Machine-designed biotherapeutics: opportunities, feasibility and advantages of deep learning in computational antibody discovery.

Antibodies are versatile molecular binders with an established and growing role as therapeutics. Computational approaches to developing and designing these molecules are being increasingly used to complement traditional lab-based processes. Nowadays, in silico methods fill multiple elements of the discovery stage, such as characterizing antibody-antigen interactions and identifying developability liabilities. Recently, computational methods tackling such problems have begun to follow machine learning paradigms, in many cases deep learning specifically. This paradigm shift offers improvements in established areas such as structure or binding prediction and opens up new possibilities such as language-based modeling of antibody repertoires or machine-learning-based generation of novel sequences. In this review, we critically examine the recent developments in (deep) machine learning approaches to therapeutic antibody design with implications for fully computational antibody design.

INDI-integrated nanobody database for immunoinformatics.

Nanobodies, a subclass of antibodies found in camelids, are versatile molecular binding scaffolds composed of a single polypeptide chain. The small size of nanobodies bestows multiple therapeutic advantages (stability, tumor penetration) with the first therapeutic approval in 2018 cementing the clinical viability of this format. Structured data and sequence information of nanobodies will enable the accelerated clinical development of nanobody-based therapeutics. Though the nanobody sequence and structure data are deposited in the public domain at an accelerating pace, the heterogeneity of sources and lack of standardization hampers reliable harvesting of nanobody information. We address this issue by creating the Integrated Database of Nanobodies for Immunoinformatics (INDI, http://naturalantibody.com/nanobodies). INDI collates nanobodies from all the major public outlets of biological sequences: patents, GenBank, next-generation sequencing repositories, structures and scientific publications. We equip INDI with powerful nanobody-specific sequence and text search facilitating access to >11 million nanobody sequences. INDI should facilitate development of novel nanobody-specific computational protocols helping to deliver on the therapeutic promise of this drug format.

AbDiver: a tool to explore the natural antibody landscape to aid therapeutic design.

MOTIVATION: Rational design of therapeutic antibodies can be improved by harnessing the natural sequence diversity of these molecules. Our understanding of the diversity of antibodies has recently been greatly facilitated through the deposition of hundreds of millions of human antibody sequences in next-generation sequencing (NGS) repositories. Contrasting a query therapeutic antibody sequence to naturally observed diversity in similar antibody sequences from NGS can provide a mutational roadmap for antibody engineers designing biotherapeutics. Because of the sheer scale of the antibody NGS datasets, performing queries across them is computationally challenging. RESULTS: To facilitate harnessing antibody NGS data, we developed AbDiver (http://naturalantibody.com/abdiver), a free portal allowing users to compare their query sequences to those observed in the natural repertoires. AbDiver offers three antibody-specific use-cases: (i) compare a query antibody to positional variability statistics precomputed from multiple independent studies, (ii) retrieve close full variable sequence matches to a query antibody and (iii) retrieve CDR3 or clonotype matches to a query antibody. We applied our system to a set of 742 therapeutic antibodies, demonstrating that for each use-case our system can retrieve relevant results for most sequences. AbDiver facilitates the navigation of vast antibody mutation space for the purpose of rational therapeutic antibody design. AVAILABILITY AND IMPLEMENTATION: AbDiver is freely accessible at http://naturalantibody.com/abdiver. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Large-scale data mining of four billion human antibody variable regions reveals convergence between therapeutic and natural antibodies that constrains search space for biologics drug discovery.

The naïve human antibody repertoire has theoretical access to an estimated > 1015 antibodies. Identifying subsets of this prohibitively large space where therapeutically relevant antibodies may be found is useful for development of these agents. It was previously demonstrated that, despite the immense sequence space, different individuals can produce the same antibodies. It was also shown that therapeutic antibodies, which typically follow seemingly unnatural development processes, can arise independently naturally. To check for biases in how the sequence space is explored, we data mined public repositories to identify 220 bioprojects with a combined seven billion reads. Of these, we created a subset of human bioprojects that we make available as the AbNGS database (https://naturalantibody.com/ngs/). AbNGS contains 135 bioprojects with four billion productive human heavy variable region sequences and 385 million unique complementarity-determining region (CDR)-H3s. We find that 270,000 (0.07% of 385 million) unique CDR-H3s are highly public in that they occur in at least five of 135 bioprojects. Of 700 unique therapeutic CDR-H3, a total of 6% has direct matches in the small set of 270,000. This observation extends to a match between CDR-H3 and V-gene call as well. Thus, the subspace of shared ('public') CDR-H3s shows utility for serving as a starting point for therapeutic antibody design.

Predictors of Long-Term Outcomes After Liver Transplantation for Unresectable Metastatic Neuroendocrine Tumors.

BACKGROUND Malignant and benign neuroendocrine tumors (NET) share many histopathological features. Liver transplantation (LT) is one of the liver-directed therapies for neuroendocrine liver metastases (NELM). The aim of this study was to determine the outcomes of patients undergoing LT for NELM. MATERIAL AND METHODS This was a retrospective study that included 19 patients who underwent LT for unresectable NELM between December 1989 and December 2022 in the Department of General, Transplant, and Liver Surgery of the Medical University of Warsaw. Kaplan-Meier estimator and Cox proportional hazards regression were used for statistical analyses. RESULTS The primary tumor was located most frequently in the pancreas. The median follow-up was 72.5 months. The overall survival (OS) was 94.7%, 88.0%, 88.0%, 70.4%, and 49.3% after 1, 3, 5, 10, and 15 years, respectively. Accordingly, the recurrence-free survival (RFS) rates were 93.8%, 72.9%, 64.8%, 27.8%, and 27.8% after 1, 3, 5, 10, and 15 years, respectively. Ki-67 index ≥5% was found as a risk factor for both worse OS (hazard ratio (HR) 7.13, 95% confidence intervals (95% CI) 1.32-38.63, P=0.023) and RFS (HR 13.68, 95% CI 1.54-121.52, P=0.019). Recipient age ≥55 years was a risk factor for worse RFS (P=0.046, HR 5.47, 95% CI 1.03-29.08). Multivariable analysis revealed Ki-67 ≥5% as the sole independent factor for worse OS (HR 13.78, 95% CI 1.48-128.56, P=0.021). CONCLUSIONS Patients with unresectable NELM achieve great OS and satisfying RFS after LT. The risk factors associated with worse outcomes are attributed to primary tumor aggressiveness.

Structural modeling of antibody variable regions using deep learning-progress and perspectives on drug discovery.

AlphaFold2 has hallmarked a generational improvement in protein structure prediction. In particular, advances in antibody structure prediction have provided a highly translatable impact on drug discovery. Though AlphaFold2 laid the groundwork for all proteins, antibody-specific applications require adjustments tailored to these molecules, which has resulted in a handful of deep learning antibody structure predictors. Herein, we review the recent advances in antibody structure prediction and relate them to their role in advancing biologics discovery.

Alpha-Fetoprotein Response after First Transarterial Chemoembolization (TACE) and Complete Pathologic Response in Patients with Hepatocellular Cancer.

Transarterial chemoembolization (TACE) is used as a bridging treatment in liver transplant candidates with hepatocellular carcinoma (HCC). Alpha-fetoprotein (AFP) is the main tumor marker used for HCC surveillance. The aim of this study was to assess the potential of using the AFP change after the first TACE in the prediction of complete tumor necrosis. The study comprised 101 patients with HCC who underwent liver transplantation (LT) after TACE in the period between January 2011 and December 2020. The ΔAFP was defined as the difference between the AFP value before the first TACE and AFP either before the second TACE or the LT. The receiver operator characteristics (ROC) curves were used to identify an optimal cut-off value. Complete tumor necrosis was found in 26.1% (18 of 69) and 6.3% (2 of 32) of patients with an initial AFP level under and over 100 ng/mL, respectively (p = 0.020). The optimal cut-off value of ΔAFP for the prediction of complete necrosis was a decline of ≥10.2 ng/mL and ≥340.5 ng/mL in the corresponding subgroups. Complete tumor necrosis rates were: 62.5% (5 of 8) in patients with an initial AFP < 100 ng/mL and decline of ≥10.2 ng/mL; 21.3% (13 of 61) in patients with an initial AFP < 100 ng/mL and decline of <10.2 ng/mL; 16.7% (2 of 12) in patients with an initial AFP > 100 ng/mL and decline of ≥340.5 ng/mL; and null in 20 patients with an initial AFP > 100 ng/mL and decline of <340.5 ng/mL, respectively (p = 0.003). The simple scoring system, based on the initial AFP and AFP decline after the first treatment, distinguished between a high, intermediate and low probability of complete necrosis, with an area under the ROC curve of 0.699 (95% confidence intervals 0.577 to 0.821, p = 0.001). Combining the initial AFP with its change after the first treatment enables early identification of the efficacy of TACE.