Graphylo: A deep learning approach for predicting regulatory DNA and RNA sites from whole-genome multiple alignments.

This study focuses on enhancing the prediction of regulatory functional sites in DNA and RNA sequences, a crucial aspect of gene regulation. Current methods, such as motif overrepresentation and machine learning, often lack specificity. To address this issue, the study leverages evolutionary information and introduces Graphylo, a deep-learning approach for predicting transcription factor binding sites in the human genome. Graphylo combines Convolutional Neural Networks for DNA sequences with Graph Convolutional Networks on phylogenetic trees, using information from placental mammals' genomes and evolutionary history. The research demonstrates that Graphylo consistently outperforms both single-species deep learning techniques and methods that incorporate inter-species conservation scores on a wide range of datasets. It achieves this by utilizing a species-based attention model for evolutionary insights and an integrated gradient approach for nucleotide-level model interpretability. This innovative approach offers a promising avenue for improving the accuracy of regulatory site prediction in genomics.

EvoLSTM: context-dependent models of sequence evolution using a sequence-to-sequence LSTM.

MOTIVATION: Accurate probabilistic models of sequence evolution are essential for a wide variety of bioinformatics tasks, including sequence alignment and phylogenetic inference. The ability to realistically simulate sequence evolution is also at the core of many benchmarking strategies. Yet, mutational processes have complex context dependencies that remain poorly modeled and understood. RESULTS: We introduce EvoLSTM, a recurrent neural network-based evolution simulator that captures mutational context dependencies. EvoLSTM uses a sequence-to-sequence long short-term memory model trained to predict mutation probabilities at each position of a given sequence, taking into consideration the 14 flanking nucleotides. EvoLSTM can realistically simulate mammalian and plant DNA sequence evolution and reveals unexpectedly strong long-range context dependencies in mutation probabilities. EvoLSTM brings modern machine-learning approaches to bear on sequence evolution. It will serve as a useful tool to study and simulate complex mutational processes. AVAILABILITY AND IMPLEMENTATION: Code and dataset are available at https://github.com/DongjoonLim/EvoLSTM. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Biofouling control with bead-entrapped quorum quenching bacteria in membrane bioreactors: physical and biological effects.

Recently, interspecies quorum quenching by bacterial cells encapsulated in a vessel was described and shown to be efficient and economically feasible for biofouling control in membrane bioreactors (MBRs). In this study, free-moving beads entrapped with quorum quenching bacteria were applied to the inhibition of biofouling in a MBR. Cell entrapping beads (CEBs) with a porous microstructure were prepared by entrapping quorum quenching bacteria ( Rhodococcus sp. BH4) into alginate beads. In MBRs provided with CEBs, the time to reach a transmembrane pressure (TMP) of 70 kPa was 10 times longer than without CEBs. The mitigation of biofouling was attributed to both physical (friction) and biological (quorum quenching) effects of CEBs, the latter being much more important. Because of the quorum quenching effect of CEBs, microbial cells in the biofilm generated fewer extracellular polymeric substances and thus formed a loosely bound biofilm, which enabled it to slough off from the membrane surface more easily. Furthermore, collisions between the moving CEBs and membranes gave rise to frictional forces that facilitated detachment of the biofilm from the membrane surface. CEBs bring bacterial quorum quenching closer to being a practical solution to the problem of biofouling in MBRs.

Intracranial recurrence of the scalp dermatofibrosarcoma.

We report a case of recurrent scalp dermatofibrosarcoma in a 30-year-old woman who underwent surgical intervention on three separate occasions during a 60-month period, and who received post-operative radiotherapy. A small, hard, elastic mass on the right parieto-occipital scalp was initially treated by simple resection in another clinic. Despite surgical intervention and radiotherapy, a recurrent tumor associated with infiltration to the calvarium was detected. The patient was then referred to our institution and a wide resection performed. Two years later, however, the patient was readmitted to our institution as a result of tumor recurrence with intracranial involvement. Scalp dermatofibrosarcoma is an uncommon but aggressive scalp tumor; therefore, wide local excision with good margins is essential to decrease the risk of regional recurrence. Close surveillance in these cases is necessary due to late tumor recurrences.