Deep learning tackles single-cell analysis-a survey of deep learning for scRNA-seq analysis.

Since its selection as the method of the year in 2013, single-cell technologies have become mature enough to provide answers to complex research questions. With the growth of single-cell profiling technologies, there has also been a significant increase in data collected from single-cell profilings, resulting in computational challenges to process these massive and complicated datasets. To address these challenges, deep learning (DL) is positioned as a competitive alternative for single-cell analyses besides the traditional machine learning approaches. Here, we survey a total of 25 DL algorithms and their applicability for a specific step in the single cell RNA-seq processing pipeline. Specifically, we establish a unified mathematical representation of variational autoencoder, autoencoder, generative adversarial network and supervised DL models, compare the training strategies and loss functions for these models, and relate the loss functions of these models to specific objectives of the data processing step. Such a presentation will allow readers to choose suitable algorithms for their particular objective at each step in the pipeline. We envision that this survey will serve as an important information portal for learning the application of DL for scRNA-seq analysis and inspire innovative uses of DL to address a broader range of new challenges in emerging multi-omics and spatial single-cell sequencing.

Beyond Triphenylphosphine: Advances on the Utilization of Triphenylphosphine Oxide.

Triphenylphosphine oxide is a well-known industrial waste byproduct, and thousands of tons of it are generated every year. Due to its chemical stability and limited applications, settlement of this waste issue has drawn extensive attention from chemists. The reduction of triphenylphosphine oxide to triphenylphosphine is heretofore the most employed solution, and is well reviewed. In view of our recent studies on the selective and efficient conversion of Ph3P(O) to other valuable organophosphorus chemicals by using sodium, the present perspective mainly highlights the advances on the utilization of Ph3P(O) to prepare a diverse range of functional organophosphorus compounds, except Ph3P, via selective P-C, C-H, and P-O bond cleavages.

Reduction of Triphenylphosphine Oxide to Triphenylphosphine by Phosphonic Acid.

A novel method for the iodine-mediated reduction of phosphine oxides (sulfides) to phosphines using phosphonic acid under solvent-free conditions is described. By using a combination of H3PO3 and I2, both tertiary monophosphine oxides and bis-phosphine oxides were reduced under this system, readily producing monodentate and bidentate phosphines, respectively, in good yields. Notably, chiral (R)-(+)-2,2'-bis(diphenylphosphino)-1,1'-binaphthyl dioxide could be also tolerated without racemization. This new approach is inexpensive and features simple conditions and a wide substrate scope.

Histone Deacetylase 3-Directed PROTACs Have Anti-inflammatory Potential by Blocking Polarization of M0-like into M1-like Macrophages.

Macrophage polarization plays a crucial role in inflammatory processes. The histone deacetylase 3 (HDAC3) has a deacetylase-independent function that can activate pro-inflammatory gene expression in lipopolysaccharide-stimulated M1-like macrophages and cannot be blocked by traditional small-molecule HDAC3 inhibitors. Here we employed the proteolysis targeting chimera (PROTAC) technology to target the deacetylase-independent function of HDAC3. We developed a potent and selective HDAC3-directed PROTAC, P7, which induces nearly complete HDAC3 degradation at low micromolar concentrations in both THP-1 cells and human primary macrophages. P7 increases the anti-inflammatory cytokine secretion in THP-1-derived M1-like macrophages. Importantly, P7 decreases the secretion of pro-inflammatory cytokines in M1-like macrophages derived from human primary macrophages. This can be explained by the observed inhibition of macrophage polarization from M0-like into M1-like macrophage. In conclusion, we demonstrate that the HDAC3-directed PROTAC P7 has anti-inflammatory activity and blocks macrophage polarization, demonstrating that this molecular mechanism can be targeted with small molecule therapeutics.

Selective C-P(O) Bond Cleavage of Organophosphine Oxides by Sodium.

Sodium exhibits better efficacy and selectivity than Li and K for converting Ph3P(O) to Ph2P(OM). The destiny of PhNa co-generated is disclosed. A series of alkyl halides R4X and aryl halides ArX all react with Ph2P(ONa) to produce the corresponding phosphine oxides in good to excellent yields.

Rana chensinensis Ovum Oil Based on CO2 Supercritical Fluid Extraction: Response Surface Methodology Optimization and Unsaturated Fatty Acid Ingredient Analysis.

Rana chensinensis ovum oil (RCOO) is an emerging source of unsaturated fatty acids (UFAs), but it is lacking in green and efficient extraction methods. In this work, using the response surface strategy, we developed a green and efficient CO2 supercritical fluid extraction (CO2-SFE) technology for RCOO. The response surface methodology (RSM), based on the Box-Behnken Design (BBD), was used to investigate the influence of four independent factors (pressure, flow, temperature, and time) on the yield of RCOO in the CO2-SFE process, and UPLC-ESI-Q-TOP-MS and HPLC were used to identify and analyze the principal UFA components of RCOO. According to the BBD response surface model, the optimal CO2-SFE condition of RCOO was pressure 29 MPa, flow 82 L/h, temperature 50 °C, and time 132 min, and the corresponding predicted optimal yield was 13.61%. The actual optimal yield obtained from the model verification was 13.29 ± 0.37%, and the average error with the predicted value was 0.38 ± 0.27%. The six principal UFAs identified in RCOO included eicosapentaenoic acid (EPA), α-linolenic acid (ALA), docosahexaenoic acid (DHA), arachidonic acid (ARA), linoleic acid (LA), and oleic acid (OA), which were important biologically active ingredients in RCOO. Pearson correlation analysis showed that the yield of these UFAs was closely related to the yield of RCOO (the correlation coefficients were greater than 0.9). Therefore, under optimal conditions, the yield of RCOO and principal UFAs always reached the optimal value at the same time. Based on the above results, this work realized the optimization of CO2-SFE green extraction process and the confirmation of principal bioactive ingredients of the extract, which laid a foundation for the green production of RCOO.

Synthesis and herbicidal activities of aryloxyacetic acid derivatives as HPPD inhibitors.

A series of aryloxyacetic acid derivatives were designed and synthesized as 4-hydoxyphenylpyruvate dioxygenase (HPPD) inhibitors. Preliminary bioassay results reveal that these derivatives are promising Arabidopsis thaliana HPPD (AtHPPD) inhibitors, in particular compounds I12 (K i = 0.011 µM) and I23 (K i = 0.012 µM), which exhibit similar activities to that of mesotrione, a commercial HPPD herbicide (K i = 0.013 µM). Furthermore, the newly synthesized compounds show significant greenhouse herbicidal activities against tested weeds at dosages of 150 g ai/ha. In particular, II4 exhibited high herbicidal activity for pre-emergence treatment that was slightly better than that of mesotrione. In addition, compound II4 was safe for weed control in maize fields at a rate of 150 g ai/ha, and was identified as the most potent candidate for a novel HPPD inhibitor herbicide. The compounds described herein may provide useful guidance for the design of new HPPD inhibiting herbicides and their modification.

Base-pair resolution detection of transcription factor binding site by deep deconvolutional network.

Motivation: Transcription factor (TF) binds to the promoter region of a gene to control gene expression. Identifying precise TF binding sites (TFBSs) is essential for understanding the detailed mechanisms of TF-mediated gene regulation. However, there is a shortage of computational approach that can deliver single base pair resolution prediction of TFBS. Results: In this paper, we propose DeepSNR, a Deep Learning algorithm for predicting TF binding location at Single Nucleotide Resolution de novo from DNA sequence. DeepSNR adopts a novel deconvolutional network (deconvNet) model and is inspired by the similarity to image segmentation by deconvNet. The proposed deconvNet architecture is constructed on top of 'DeepBind' and we trained the entire model using TF-specific data from ChIP-exonuclease (ChIP-exo) experiments. DeepSNR has been shown to outperform motif search-based methods for several evaluation metrics. We have also demonstrated the usefulness of DeepSNR in the regulatory analysis of TFBS as well as in improving the TFBS prediction specificity using ChIP-seq data. Availability and implementation: DeepSNR is available open source in the GitHub repository (https://github.com/sirajulsalekin/DeepSNR). Supplementary information: Supplementary data are available at Bioinformatics online.

HOXA11-AS promotes the growth and invasion of renal cancer by sponging miR-146b-5p to upregulate MMP16 expression.

Recently, increasing studies showed that long noncoding RNAs (lncRNAs) play critical roles in tumor progression. However, the function and underlying mechanism of HOMEOBOX A11 antisense RNA (HOXA11-AS) on renal cancer remain unclear. In the current study, our data showed that the expression of HOXA11-AS was significantly upregulated in clear cell renal cell carcinoma (ccRCC) tissues and cell lines. High HOXA11-AS expression was associated with the advanced clinical stage, tumor stage, and lymph node metastasis. Function assays showed that HOXA11-AS inhibition significantly suppressed renal cancer cells growth, invasion, and ETM phenotype. In addition, underlying mechanism revealed that HOXA11-AS could act as a competing endogenous RNA (ceRNA) that repressed miR-146b-5p expression, which regulated its downstream target MMP16 in renal cancer. Taken together, our findings suggested that HOXA11-AS could promote renal cancer cells growth and invasion by modulating miR-146b-5p-MMP16 axis. Thus, our findings suggested that HOXA11-AS could serve as potential therapeutic target for the treatment of renal cancer.

A New Approach to Guided Wave Ray Tomography for Temperature-Robust Damage Detection Using Piezoelectric Sensors.

In this paper, a new approach to guided wave ray tomography for temperature-robust damage detection with time-of-flight (TOF) temperature compensation is developed. Based on the linear relationship between the TOF of a guided wave and temperature, analyses show that the TOF of the baseline signal can be compensated by the temperature measurement of the inspected materials without estimating the temperature compensation parameters. The inversion is based on the optimization of the TOF misfit function between the inspected and compensated baseline TOFs of the guided waves, and is applied by the elastic net penalty approach to perform thickness change mapping in a structural health monitoring (SHM) application. Experiments that are conducted in isotropic plates by piezoelectric sensors demonstrate the effectiveness of the proposed method. According to the results, our approach not only eliminates the artefacts that are caused by a temperature variation from 25 °C to 70 °C but also provides more accurate and clearer imaging of damage than conventional ray tomography methods.

Early response index: a statistic to discover potential early stage disease biomarkers.

BACKGROUND: Identifying disease correlated features early before large number of molecules are impacted by disease progression with significant abundance change is very advantageous to biologists for developing early disease diagnosis biomarkers. Disease correlated features have relatively low level of abundance change at early stages. Finding them using existing bioinformatic tools in high throughput data is a challenging task since the technology suffers from limited dynamic range and significant noise. Most existing biomarker discovery algorithms can only detect molecules with high abundance changes, frequently missing early disease diagnostic markers. RESULTS: We present a new statistic called early response index (ERI) to prioritize disease correlated molecules as potential early biomarkers. Instead of classification accuracy, ERI measures the average classification accuracy improvement attainable by a feature when it is united with other counterparts for classification. ERI is more sensitive to abundance changes than other ranking statistics. We have shown that ERI significantly outperforms SAM and Localfdr in detecting early responding molecules in a proteomics study of a mouse model of multiple sclerosis. Importantly, ERI was able to detect many disease relevant proteins before those algorithms detect them at a later time point. CONCLUSIONS: ERI method is more sensitive for significant feature detection during early stage of disease development. It potentially has a higher specificity for biomarker discovery, and can be used to identify critical time frame for disease intervention.

t-BuOK-mediated reductive addition of P(O)-H compounds to terminal alkynes forming ß-arylphosphine oxides.

A novel and efficient t-BuOK-mediated reductive addition of P(O)-H compounds to terminal alkynes was developed. A variety of ß-arylphosphine oxides including the valuable ß-heteroarylphosphine oxides were produced in moderate to high yields under mild reaction conditions. This reaction may proceed via a tandem process involving regio-selective double addition and subsequent transfer hydrogenation.

PeakLink: a new peptide peak linking method in LC-MS/MS using wavelet and SVM.

MOTIVATION: In liquid chromatography-mass spectrometry/tandem mass spectrometry (LC-MS/MS), it is necessary to link tandem MS-identified peptide peaks so that protein expression changes between the two runs can be tracked. However, only a small number of peptides can be identified and linked by tandem MS in two runs, and it becomes necessary to link peptide peaks with tandem identification in one run to their corresponding ones in another run without identification. In the past, peptide peaks are linked based on similarities in retention time (rt), mass or peak shape after rt alignment, which corrects mean rt shifts between runs. However, the accuracy in linking is still limited especially for complex samples collected from different conditions. Consequently, large-scale proteomics studies that require comparison of protein expression profiles of hundreds of patients can not be carried out effectively. METHOD: In this article, we consider the problem of linking peptides from a pair of LC-MS/MS runs and propose a new method, PeakLink (PL), which uses information in both the time and frequency domain as inputs to a non-linear support vector machine (SVM) classifier. The PL algorithm first uses a threshold on an rt likelihood ratio score to remove candidate corresponding peaks with excessively large elution time shifts, then PL calculates the correlation between a pair of candidate peaks after reducing noise through wavelet transformation. After converting rt and peak shape correlation to statistical scores, an SVM classifier is trained and applied for differentiating corresponding and non-corresponding peptide peaks. RESULTS: PL is tested in multiple challenging cases, in which LC-MS/MS samples are collected from different disease states, different instruments and different laboratories. Testing results show significant improvement in linking accuracy compared with other algorithms. AVAILABILITY AND IMPLEMENTATION: M files for the PL alignment method are available at http://compgenomics.utsa.edu/zgroup/PeakLink. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MZDASoft: a software architecture that enables large-scale comparison of protein expression levels over multiple samples based on liquid chromatography/tandem mass spectrometry.

RATIONALE: Without accurate peak linking/alignment, only the expression levels of a small percentage of proteins can be compared across multiple samples in Liquid Chromatography/Mass Spectrometry/Tandem Mass Spectrometry (LC/MS/MS) due to the selective nature of tandem MS peptide identification. This greatly hampers biomedical research that aims at finding biomarkers for disease diagnosis, treatment, and the understanding of disease mechanisms. A recent algorithm, PeakLink, has allowed the accurate linking of LC/MS peaks without tandem MS identifications to their corresponding ones with identifications across multiple samples collected from different instruments, tissues and labs, which greatly enhanced the ability of comparing proteins. However, PeakLink cannot be implemented practically for large numbers of samples based on existing software architectures, because it requires access to peak elution profiles from multiple LC/MS/MS samples simultaneously. METHODS: We propose a new architecture based on parallel processing, which extracts LC/MS peak features, and saves them in database files to enable the implementation of PeakLink for multiple samples. The software has been deployed in High-Performance Computing (HPC) environments. The core part of the software, MZDASoft Parallel Peak Extractor (PPE), can be downloaded with a user and developer's guide, and it can be run on HPC centers directly. The quantification applications, MZDASoft TandemQuant and MZDASoft PeakLink, are written in Matlab, which are compiled with a Matlab runtime compiler. A sample script that incorporates all necessary processing steps of MZDASoft for LC/MS/MS quantification in a parallel processing environment is available. The project webpage is http://compgenomics.utsa.edu/zgroup/MZDASoft. RESULTS: The proposed architecture enables the implementation of PeakLink for multiple samples. Significantly more (100%-500%) proteins can be compared over multiple samples with better quantification accuracy in test cases. CONCLUSION: MZDASoft enables large-scale comparison of protein expression levels over multiple samples with much larger protein comparison coverage and better quantification accuracy. It is an efficient implementation based on parallel processing which can be used to process large amounts of data.

Machine Learning for Risk Prediction of Recurrent AKI in Adult Patients After Hospital Discharge.

Recurrent AKI has been found common among hospitalized patients after discharge, and early prediction may allow timely intervention and optimized post-discharge treatment [1]. There are significant gaps in the literature regarding the risk prediction on the post-AKI population, and most current works only included a limited number of pre-selected variables [2]. In this study, we built and compared machine learning models using both knowledge-based and data-driven features in predicting the risk of recurrent AKI within 1-year of discharge. Our results showed that the additional use of data-driven features statistically improved the model performances, with best AUC=0.766 by using logistic regression.

reguloGPT: Harnessing GPT for Knowledge Graph Construction of Molecular Regulatory Pathways.

Motivation: Molecular Regulatory Pathways (MRPs) are crucial for understanding biological functions. Knowledge Graphs (KGs) have become vital in organizing and analyzing MRPs, providing structured representations of complex biological interactions. Current tools for mining KGs from biomedical literature are inadequate in capturing complex, hierarchical relationships and contextual information about MRPs. Large Language Models (LLMs) like GPT-4 offer a promising solution, with advanced capabilities to decipher the intricate nuances of language. However, their potential for end-to-end KG construction, particularly for MRPs, remains largely unexplored. Results: We present reguloGPT, a novel GPT-4 based in-context learning prompt, designed for the end-to-end joint name entity recognition, N-ary relationship extraction, and context predictions from a sentence that describes regulatory interactions with MRPs. Our reguloGPT approach introduces a context-aware relational graph that effectively embodies the hierarchical structure of MRPs and resolves semantic inconsistencies by embedding context directly within relational edges. We created a benchmark dataset including 400 annotated PubMed titles on N6-methyladenosine (m6A) regulations. Rigorous evaluation of reguloGPT on the benchmark dataset demonstrated marked improvement over existing algorithms. We further developed a novel G-Eval scheme, leveraging GPT-4 for annotation-free performance evaluation and demonstrated its agreement with traditional annotation-based evaluations. Utilizing reguloGPT predictions on m6A-related titles, we constructed the m6A-KG and demonstrated its utility in elucidating m6A's regulatory mechanisms in cancer phenotypes across various cancers. These results underscore reguloGPT's transformative potential for extracting biological knowledge from the literature. Availability and implementation: The source code of reguloGPT, the m6A title and benchmark datasets, and m6A-KG are available at: https://github.com/Huang-AI4Medicine-Lab/reguloGPT.

Small Molecule MIF Modulation Enhances Ferroptosis by Impairing DNA Repair Mechanisms.

Ferroptosis is a form of regulated cell death that can be modulated by small molecules and has the potential for the development of therapeutics for oncology. Although excessive lipid peroxidation is the defining hallmark of ferroptosis, DNA damage may also play a significant role. In this study, a potential mechanistic role for MIF in homologous recombination (HR) DNA repair is identified. The inhibition or genetic depletion of MIF or other HR proteins, such as breast cancer type 1 susceptibility protein (BRCA1), is demonstrated to significantly enhance the sensitivity of cells to ferroptosis. The interference with HR results in the translocation of the tumor suppressor protein p53 to the mitochondria, which in turn stimulates the production of reactive oxygen species. Taken together, the findings demonstrate that MIF-directed small molecules enhance ferroptosis via a putative MIF-BRCA1-RAD51 axis in HR, which causes resistance to ferroptosis. This suggests a potential novel druggable route to enhance ferroptosis by targeted anticancer therapeutics in the future.

BPDA2d--a 2D global optimization-based Bayesian peptide detection algorithm for liquid chromatograph-mass spectrometry.

MOTIVATION: Peptide detection is a crucial step in mass spectrometry (MS) based proteomics. Most existing algorithms are based upon greedy isotope template matching and thus may be prone to error propagation and ineffective to detect overlapping peptides. In addition, existing algorithms usually work at different charge states separately, isolating useful information that can be drawn from other charge states, which may lead to poor detection of low abundance peptides. RESULTS: BPDA2d models spectra as a mixture of candidate peptide signals and systematically evaluates all possible combinations of possible peptide candidates to interpret the given spectra. For each candidate, BPDA2d takes into account its elution profile, charge state distribution and isotope pattern, and it combines all evidence to infer the candidate's signal and existence probability. By piecing all evidence together--especially by deriving information across charge states--low abundance peptides can be better identified and peptide detection rates can be improved. Instead of local template matching, BPDA2d performs global optimization for all candidates and systematically optimizes their signals. Since BPDA2d looks for the optimal among all possible interpretations of the given spectra, it has the capability in handling complex spectra where features overlap. BPDA2d estimates the posterior existence probability of detected peptides, which can be directly used for probability-based evaluation in subsequent processing steps. Our experiments indicate that BPDA2d outperforms state-of-the-art detection methods on both simulated data and real liquid chromatography-mass spectrometry data, according to sensitivity and detection accuracy. AVAILABILITY: The BPDA2d software package is available at http://gsp.tamu.edu/Publications/supplementary/sun11a/.

Full waveform inversion guided wave tomography with a recurrent neural network.

Corrosion quantitative detection of plate or plate-like structure materials is crucial in industrial Non-Destructive Testing (NDT) for determining their remaining life. For doing that, a novel ultrasonic guided wave tomography method, incorporating recurrent neural network (RNN) into full waveform inversion (FWI) called as RNN-FWI, is proposed in this paper. When the wave equation of an acoustic model is solved by a forward model with the cyclic calculation units of an RNN, it is shown that the inversion of the forward model can be obtained iteratively by minimizing a waveform misfit function of quadratic Wasserstein distance between the modeled and measured data. It is also demonstrated that the gradient of the objective function can be obtained by automatic differentiation while the parameters of the waveform velocity model are updated by the adaptive momentum estimation algorithm (Adam). The U-Net deep image prior (DIP) is used as the velocity model regularization in each iteration. The final thickness maps of the plate or plate-like structure materials shown can be archived by the dispersion characteristics of guided waves. Both the numerical simulation and experimental results show that the proposed RNN-FWI tomography method performs better than the conventional time-domain FWI in terms of convergence rate, initial model requirement, and robustness.

PD-L1 expression and prognosis in definitive radiotherapy patients with neuroendocrine cervical carcinoma.

Background: Neuroendocrine carcinoma of the cervix (NECC) is more prone to lymphatic infiltration, lymph node involvement, local recurrence, and distant metastasis. Using concurrent chemoradiotherapy (CCRT) with or without adjuvant chemotherapy as the standard treatment for locally advanced NECCs and CCRT for patients with early lesions confined to the cervix. However, the prognosis of NECC patients treated with definitive radiotherapy (RT) is unknown. Immune checkpoint inhibitors are a promising therapeutic strategy for locally advanced cervical cancer. Some reports suggest that the expression of PD-L1 in solid tumors correlates with prognosis. Aim: This study investigates prognostic factors for survival in patients with neuroendocrine cervical carcinoma (NECC) treated with definitive RT and the relationship between PD-L1 expression and prognosis in these patients. Methods: This retrospective study included 66 patients with histologically confirmed NECC who received RT with or without chemotherapy. From January 2015 to December 2020, patients received routine extended-field irradiation (EFI), and PD-L1 expression was assessed by immunohistochemistry. The most commonly used chemotherapy agents were etoposide-platinum and paclitaxel-platinum. Results: PD-L1 expression was positive in 17 of 45 (37.8%) patients. There were 52 cases of pure NECC and 14 cases of mixed carcinoma. Sixty stage IB-III patients received definitive RT. The 3- and 5-year progression-free survival (PFS) was 39.8% and 34.1%, and 3- and 5-year overall survival (OS) was 48.0% and 40.2%, respectively. There was no significant difference in 3 and 5-year PFS and 3 and 5-year OS between patients with pure and mixed carcinoma. Positive PD-L1 expression was associated with higher 3-year PFS in patients with mixed histology. Univariate analysis showed that lymph node metastasis (LNM) and the International Federation of Gynecology and Obstetrics stages predicted 3- and 5-year PFS in patients who received definitive RT. The median OS in patients receiving less than four cycles and at least four cycles of chemotherapy (CT) was 26.0 and 44.0 months, respectively (P = 0.038); moreover, 3- and 5-year PFS was 34.1% and 25.7% in the former and 46.4% and 40.4% in the latter. There were no significant differences in OS and PFS between pelvic irradiation and prophylactic EFI in patients treated with definitive RT. There were no significant differences in para-aortic failure rate after concurrent chemoradiotherapy between patients who underwent pelvic irradiation or prophylactic EFI (P = 0.147). Conclusion: In patients with mixed NECC, positive PD-L1 expression is correlated with higher 3-year PFS. Chemoradiotherapy was effective for NECCs. The LNM and stage predicted PFS. Four or more cycles of chemotherapy improve prognosis. Prophylactic EFI did not significantly improve PFS and OS. Relevance for Patients: This study is relevant to patients as it confirms that chemoradiotherapy is effective for both early and locally advanced NECC and that four or more cycles of chemotherapy improved prognosis. The regimen should be carefully evaluated to ensure that patients receive the most effective radiation therapy for the prophylactic of para-aortic LNM. Potential risk factors for the recurrence of radical radiotherapy should be fully understood to minimize these risks. This study observed that PD-L1 expression positive in patients with mixed NECC types is correlated with higher 3-year PFS.