Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

General General

Deep Learning and Computer Vision Strategies for Automated Gene Editing with a Single-Cell Electroporation Platform.

In SLAS technology

Single-cell delivery platforms like microinjection and nanoprobe electroporation enable unparalleled control over cell manipulation tasks but are generally limited in throughput. Here, we present an automated single-cell electroporation system capable of automatically detecting cells with artificial intelligence (AI) software and delivering exogenous cargoes of different sizes with uniform dosage. We implemented a fully convolutional network (FCN) architecture to precisely locate the nuclei and cytosol of six cell types with various shapes and sizes, using phase contrast microscopy. Nuclear staining or reporter fluorescence was used along with phase contrast images of cells within the same field of view to facilitate the manual annotation process. Furthermore, we leveraged the near-human inference capabilities of the FCN network in detecting stained nuclei to automatically generate ground-truth labels of thousands of cells within seconds, and observed no statistically significant difference in performance compared to training with manual annotations. The average detection sensitivity and precision of the FCN network were 95±1.7% and 90±1.8%, respectively, outperforming a traditional image-processing algorithm (72±7.2% and 72±5.5%) used for comparison. To test the platform, we delivered fluorescent-labeled proteins into adhered cells and measured a delivery efficiency of 90%. As a demonstration, we used the automated single-cell electroporation platform to deliver Cas9-guide RNA (gRNA) complexes into an induced pluripotent stem cell (iPSC) line to knock out a green fluorescent protein-encoding gene in a population of ~200 cells. The results demonstrate that automated single-cell delivery is a useful cell manipulation tool for applications that demand throughput, control, and precision.

Patino Cesar A, Mukherjee Prithvijit, Lemaitre Vincent, Pathak Nibir, Espinosa Horacio D


CRISPR-Cas9, computer vision, deep learning, electroporation, single-cell

General General

Machine Learning Algorithms Applied to Identify Microbial Species by Their Motility.

In Life (Basel, Switzerland)

(1) Background: Future missions to potentially habitable places in the Solar System require biochemistry-independent methods for detecting potential alien life forms. The technology was not advanced enough for onboard machine analysis of microscopic observations to be performed in past missions, but recent increases in computational power make the use of automated in-situ analyses feasible. (2) Methods: Here, we present a semi-automated experimental setup, capable of distinguishing the movement of abiotic particles due to Brownian motion from the motility behavior of the bacteria Pseudoalteromonas haloplanktis, Planococcus halocryophilus, Bacillus subtilis, and Escherichia coli. Supervised machine learning algorithms were also used to specifically identify these species based on their characteristic motility behavior. (3) Results: While we were able to distinguish microbial motility from the abiotic movements due to Brownian motion with an accuracy exceeding 99%, the accuracy of the automated identification rates for the selected species does not exceed 82%. (4) Conclusions: Motility is an excellent biosignature, which can be used as a tool for upcoming life-detection missions. This study serves as the basis for the further development of a microscopic life recognition system for upcoming missions to Mars or the ocean worlds of the outer Solar System.

Riekeles Max, Schirmack Janosch, Schulze-Makuch Dirk


automation, biosignature, life detection, machine learning, motility, species identification

General General

Machine Learning-Based Amino Acid Substitution of Short Peptides: Acquisition of Peptides with Enhanced Inhibitory Activities against α-Amylase and α-Glucosidase.

In ACS biomaterials science & engineering ; h5-index 39.0

We developed a method for efficiently activating functional peptides with a large structural contribution using the peptide-searching method with machine learning. The physicochemical properties of the amino acids were employed as variables. As a model peptide, we used GHWYYRCW, which is a functional peptide that inhibits α-amylase derived from human pancreatic juice. First, training data were acquired. A total of 153 peptides were prepared in which 1 amino acid in GHWYYRCW was replaced to construct a 1-amino acid substitution coverage peptide library. The inhibitory activity of each peptide against α-amylase and α-glucosidase was evaluated. Second, random forest (RF) regression analysis was performed using 120 variables, and the enzyme inhibitory activity of the peptide was related to the physicochemical properties. The constructed model had many features describing the charge of the amino acid (isoelectric point and pK2). Then, high inhibitory (HI) peptides were predicted using a library of peptides with 2- or 3-amino acid substitution as test data, which were called HI2 and HI3 peptides. As results, the first or seventh amino acid of the HI2 peptide was replaced with Arg, Trp, or Tyr. We found that all 30 HI2 peptides had significantly higher activity than the original sequence (100%) and 26 of the 30 HI3 peptides were significantly active (86.7%). However, the actual inhibitory activity of the HI3 peptides was improved to a lesser extent. The docking simulation clarified that the CDOCKER energy decrease was roughly correlated with the inhibitory activity. The machine learning-based predictive model was a promising tool for design of substituted peptides with high activity values, and it was assumed that the advanced model that forecasts the interaction index such as the CDOCKER energy substituting for the inhibitory activity would be used to design HI peptides, even in the case of the HI3 peptides.

Yamashita Haruki, Fujitani Masaya, Shimizu Kazunori, Kanie Kei, Kato Ryuji, Honda Hiroyuki


amino acid index, data mining, peptide array, physicochemical property, screening system

Radiology Radiology

Deep learning image reconstruction for improvement of image quality of abdominal computed tomography: comparison with hybrid iterative reconstruction.

In Japanese journal of radiology

PURPOSE : To evaluate the usefulness of the deep learning image reconstruction (DLIR) to enhance the image quality of abdominal CT, compared to iterative reconstruction technique.

METHOD : Pre and post-contrast abdominal CT images in 50 patients were reconstructed with 2 different algorithms: hybrid iterative reconstruction (hybrid IR: ASiR-V 50%) and DLIR (TrueFidelity). Standard deviation of attenuation in normal liver parenchyma was measured as the image noise on pre and post-contrast CT. The contrast-to-noise ratio (CNR) for the aorta, and the signal-to-noise ratio (SNR) of the liver were calculated on post-contrast CT. The overall image quality was graded on a 5-point scale ranging from 1 (poor) to 5 (excellent).

RESULTS : The image noise was significantly decreased by DLIR compared to hybrid-IR [hybrid IR, median 8.3 Hounsfield unit (HU) (interquartile range (IQR) 7.6-9.2 HU); DLIR, median 5.2 HU (IQR 4.6-5.8), P < 0.0001 for post-contrast CT]. The CNR and SNR were significantly improved by DLIR [CNR, median 4.5 (IQR 3.8-5.6) vs 7.3 (IQR 6.2-8.8), P < 0.0001; SNR, median 9.4 (IQR 8.3-10.1) vs 15.0 (IQR 13.2-16.4), P < 0.0001]. The overall image quality score was also higher for DLIR compared to hybrid-IR (hybrid IR 3.1 ± 0.6 vs DLIR 4.6 ± 0.5, P < 0.0001 for post-contrast CT).

CONCLUSIONS : Image noise, overall image quality, CNR and SNR for abdominal CT images are improved with DLIR compared to hybrid IR.

Ichikawa Yasutaka, Kanii Yoshinori, Yamazaki Akio, Nagasawa Naoki, Nagata Motonori, Ishida Masaki, Kitagawa Kakuya, Sakuma Hajime


Abdomen, Computed tomography, Deep learning image reconstruction, Image noise, Image quality

Pathology Pathology

High-Dimensional Immune Monitoring for Chimeric Antigen Receptor T Cell Therapies.

In Current hematologic malignancy reports

PURPOSE OF REVIEW : High-dimensional flow cytometry experiments have become a method of choice for high-throughput integration and characterization of cell populations. Here, we present a summary of state-of-the-art R-based pipelines used for differential analyses of cytometry data, largely based on chimeric antigen receptor (CAR) T cell therapies. These pipelines are based on publicly available R libraries, put together in a systematic and functional fashion, therefore free of cost.

RECENT FINDINGS : In recent years, existing tools tailored to analyze complex high-dimensional data such as single-cell RNA sequencing (scRNAseq) have been successfully ported to cytometry studies due to the similar nature of flow cytometry and scRNAseq platforms. Existing environments like Cytobank (Kotecha et al., 2010), FlowJo (FlowJo™ Software) and FCS Express ( already offer a variety of these ported tools, but they either come at a premium or are fairly complicated to manage by an inexperienced user. To mitigate these limitations, experienced cytometrists and bioinformaticians usually incorporate these functions into an RShiny ( application that ultimately offers a user-friendly, intuitive environment that can be used to analyze flow cytometry data. Computational tools and Shiny-based tools are the perfect answer to the ever-growing dimensionality and complexity of flow cytometry data, by offering a dynamic, yet user-friendly exploratory space, tailored to bridge the space between the lab experimental world and the computational, machine learning space.

Sharma Sujata, Quinn David, Melenhorst J Joseph, Pruteanu-Malinici Iulian


Annotation, Clustering, K-means, PCA, UMAP, tSNE

Cardiology Cardiology

[Artificial intelligence in cardiology : Relevance, current applications, and future developments].

In Herzschrittmachertherapie & Elektrophysiologie

Big data and applications of artificial intelligence (AI), such as machine learning or deep learning, will enrich healthcare in the future and become increasingly important. Among other things, they have the potential to avoid unnecessary examinations as well as diagnostic and therapeutic errors. They could enable improved, early and accelerated decision-making. In the article, the authors provide an overview of current AI-based applications in cardiology. The examples describe innovative solutions for risk assessment, diagnosis and therapy support up to patient self-management. Big data and AI serve as a basis for efficient, predictive, preventive and personalised medicine. However, the examples also show that research is needed to further develop the solutions for the benefit of the patient and the medical profession, to demonstrate the effectiveness and benefits in health care and to establish legal and ethical standards.

Zippel-Schultz Bettina, Schultz Carsten, Müller-Wieland Dirk, Remppis Andrew B, Stockburger Martin, Perings Christian, Helms Thomas M


Acceptance, Big data, Decision-making support, Risk assessment, Self-management