Crowd-sourced benchmarking of single-sample tumor subclonal reconstruction.

Subclonal reconstruction algorithms use bulk DNA sequencing data to quantify parameters of tumor evolution, allowing an assessment of how cancers initiate, progress and respond to selective pressures. We launched the ICGC-TCGA (International Cancer Genome Consortium-The Cancer Genome Atlas) DREAM Somatic Mutation Calling Tumor Heterogeneity and Evolution Challenge to benchmark existing subclonal reconstruction algorithms. This 7-year community effort used cloud computing to benchmark 31 subclonal reconstruction algorithms on 51 simulated tumors. Algorithms were scored on seven independent tasks, leading to 12,061 total runs. Algorithm choice influenced performance substantially more than tumor features but purity-adjusted read depth, copy-number state and read mappability were associated with the performance of most algorithms on most tasks. No single algorithm was a top performer for all seven tasks and existing ensemble strategies were unable to outperform the best individual methods, highlighting a key research need. All containerized methods, evaluation code and datasets are available to support further assessment of the determinants of subclonal reconstruction accuracy and development of improved methods to understand tumor evolution.

ASOs are an effective treatment for disease-associated oligodendrocyte signatures in premanifest and symptomatic SCA3 mice.

Spinocerebellar ataxia type 3 (SCA3) is the most common dominantly inherited ataxia. Currently, no preventive or disease-modifying treatments exist for this progressive neurodegenerative disorder, although efforts using gene silencing approaches are under clinical trial investigation. The disease is caused by a CAG repeat expansion in the mutant gene, ATXN3, producing an enlarged polyglutamine tract in the mutant protein. Similar to other paradigmatic neurodegenerative diseases, studies evaluating the pathogenic mechanism focus primarily on neuronal implications. Consequently, therapeutic interventions often overlook non-neuronal contributions to disease. Our lab recently reported that oligodendrocytes display some of the earliest and most progressive dysfunction in SCA3 mice. Evidence of disease-associated oligodendrocyte signatures has also been reported in other neurodegenerative diseases, including Alzheimer's disease, amyotrophic lateral sclerosis, Parkinson's disease, and Huntington's disease. Here, we assess the effects of anti-ATXN3 antisense oligonucleotide (ASO) treatment on oligodendrocyte dysfunction in premanifest and symptomatic SCA3 mice. We report a severe, but modifiable, deficit in oligodendrocyte maturation caused by the toxic gain-of-function of mutant ATXN3 early in SCA3 disease that is transcriptionally, biochemically, and functionally rescued with anti-ATXN3 ASO. Our results highlight the promising use of an ASO therapy across neurodegenerative diseases that requires glial targeting in addition to affected neuronal populations.

Assessing the impact of body location on the accuracy of detecting daily activities with accelerometer data.

Recent advancements in digital biomarkers have highlighted the importance of accelerometer and gyroscope data for monitoring activities, identifying motion-related diseases, and assessing disease severity. Prior studies predominantly limit sensor placement to one or two locations. Here, we conducted a trial focusing on the impact of sensor placement in predicting 21 common activities using convolutional neural networks (CNN) and long short-term memory networks (LSTM). Our research found that the optimal locations for activity detection are the right and left upper arms, right wrist, and lower back. These locations yielded an average AUC of 0.76-0.77 using both accelerometer and gyroscope data. Combining data from all locations improved AUC to 0.796 for accelerometer and 0.811 for gyroscope data. We also noted specific activity-body part sensitivity relationships. This study provides a valuable reference for selecting appropriate sensor locations in future digital biomarker studies focused on specific activities.

Predicting Single Neuron Responses of the Primary Visual Cortex with Deep Learning Model.

Modeling neuron responses to stimuli can shed light on next-generation technologies such as brain-chip interfaces. Furthermore, high-performing models can serve to help formulate hypotheses and reveal the mechanisms underlying neural responses. Here the state-of-the-art computational model is presented for predicting single neuron responses to natural stimuli in the primary visual cortex (V1) of mice. The algorithm incorporates object positions and assembles multiple models with different train-validation data, resulting in a 15%-30% improvement over the existing models in cross-subject predictions and ranking first in the SENSORIUM 2022 Challenge, which benchmarks methods for neuron-specific prediction based on thousands of images. Importantly, The model reveals evidence that the spatial organizations of V1 are conserved across mice. This model will serve as an important noninvasive tool for understanding and utilizing the response patterns of primary visual cortex neurons.

Artificial intelligence approaches for molecular representation in drug response prediction.

Drug response prediction is essential for drug development and disease treatment. One key question in predicting drug response is the representation of molecules, which has been greatly advanced by artificial intelligence (AI) techniques in recent years. In this review, we first describe different types of representation methods, pinpointing their key principles and discussing their limitations. Thereafter we discuss potential ways how these methods could be further developed. We expect that this review will provide useful guidance for researchers in the community.

Mapping combinatorial drug effects to DNA damage response kinase inhibitors.

One fundamental principle that underlies various cancer treatments, such as traditional chemotherapy and radiotherapy, involves the induction of catastrophic DNA damage, leading to the apoptosis of cancer cells. In our study, we conduct a comprehensive dose-response combination screening focused on inhibitors that target key kinases involved in the DNA damage response (DDR): ATR, ATM, and DNA-PK. This screening involves 87 anti-cancer agents, including six DDR inhibitors, and encompasses 62 different cell lines spanning 12 types of tumors, resulting in a total of 17,912 combination treatment experiments. Within these combinations, we analyze the most effective and synergistic drug pairs across all tested cell lines, considering the variations among cancers originating from different tissues. Our analysis reveals inhibitors of five DDR-related pathways (DNA topoisomerase, PLK1 kinase, p53-inducible ribonucleotide reductase, PARP, and cell cycle checkpoint proteins) that exhibit strong combinatorial efficacy and synergy when used alongside ATM/ATR/DNA-PK inhibitors.

Systematic dissection of genomic features determining the vast diversity of conotoxins.

BACKGROUND: Conus, a highly diverse species of venomous predators, has attracted significant attention in neuroscience and new drug development due to their rich collection of neuroactive peptides called conotoxins. Recent advancements in transcriptome, proteome, and genome analyses have facilitated the identification of conotoxins within Conus' venom glands, providing insights into the genetic features and evolutionary patterns of conotoxin genes. However, the underlying mechanism behind the extraordinary hypervariability of conotoxins remains largely unknown. RESULTS: We analyzed the transcriptomes of 34 Conus species, examining various tissues such as the venom duct, venom bulb, and salivary gland, leading to the identification of conotoxin genes. Genetic variation analysis revealed that a subset of these genes (15.78% of the total) in Conus species underwent positive selection (Ka/Ks > 1, p < 0.01). Additionally, we reassembled and annotated the genome of C. betulinus, uncovering 221 conotoxin-encoding genes. These genes primarily consisted of three exons, with a significant portion showing high transcriptional activity in the venom ducts. Importantly, the flanking regions and adjacent introns of conotoxin genes exhibited a higher prevalence of transposon elements, suggesting their potential contribution to the extensive variability observed in conotoxins. Furthermore, we detected genome duplication in C. betulinus, which likely contributed to the expansion of conotoxin gene numbers. Interestingly, our study also provided evidence of introgression among Conus species, indicating that interspecies hybridization may have played a role in shaping the evolution of diverse conotoxin genes. CONCLUSIONS: This study highlights the impact of adaptive evolution and introgressive hybridization on the genetic diversity of conotoxin genes and the evolution of Conus. We also propose a hypothesis suggesting that transposable elements might significantly contribute to the remarkable diversity observed in conotoxins. These findings not only enhance our understanding of peptide genetic diversity but also present a novel approach for peptide bioengineering.

Harmonizing across datasets to improve the transferability of drug combination prediction.

Combination treatment has multiple advantages over traditional monotherapy in clinics, thus becoming a target of interest for many high-throughput screening (HTS) studies, which enables the development of machine learning models predicting the response of new drug combinations. However, most existing models have been tested only within a single study, and these models cannot generalize across different datasets due to significantly variable experimental settings. Here, we thoroughly assessed the transferability issue of single-study-derived models on new datasets. More importantly, we propose a method to overcome the experimental variability by harmonizing dose-response curves of different studies. Our method improves the prediction performance of machine learning models by 184% and 1367% compared to the baseline models in intra-study and inter-study predictions, respectively, and shows consistent improvement in multiple cross-validation settings. Our study addresses the crucial question of the transferability in drug combination predictions, which is fundamental for such models to be extrapolated to new drug combination discovery and clinical applications that are de facto different datasets.

The ENCODE Imputation Challenge: a critical assessment of methods for cross-cell type imputation of epigenomic profiles.

A promising alternative to comprehensively performing genomics experiments is to, instead, perform a subset of experiments and use computational methods to impute the remainder. However, identifying the best imputation methods and what measures meaningfully evaluate performance are open questions. We address these questions by comprehensively analyzing 23 methods from the ENCODE Imputation Challenge. We find that imputation evaluations are challenging and confounded by distributional shifts from differences in data collection and processing over time, the amount of available data, and redundancy among performance measures. Our analyses suggest simple steps for overcoming these issues and promising directions for more robust research.

Computational approaches for detecting disease-associated alternative splicing events.

Alternative splicing (AS) is a key transcriptional regulation pathway. Recent studies have shown that AS events are associated with the occurrence of complex diseases. Various computational approaches have been developed for the detection of disease-associated AS events. In this review, we first describe the metrics used for quantitative characterization of AS events. Second, we review and discuss the three types of methods for detecting disease-associated splicing events, which are differential splicing analysis, aberrant splicing detection and splicing-related network analysis. Third, to further exploit the genetic mechanism of disease-associated AS events, we describe the methods for detecting genetic variants that potentially regulate splicing. For each type of methods, we conducted experimental comparison to illustrate their performance. Finally, we discuss the limitations of these methods and point out potential ways to address them. We anticipate that this review provides a systematic understanding of computational approaches for the analysis of disease-associated splicing.

Developing better digital health measures of Parkinson's disease using free living data and a crowdsourced data analysis challenge.

One of the promising opportunities of digital health is its potential to lead to more holistic understandings of diseases by interacting with the daily life of patients and through the collection of large amounts of real-world data. Validating and benchmarking indicators of disease severity in the home setting is difficult, however, given the large number of confounders present in the real world and the challenges in collecting ground truth data in the home. Here we leverage two datasets collected from patients with Parkinson's disease, which couples continuous wrist-worn accelerometer data with frequent symptom reports in the home setting, to develop digital biomarkers of symptom severity. Using these data, we performed a public benchmarking challenge in which participants were asked to build measures of severity across 3 symptoms (on/off medication, dyskinesia, and tremor). 42 teams participated and performance was improved over baseline models for each subchallenge. Additional ensemble modeling across submissions further improved performance, and the top models validated in a subset of patients whose symptoms were observed and rated by trained clinicians.

A Crowdsourcing Approach to Develop Machine Learning Models to Quantify Radiographic Joint Damage in Rheumatoid Arthritis.

Importance: An automated, accurate method is needed for unbiased assessment quantifying accrual of joint space narrowing and erosions on radiographic images of the hands and wrists, and feet for clinical trials, monitoring of joint damage over time, assisting rheumatologists with treatment decisions. Such a method has the potential to be directly integrated into electronic health records. Objectives: To design and implement an international crowdsourcing competition to catalyze the development of machine learning methods to quantify radiographic damage in rheumatoid arthritis (RA). Design, Setting, and Participants: This diagnostic/prognostic study describes the Rheumatoid Arthritis 2-Dialogue for Reverse Engineering Assessment and Methods (RA2-DREAM Challenge), which used existing radiographic images and expert-curated Sharp-van der Heijde (SvH) scores from 2 clinical studies (674 radiographic sets from 562 patients) for training (367 sets), leaderboard (119 sets), and final evaluation (188 sets). Challenge participants were tasked with developing methods to automatically quantify overall damage (subchallenge 1), joint space narrowing (subchallenge 2), and erosions (subchallenge 3). The challenge was finished on June 30, 2020. Main Outcomes and Measures: Scores derived from submitted algorithms were compared with the expert-curated SvH scores, and a baseline model was created for benchmark comparison. Performances were ranked using weighted root mean square error (RMSE). The performance and reproductivity of each algorithm was assessed using Bayes factor from bootstrapped data, and further evaluated with a postchallenge independent validation data set. Results: The RA2-DREAM Challenge received a total of 173 submissions from 26 participants or teams in 7 countries for the leaderboard round, and 13 submissions were included in the final evaluation. The weighted RMSEs metric showed that the winning algorithms produced scores that were very close to the expert-curated SvH scores. Top teams included Team Shirin for subchallenge 1 (weighted RMSE, 0.44), HYL-YFG (Hongyang Li and Yuanfang Guan) subchallenge 2 (weighted RMSE, 0.38), and Gold Therapy for subchallenge 3 (weighted RMSE, 0.43). Bootstrapping/Bayes factor approach and the postchallenge independent validation confirmed the reproducibility and the estimation concordance indices between final evaluation and postchallenge independent validation data set were 0.71 for subchallenge 1, 0.78 for subchallenge 2, and 0.82 for subchallenge 3. Conclusions and Relevance: The RA2-DREAM Challenge resulted in the development of algorithms that provide feasible, quick, and accurate methods to quantify joint damage in RA. Ultimately, these methods could help research studies on RA joint damage and may be integrated into electronic health records to help clinicians serve patients better by providing timely, reliable, and quantitative information for making treatment decisions to prevent further damage.

Generic medical concept embedding and time decay for diverse patient outcome prediction tasks.

Many fields, including Natural Language Processing (NLP), have recently witnessed the benefit of pre-training with large generic datasets to improve the accuracy of prediction tasks. However, there exist key differences between the longitudinal healthcare data (e.g., claims) and NLP tasks, which make the direct application of NLP pre-training methods to healthcare data inappropriate. In this article, we developed a pre-training scheme for longitudinal healthcare data that leverages the pairing of medical history and a future event. We then conducted systematic evaluations of various methods on ten patient-level prediction tasks encompassing adverse events, misdiagnosis, disease risks, and readmission. In addition to substantially reducing model size, our results show that a universal medical concept embedding pretrained with generic big data as well as carefully designed time decay modeling improves the accuracy of different downstream prediction tasks.

Protocol for using Ciclops to build models trained on cross-platform transcriptome data for clinical outcome prediction.

Designing robust, generalizable models based on cross-platform data to predict clinical outcomes remains challenging. Building explainable models is important because models may perform differently depending on the conditions of the samples. Here, we describe the use of Ciclops (cross-platform training in clinical outcome predictions), freely available software that can build explainable models to deliver across cross-platform datasets for predicting clinical outcomes. This protocol also utilizes SHAP, a post-training analysis allowing for assessing potential biomarkers of the clinical outcome under study. For complete details on the use and execution of this protocol, please refer to Zhang et al. (2022).

Asymmetric Predictive Relationships Across Histone Modifications.

Decoding the epigenomic landscapes in diverse tissues and cell types is fundamental to understanding molecular mechanisms underlying many essential cellular processes and human diseases. Recent advances in artificial intelligence provide new methods and strategies for imputing unknown epigenomes based on existing data, yet how to reveal the predictive relationships among epigenetic marks remains largely unexplored. Here we present a machine learning approach for epigenomic imputation and interpretation. Through dissection of the spatial contributions from six histone marks, we reveal the prevalent and asymmetric cross-prediction relationships among these marks. Meanwhile, our approach achieved high predictive performance on held-out prospective epigenomes and outperformed the state-of-the-art. To facilitate future research, we further applied this approach to impute a total of 527 and 2,455 unavailable genome-wide histone modification signal tracks for the ENCODE3 and Roadmap datasets, respectively.

Micro-dissection and integration of long and short reads to create a robust catalog of kidney compartment-specific isoforms.

Studying isoform expression at the microscopic level has always been a challenging task. A classical example is kidney, where glomerular and tubulo-interstitial compartments carry out drastically different physiological functions and thus presumably their isoform expression also differs. We aim at developing an experimental and computational pipeline for identifying isoforms at microscopic structure-level. We microdissected glomerular and tubulo-interstitial compartments from healthy human kidney tissues from two cohorts. The two compartments were separately sequenced with the PacBio RS II platform. These transcripts were then validated using transcripts of the same samples by the traditional Illumina RNA-Seq protocol, distinct Illumina RNA-Seq short reads from European Renal cDNA Bank (ERCB) samples, and annotated GENCODE transcript list, thus identifying novel transcripts. We identified 14,739 and 14,259 annotated transcripts, and 17,268 and 13,118 potentially novel transcripts in the glomerular and tubulo-interstitial compartments, respectively. Of note, relying solely on either short or long reads would have resulted in many erroneous identifications. We identified distinct pathways involved in glomerular and tubulo-interstitial compartments at the isoform level, creating an important experimental and computational resource for the kidney research community.

Enabling Eating Detection in a Free-living Environment: Integrative Engineering and Machine Learning Study.

BACKGROUND: Monitoring eating is central to the care of many conditions such as diabetes, eating disorders, heart diseases, and dementia. However, automatic tracking of eating in a free-living environment remains a challenge because of the lack of a mature system and large-scale, reliable training set. OBJECTIVE: This study aims to fill in this gap by an integrative engineering and machine learning effort and conducting a large-scale study in terms of monitoring hours on wearable-based eating detection. METHODS: This prospective, longitudinal, passively collected study, covering 3828 hours of records, was made possible by programming a digital system that streams diary, accelerometer, and gyroscope data from Apple Watches to iPhones and then transfers the data to the cloud. RESULTS: On the basis of this data collection, we developed deep learning models leveraging spatial and time augmentation and inferring eating at an area under the curve (AUC) of 0.825 within 5 minutes in the general population. In addition, the longitudinal follow-up of the study design encouraged us to develop personalized models that detect eating behavior at an AUC of 0.872. When aggregated to individual meals, the AUC is 0.951. We then prospectively collected an independent validation cohort in a different season of the year and validated the robustness of the models (0.941 for meal-level aggregation). CONCLUSIONS: The accuracy of this model and the data streaming platform promises immediate deployment for monitoring eating in applications such as diabetic integrative care.

Machine learning for artemisinin resistance in malaria treatment across in vivo-in vitro platforms.

Drug resistance has been rapidly evolving with regard to the first-line malaria treatment, artemisinin-based combination therapies. It has been an open question whether predictive models for this drug resistance status can be generalized across in vivo-in vitro transcriptomic measurements. In this study, we present a model that predicts artemisinin treatment resistance developed with transcriptomic information of Plasmodium falciparum. We demonstrated the robustness of this model across in vivo clearance rate and in vitro IC50 measurement and based on different microarray and data processing modalities. The validity of the algorithm is further supported by its first placement in the DREAM Malaria challenge. We identified transcription biomarkers to artemisinin treatment resistance that can predict artemisinin resistance and are conserved in their expression modules. This is a critical step in the research of malaria treatment, as it demonstrated the potential of a platform-robust, personalized model for artemisinin resistance using molecular biomarkers.

Impaired Oligodendrocyte Maturation Is an Early Feature in SCA3 Disease Pathogenesis.

Spinocerebellar ataxia Type 3 (SCA3), the most common dominantly inherited ataxia, is a polyglutamine neurodegenerative disease for which there is no disease-modifying therapy. The polyglutamine-encoding CAG repeat expansion in the ATXN3 gene results in expression of a mutant form of the ATXN3 protein, a deubiquitinase that causes selective neurodegeneration despite being widely expressed. The mechanisms driving neurodegeneration in SCA3 are unclear. Research to date, however, has focused almost exclusively on neurons. Here, using equal male and female age-matched transgenic mice expressing full-length human mutant ATXN3, we identified early and robust transcriptional changes in selectively vulnerable brain regions that implicate oligodendrocytes in disease pathogenesis. We mapped transcriptional changes across early, mid, and late stages of disease in two selectively vulnerable brain regions: the cerebellum and brainstem. The most significant disease-associated module through weighted gene coexpression network analysis revealed dysfunction in SCA3 oligodendrocyte maturation. These results reflect a toxic gain-of-function mechanism, as ATXN3 KO mice do not exhibit any impairments in oligodendrocyte maturation. Genetic crosses to reporter mice revealed a marked reduction in mature oligodendrocytes in SCA3-disease vulnerable brain regions, and ultrastructural microscopy confirmed abnormalities in axonal myelination. Further study of isolated oligodendrocyte precursor cells from SCA3 mice established that this impairment in oligodendrocyte maturation is a cell-autonomous process. We conclude that SCA3 is not simply a disease of neurons, and the search for therapeutic strategies and disease biomarkers will need to account for non-neuronal involvement in SCA3 pathogenesis.SIGNIFICANCE STATEMENT Despite advances in spinocerebellar ataxia Type 3 (SCA3) disease understanding, much remains unknown about how the disease gene causes brain dysfunction ultimately leading to cell death. We completed a longitudinal transcriptomic analysis of vulnerable brain regions in SCA3 mice to define the earliest and most robust changes across disease progression. Through gene network analyses followed up with biochemical and histologic studies in SCA3 mice, we provide evidence for severe dysfunction in oligodendrocyte maturation early in SCA3 pathogenesis. Our results advance understanding of SCA3 disease mechanisms, identify additional routes for therapeutic intervention, and may provide broader insight into polyglutamine diseases beyond SCA3.

Heterogeneous digital biomarker integration out-performs patient self-reports in predicting Parkinson's disease.

Parkinson's disease (PD) is one of the first diseases where digital biomarkers demonstrated excellent performance in differentiating disease from healthy individuals. However, no study has systematically compared and leveraged multiple types of digital biomarkers to predict PD. Particularly, machine learning works on the fine-motor skills of PD are limited. Here, we developed deep learning methods that achieved an AUC (Area Under the receiver operator characteristic Curve) of 0.933 in identifying PD patients on 6418 individuals using 75048 tapping accelerometer and position records. Performance of tapping is superior to gait/rest and voice-based models obtained from the same benchmark population. Assembling the three models achieved a higher AUC of 0.944. Notably, the models not only correlated strongly to, but also performed better than patient self-reported symptom scores in diagnosing PD. This study demonstrates the complementary predictive power of tapping, gait/rest and voice data and establishes integrative deep learning-based models for identifying PD.