Urine culture images collected using bacteriology automation are currently interpreted by technologists during routine standard-of-care workflows. Machine learning may be able to improve the harmonization of and assist with these interpretations.

A deep learning model, BacterioSight, was developed, trained, and tested on standard BD-Kiestra images of routine blood agar urine cultures from 2 different medical centers.

BacterioSight displayed performance on par with standard-of-care-trained technologist interpretations. BacterioSight accuracy ranged from 97% when compared to standard-of-care (single technologist) and reached 100% when compared to a consensus reached by a group of technologists (gold standard in this study). Variability in image interpretation by trained technologists was identified and annotation „fuzziness” was quantified and found to correlate with reduced confidence in BacterioSight interpretation. Intra-testing (training and testing performed within the same institution) performed welubset of cultures with high confidence. In addition, our results highlight image interpretation variability by trained technologist within an institution and globally across institutions. We propose a model in which deep learning can enhance patient care by identifying inherent sample annotation variability and improving personnel training.The addition of fludarabine to cyclophosphamide as a lymphodepleting regimen prior to CD19 chimeric antigen receptor (CAR) T-cell therapy significantly improved outcomes in patients with relapsed/refractory (r/r) B-cell acute lymphoblastic leukemia (B-ALL). Fludarabine exposure, previously shown to be highly variable when dosing is based on body surface area (BSA), is a predictor for survival in allogeneic hematopoietic cell transplantation (allo-HCT). Hence, we hypothesized that an optimal exposure of fludarabine might be of clinical importance in CD19 CAR T-cell treatment. We examined the effect of cumulative fludarabine exposure during lymphodepletion, defined as concentration-time curve (AUC), on clinical outcome and lymphocyte kinetics. A retrospective analysis was conducted with data from 26 patients receiving tisagenlecleucel for r/r B-ALL. Exposure of fludarabine was shown to be a predictor for leukemia-free survival (LFS), B-cell aplasia, and CD19-positive relapse following CAR T-cell infusion. Minimal event probability was observed at a cumulative fludarabine AUCT0-∞ ≥14 mg*h/L, and underexposure was defined as an AUCT0-∞ less then 14 mg*h/L. In the underexposed group, the median LFS was 1.8 months, and the occurrence of CD19-positive relapse within 1 year was 100%, which was higher compared with the group with an AUCT0-∞ ≥14 mg*h/L (12.9 months; P less then .001; and 27.4%; P = .0001, respectively). Furthermore, the duration of B-cell aplasia within 6 months was shorter in the underexposed group (77.3% vs 37.3%; P = .009). These results suggest that optimizing fludarabine exposure may have a relevant impact on LFS following CAR T-cell therapy, which needs to be validated in a prospective clinical trial.Bone marrow-derived progenitor cells (BMDPCs) are mobilized to the circulation in pregnancy and get recruited to the pregnant decidua where they contribute functionally to decidualization and successful implantation. However, the molecular mechanisms underlying BMDPCs recruitment to the decidua are unknown. CXCL12 ligand and its CXCR4 receptor play crucial roles in the mobilization and homing of stem/progenitor cells to various tissues. To investigate the role of CXCL12-CXCR4 axis in BMDPCs recruitment to decidua, we created transgenic GFP mice harboring CXCR4 gene susceptible to tamoxifen-inducible Cre-mediated ablation. These mice served as BM donors into wild-type C57BL/6 J female recipients using a 5-fluorouracil-based nongonadotoxic submyeloablation to achieve BM-specific CXCR4 knockout (CXCR4KO). Successful CXCR4 ablation was confirmed by RT-PCR and in vitro cell migration assays. Flow cytometry and immunohistochemistry showed a significant increase in GFP+ BM-derived cells (BMDCs) in the implantation site as compared to the nonpregnant uterus of control (2.7-fold) and CXCR4KO (1.8-fold) mice. This increase was uterus-specific and was not observed in other organs. This pregnancy-induced increase occurred in both hematopoietic (CD45+) and nonhematopoietic (CD45-) uterine BMDCs in control mice. In contrast, in CXCR4KO mice there was no increase in nonhematopoietic BMDCs in the pregnant uterus. Moreover, decidual recruitment of myeloid cells but not NK cells was diminished by BM CXCR4 deletion. Immunofluorescence showed the presence of nonhematopoietic GFP+ cells that were negative for CD45 (panleukocyte) and DBA (NK) markers in control but not CXCR4KO decidua. In conclusion, we report that CXCR4 expression in nonhematopoietic BMDPCs is essential for their recruitment to the pregnant decidua.Protein remote homology detection is one of the most fundamental research tool for protein structure and function prediction. Most search methods for protein remote homology detection are evaluated based on the Structural Classification of Proteins-extended (SCOPe) benchmark, but the diverse hierarchical structure relationships between the query protein and candidate proteins are ignored by these methods. In order to further improve the predictive performance for protein remote homology detection, a search framework based on the predicted protein hierarchical relationships (PHR-search) is proposed. In the PHR-search framework, the superfamily level prediction information is obtained by extracting the local and global features of the Hidden Markov Model (HMM) profile through a convolution neural network and it is converted to the fold level and class level prediction information according to the hierarchical relationships of SCOPe. Based on these predicted protein hierarchical relationships, filtering strategy and re-ranking strategy are used to construct the two-level search of PHR-search. Experimental results show that the PHR-search framework achieves the state-of-the-art performance by employing five basic search methods, including HHblits, JackHMMER, PSI-BLAST, DELTA-BLAST and PSI-BLASTexB. Furthermore, the web server of PHR-search is established, which can be accessed at http//bliulab.net/PHR-search.The anterior optic pathway is one of the preferential sites of involvement in CNS inflammatory demyelinating diseases, such as multiple sclerosis and neuromyelitis optica, with optic neuritis being a common presenting symptom. What is more, optic nerve involvement in these diseases is often subclinical, with optical coherence tomography demonstrating progressive neuroretinal thinning in absence of optic neuritis. The pathological substrate for these findings is poorly understood and requires investigation. We had access to post-mortem tissue samples of optic nerves, chiasms, and tracts from 29 multiple sclerosis (mean age 59.5, range 25-84 years; 73 samples), 6 neuromyelitis optica spectrum disorders (56, 18-84 years; 22 samples), 6 acute disseminated encephalomyelitis (25, 10-39 years; 12 samples) cases and 5 non-neurological controls (55.2, 44-64 years; 16 samples). Formalin-fixed paraffin-embedded samples were immunolabelled for myelin, inflammation (microglial/macrophage, T- and B-cells, complement), acutspectrum disorder, cases with a history of optic neuritis had extensive demyelination and lost aquaporin-4 reactivity. In contrast, those without prior optic neuritis did not have demyelination but rather diffuse microglial/macrophage, T and B-lymphocyte inflammation in both parenchymal and meningeal compartments, and acute axonal injury was present in 75% of cases. Acute demyelinating encephalomyelitis featured intense inflammation, and perivenular demyelination in 33% of cases. Our findings suggest that chronic inflammation is frequent and leads to neurodegeneration in multiple sclerosis and neuromyelitis optica, regardless of disease stage. The chronic inflammation and subsequent neurodegeneration occurring along the optic pathway broadens the plaque-centred view of these diseases and partly explains the progressive neuroretinal changes observed in optic coherence tomography studies.

With the vast improvements in sequencing technologies and increased number of protocols, sequencing is being used to answer complex biological problems. Subsequently, analysis pipelines have become more time consuming and complicated, usually requiring highly extensive pre-validation steps. Here we present SeqWho, a program designed to assess heuristically the quality of sequencing files and reliably classify the organism and protocol type by using Random Forest classifiers trained on biases native in k-mer frequencies and repeat sequence identities.

Using one of our primary models, we show that our method accurately and rapidly classifies human and mouse sequences from nine different sequencing libraries by species, library, and both together, 98.32%, 97.86%, and 96.38% of the time respectively. Ultimately, we demonstrate that SeqWho is a powerful method for reliably validating the quality and identity of the sequencing files used in any pipeline.

https//github.com/DaehwanKimLab/seqwho.

Supplementary data are available at Bioinformatics online.

Supplementary data are available at Bioinformatics online.

Protein model quality assessment is a key component of protein structure prediction. In recent research, the voxelization feature was used to characterize the local structural information of residues, but it may be insufficient for describing residue-level topological information. Design features that can further reflect residue-level topology when combined with deep learning methods are therefore crucial to improve the performance of model quality assessment.

We developed a deep-learning method, DeepUMQA, based on Ultrafast Shape Recognition (USR) for the residue-level single-model quality assessment. In the framework of the deep residual neural network, the residue-level USR feature was introduced to describe the topological relationship between the residue and overall structure by calculating the first moment of a set of residue distance sets and then combined with 1D, 2D, and voxelization features to assess the quality of the model. Experimental results on the CASP13, CASP14 test datasets and CAMEO blind test show that USR could supplement the voxelization features to comprehensively characterize residue structure information and significantly improve model assessment accuracy. The performance of DeepUMQA ranks among the top during the state-of-the-art single-model quality assessment methods, including ProQ2, ProQ3, ProQ3D, Ornate, VoroMQA, ProteinGCN, ResNetQA, QDeep, GraphQA, ModFOLD6, ModFOLD7, ModFOLD8, QMEAN3, QMEANDisCo3 and DeepAccNet.

The DeepUMQA server is freely available at http//zhanglab-bioinf.com/DeepUMQA/.

Supplementary data are available at Bioinformatics online.

Supplementary data are available at Bioinformatics online.Numerous cancer types have shown to present hypermethylation of CpG islands, also known as a CpG island methylator phenotype (CIMP), often associated with survival variation. Despite extensive research on CIMP, the etiology of this variability remains elusive, possibly due to lack of consistency in defining CIMP. In this work, we utilize a pan-cancer approach to further explore CIMP, focusing on 26 cancer types profiled in the Cancer Genome Atlas (TCGA). We defined CIMP systematically and agnostically, discarding any effects associated with age, gender or tumor purity. We then clustered samples based on their most variable DNA methylation values and analyzed resulting patient groups. Our results confirmed the existence of CIMP in 19 cancers, including gliomas and colorectal cancer. We further showed that CIMP was associated with survival differences in eight cancer types and, in five, represented a prognostic biomarker independent of clinical factors. By analyzing genetic and transcriptomic data, we further uncovered potential drivers of CIMP and classified them in four categories mutations in genes directly involved in DNA demethylation; mutations in histone methyltransferases; mutations in genes not involved in methylation turnover, such as KRAS and BRAF; and microsatellite instability.