Machine Learning System for Lung Neoplasms Distinguished Based on Scleral Data.

Lung cancer remains the most commonly diagnosed cancer and the leading cause of death from cancer. Recent research shows that the human eye can provide useful information about one's health status, but few studies have revealed that the eye's features are associated with the risk of cancer. The aims of this paper are to explore the association between scleral features and lung neoplasms and develop a non-invasive artificial intelligence (AI) method for detecting lung neoplasms based on scleral images. A novel instrument was specially developed to take the reflection-free scleral images. Then, various algorithms and different strategies were applied to find the most effective deep learning algorithm. Ultimately, the detection method based on scleral images and the multi-instance learning (MIL) model was developed to predict benign or malignant lung neoplasms. From March 2017 to January 2019, 3923 subjects were recruited for the experiment. Using the pathological diagnosis of bronchoscopy as the gold standard, 95 participants were enrolled to take scleral image screens, and 950 scleral images were fed to AI analysis. Our non-invasive AI method had an AUC of 0.897 ± 0.041(95% CI), a sensitivity of 0.836 ± 0.048 (95% CI), and a specificity of 0.828 ± 0.095 (95% CI) for distinguishing between benign and malignant lung nodules. This study suggested that scleral features such as blood vessels may be associated with lung cancer, and the non-invasive AI method based on scleral images can assist in lung neoplasm detection. This technique may hold promise for evaluating the risk of lung cancer in an asymptomatic population in areas with a shortage of medical resources and as a cost-effective adjunctive tool for LDCT screening at hospitals.

RATING: Medical knowledge-guided rheumatoid arthritis assessment from multimodal ultrasound images via deep learning.

Multimodal ultrasound has demonstrated its power in the clinical assessment of rheumatoid arthritis (RA). However, for radiologists, it requires strong experience. In this paper, we propose a rheumatoid arthritis knowledge guided (RATING) system that automatically scores the RA activity and generates interpretable features to assist radiologists' decision-making based on deep learning. RATING leverages the complementary advantages of multimodal ultrasound images and solves the limited training data problem with self-supervised pretraining. RATING outperforms all of the existing methods, achieving an accuracy of 86.1% on a prospective test dataset and 85.0% on an external test dataset. A reader study demonstrates that the RATING system improves the average accuracy of 10 radiologists from 41.4% to 64.0%. As an assistive tool, not only can RATING indicate the possible lesions and enhance the diagnostic performance with multimodal ultrasound but it can also enlighten the road to human-machine collaboration in healthcare.

Miniaturized microfluidic-based nucleic acid analyzer to identify new biomarkers of biopsy lung cancer samples for subtyping.

Identifying new biomarkers is necessary and important to diagnose and treat malignant lung cancer. However, existing protein marker detection methods usually require complex operation steps, leading to a lag time for diagnosis. Herein, we developed a rapid, minimally invasive, and convenient nucleic acid biomarker recognition method, which enabled the combined specific detection of 11 lung cancer typing markers in a microliter reaction system after only one sampling. The primers for the combined specific detection of 11 lung cancer typing markers were designed and screened, and the microfluidic chip for parallel detection of the multiple markers was designed and developed. Furthermore, a miniaturized microfluidic-based analyzer was also constructed. By developing a microfluidic chip and a miniaturized nucleic acid analyzer, we enabled the detection of the mRNA expression levels of multiple biomarkers in rice-sized tissue samples. The miniaturized nucleic acid analyzer could detect ≥10 copies of nucleic acids. The cell volume of the typing reaction on the microfluidic chip was only 0.94 µL, less than 1/25 of that of the conventional 25-µL Eppendorf tube PCR method, which significantly reduced the testing cost and significantly simplified the analysis of multiple biomarkers in parallel. With a simple injection operation and reverse transcription loop-mediated isothermal amplification (RT-LAMP), real-time detection of 11 lung cancer nucleic acid biomarkers was performed within 45 min. Given these compelling features, 86 clinical samples were tested using the miniaturized nucleic acid analyzer and classified according to the cutoff values of the 11 biomarkers. Furthermore, multi-biomarker analysis was conducted by a machine learning model to classify different subtypes of lung cancer, with an average area under the curve (AUC) of 0.934. This method shows great potential for the identification of new nucleic acid biomarkers and the accurate diagnosis of lung cancer.

Deep learning with weak annotation from diagnosis reports for detection of multiple head disorders: a prospective, multicentre study.

BACKGROUND: A large training dataset with high-quality annotations is necessary for building an accurate and generalisable deep learning system, which can be difficult and expensive to prepare in medical applications. We present a novel deep-learning-based system, requiring no annotator but weak annotation from a diagnosis report, for accurate and generalisable performance in detecting multiple head disorders from CT scans, including ischaemia, haemorrhage, tumours, and skull fractures. METHODS: Our system was developed on 104 597 head CT scans from the Chinese PLA General Hospital, with associated textual diagnosis reports. Without expert annotation, we used keyword matching on the reports to automatically generate disorder labels for each scan. The labels were inaccurate because of the unreliable annotator-free strategy and inexact because of scan-level annotation. We proposed RoLo, a novel weakly supervised learning algorithm, with a noise-tolerant mechanism and a multi-instance learning strategy to address these issues. RoLo was tested on retrospective (2357 scans from the Chinese PLA General Hospital), prospective (650 scans from the Chinese PLA General Hospital), cross-centre (1525 scans from the Brain Hospital of Hunan Province), cross-equipment (1484 scans from the Chinese PLA General Hospital), and cross-nation (CQ500 public dataset from India) test datasets. Four radiologists were tested on the prospective test dataset before and after viewing system recommendations to assess whether the system could improve diagnostic performance. FINDINGS: The area under the receiver operating characteristic curve for detecting the four disorder types was 0·976 (95% CI 0·976-0·976) for retrospective, 0·975 (0·974-0·976) for prospective, 0·965 (0·964-0·966) for cross-centre, and 0·971 (0·971-0·972) for cross-equipment test datasets, and 0·964 (0·964-0·966) for CQ500 (with only haemorrhage and fracture). The system achieved similar performance to four radiologists and helped to improve sensitivity and specificity by 0·109 (95% CI 0·086-0·131) and 0·022 (0·017-0·026), respectively. INTERPRETATION: Without expert annotated data, our system achieved accurate and generalisable performance for head disorder detection. The system improved the diagnostic performance of radiologists. Because of its accuracy and generalisability, our computer-aided diganostic system could be used in clinical practice to improve the accuracy and efficiency of radiologists in different hospitals. FUNDING: National Key R&D Program of China, National Natural Science Foundation of China, and Beijing Natural Science Foundation.

Improve thermostability of Bacillus sp. TS chitosanase through structure-based alignment.

Chitosanases can catalyze the release of chitooligosaccharides which have a number of medical applications. Therefore, Chitosanases are good candidates for large-scale enzymatic synthesis due to their favorable thermostability properties and high catalytic efficiency. To further improve the thermostability of a chitosanase from Bacillus sp. TS, which has a half-life of 5.32 min, we mutated specific serine residues that we identified as potentially relevant through structure comparison with thermophilic CelA from Clostridium thermocellum. Out of a total of 15 mutants, three, namely S265G, S276A, and S347G, show higher thermostability. Their half-lives at 60 °C were calculated as 34.57 min, 36.79 min and 7.2 min. The Km values of S265G, S276A and S347G mutants show substrate binding ability comparable to that of the wild-type enzyme, while the S265G mutant displays a significant decrease of enzymatic activities. Additionally, we studied the synergistic effects of combined mutations, observing that all double mutants and the triple mutant are more stable than the wild-type enzyme and single mutants. Finally, we investigated the mechanisms which might give a reasonable explanation for the improved thermostability via comparative analysis of the resulting 3D structures.

Rational design and structure-based engineering of alkaline pectate lyase from Paenibacillus sp. 0602 to improve thermostability.

BACKGROUND: Ramie degumming is often carried out at high temperatures; therefore, thermostable alkaline pectate lyase (PL) is beneficial for ramie degumming for industrial applications. Thermostable PLs are usually obtained by exploring new enzymes or reconstructing existing enzyme by rational design. Here, we improved the thermostability of an alkaline pectate lyase (PelN) from Paenibacillus sp. 0602 with rational design and structure-based engineering. RESULTS: From 26 mutants, two mutants of G241A and G241V showed a higher thermostability compared with the wild-type PL. The mutant K93I showed increasing specific activity at 45 °C. Subsequently, we obtained combinational mutations (K93I/G241A) and found that their thermostability and specific activity improved simultaneously. The K93I/G241A mutant showed a half-life time of 15.9 min longer at 60 °C and a melting temperature of 1.6 °C higher than those of the wild PL. The optimum temperature decreased remarkably from 67.5 °C to 60 °C, accompanied by a 57% decrease in Km compared with the Km value of the wild-type strain. Finally, we found that the intramolecular interaction in PelN was the source in the improvements of molecular properties by comparing the model structures. Rational design of PelN was performed by stabilizing the α-helices with high conservation and increasing the stability of the overall structure of the protein. Two engineering strategies were applied by decreasing the mutation energy calculated by Discovery Studio and predicting the free energy in the process of protein folding by the PoPMuSiC algorithm. CONCLUSIONS: The results demonstrated that the K93I/G241A mutant was more suitable for industrial production than the wild-type enzyme. Furthermore, the two forementioned strategies could be extended to reveal engineering of other kinds of industrial enzymes.

Structure-based engineering of a pectate lyase with improved specific activity for ramie degumming.

Biotechnological applications of microbial pectate lyases (Pels) in plant fiber processing are promising, eco-friendly substitutes for conventional chemical degumming processes. However, to potentiate the enzymes' use for industrial applications, resolving the molecular structure to elucidate catalytic mechanisms becomes necessary. In this manuscript, we report the high resolution (1.45 Å) crystal structure of pectate lyase (pelN) from Paenibacillus sp. 0602 in apo form. Through sequence alignment and structural superposition with other members of the polysaccharide lyase (PL) family 1 (PL1), we determined that pelN shares the characteristic right-handed ß-helix and is structurally similar to other members of the PL1 family, while exhibiting key differences in terms of catalytic and substrate binding residues. Then, based on information from structure alignments with other PLs, we engineered a novel pelN. Our rational design yielded a pelN mutant with a temperature for enzymatic activity optimally shifted from 67.5 to 60 °C. Most importantly, this pelN mutant displayed both higher specific activity and ramie fiber degumming ability when compared with the wild-type enzyme. Altogether, our rational design method shows great potential for industrial applications. Moreover, we expect the reported high-resolution crystal structure to provide a solid foundation for future rational, structure-based engineering of genetically enhanced pelNs.

A highly Conserved Aspartic Acid Residue of the Chitosanase from Bacillus Sp. TS Is Involved in the Substrate Binding.

The chitosanase from Bacillus sp. TS (CsnTS) is an enzyme belonging to the glycoside hydrolase family 8. The sequence of CsnTS shares 98 % identity with the chitosanase from Bacillus sp. K17. Crystallography analysis and site-direct mutagenesis of the chitosanase from Bacillus sp. K17 identified the important residues involved in the catalytic interaction and substrate binding. However, despite progress in understanding the catalytic mechanism of the chitosanase from the family GH8, the functional roles of some residues that are highly conserved throughout this family have not been fully elucidated. This study focused on one of these residues, i.e., the aspartic acid residue at position 318. We found that apart from asparagine, mutation of Asp318 resulted in significant loss of enzyme activity. In-depth investigations showed that mutation of this residue not only impaired enzymatic activity but also affected substrate binding. Taken together, our results showed that Asp318 plays an important role in CsnTS activity.

Extracellular overexpression of chitosanase from Bacillus sp. TS in Escherichia coli.

The chitosanase gene from a Bacillus sp. strain isolated from soil in East China was cloned and expressed in Escherichia coli. The gene had 1224 nucleotides and encoded a mature protein of 407 amino acid residues. The optimum pH and temperature of the purified recombinant chitosanase were 5.0 and 60 °C, respectively, and the enzyme was stable below 40 °C. The K m, V max, and specific activity of the enzyme were 1.19 mg mL(-1), 674.71 µmol min(-1) at 50 °C, and 555.3 U mg(-1), respectively. Mn(2+) was an activator of the recombinant chitosanase, while Co(2+) was an inhibitor. Hg(2+) and Cu(2+) inhibited the enzyme at 1 mM. The highest level of enzyme activity (186 U mL(-1)) was achieved in culture medium using high cell-density cultivation in a 7-L fermenter. The main products of chitosan hydrolyzed by recombinant chitosanase were (GlcN)3-6. The chitosanases was successfully secreted to the culture media through the widely used SecB-dependent type II pathway in E. coli. The high yield of the extracellular overexpression, relevant thermostability, and effective hydrolysis of commercial grade chitosan showed that this recombinant enzyme had a great potential for industrial applications.

Single molecule imaging of the trans-translation entry process via anchoring of the tagged ribosome.

Trans-translation is an eubacterial quality control system to rescue the stalled ribosome, in which multiple components such as transfer messenger RNA (tmRNA) and Small protein B (SmpB) are involved. However, how these molecules interact with ribosome remains elusive. Here, we report the single molecule analysis of the trans-translation process. We developed a new method to label the functional ribosome, in which a tag protein (the HaloTag protein of 297 amino acids) was fused to the 30S ribosomal protein S2 and covalently labelled with specific ligand (HaloTag ligand), resulting in the stable and specific labelling of ribosome. Ribosomes were anchored onto the glass surface using biotinylated derivative of the Cy3 HaloTag ligand (i.e. biotin-Cy3-ligand), and real-time interactions of Cy5-tmRNA/SmpB/EF-Tu ternary complexes with anchored ribosomes are observed as a model of the trans-translation entry. Statistical analysis revealed that Cy5-tmRNA/SmpB/EF-Tu ternary complexes bind to the anchored ribosome with the second-order rate constant of 2.6 × 10(6) (1/M/s) and tmRNAs undergo multi-modal pathway before release from ribosome. The methods presented here are also applicable to the analysis for general translation processes.