Predicting antibody binders and generating synthetic antibodies using deep learning.

The antibody drug field has continually sought improvements to methods for candidate discovery and engineering. Historically, most such methods have been laboratory-based, but informatics methods have recently started to make an impact. Deep learning, a subfield of machine learning, is rapidly gaining prominence in the biomedical research. Recent advances in microfluidics technologies and next-generation sequencing have not only revolutionized therapeutic antibody discovery, but also contributed to a vast amount of antibody repertoire sequencing data, providing opportunities for deep learning-based applications. Previously, we used microfluidics, yeast display, and deep sequencing to generate a panel of binder and non-binder antibody sequences to the cancer immunotherapy targets PD-1 and CTLA-4. Here we encoded the antibody light and heavy chain complementarity-determining regions (CDR3s) into antibody images, then built and trained convolutional neural network models to classify binders and non-binders. To improve model interpretability, we performed in silico mutagenesis to identify CDR3 residues that were important for binder classification. We further built generative deep learning models using generative adversarial network models to produce synthetic antibodies against PD-1 and CTLA-4. Our models generated variable length CDR3 sequences that resemble real sequences. Overall, our study demonstrates that deep learning methods can be leveraged to mine and learn patterns in antibody sequences, offering insights into antibody engineering, optimization, and discovery.

Single-cell transcriptomics reveals the effect of PD-L1/TGF-ß blockade on the tumor microenvironment.

BACKGROUND: The anti-tumor activity of anti-PD-1/PD-L1 therapies correlates with T cell infiltration in tumors. Thus, a major goal in oncology is to find strategies that enhance T cell infiltration and efficacy of anti-PD-1/PD-L1 therapy. TGF-ß has been shown to contribute to T cell exclusion, and anti-TGF-ß improves anti-PD-L1 efficacy in vivo. However, TGF-ß inhibition has frequently been shown to induce toxicity in the clinic, and the clinical efficacy of combination PD-L1 and TGF-ß blockade has not yet been proven. To identify strategies to overcome resistance to PD-L1 blockade, the transcriptional programs associated with PD-L1 and/or TGF-ß blockade in the tumor microenvironment should be further elucidated. RESULTS: We used single-cell RNA sequencing in a mouse model to characterize the transcriptomic effects of PD-L1 and/or TGF-ß blockade on nearly 30,000 single cells in the tumor and surrounding microenvironment. Combination treatment led to upregulation of immune response genes, including multiple chemokine genes such as CCL5, in macrophages, and downregulation of extracellular matrix genes in fibroblasts. Analysis of publicly available tumor transcriptome profiles showed that the chemokine CCL5 was strongly associated with immune cell infiltration in various human cancers. Further investigation with in vivo models showed that intratumorally administered CCL5 enhanced cytotoxic lymphocytes and the anti-tumor activity of anti-PD-L1. CONCLUSIONS: Taken together, our data could be leveraged translationally to complement or find alternatives to anti-PD-L1 plus anti-TGF-ß combination therapy, for example through companion biomarkers, and/or to identify novel targets that could be modulated to overcome resistance.

Recovery of the salt marsh periwinkle (Littoraria irrorata) 9 years after the Deepwater Horizon oil spill: Size matters.

Prior studies indicated salt marsh periwinkles (Littoraria irrorata) were strongly impacted in heavily oiled marshes for at least 5 years following the Deepwater Horizon oil spill. Here, we detail longer-term effects and recovery over nine years. Our analysis found that neither density nor population size structure recovered at heavily oiled sites where snails were smaller and variability in size structure and density was increased. Total aboveground live plant biomass and stem density remained lower over time in heavily oiled marshes, and we speculate that the resulting more open canopy stimulated benthic microalgal production contributing to high spring periwinkle densities or that the lower stem density reduced the ability of subadults and small adults to escape predation. Our data indicate that periwinkle population recovery may take one to two decades after the oil spill at moderately oiled and heavily oiled sites, respectively.

Affinity maturation of antibodies by combinatorial codon mutagenesis versus error-prone PCR.

IN VITRO: affinity maturation of therapeutic monoclonal antibodies is commonly applied to achieve desired properties, such as improved binding kinetics and affinity. Currently there are no universally accepted protocols for generation of variegated antibody libraries or selection thereof. Here, we performed affinity maturation using a yeast-based single-chain variable fragment (scFv) expression system to compare two mutagenesis methods: random mutagenesis across the entire V(D)J region by error-prone PCR, and a novel combinatorial mutagenesis process limited to the complementarity-determining regions (CDRs). We applied both methods of mutagenesis to four human antibodies against well-known immuno-oncology target proteins. Detailed sequence analysis showed an even mutational distribution across the entire length of the scFv for the error-prone PCR method and an almost exclusive targeting of the CDRs for the combinatorial method. Though there were distinct mutagenesis profiles for each target antibody and mutagenesis method, we found that both methods improved scFv affinity with similar efficiency. When a subset of the affinity-matured antibodies was expressed as full-length immunoglobulin, the measured affinity constants were mostly comparable to those of the respective scFv, but the full-length antibodies were inferior to their scFv counterparts for one of the targets. Furthermore, we found that improved affinity for the full-length antibody did not always translate into enhanced binding to cell-surface expressed antigen or improved immune checkpoint blocking ability, suggesting that screening with full-length antibody or antigen-binding fragment formats might be advantageous and the subject of a future study.

Massively parallel interrogation and mining of natively paired human TCRαß repertoires.

T cells engineered to express antigen-specific T cell receptors (TCRs) are potent therapies for viral infections and cancer. However, efficient identification of clinical candidate TCRs is complicated by the size and complexity of T cell repertoires and the challenges of working with primary T cells. Here we present a high-throughput method to identify TCRs with high functional avidity from diverse human T cell repertoires. The approach used massively parallel microfluidics to generate libraries of natively paired, full-length TCRαß clones, from millions of primary T cells, which were then expressed in Jurkat cells. The TCRαß-Jurkat libraries enabled repeated screening and panning for antigen-reactive TCRs using peptide major histocompatibility complex binding and cellular activation. We captured more than 2.9 million natively paired TCRαß clonotypes from six healthy human donors and identified rare (<0.001% frequency) viral-antigen-reactive TCRs. We also mined a tumor-infiltrating lymphocyte sample from a patient with melanoma and identified several tumor-specific TCRs, which, after expression in primary T cells, led to tumor cell killing.

Rare, high-affinity anti-pathogen antibodies from human repertoires, discovered using microfluidics and molecular genomics.

Affinity-matured, functional anti-pathogen antibodies are present at low frequencies in natural human repertoires. These antibodies are often excellent candidates for therapeutic monoclonal antibodies. However, mining natural human antibody repertoires is a challenge. In this study, we demonstrate a new method that uses microfluidics, yeast display, and deep sequencing to identify 247 natively paired anti-pathogen single-chain variable fragments (scFvs), which were initially as rare as 1 in 100,000 in the human repertoires. Influenza A vaccination increased the frequency of influenza A antigen-binding scFv within the peripheral B cell repertoire from <0.1% in non-vaccinated donors to 0.3-0.4% in vaccinated donors, whereas pneumococcus vaccination did not increase the frequency of antigen-binding scFv. However, the pneumococcus scFv binders from the vaccinated library had higher heavy and light chain Replacement/Silent mutation (R/S) ratios, a measure of affinity maturation, than the pneumococcus binders from the corresponding non-vaccinated library. Thus, pneumococcus vaccination may increase the frequency of affinity-matured antibodies in human repertoires. We synthesized 10 anti-influenza A and nine anti-pneumococcus full-length antibodies that were highly abundant among antigen-binding scFv. All 10 anti-influenza A antibodies bound the appropriate antigen at KD<10 nM and neutralized virus in cellular assays. All nine anti-pneumococcus full-length antibodies bound at least one polysaccharide serotype, and 71% of the anti-pneumococcus antibodies that we tested were functional in cell killing assays. Our approach has future application in a variety of fields, including the development of therapeutic antibodies for emerging viral diseases, autoimmune disorders, and cancer.

Subacute osteomyelitis of the femur due to Fusobacterium nucleatum in a 7-year-old boy.

Subacute hematogenous osteomyelitis is an insidious infection, which commonly has a delayed diagnosis. We describe the case of a 7-year-old boy with subacute osteomyelitis, which was initially considered to be a bone tumor. Infection should be considered in all cases of bone pain, especially in children, even in the absence of typical systemic features of inflammation.

A distinct evolution of the T-cell repertoire categorizes treatment refractory gastrointestinal acute graft-versus-host disease.

Steroid refractory gastrointestinal (GI) acute graft-versus-host disease (aGVHD) is a major cause of mortality in hematopoietic stem cell transplantation (HCT) without immune markers to establish a diagnosis or guide therapy. We found that T-cell receptor ß (TCRß) complementarity-determining region 3 repertoire sequencing reveals patterns that could eventually serve as a disease biomarker of T-cell alloreactivity in aGVHD. We identified T-cell clones in GI biopsies in a heterogeneous group of 15 allogeneic HCT patients with GI aGVHD symptoms. Seven steroid-refractory aGVHD patients showed a more conserved TCRß clonal structure between different biopsy sites in the GI tract than 8 primary therapy-responsive patients. Tracking GI clones identified longitudinally at endoscopy in the blood also revealed an increased clonal expansion in patients with steroid-refractory disease. Immune repertoire sequencing-based methods could enable a novel personalized way to guide diagnosis and therapy in diseases where T-cell activity is a major determinant.

Sequence features that drive human promoter function and tissue specificity.

Promoters are important regulatory elements that contain the necessary sequence features for cells to initiate transcription. To functionally characterize a large set of human promoters, we measured the transcriptional activities of 4575 putative promoters across eight cell lines using transient transfection reporter assays. In parallel, we measured gene expression in the same cell lines and observed a significant correlation between promoter activity and endogenous gene expression (r = 0.43). As transient transfection assays directly measure the promoting effect of a defined fragment of DNA sequence, decoupled from epigenetic, chromatin, or long-range regulatory effects, we sought to predict whether a promoter was active using sequence features alone. CG dinucleotide content was highly predictive of ubiquitous promoter activity, necessitating the separation of promoters into two groups: high CG promoters, mostly ubiquitously active, and low CG promoters, mostly cell line-specific. Computational models trained on the binding potential of transcriptional factor (TF) binding motifs could predict promoter activities in both high and low CG groups: average area under the receiver operating characteristic curve (AUC) of the models was 91% and exceeded the AUC of CG content by an average of 23%. Known relationships, for example, between HNF4A and hepatocytes, were recapitulated in the corresponding cell lines, in this case the liver-derived cell line HepG2. Half of the associations between tissue-specific TFs and cell line-specific promoters were new. Our study underscores the importance of collecting functional information from complementary assays and conditions to understand biology in a systematic framework.

The potential of stem cells in the treatment of knee cartilage defects.

Cartilage is frequently damaged but only shows a limited capacity for repair. There are a number of treatment strategies currently available for the repair of articular cartilage defects including abrasion chondroplasty, subchondral drilling, microfracture and mosaicplasty but these show variable results. For the younger patients, there is great interest in the potential of cell-based strategies to provide a biological replacement of damaged cartilage using autologous chondrocytes. The results of clinical studies using these cell-based techniques do not conclusively show improvement over conventional techniques. These techniques also do not consistently result in the formation of the desired hyaline cartilage rather than fibrocartilage. Mesenchymal stem cells present a promising cell source for cartilage repair. Mesenchymal stem cells have been isolated from a number of adult tissues including the bone marrow and the synovial fat pad. These cells have the ability to proliferate in culture and differentiate down different pathways including the chondrogenic pathway. In the first instance, differentiated stem cells can be used for the repair of localised cartilage defects by producing hyaline cartilage. In the future, this strategy has the potential to be extended to treat more generalised cartilage defects, especially as the cell source is not a limiting factor. The use of cell-based therapies also allows the versatility of using scaffolds and growth factors, with recombinant proteins or gene therapy. A number of challenges however still need to be overcome including further work on identifying the optimal source of stem cells, along with refining the conditions that enhance expansion and chondrogenesis.

Model-based analysis of ChIP-Seq (MACS).

We present Model-based Analysis of ChIP-Seq data, MACS, which analyzes data generated by short read sequencers such as Solexa's Genome Analyzer. MACS empirically models the shift size of ChIP-Seq tags, and uses it to improve the spatial resolution of predicted binding sites. MACS also uses a dynamic Poisson distribution to effectively capture local biases in the genome, allowing for more robust predictions. MACS compares favorably to existing ChIP-Seq peak-finding algorithms, and is freely available.

Does the Lachman testing method affect the reliability of the International Knee Documentation Committee (IKDC) Form?

The aim of this study was to evaluate the effect of manual and instrumented means of Lachman testing on the reliability of the IKDC form. A single observer assessed 102 patients with ACL deficiency (direct comparison group). Another observer assessed 35 of these patients (inter-observer group) and the initial observer re-assessed 47 patients (test-retest group). The Lachman test was performed by both manual and instrumented means and the IKDC form was completed. Direct comparison of the manual and instrumented Lachman test revealed satisfactory levels for use. Further comparison revealed satisfactory test re-test and unsatisfactory inter-observer reliability for both means. On application into the IKDC form, direct comparison of both means of testing revealed satisfactory agreement for the overall score, but not the ligament group or Lachman item scores. Test-retest and inter-observer reliability testing revealed unsatisfactory agreement for the overall, ligament group and Lachman item scores for both means of testing. When using the IKDC form we recommend that a single observer perform the Lachman test by manual means on each occasion. If the original IKDC form is used only the overall score should be presented. Where the new IKDC form is used we recommend caution in the presentation of the examination section. We call into question the usefulness of the original IKDC form and the examination section of the new IKDC form in clinical research.