderm

The MED-1,2 GATA factors contribute to specification of E, the progenitor of the Caenorhabditis elegans endoderm, through the genes end-1 and end-3, and in parallel with the maternal factors SKN-1, POP-1 and PAL-1. END-1,3 activate elt-2 and elt-7 to initiate a program of intestinal development, which is maintained by positive autoregulation. Here, we advance the understanding of MED-1,2 in E specification. We find that expression of end-1 and end-3 is greatly reduced in med-1,2(-) embryos. We generated strains in which MED sites have been mutated in end-1 and end-3. Without MED input, gut specification relies primarily on POP-1 and PAL-1. 25% of embryos fail to make intestine, while those that do display abnormal numbers of gut cells due to a delayed and stochastic acquisition of intestine fate. Surviving adults exhibit phenotypes consistent with a primary defect in the intestine. Our results establish that MED-1,2 provide robustness to endoderm specification through end-1 and end-3, and reveal that gut differentiation may be more directly linked to specification than previously appreciated. The results argue against an "all-or-none" description of cell specification, and suggest that activation of tissue-specific master regulators, even when expression of these is maintained by positive autoregulation, does not guarantee proper function of differentiated cells.