MultiScale-CNN-4mCPred: a multi-scale CNN and adaptive embedding-based method for mouse genome DNA N4-methylcytosine prediction.

N4-methylcytosine (4mC) is an important epigenetic mechanism, which regulates many cellular processes such as cell differentiation and gene expression. The knowledge about the 4mC sites is a key foundation to exploring its roles. Due to the limitation of techniques, precise detection of 4mC is still a challenging task. In this paper, we presented a multi-scale convolution neural network (CNN) and adaptive embedding-based computational method for predicting 4mC sites in mouse genome, which was referred to as MultiScale-CNN-4mCPred. The MultiScale-CNN-4mCPred used adaptive embedding to encode nucleotides, and then utilized multi-scale CNNs as well as long short-term memory to extract more in-depth local properties and contextual semantics in the sequences. The MultiScale-CNN-4mCPred is an end-to-end learning method, which requires no sophisticated feature design. The MultiScale-CNN-4mCPred reached an accuracy of 81.66% in the 10-fold cross-validation, and an accuracy of 84.69% in the independent test, outperforming state-of-the-art methods. We implemented the proposed method into a user-friendly web application which is freely available at: http://www.biolscience.cn/MultiScale-CNN-4mCPred/ .

Deep6mAPred: A CNN and Bi-LSTM-based deep learning method for predicting DNA N6-methyladenosine sites across plant species.

DNA N6-methyladenine (6mA) is a key DNA modification, which plays versatile roles in the cellular processes, including regulation of gene expression, DNA repair, and DNA replication. DNA 6mA is closely associated with many diseases in the mammals and with growth as well as development of plants. Precisely detecting DNA 6mA sites is of great importance to exploration of 6mA functions. Although many computational methods have been presented for DNA 6mA prediction, there is still a wide gap in the practical application. We presented a convolution neural network (CNN) and bi-directional long-short term memory (Bi-LSTM)-based deep learning method (Deep6mAPred) for predicting DNA 6mA sites across plant species. The Deep6mAPred stacked the CNNs and the Bi-LSTMs in a paralleling manner instead of a series-connection manner. The Deep6mAPred also employed the attention mechanism for improving the representations of sequences. The Deep6mAPred reached an accuracy of 0.9556 over the independent rice dataset, far outperforming the state-of-the-art methods. The tests across plant species showed that the Deep6mAPred is of a remarkable advantage over the state of the art methods. We developed a user-friendly web application for DNA 6mA prediction, which is freely available at http://106.13.196.152:7001/ for all the scientific researchers. The Deep6mAPred would enrich tools to predict DNA 6mA sites and speed up the exploration of DNA modification.

Criteria to Evaluate Tumor Enlargement During the Active Surveillance of High-Risk Thyroid Nodules: Which is Better, Diameter or Volume?

INTRODUCTION: Tumor enlargement is the most common parameter identifying disease progression during active surveillance, but the value and significance of the changes in tumor diameter and volume in the evaluation of tumor growth have not been compared. METHODS: This cohort study included 468 patients with high-risk thyroid nodule, in whom nodule size change was monitored using ultrasound, to compare the changes in tumor diameter and volume in assessing tumor growth. RESULTS: A total of 569 high-risk thyroid nodules were found in the 468 patients. A total of 14 nodules (2.5%) showed a diameter increase ≥ 3 mm. The number of nodules with a peak volume change exceeding 50% and 100% was 185 (32.5%) and 86 (15.1%), respectively. Among the 555 stable nodules, the number of nodules with volume fluctuations exceeding 50% and 100% was 171 (30.8%) and 72 (13.0%), respectively. Among 212 stable nodules at the baseline and in the first three follow-up, the percentage of peak volume fluctuations exceeding 50% (48.5% vs. 28.5%, p = 0.004) and 100% (26.5% vs. 8.3%, p < 0.001) in the nodules with the sum of three diameters (SOTDs) ≤ 1 cm was significantly higher than that of nodules with SOTDs > 1 cm. A statistically significant difference was also found in the range distribution of SOTDs ≤ 1 cm and SOTDs > 1 cm (p = 0.007). CONCLUSIONS: Volume is not an appropriate method for determining tumor growth. Tumor diameter measurement alone serves as a better surrogate for disease progression in sonographically high-risk thyroid nodules than volume.

Ultrasonography for the Prediction of High-Volume Lymph Node Metastases in Papillary Thyroid Carcinoma: Should Surgeons Believe Ultrasound Results?

BACKGROUND: Lymph node metastasis (LNM) often occurs in papillary thyroid carcinoma (PTC); the efficacy of ultrasound for predicting high-volume lymph node metastases (LNMs) in patients with PTC remains unexplored. METHODS: The medical records of 2073 consecutive PTC patients were reviewed. Sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) were calculated to evaluate the efficacy of ultrasound. Risk factors for LNM/high-volume LNMs and lymph node involvement on ultrasound (usLNM) were identified by univariate and multivariate analyses. RESULTS: Of all the patients, 936 (45.2%) patients had LNMs, and 254 (12.3%) patients had high-volume LNMs. The sensitivity of ultrasound for detecting LNM/high-volume LNMs was 27.9% and 63.8%, respectively; the specificity was 93.1% and 90.3%, respectively. The NPV for ultrasound in detecting high-volume LNMs was 94.7%. In multivariate analysis, male sex (OR = 2.108, p < 0.001), tumor diameter > 1.0 cm (OR = 2.304, p < 0.001) and usLNM (+) (OR = 12.553, p < 0.001) were independent clinical risk factors for high-volume LNMs. Tumor diameter > 1 cm (OR = 3.036, p < 0.001) and male sex (OR = 1.642, p < 0.001) were independent clinical risk factors for usLNM; a skilled sonographer (OR = 1.121, p = 0.358) was not significantly associated with usLNM. CONCLUSIONS: Lymph node involvement found by ultrasound has great predictive value for high-volume LNMs; the NPV is very high for patients without lymph node involvement on ultrasound. The ultrasound results do not appear to be influenced by the experience of the sonographer.

A New Model System for Exploring Assembly Mechanisms of the HIV-1 Immature Capsid In Vivo.

The assembly of the HIV-1 immature capsid (HIC) is an essential step in the virus life cycle. In vivo, the HIC is composed of [Formula: see text] hexameric building blocks, and it takes 5-6 min to complete the assembly process. The involvement of numerous building blocks and the rapid timecourse makes it difficult to understand the HIC assembly process. In this work, we study HIC assembly in vivo by using differential equations. We first obtain a full model with 420 differential equations. Then, we reduce six addition reactions for separate building blocks to a single complex reaction. This strategy reduces the full model to 70 equations. Subsequently, the theoretical analysis of the reduced model shows that it might not be an effective way to decrease the HIC concentration at the equilibrium state by decreasing the microscopic on-rate constants. Based on experimental data, we estimate that the nucleating structure is much smaller than the HIC. We also estimate that the microscopic on-rate constant for nucleation reactions is far less than that for elongation reactions. The parametric collinearity investigation testifies the reliability of these two characteristics, which might explain why free building blocks do not readily polymerize into higher-order polymers until their concentration reaches a threshold value. These results can provide further insight into the assembly mechanisms of the HIC in vivo.

Mathematical modeling and quantitative analysis of HIV-1 Gag trafficking and polymerization.

Gag, as the major structural protein of HIV-1, is necessary for the assembly of the HIV-1 sphere shell. An in-depth understanding of its trafficking and polymerization is important for gaining further insights into the mechanisms of HIV-1 replication and the design of antiviral drugs. We developed a mathematical model to simulate two biophysical processes, specifically Gag monomer and dimer transport in the cytoplasm and the polymerization of monomers to form a hexamer underneath the plasma membrane. Using experimental data, an optimization approach was utilized to identify the model parameters, and the identifiability and sensitivity of these parameters were then analyzed. Using our model, we analyzed the weight of the pathways involved in the polymerization reactions and concluded that the predominant pathways for the formation of a hexamer might be the polymerization of two monomers to form a dimer, the polymerization of a dimer and a monomer to form a trimer, and the polymerization of two trimers to form a hexamer. We then deduced that the dimer and trimer intermediates might be crucial in hexamer formation. We also explored four theoretical combined methods for Gag suppression, and hypothesized that the N-terminal glycine residue of the MA domain of Gag might be a promising drug target. This work serves as a guide for future theoretical and experimental efforts aiming to understand HIV-1 Gag trafficking and polymerization, and might help accelerate the efficiency of anti-AIDS drug design.

Diagnosis and Clinical Analysis of Primary Thyroid Lymphoma.

Objective To summarize our experiences in the diagnosis and prognosis of different subtypes of primary thyroid lymphoma (PTL). Methods The clinical data of 27 PTL patients who were treated in our hospital from January 1998 to December 2014 were retrospectively analyzed. The pathological types of these patients included B cell lymphoma unclassifiable (BCLU) (n=5),mucosa-associated lymphiod tissue lymphoma (MALT) (n=9),diffuse large B cell lymphoma (DLBCL) (n=12),and T cell lymphoma (n=1). Results Of all these 27 cases,the most common clinical symptom was painless swelling of the neck (n=21,77.8%). Of 7 patients who had received preoperative fine needle biopsy,lymphoma was suspected in 2 cases (28.6%). Among these 7 cases,the positive rate of suspicious lymphoma was 66.7% in 3 DLBCL patients,0 in 3 MALT patients,and 0 in 1 BCLU paitent. Also,25 patients underwent intraoperative frozen pathological examination,which revealed lymphoma or suspicious lymphoma in 16 cases (64.0%); in these patients,the positive rate was 66.7% for BCLU,77.8% for MALT,58.3% for DLBCL,and 0 for T-cell lymphomas. The overall survival was (89.3±12.4) months,and the overall 5-year survival rate was 61.6%. The estimated survival in symptomatic group was 31.6 months,which was significantly shorter than that in asymptomatic group (97.9 months) (P=0.032). Other factors including age,sex,tumor size,tumor stage,international prognostic index,tracheal compression,lactate dehydrogenase,residual tumor,and pathological type showed no significant effect on survival(all P>0.05). Conclusions DLBCL has the highest fine needle biopsy positive rate,MALT has the highest frozen pathological positive rate,and intraoperative frozen pathology has more malignant results than the preoperative fine needle biopsy in the diagnosis. The accompanying lymphoma symptoms may be an adverse prognostic factor.

Risk Factors of Lymphnode Metastasis in Patients with Thyroid Papillary Carcinoma Associated with Graves Disease.

Objective To summarize the characteristics of lymph node metastasis in patients with papillary thyroid carcinoma accompanied with Graves disease,and to provide evidence for clinical treatment. Methods Totally 98 patients with papillary thyroid carcinoma and Graves disease who had been treated in Peking Union Medical College Hospital from January 2004 to December 2013 were divided into the lymph node metastasis positive group (n=34) and lymph node metastasis negative group (n=64). The general information,blood biochemical results,pathological results,and prognoses were compared between these two groups. Results These two groups showed no significant differences in gender (χ2=0.2113,P=0.6458),age (t=1.7000,P=0.0922),tumor diameter (t=1.2559,P=0.2122),and multifocal tumors (χ2=1.9170,P=0.1661). The median level of thyrotropin receptor antibody (TR-Ab) value in the lymph node metastasis positive group was 4.84 U/L,which was significantly higher than that in the negative group which was 2.99 U/L (t=2.0169,P=0.0465). There were no significant differences in serum thyroid stimulating hormone (t=0.0257,P=0.9800),free triiodothyronine (t=1.3610,P=0.1770),free thyroxine (t=0.0082,P=0.9930),thyroid peroxidase antibody (t=0.0177,P=0.9860),and thyroglobulin antibody levels (t=1.1450,P=0.2550) between two groups. The postoperative pathological results showed that tumor capsular invasion rate (26.5% vs. 9.38%;χ2=5.006,P=0.0253) and lymph node recurrence rate (14.7% vs. 1.56%;χ2=4.583,P=0.0323) were significantly higher in the positive group than in the negative group. The distal metastasis rate in the positive group and negative group were 5.88% and 0,respectively. Conclusions There is no definite association between lymph node metastasis and tumor size in patients with thyroid papillary carcinoma associated with Graves disease. The risk factors for lymph node metastasis include TR-Ab and tumor capsular invasion,with a higher incidence of lymph nodes recurrence.

The clinical prognosis of patients with cN0 papillary thyroid microcarcinoma by central neck dissection.

BACKGROUND: Central lymph node metastasis of papillary thyroid microcarcinoma (PTMC) is common; however, prophylactic central lymph node dissection (CLND) is still controversial because of the possible increased morbidity. The purpose of this study is to determine the clinical outcome of patients with cN0 PTMC by central neck dissection. METHODS: A retrospective cohort study was conducted on patients with PTMC without preoperative evidence of lymph node disease (cN0), and the outcomes were compared between patients undergoing total thyroidectomy (TT) alone (group A) and patients undergoing TT with CLND (group B). RESULTS: In this study, 242 patients with cN0 PTMC were included. Group A had 108 patients and group B had 134 patients. During a follow-up of over 60 months, the long-term postoperative complications were equivalent between the two groups. In group B, the presence of involved central neck lymph nodes upstaged 16% of patients to stage III disease, which necessitated additional postoperative radioactive iodine treatment. More patients had recurrences in group A. The rate of reoperation in the central compartment was higher in group A than in group B (8.3% vs 2.2%, P < 0.01). CONCLUSIONS: Prophylactic CLND does not increase long-term postoperative complications and reduces the risk of recurrence in the central compartment.

BRAFV600E mutation does not predict lymph node metastases and recurrence in Chinese papillary thyroid microcarcinoma patients.

OBJECT: Previous studies suggest BRAFV600E mutation is a marker for poor prognosis in papillary thyroid cancer, however, its ability to further risk stratify papillary thyroid microcarcinoma (PTMC) remains controversial. We aimed to explore the association between BRAFV600E mutation and the clinicopathological features and recurrence in Chinese PTMC patients. METHODS: We retrospectively reviewed 2094 PTMC patients who underwent surgery and had a valid BRAFV600E mutation test result. Among them, 1292 patients had complete follow-up data. The mutation incidence was determined. Moreover, the clinicopathological characteristics, disease-free survival (DFS), and response to therapy distribution were compared between the mutation and non-mutation groups. RESULTS: BRAFV600E mutation was observed in 90.6 % of all patients and 89.2 % of patients with complete follow-up data. No significant difference was observed in lymph node metastases (LNM) number categories between the mutation and non-mutation groups among all patients (P = 0.329) and 1292 patients (P = 0.408). Neither the 3-year DFS (97.9 % vs. 98.0 %, P = 0.832) nor the response to therapy distribution (P > 0.05) indicated a significant difference between the mutation and non-mutation groups. The 3-year DFS differs among patients having different LNM number categories (99.8 % vs. 98.5 % vs. 77.3 %, P < 0.001). Multivariate analysis revealed that high-volume (over 5) LNM (Total thyroidectomy (TT): OR = 4.000, 95 % CI 2.390-6.694, P < 0.001; Unilateral thyroidectomy (UT): OR = 4.183, 95 % CI 1.565-11.190, P = 0.004), rather than BRAFV600E mutation (P > 0.05), was an independent risk factor of response to therapy. CONCLUSIONS: Our results suggested that BRAFV600E mutation could not accurately predict LNM or the recurrence of Chinese PTMC patients. Moreover, high-volume LNM is significantly associated with PTMC prognosis.

A Long-Term Study Comparing the Quality of Life and Psychological Status of Patients with Highly Suspicious Thyroid Nodules ≤1 cm Undergoing Active Surveillance with Those Undergoing Immediate Surgery.

Background: Limited information is available on the long-term impact of active surveillance (AS) and immediate surgery (IS) on the quality of life (QoL) and psychological status of patients with highly suspicious subcentimeter thyroid nodules. Methods: A prospective study was conducted on 752 patients showing highly suspicious subcentimeter thyroid nodules, among whom 584 chose AS and 168 chose IS. All patients underwent at least two assessments regarding their QoL and psychological status, using three questionnaires: Thyroid Cancer-Specific Quality of Life (THYCA-QoL), Hospital Anxiety and Depression Scale (HADS), and European Organization for Research and Treatment of Cancer (EORTC) Quality of Life Core Questionnaire (QLQ-C30). Propensity-score matching (PSM) at a ratio of 3:1 was utilized on patients in the AS and IS groups to mitigate selection bias (504 patients in the AS group and 168 in the IS group). Subsequently, the mixed linear model was used to analyze the QoL data. Results: The median time from the initial evaluation to the last follow-up in the AS and IS groups was 24.0 and 14.2 months, respectively. The AS group showed superior QoL outcomes compared to the IS group, mainly manifested in voice (p < 0.001), sympathetic (p = 0.008), throat/mouth (p < 0.001), and problems with scar (p < 0.001) domains, as per the THYCA-QoL questionnaire. Further, the EORTC QLQ-C30 questionnaire highlighted better outcomes in physical function (p = 0.029), role function (p < 0.001), social function (p < 0.001), global health status (p < 0.001), fatigue (p = 0.012), pain (p = 0.028), appetite loss (p = 0.017), and financial difficulties (p < 0.001). Compared to the initial assessment (1 week after surgery), the IS group showed progressive improvements in QoL, especially in voice (p = 0.024), throat/mouth (p < 0.001), physical function (p = 0.004), social function (p = 0.014), nausea and vomiting (p < 0.001), pain (p = 0.006), and appetite loss (p = 0.048) domains as per both questionnaires. Conclusion: Patients with highly suspicious subcentimeter thyroid nodules who choose IS tend to experience a poorer long-term QoL compared to those who choose AS. Although the situation may improve over time, certain issues might persist, making AS a favorable option for these patients.

Dynamics analysis of building block synthesis reactions for virus assembly in vitro.

Virus assembly from structural protein monomers to virus shells is a key step of virus replication. Some drug targets were found in this process. It consists of two steps. Virus structural protein monomers firstly polymerize to building blocks, then these building blocks assemble into virus shells. So, these building block synthesis reactions in the first step are fundamental for virus assembly. Typically, virus building blocks are made up of less than six monomers. They are of five types, including dimer, trimer, tetramer, pentamer and hexamer. In this work, we develop five synthesis reaction dynamical models for these five types, respectively. Then, we prove the existence and uniqueness of the positive equilibrium solution for these dynamical models one by one. Subsequently, we also analyze the stability of the equilibrium states, respectively. We got the function of monomer and dimer concentrations for dimer building blocks in the equilibrium state. We also got the function of all intermediate polymers and monomers for trimer, tetramer, pentamer and hexamer building blocks in the equilibrium state, respectively. Based on our analysis, dimer building blocks in the equilibrium state will decrease as the ratio of the off-rate constant to the on-rate constant increases. Trimer building blocks in the equilibrium state will decrease with the increasing ratio of the off-rate constant to the on-rate constant of trimers. These results may provide further insight into the virus-building block synthesis dynamic property in vitro.

LangMoDHS: A deep learning language model for predicting DNase I hypersensitive sites in mouse genome.

DNase I hypersensitive sites (DHSs) are a specific genomic region, which is critical to detect or understand cis-regulatory elements. Although there are many methods developed to detect DHSs, there is a big gap in practice. We presented a deep learning-based language model for predicting DHSs, named LangMoDHS. The LangMoDHS mainly comprised the convolutional neural network (CNN), the bi-directional long short-term memory (Bi-LSTM) and the feed-forward attention. The CNN and the Bi-LSTM were stacked in a parallel manner, which was helpful to accumulate multiple-view representations from primary DNA sequences. We conducted 5-fold cross-validations and independent tests over 14 tissues and 4 developmental stages. The empirical experiments showed that the LangMoDHS is competitive with or slightly better than the iDHS-Deep, which is the latest method for predicting DHSs. The empirical experiments also implied substantial contribution of the CNN, Bi-LSTM, and attention to DHSs prediction. We implemented the LangMoDHS as a user-friendly web server which is accessible at http:/www.biolscience.cn/LangMoDHS/. We used indices related to information entropy to explore the sequence motif of DHSs. The analysis provided a certain insight into the DHSs.

Active surveillance versus immediate surgery: A comparison of clinical and quality of life outcomes among patients with highly suspicious thyroid nodules 1 cm or smaller in China.

INTRODUCTION: Active surveillance (AS) is considered an alternative to immediate surgery (IS) for low-risk papillary thyroid microcarcinoma (PTMC) patients. However, it is difficult to decide between AS and IS due to limited evidence regarding risks and benefits for patients in China. METHODS: This study prospectively enrolled 485 patients with highly suspicious thyroid nodules

MPMABP: A CNN and Bi-LSTM-Based Method for Predicting Multi-Activities of Bioactive Peptides.

Bioactive peptides are typically small functional peptides with 2-20 amino acid residues and play versatile roles in metabolic and biological processes. Bioactive peptides are multi-functional, so it is vastly challenging to accurately detect all their functions simultaneously. We proposed a convolution neural network (CNN) and bi-directional long short-term memory (Bi-LSTM)-based deep learning method (called MPMABP) for recognizing multi-activities of bioactive peptides. The MPMABP stacked five CNNs at different scales, and used the residual network to preserve the information from loss. The empirical results showed that the MPMABP is superior to the state-of-the-art methods. Analysis on the distribution of amino acids indicated that the lysine preferred to appear in the anti-cancer peptide, the leucine in the anti-diabetic peptide, and the proline in the anti-hypertensive peptide. The method and analysis are beneficial to recognize multi-activities of bioactive peptides.

PRIP: A Protein-RNA Interface Predictor Based on Semantics of Sequences.

RNA-protein interactions play an indispensable role in many biological processes. Growing evidence has indicated that aberration of the RNA-protein interaction is associated with many serious human diseases. The precise and quick detection of RNA-protein interactions is crucial to finding new functions and to uncovering the mechanism of interactions. Although many methods have been presented to recognize RNA-binding sites, there is much room left for the improvement of predictive accuracy. We present a sequence semantics-based method (called PRIP) for predicting RNA-binding interfaces. The PRIP extracted semantic embedding by pre-training the Word2vec with the corpus. Extreme gradient boosting was employed to train a classifier. The PRIP obtained a SN of 0.73 over the five-fold cross validation and a SN of 0.67 over the independent test, outperforming the state-of-the-art methods. Compared with other methods, this PRIP learned the hidden relations between words in the context. The analysis of the semantics relationship implied that the semantics of some words were specific to RNA-binding interfaces. This method is helpful to explore the mechanism of RNA-protein interactions from a semantics point of view.

Related factor analysis for predicting large-volume central cervical lymph node metastasis in papillary thyroid carcinoma.

The aim of this study was to investigate the factors related to large-volume central cervical lymph node metastasis (LNM) in papillary thyroid carcinoma. A retrospective study of 340 patients with 642 papillary thyroid carcinoma nodules who underwent thyroidectomy in Peking Union Medical College Hospital between 2011 and 2015 was conducted. These nodules were divided into two groups by the number of central cervical lymph node metastases: large-volume central cervical LNM (>5 metastatic lymph nodes, n = 129) and no central cervical LNM (n = 211). We evaluated the correlations between gender, age, chronic lymphocytic thyroiditis, thyroid ultrasonographic features, and large-volume central cervical LNM. We found that younger age (≤40 years) (OR = 3.796, 95% CI = 2.842, 5.070), male gender (OR = 4.005, 95% CI = 2.858, 5.61), and ultrasonographic features such as tumor macroaxis size (OR = 2.985, 95% CI = 1.581, 5.633), tumor located in the isthmus (OR = 7.578, 95% CI = 4.863, 11.810), ill-defined margin (OR = 3.008, 95% CI = 1.986, 4.556), microcalcification (OR = 2.155, 95% CI = 1.585, 2.929), and abnormal cervical lymph nodes (OR = 13.753, 95% CI = 9.278, 20.385) were independent risk factors for large-volume central cervical LNM in papillary thyroid carcinoma, while chronic lymphocytic thyroiditis (OR = 0.248, 95% CI = 0.172, 0.358) was a protective factor. Younger age (≤40 years), male sex, and ultrasonographic features such as tumor macroaxis size, tumor located in the isthmus, ill-defined margin, microcalcification, and abnormal cervical lymph nodes were independent risk factors for large-volume central cervical LNM in papillary thyroid carcinoma, while chronic lymphocytic thyroiditis can be considered a protective factor. Our results provide a reference for adjusting clinical treatment approaches.

A capsule network-based method for identifying transcription factors.

Transcription factors (TFs) are typical regulators for gene expression and play versatile roles in cellular processes. Since it is time-consuming, costly, and labor-intensive to detect it by using physical methods, it is desired to develop a computational method to detect TFs. Here, we presented a capsule network-based method for identifying TFs. This method is an end-to-end deep learning method, consisting mainly of an embedding layer, bidirectional long short-term memory (LSTM) layer, capsule network layer, and three fully connected layers. The presented method obtained an accuracy of 0.8820, being superior to the state-of-the-art methods. These empirical experiments showed that the inclusion of the capsule network promoted great performances and that the capsule network-based representation was superior to the property-based representation for distinguishing between TFs and non-TFs. We also implemented the presented method into a user-friendly web server, which is freely available at http://www.biolscience.cn/Capsule_TF/ for all scientific researchers.

Enhancer-LSTMAtt: A Bi-LSTM and Attention-Based Deep Learning Method for Enhancer Recognition.

Enhancers are short DNA segments that play a key role in biological processes, such as accelerating transcription of target genes. Since the enhancer resides anywhere in a genome sequence, it is difficult to precisely identify enhancers. We presented a bi-directional long-short term memory (Bi-LSTM) and attention-based deep learning method (Enhancer-LSTMAtt) for enhancer recognition. Enhancer-LSTMAtt is an end-to-end deep learning model that consists mainly of deep residual neural network, Bi-LSTM, and feed-forward attention. We extensively compared the Enhancer-LSTMAtt with 19 state-of-the-art methods by 5-fold cross validation, 10-fold cross validation and independent test. Enhancer-LSTMAtt achieved competitive performances, especially in the independent test. We realized Enhancer-LSTMAtt into a user-friendly web application. Enhancer-LSTMAtt is applicable not only to recognizing enhancers, but also to distinguishing strong enhancer from weak enhancers. Enhancer-LSTMAtt is believed to become a promising tool for identifying enhancers.

An immediate postoperative response to therapy assessment can help avoid unnecessary RAI therapy.

Background: Radioiodine (RAI) therapy plays a vital role in the postoperative treatment of differentiated thyroid cancer (DTC) patients underwent total thyroidectomy (TT). However, even in the presence of capsular invasion and lymph node metastasis prognosis can be excellent and a postoperative RAI treatment might not be necessary for all patients. Therefore, this study explored the criteria for avoiding unnecessary RAI therapy in these patients. Method: We applied response to therapy assessment immediately after surgery and prospectively recruited 179 excellent or indeterminate response DTC patients with capsular invasion and/or LNM who underwent TT without RAI therapy. During the follow-up, thyroglobulin (Tg), thyroglobulin antibody (TgAb) levels, and cervical ultrasonography were collected and analyzed. Disease-free survival (DFS) was calculated using the Kaplan-Meier method. In addition, response to therapy assessments was performed on patients during each follow-up. Results: The mean follow-up period was 29.85 ± 17.44 months, and the 3- and 5-year DFS for all the patients was 99.3% in each. At the last follow-up, 165 (92.2%) patients had excellent responses, while 12 (6.7%) had an indeterminate response, and one (0.6%) each had biochemical and incomplete responses. No significant difference was observed in response to therapy between the subgroups of LNM and tumor invasion (P>0.05). For patients with capsular invasion and a number of metastatic lymph nodes ≤5 and >5, the proportions of recorded excellent responses were 95.9%, 91.0%, and 85.7%, respectively. Better responses were observed in females (excellent response: 95.5%, P=0.023), patients with stimulated Tg (s-Tg) ≤1ng/ml (excellent response: 100%, P<0.001), s-Tg ≤ 2ng/ml (excellent response: 98.4%, P<0.001), and excellent response for the immediate postoperative assessment (excellent response: 98.5%, P=0.004). Conclusions: The current study suggested that the response to therapy assessment immediately applied postoperatively could help avoid unnecessary RAI therapy among DTC patients with capsular invasion and/or LNM. Moreover, excellent response patients and patients with indeterminate response and s-Tg ≤ 2ng/ml could be managed without RAI therapy.